JP2013050412A - Vehicle itself position recognition system, vehicle itself position recognition program, and vehicle itself position recognition method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To realize a technique enabling appropriate determination of a recognition ratio of a group of features constituted by plural features in order to determine a recognition target in an image recognition process.SOLUTION: A system includes: a recognition-requiring range acquisition part 27 for acquiring a recognition-requiring range that is set for each unit of recognizing feature as a range of performing an image recognition process; a recognition ratio determination part 26 for determining a recognition ratio for each unit of recognizing feature on the basis of a predicted recognition ratio ER predetermined for each category of feature; and a recognition target selection part 25 for selecting a unit of recognizing feature as a recognition target on the basis of a recognition ratio from among plural units of recognizing features with mutual overlapping recognition-requiring ranges. Further, for a specific unit of recognizing features constituted by a group of features distributedly disposed in a road width direction, the recognition ratio determination part 26 determines a recognition ratio on the basis of a predicted recognition ratio ER of remaining features constituting the aforementioned specific unit of recognizing features in a case where a part of plural features constituting the aforementioned specific unit of recognizing features is image-recognized in accordance with the image recognition result of each feature at each temporal point.

Description

  The present invention relates to a host vehicle position recognition system, a host vehicle position recognition program, and a host vehicle position recognition method that recognize a host vehicle position using an image captured by a camera provided in the host vehicle.

  As a conventional technique of the vehicle position recognition system as described above, there is a technique described in, for example, Japanese Unexamined Patent Application Publication No. 2009-58429 (Patent Document 1). Patent Document 1 describes a technique for performing image recognition processing of a feature included in a photographed image by a camera and correcting the estimated vehicle position based on the result of image recognition and position information of the feature. . At this time, the feature to be recognized in the image recognition process is determined based on the recognition rate, which is the rate of successful image recognition of each feature. Specifically, when a plurality of features that can be recognized are arranged at narrow intervals, a feature having a high recognition rate is determined as a feature to be recognized. Thereby, it is possible to increase the recognition rate of the feature per fixed distance while reducing the calculation load related to the image recognition processing.

  By the way, as described in, for example, Japanese Patent Application Laid-Open No. 2009-109341 (Patent Document 2), image recognition is performed on a feature group composed of a plurality of features (in the example of Patent Document 2, a pair of crosswalk signs). A technique to be recognized in processing is known. However, Patent Document 1 does not describe the case where such a feature group is set as a recognition target, and naturally, a method for determining the recognition rate for the feature group for determining the recognition target in the image recognition processing. There is no mention.

JP 2009-58429 A JP 2009-109341 A

  Therefore, it is desired to realize a technique that can appropriately determine a recognition rate for determining a recognition target in an image recognition process for a feature group including a plurality of features.

  According to the present invention, an estimated own vehicle position acquisition unit that acquires an estimated own vehicle position, which is an estimated position of the own vehicle, and a captured image captured by a camera provided in the own vehicle are acquired and included in the captured image An image processing unit that performs image recognition processing of a feature to be obtained, a road information acquisition unit that acquires road information including position information of the feature, a recognition result of the feature by the image recognition processing, and a land included in the road information A feature configuration of the vehicle position recognition system including an estimated vehicle position correction unit that corrects the estimated vehicle position based on the position information of the object is a single feature or a plurality of predetermined features. A recognition request range acquisition unit that acquires a recognition request range set for each recognition feature unit along a road length direction as a range in which the image recognition processing is performed, with a feature group configured by And the percentage of successful image recognition A recognition rate determining unit that determines a rate for each recognized feature unit based on an expected recognition rate predetermined for each type of feature, and the recognition based on the recognition rate of each recognized feature unit A recognition target selecting unit that selects the recognized feature unit to be recognized in the image recognition process from a plurality of the recognized feature units whose request ranges overlap each other, and the recognition rate determining unit includes a road According to the image recognition result of each feature constituting the specific recognition feature unit at each time point for the specific recognition feature unit that is the recognition feature unit composed of the feature group divided in the length direction When a part of a plurality of features constituting the specific recognition feature unit is image-recognized, the recognition rate is determined based on the expected recognition rate of the remaining features constituting the specific recognition feature unit. Execute specific recognition rate determination process Located in.

According to the above feature configuration, by executing the specific recognition rate determination process, the recognition rate of the specific recognition feature unit composed of the feature group arranged separately in the road length direction is determined as the image recognition at each time point. It is possible to make an appropriate decision in consideration of the result. As a supplementary explanation, when the recognition rate, which is the rate of successful image recognition, is taken into consideration to the expected recognition rate of features that have already been image-recognized, there is a risk that a lower recognition rate will be determined than the actual success rate. There is. On the other hand, according to the above feature configuration, since the recognition rate is determined based on the expected recognition rate of the features that have not yet been image-recognized, the expected recognition rate of all the features is determined regardless of the image recognition result. Compared to the case where the recognition rate is determined based on the recognition rate, it is possible to obtain a recognition rate that matches the current state at each time point.
As described above, according to the feature configuration described above, it is possible to appropriately determine a recognition rate for determining a recognition target in the image recognition process for a feature group including a plurality of features.

  Here, the recognition request range is set based on a feature-specific request range that is set for each feature that constitutes the recognized feature unit, and the recognition rate determination unit, the recognition rate determination unit of the specific recognition feature unit When determining the recognition rate, the specific recognition rate is determined when the feature corresponding to the requested range for each feature is recognized in the first determination area including the end portion on the rear side in the traveling direction in the requested range for each feature. When the feature corresponding to the required range for each feature is recognized in the second determination area other than the first determination area in the recognition required range configured by the required range for each feature. Is preferably configured to prohibit the execution of the specific recognition rate determination process.

  Even in consideration of the error of the estimated vehicle position, in the first determination area set on the rear side in the traveling direction in the required range for each feature, the front side in the traveling direction with respect to the feature corresponding to the required range for each feature It is unlikely that other features placed in the image will be recognized. In the above configuration, since the specific recognition rate determination process is executed only when the feature is image-recognized in the first determination region, there is a possibility that the feature that has been image-recognized is the other feature. When the value is not low, execution of the specific recognition rate determination process can be prohibited. Thereby, it is possible to prevent the recognition target selection unit from selecting an appropriate recognition rate that is higher than the actual success rate for the specific recognition feature unit.

  In addition, the recognition rate determination unit is the specific recognition feature unit in which the recognition requirement range overlaps with the other recognition feature unit, and for the features constituting the other recognition feature unit It is preferable that the specific recognition rate determination process is executed only for the specific recognition feature unit having the features arranged on the rear side in the traveling direction.

  According to this configuration, the specific recognition feature unit to be executed for the specific recognition rate determination process is limited to the specific recognition feature unit whose recognition request range overlaps with other recognition feature units. It is possible to prohibit the recognition rate determination process from being executed when it is not necessary to select an object unit. In addition, the specific recognition feature unit that is the target of executing the specific recognition rate determination process is a feature arranged on the rear side in the traveling direction with respect to the features that constitute other recognition feature units whose recognition request ranges overlap each other. Since it is limited to the specific recognition feature unit having an object, the specific recognition feature unit that is the execution target of the specific recognition rate determination process is at least according to the image recognition result of the feature located at the rearmost side in the traveling direction, It is possible to limit the selection result by the recognition target selection unit to change. Thus, it is possible to suppress the calculation load by suppressing the specific recognition rate determination process from being performed more than necessary.

  In the specific recognition rate determination process, the recognition rate determination unit determines the expected recognition rate of all remaining features other than the image-recognized features in the features constituting the specific recognition feature unit. Is determined as the recognition rate of the specific recognition feature unit, and in the normal recognition rate determination process other than the specific recognition rate determination process, the prediction of all the features constituting the specific recognition feature unit is determined. A value obtained by multiplying the recognition rates with each other is preferably determined as the recognition rate of the specific recognition feature unit.

  According to this configuration, since the recognition rate can be derived with a simple configuration in any of the specific recognition rate determination processing and the normal recognition rate determination processing, when these are calculated and derived as necessary In addition, the load related to the calculation can be reduced. Further, when the recognition rate is calculated in advance and stored in the storage device, the cost for the maintenance can be reduced.

  The technical features of the vehicle position recognition system according to the present invention having the above-described configurations can be applied to a vehicle position recognition program and a vehicle position recognition method, and the present invention also includes such a program and method. Can be subject to rights.

  In this case, the feature configuration of the host vehicle position recognition program includes an estimated host vehicle position acquisition function for acquiring an estimated host vehicle position that is an estimated position of the host vehicle, and a photographed image shot by a camera provided in the host vehicle. An image processing function for performing image recognition processing of a feature included in the captured image, a road information acquisition function for acquiring road information including positional information of the feature, and feature recognition by the image recognition processing A vehicle position recognition program for realizing an estimated vehicle position correction function for correcting the estimated vehicle position based on a result and position information of a feature included in the road information, Recognition set for each recognition feature unit along the road length direction as a range for performing the image recognition processing, with a feature group composed of a plurality of predetermined features or features as recognition feature units Get request range A recognition request range acquisition function, and a recognition rate determination function for determining a recognition rate, which is a rate of successful image recognition, for each recognition feature unit based on an expected recognition rate predetermined for each type of feature, Based on the recognition rate of each recognized feature unit, the recognized feature unit to be recognized in the image recognition process is selected from the plurality of recognized feature units whose recognition request ranges overlap each other. A recognition target selection function implemented by a computer, and the recognition rate determination function is configured for each specific recognition feature unit, which is a recognition feature unit composed of feature groups arranged separately in a road length direction, at each time point. When a part of a plurality of features constituting the specific recognition feature unit is image-recognized according to the image recognition result of each feature constituting the specific recognition feature unit at the specific recognition feature unit Configure units It lies in a function to perform a specific recognition rate determining process for determining the recognition rate based on the expected recognition rate of Rino feature.

  In addition, the characteristic configuration of the vehicle position recognition method includes an estimated vehicle position acquisition step for acquiring an estimated vehicle position that is an estimated position of the vehicle, and a captured image captured by a camera provided in the vehicle. An image processing step for performing image recognition processing of the feature included in the captured image, a road information acquisition step for acquiring road information including position information of the feature, and a recognition result of the feature by the image recognition processing, An estimated vehicle position correcting step for correcting the estimated vehicle position based on position information of the feature included in the road information, wherein the vehicle position recognition method comprises a single feature or a predetermined feature. A recognition request range set for each recognized feature unit along the road length direction is obtained as a range to be subjected to the image recognition processing, with a feature group composed of a plurality of specified features as a recognized feature unit. Recognition requirements A recognition rate determination step for determining a recognition rate, which is a rate of successful image recognition, for each recognized feature unit based on an expected recognition rate predetermined for each type of feature, and the recognized feature unit A recognition target selection step of selecting the recognition feature unit to be recognized in the image recognition process from the plurality of recognition feature units whose recognition request ranges overlap each other based on the respective recognition rates of In the recognition rate determination step, the specific recognition feature unit at each point in time for the specific recognition feature unit that is the recognition feature unit composed of the feature group arranged separately in the road length direction. If a part of a plurality of features constituting the specific recognition feature unit is image-recognized according to the image recognition result of each feature constituting the remaining features constituting the specific recognition feature unit Said In that it performs a specific recognition rate determining process for determining the recognition rate based on the recognition rate.

  Naturally, these vehicle position recognition programs and vehicle position recognition methods can also obtain the effects of the vehicle position recognition system described above, and some additional examples given as examples of suitable configurations thereof. It is possible to incorporate technology.

It is a mimetic diagram showing a schematic structure of a navigation device concerning an embodiment of the present invention. It is a schematic diagram which shows an example of the running condition of the vehicle which concerns on embodiment of this invention, (a) shows the road network which a node and a link represent, (b) is provided in the road corresponding to (a), and the said road (C) shows a recognition request range and an overlapping area, and (d) shows a vehicle position recognized on the vehicle side on the road corresponding to (b). It is a schematic diagram which shows another example of the driving | running | working condition of the vehicle which concerns on embodiment of this invention, (a) shows the road network which a node and a link represent, (b) shows the road corresponding to (a), and the said road (C) shows a recognition request range and an overlapping area, and (d) shows the vehicle position recognized on the vehicle side on the road corresponding to (b). It is a conceptual diagram which shows an example of the information memorize | stored in the prediction recognition rate memory | storage part which concerns on embodiment of this invention. It is a flowchart which shows an example of the whole procedure of the own vehicle position recognition process which concerns on embodiment of this invention. It is a flowchart which shows an example of the procedure of the estimation own vehicle position correction process which concerns on embodiment of this invention. It is a flowchart which shows an example of the procedure of the image recognition process which concerns on embodiment of this invention.

  Embodiments of the present invention will be described with reference to the drawings. Here, the case where the vehicle position recognition system according to the present invention is applied to an in-vehicle navigation device will be described as an example. As shown in FIG. 1, the navigation device 1 according to the present embodiment includes a host vehicle position recognition unit 2, and a host vehicle position recognition system is built around the host vehicle position recognition unit 2.

  In the following description, “traveling direction front D1” and “traveling direction rear D2” (see FIG. 2) indicate that the host vehicle 3 (hereinafter, also referred to as “vehicle 3”) advances along the road length direction L. It is defined based on the state of traveling. Therefore, “traveling direction front D1” indicates a direction toward the front of the vehicle 3, and “traveling direction rear D2” indicates a direction toward the rear of the vehicle 3.

1. Schematic Configuration of Navigation Device As shown in FIG. 1, the navigation device 1 includes a host vehicle position recognition unit 2, a control unit 80, an estimated host vehicle position deriving unit 94, a road information storage unit 10, and an expected recognition rate storage. Part 11. The own vehicle position recognition unit 2 and the control unit 80 include a plurality of functional units.

  Each functional unit included in the navigation device 1 is a hardware or software (functional or functional unit for performing various processes on input data using a common arithmetic processing unit such as a CPU or the like as a core member. Program) or both. These functional units are configured to be able to exchange information with each other via a communication line, and are configured to be able to extract data from the storage units 10 and 11. Here, when each functional unit is configured by software (program), the software is stored in a storage device that can be referred to by the arithmetic processing device.

  The road information storage unit 10 and the expected recognition rate storage unit 11 are databases configured by a storage device. This storage device includes, as a hardware configuration, a recording medium capable of storing and rewriting information, such as a hard disk drive and a flash memory. Each of the storage units 10 and 11 may have independent hardware, or may be provided in common hardware.

  The control unit 80 includes a route setting unit 81, a route search unit 82, and a route guide unit 83. The route setting unit 81 is a functional unit that sets, for example, a departure place such as the vehicle position, an input destination, a passing point, and traveling conditions (whether or not an expressway is used). The route search unit 82 is a functional unit that performs calculation processing (route search processing) for searching for a guide route from the departure point to the destination based on the conditions set by the route setting unit 81. The route guidance unit 83 operates according to the guidance from the display screen of a monitor (not shown) or voice guidance from a speaker (not shown) according to the route from the departure point to the destination searched by the route search unit 82. It is a functional part which performs the calculation process (route guidance process) for performing suitable route guidance with respect to a person.

  The road information storage unit 10 stores (stores) road information RD (road map data) that is referred to when the above-described route search processing or route guidance processing is executed, or when map display processing on a monitor is executed. ) In the present embodiment, the road information RD includes, as conceptually shown in FIG. 2A, information on a large number of nodes N having position information on a map expressed by latitude and longitude, and two nodes N. Information of a number of links K that are connected to form a route corresponding to a road. The node N is set at a road intersection, a turning point, a branch point, or the like, for example.

  The road information RD includes road type information (types such as highways, toll roads, national roads, prefectural roads), link length information, and the like as link information (link attributes) of each link K. The road information RD also includes information on shape interpolation points that are arranged between the two nodes N (that is, on the link K) and indicate the detailed shape of the link K, and information on the road width.

  In addition, the road information RD includes information (feature information) of various features 50 provided on or around the road. The feature 50 in which the feature information is stored in the road information storage unit 10 includes a road marking and a three-dimensional structure whose relative position with respect to the road is fixed. Here, the road marking is a symbol or character for regulation or instruction provided on the road surface by painting or the like. The road marking includes, for example, a sign indicating that it is a pedestrian crossing (see pedestrian crossing sign 51, FIG. 2B), a sign indicating a stop line (see stop line sign 53, FIG. 3B), lane marking Signs (division line markings) representing the center line and lane boundary lines (lane marks), signs indicating that there is a pedestrian crossing ahead (see pedestrian crossing warning sign 52, Fig. 2 (b)), intersection shape Or a T-shaped marking (intersection shape marking) or the like. The three-dimensional structure includes, for example, various three-dimensional objects such as traffic lights, signs, overpasses, and tunnels, in addition to three-dimensional objects for forming lanes such as separation bands, curbs, side grooves, and the like.

  The feature information includes at least position information and attribute information of the feature 50. Here, the position information is information representing the position (latitude and longitude) of the feature 50 on the map. Basically, the representative point of the feature 50 (for example, the center of the feature 50 in the length direction and the width direction). ). The attribute information is information representing the attribute of the feature 50. In this example, the attribute information includes type information and form information. The type information is information representing the type of the feature 50, and basically the feature 50 having the same shape is defined as one type. In the present embodiment, the types of the features 50 include “pedestrian crossing sign”, “pedestrian crossing notice sign”, and “stop line sign” as shown in FIG. The form information is information representing the form of the feature 50 and has information such as the shape and size of the feature 50.

  The road information RD as described above is made into a database and stored in a form according to the specifications of the road information storage unit 10. For example, the road information RD may be divided into a plurality of layers associated with each other and stored in the road information storage unit 10. Specifically, a layer (road network layer) indicating connection information between roads by the node N and the link K, a layer (road shape layer) indicating information on shape interpolation points and road widths, and detailed information on roads ( The road information RD can be divided into at least three layers including a layer (road attribute layer) indicating information on various features 50 provided on or around the road.

  The estimated own vehicle position deriving unit 94 derives an estimated own vehicle position EP that is an estimated position of the own vehicle 3 based on outputs of the GPS measurement unit 91, the distance sensor 92, and the direction sensor 93 provided in the vehicle 3. Part. Specifically, the estimated own vehicle position deriving unit 94 analyzes a GPS (Global Positioning System) signal acquired from the GPS measurement unit 91, derives the current position (latitude and longitude) of the own vehicle 3, and obtains GPS position data. Get. The estimated vehicle position deriving unit 94 derives a dead reckoning position based on the moving distance information and the direction information acquired from the distance sensor 92 and the direction sensor 93, and obtains dead reckoning position data. Then, the estimated own vehicle position deriving unit 94 performs a calculation for deriving the estimated own vehicle position EP that is the estimated position of the own vehicle 3 from the GPS position data and the dead reckoning position data by a known method, and the derived estimated own vehicle Information on the position EP is output to the vehicle position recognition unit 2.

  The estimated vehicle position EP derived as described above is information including a measurement error, and may be off the road depending on the case. In this embodiment, in such a case, based on the road map data stored in the road information storage unit 10, the estimated vehicle position deriving unit 94 adjusts the estimated vehicle position EP on the road shown on the road map. (Map matching process) is performed, and information on the estimated vehicle position EP after the correction is output to the vehicle position recognition unit 2.

  The own vehicle position recognition unit 2 includes functional units 22 to 27 for correcting the estimated own vehicle position EP acquired from the estimated own vehicle position deriving unit 94. The configuration of the host vehicle position recognition unit 2 will be described in detail in the section “2. Configuration of the host vehicle position recognition unit” later. The host vehicle position recognition unit 2 is a camera 90 ( By correcting the estimated vehicle position EP using the captured image PG according to FIGS. 1 and 2, it is possible to recognize the vehicle position with higher accuracy than the estimated vehicle position EP.

  In this embodiment, as shown in FIG. 2B, the camera 90 is a back camera (rear camera) that captures the rear of the vehicle 3, and an image PG captured by the camera 90 is behind the vehicle 3 (rear in the traveling direction). D2 side) road surface is included. Specifically, in this embodiment, the camera 90 is installed in the vehicle 3 with a depression angle (for example, about 30 degrees) on the optical axis so that the road surface is mainly photographed, and the estimated vehicle position EP is The feature 50 as a target in the image recognition for correction is a road marking provided on the road surface.

2. Next, the configuration of the vehicle position recognition unit 2, which is a main part of the present invention, will be described. As shown in FIG. 1, the vehicle position recognition unit 2 includes an estimated vehicle position acquisition unit 21, an image processing unit 22, a road information acquisition unit 23, an estimated vehicle position correction unit 24, a recognition target selection unit 25, a recognition rate. A determination unit 26 and a recognition request range acquisition unit 27 are provided.

2-1. Configuration of Estimated Own Vehicle Position Acquisition Unit The estimated own vehicle position acquisition unit 21 is a functional unit that acquires an estimated own vehicle position EP that is an estimated position of the own vehicle 3. In the present embodiment, the estimated own vehicle position obtaining unit 21 obtains the estimated own vehicle position EP by inputting the estimated own vehicle position EP derived by the estimated own vehicle position deriving unit 94 to the estimated own vehicle position obtaining unit 21. To do.

2-2. Configuration of Image Processing Unit The image processing unit 22 is a functional unit that acquires a captured image PG captured by the camera 90 provided in the vehicle 3 and performs image recognition processing of the feature 50 included in the captured image PG. . That is, the image processing unit 22 has an image acquisition function and an image recognition function. The image processing unit 22 performs image recognition processing on the recognition feature unit 60 as shown in FIG. 2D and FIG. Here, the recognized feature unit 60 is a single feature 50 or a feature group (feature set) composed of a plurality of predetermined features 50. In the example shown in FIG. 2D and FIG. 3D, the first recognized feature unit 61 is composed of a single feature 50. On the other hand, each of the second recognized feature unit 62 and the third recognized feature unit 63 is configured by a feature group including a plurality of features 50 arranged at different positions.

  Specifically, the first recognized feature unit 61 is composed of a single pedestrian crossing sign 51. In addition, each of the second recognized feature unit 62 and the third recognized feature unit 63 is composed of a feature group including a plurality (two in this example) of features 50 of the same type. The second recognized feature unit 62 is composed of a feature group composed of two pedestrian crossing warning signs 52, and the third recognized feature unit 63 is composed of a feature group composed of two stop line signs 53. ing.

  Note that the recognized feature unit 60 is configured by the feature 50 in a form capable of specifying at least the position in the road length direction L when the image is recognized (that is, when the image recognition is successful). Therefore, the feature 50 that is continuously or intermittently provided along the road length direction L such as a lane marking (not shown) basically does not constitute the recognized feature unit 60.

  In addition, each feature 50 basically constitutes a recognized feature unit 60 alone, but two pedestrian crossing warning signs 52 shown in FIG. 2 (d) and two stop line signs 53 shown in FIG. 3 (d). As described above, with respect to a plurality of features 50 (feature group) of the same type arranged close to the road length direction L, the plurality of features 50 are set as one set to suppress erroneous recognition. The formation rule of the recognized feature unit 60 is determined so that the recognized feature unit 60 is configured. And the recognition feature unit 60 which consists of such a feature group is made into the specific recognition feature unit 60a mentioned later. Here, “closely arranged” means that the distance in the road length direction L is equal to or smaller than a predetermined distance, or the width of the road length direction L occupied by the feature group is equal to or smaller than the predetermined distance. To do. This predetermined distance can be set based on the maximum value of an error that can be included in the estimated host vehicle position EP, and can be a value within a range of 10 meters or more and 100 meters or less, for example. Further, without being based on the interval in the road length direction L, “arranged in close proximity” can be a positional relationship in which the feature-specific required ranges AF described later overlap each other.

  The image processing unit 22 acquires the captured image PG within the recognition request range A and performs image recognition of the recognition feature unit 60 to be recognized. The captured images PG at predetermined time intervals by the camera 90 are temporarily stored in a buffer memory (not shown). The image processing unit 22 acquires the captured image PG from this buffer memory. Here, the recognition request range A is a range that is set along the road length direction L (that is, along the link K) as a range for performing image recognition processing, and is shown in FIGS. 2 (c) and 3 (c). Is set for each recognized feature unit 60 as shown in FIG. Then, the image processing unit 22 basically performs image recognition processing on the captured image PG in the recognition request range A with the recognition feature unit 60 corresponding to the recognition request range A as a recognition target. However, as shown in FIG. 2C and FIG. 3C, when the recognition request range A has an overlapping region B that overlaps with another recognition request range A, the captured image PG in the overlap region B Is performed with the recognition feature unit 60 selected by the recognition target selection unit 25 described later as a recognition target.

  In the present embodiment, the captured image PG captured by the camera 90 in a state where the estimated host vehicle position EP is included in the recognition request range A is set as a captured image in the recognition request range A. A position (for example, an end on the forward direction D1 side in the traveling direction in the photographed image PG) determined based on the estimated own vehicle position EP and the installation form of the camera 90 on the vehicle 3 (attachment position, attachment angle, angle of view, etc.) The captured image PG that is included in the recognition request range A for the position (that is, the position shown in the end) or the position of the camera 90) can be used as the captured image PG in the recognition request range A. .

  Then, when all (single or plural) features 50 constituting the recognition feature unit 60 to be recognized are image-recognized, the image processing unit 22 has succeeded in image recognition of the recognition feature unit 60. And information of the determination result is output to the estimated own vehicle position correcting unit 24. Note that the image recognition processing by the image processing unit 22 is, for example, a pattern matching (template matching) method based on the contour information acquired from the captured image PG and the form information of the recognition target feature 50 included in the road information RD. It can be set as the structure performed using.

2-3. Configuration of Road Information Acquisition Unit The road information acquisition unit 23 is a functional unit that acquires road information RD including position information of the feature 50. In the present embodiment, the road information acquisition unit 23 extracts and acquires road information RD from the road information storage unit 10, and the road information RD acquired by the road information acquisition unit 23 is recognized by the recognition target selection unit 25. It is used in various processes executed by the vehicle position recognition unit 2 including a unit 60 selection process, a recognition rate determination process by the recognition rate determination unit 26, and an estimated vehicle position correction process by the estimated vehicle position correction unit 24. .

  The road information acquisition unit 23 selects a recognized feature unit 60 (that is, a target of image recognition processing by the image processing unit 22 from among a plurality of recognized feature units 60 whose position information is stored in the road information storage unit 10 (that is, The recognition feature unit 60) of the processing candidate is extracted, and the feature information of the recognition feature unit 60 (specifically, feature information of each feature 50 constituting the recognition feature unit 60) is acquired. . In the present embodiment, the road information acquisition unit 23 sets a predetermined search range on the forward direction D1 side with respect to the vehicle 3 based on the estimated own vehicle position EP acquired by the estimated own vehicle position acquisition unit 21, and performs the search. The feature information of the recognized feature unit 60 of the processing candidate existing within the range is acquired. The acquisition of the feature information is performed until at least the estimated own vehicle position EP enters the recognition request range A for the recognized feature unit 60 of the processing candidate.

  Here, the recognized feature unit 60 of the processing candidate is a recognized feature unit 60 whose existence position has been grasped in advance, and can be included in a captured image PG photographed in the future in a state where image recognition is possible. The form is recognized feature unit 60. In the present embodiment, as described above, since the camera 90 mainly captures the road surface behind the vehicle, the recognized feature unit 60 or the like including the three-dimensional feature 50 such as a traffic light is excluded, and the processing candidate is selected. A recognized feature unit 60 is selected.

  In this embodiment, information of the recognized feature unit 60 for each feature 50 is stored in the road information storage unit 10 in advance, but the road information acquisition unit 23 is stored in the road information storage unit 10. Each time the feature information of the feature 50 existing within the search range is acquired based on the feature information of the feature 50 and the formation rule of the recognized feature unit 60, the recognized feature unit of the feature 50 is acquired. 60 may be set.

2-4. Configuration of Recognition Request Range Acquisition Unit The recognition request range acquisition unit 27 is a functional unit that acquires a recognition request range A set for each recognition feature unit 60 along the road length direction L as a range for performing image recognition processing. is there. The recognition request range acquisition unit 27 acquires the recognition request range A for each recognition candidate unit 60 of the processing candidate extracted from the road information storage unit 10 by the road information acquisition unit 23. Specifically, in the present embodiment, the recognition request range acquisition unit 27 is based on the feature information (specifically position information) of the recognition feature unit 60 of the processing candidate and the setting rule for the recognition request range A, A recognition request range A is set and acquired. That is, in this embodiment, the recognition request range acquisition unit 27 has a recognition request range setting function and a recognition request range acquisition function.

  In the present embodiment, as shown in FIG. 2C and FIG. 3C, the recognition request range A is a feature-specific request range AF set for each feature 50 constituting the recognition feature unit 60. Set based on. For this reason, in the present embodiment, the setting rule for the recognition request range A includes the size of the feature-specific request range AF (the size in the road length direction L), the feature-specific request range AF, and the feature 50 to be set. And the positional relationship between the feature-specific required range AF and the recognition required range A.

  Specifically, each element defined by the setting rule for the recognition request range A will be described. In the present embodiment, the size of the feature-specific request range AF is set to the same value for all feature types. This value can be a fixed value, or can be set variably according to the vehicle speed, the travel distance from the previous correction by the estimated vehicle position correction unit 24, or the like. Then, by appropriately setting the size of the required range AF for each feature, the actual position of the recognition target feature 50 (the position in the road length direction L) can be determined with a high probability. It is possible to fit in. This point will be described later.

  In the present embodiment, the positional relationship between the feature-specific required range AF and the setting target feature 50 is the same positional relationship for all the feature types. Specifically, as shown in FIG. 2 and FIG. 3, the feature-specific required range AF (FIG. 2C, FIG. 3C) is the setting target feature 50 (FIG. 2) in the center of the range. 2 (d) and FIG. 3 (d)) are set to have the same length on both sides in the road length direction L with respect to the feature 50.

  In this embodiment, the arrangement relationship between the feature-specific required range AF and the recognition required range A is such that the feature-specific required range AF for all the features 50 constituting the same recognized feature unit 60 is The arrangement relation is included in the recognition request range A corresponding to the recognized feature unit 60. Specifically, as shown in FIG. 2C and FIG. 3C, the recognition request range A is a feature-specific request range for all the features 50 constituting the recognition feature unit 60 to be set. The minimum range including all AF is set. Therefore, for the recognized feature unit 60 composed of one feature 50 like the first recognized feature unit 61, the recognition required range A and the feature-specific required range AF are equal.

  Here, by appropriately setting the size of the required range AF for each feature, the actual position of the recognition target feature 50 (the position in the road length direction L) can be determined with a high probability. The reason why it can be accommodated within will be described with reference to FIG. The same applies to FIG. FIG. 2B is a diagram showing the actual state of the road, and the position of the vehicle 3 on the road is shown as an actual position. FIG. 2A shows road information RD corresponding to the road shown in FIG. On the other hand, FIG. 2 (d) shows the vehicle position on the map data recognized on the vehicle 3 side based on the estimated vehicle position EP on the road shown in FIG. 2 (b). In this example, Due to the error included in the estimated host vehicle position EP, the estimated host vehicle position EP is shifted to the rear direction D2 side in the traveling direction with respect to the actual position of the vehicle 3 (FIG. 2B). In FIG. 2D, for the convenience of explanation, the road information RD is forward in the traveling direction so that the estimated own vehicle position EP is the same position in the road length direction L as the vehicle 3 in FIG. Shown shifted to the D1 side.

  In such a case, the position of each feature 50 (FIG. 2D) specified on the vehicle 3 side based on the estimated own vehicle position EP and road information RD (specifically, position information of the feature 50) is actual. It shifts to the front direction D1 side in the traveling direction with respect to the position (FIG. 2B). At this time, by appropriately setting the size of the required range AF for each feature, that is, by setting the size of the required range AF for each feature in consideration of an error that may be included in the estimated vehicle position EP. The actual position (FIG. 2 (b)) of the corresponding feature 50 is included in the feature-specific required range AF (FIG. 2 (c)) set based on the estimated own vehicle position EP. Can do. The size of the required range AF for each feature can be set to, for example, a value that is twice or more than the maximum value of the error that can be included in the estimated vehicle position EP.

2-5. Configuration of Estimated Own Vehicle Position Correction Unit The estimated own vehicle position correction unit 24 recognizes the recognition result of the feature 50 (recognized feature unit 60) by the image recognition processing of the image processing unit 22 and the feature 50 included in the road information RD. This is a functional unit that corrects the estimated vehicle position EP based on the position information. That is, when the image processing unit 22 succeeds in the image recognition of the recognized feature unit 60 by the image processing unit 22, the estimated vehicle position correcting unit 24 estimates using the position information of the feature 50 constituting the recognized feature unit 60. The own vehicle position EP is corrected. In this example, the estimated host vehicle position correcting unit 24 corrects the estimated host vehicle position EP at least in the road length direction L.

  Specifically, the estimated own vehicle position correcting unit 24 is based on the installation form of the camera 90 on the vehicle 3 and at the time of acquiring the captured image PG in which the feature 50 constituting the recognized feature unit 60 is recognized. The positional relationship between the host vehicle 3 and the recognized feature unit 60 (the recognized feature 50) is calculated. At this time, the position and size of the recognized feature unit 60 in the captured image PG are taken into consideration. The estimated vehicle position correction unit 24 uses the calculation result of the positional relationship and the feature information (specifically, position information) of the recognized feature unit 60 included in the road information RD acquired by the road information acquisition unit 23. Based on the calculation based on the information, a highly accurate vehicle position (feature-dependent vehicle position) based on the feature information is acquired. It is also possible to use a predetermined fixed positional relationship without performing the calculation of the positional relationship.

  Depending on the setting form of the camera 90, the position of the host vehicle 3 at the time of acquiring the captured image PG in which the features 50 constituting the recognized feature unit 60 are recognized is identified with the position of the recognized feature unit 60. It is also possible. In this case, the feature-based vehicle position is the same as the position of the recognized feature unit 60. Further, when the recognized feature unit 60 that has succeeded in image recognition is configured by a group of a plurality of features 50 (that is, the captured image PG that has been image-recognized is a plurality of features 50 that constitute the recognized feature unit 60. For example, the feature-based vehicle position is acquired using only the photographed image PG in which the feature 50 located closest to the front side D1 in the traveling direction is image-recognized. In addition, an average value of the feature-dependent vehicle positions derived from the plurality of captured images PG in which each of the plurality of features 50 is image-recognized is set as the final feature-dependent vehicle position. You can also

  Then, the estimated vehicle position correction unit 24 corrects the estimated vehicle position EP by replacing the acquired feature-dependent vehicle position with the estimated vehicle position EP. In addition, the vehicle itself is not considered in place of the position, but considering the travel distance (capable of being acquired from the distance sensor 92) from the time of photographing of the photographed image PG in which the feature 50 constituting the recognized feature unit 60 is image-recognized. A configuration in which the position is adjusted is also possible.

2-6. Configuration of Recognition Target Selection Unit The recognition target selection unit 25 selects an image processing unit from among a plurality of recognition feature units 60 whose recognition request ranges A overlap each other based on the respective recognition rates R of the recognition feature units 60. 22 is a functional unit that selects a recognition feature unit 60 to be recognized in the image recognition processing by the image recognition process 22. Note that the recognition rate R is an index (estimated value of the success rate) indicating the rate of successful image recognition of the recognized feature unit 60 (the rate at which the recognized feature unit 60 is image-recognized). Determined by the unit 26.

  As described above, for the captured image PG in the recognition request range A, basically, the image recognition process by the image processing unit 22 is executed with the recognition feature unit 60 corresponding to the recognition request range A as a recognition target. The However, as shown in FIG. 2C and FIG. 3C, when the recognition request range A has an overlapping region B that overlaps with another recognition request range A, the captured image PG in the overlap region B As for the recognition feature unit 60 selected by the recognition target selection unit 25, the recognition target unit 60 is set as the recognition target. At this time, the recognition target selection unit 25 selects the recognized feature unit 60 having the highest recognition rate R from among the plurality of recognized feature units 60 in which the recognition request range A overlaps with each other in the overlapping region B. When there are a plurality of recognized feature units 60 having the highest recognition rate R, it is possible to select one recognized feature unit 60 based on other conditions. For example, the feature 50 closer to the intersection is more likely to be photographed under a situation where the speed change of the vehicle 3 is large, and as a result, it is more distant from the intersection in consideration of the general tendency that image recognition becomes difficult. The recognized feature unit 60 can be selected.

  Specifically, with reference to FIG. 2C, the first recognized feature is not recognized for the captured image PG in the non-overlapping area excluding the overlapping area B in the first recognition request range A1 regardless of the recognition rate R. A unit 61 (pedestrian crossing sign 51) is a recognition target. On the other hand, for the captured image PG in the non-overlapping area excluding the overlapping area B in the second recognition request range A2, regardless of the recognition rate R, the second recognized feature unit 62 (pedestrian crossing warning sign 52) is the recognition target. Is done.

  For the captured image PG in the overlapping area B, the recognition target to be recognized according to the magnitude relationship between the recognition rate R of the first recognition feature unit 61 and the recognition rate R of the second recognition feature unit 62. An object unit 60 is selected. Specifically, for the captured image PG in the overlapping region B, when the recognition rate R of the first recognized feature unit 61 is higher than the recognition rate R of the second recognized feature unit 62, the first recognized feature unit. When 61 (pedestrian crossing sign 51) is a recognition target and the recognition rate R of the second recognized feature unit 62 is higher than the recognition rate R of the first recognized feature unit 61, the second recognized feature unit 62 (crossing) The sidewalk notice sign 52) is the recognition target.

  As will be described later, for the specific recognition feature unit 60a that is the specific recognition feature unit 60, the recognition rate R is once again determined (re-determined) by the recognition rate determination unit 26 after the recognition rate R is once determined. There is a case. When the recognition rate R is redetermined, the recognition target selection unit 25 reselects the recognition feature unit 60 to be recognized for the captured image PG in the overlapping area B based on the recognition rate R after the redetermination. Is configured to do. Of course, the same recognized feature unit 60 may be selected again by the reselection process.

2-7. Configuration of Recognition Rate Determining Unit The recognition rate determining unit 26 determines a recognition rate R, which is a rate of successful image recognition, for each recognized feature unit 60 based on an expected recognition rate ER determined in advance for each type of the feature 50. It is a functional part to be determined. In order to realize such a function, the recognition rate determination unit 26 includes an expected recognition rate acquisition unit 31, a normal recognition rate determination processing unit 32, and a specific recognition rate determination processing unit 33 in this example. In the present embodiment, the recognition request range A is configured to determine the recognition rate R only for the recognized feature unit 60 having the overlapping region B.

2-7-1. Configuration of Expected Recognition Rate Acquisition Unit The expected recognition rate acquisition unit 31 is a functional unit that acquires the expected recognition rate ER of each feature 50 constituting the recognized feature unit 60. In the present embodiment, the predicted recognition rate ER is associated with the feature type and stored in the predicted recognition rate storage unit 11, and the predicted recognition rate acquisition unit 31 receives the required predicted recognition rate from the predicted recognition rate storage unit 11. Extract and obtain ER.

  Here, the expected recognition rate ER represents an average success rate (success probability) of image recognition, which is predetermined for each type of the feature 50, and is set to a value of 0 or more and 1 or less. In the present embodiment, the expected recognition rate ER is uniquely determined for each feature type according to the form of the feature 50 according to the feature type, the arrangement tendency, and the like. In the example illustrated in FIG. 5, the expected recognition rates ER of the pedestrian crossing sign 51, the pedestrian crossing notice sign 52, and the stop line sign 53 are set to “ER1”, “ER2”, and “ER3”.

2-7-2. Configuration of Normal Recognition Rate Determination Processing Unit The normal recognition rate determination processing unit 32 is a functional unit that executes normal recognition rate determination processing. The recognition rate determination process by the recognition rate determination unit 26 is basically a normal recognition rate determination process. Only in a specific case, the specific recognition rate determination processing by the specific recognition rate determination processing unit 33 described later is executed, and a recognition rate R different from the recognition rate R determined by the normal recognition rate determination processing is determined. The That is, it can be said that the normal recognition rate determination process is a recognition rate determination process other than the specific recognition rate determination process.

  In the normal recognition rate determination process, unlike the specific recognition rate determination process described later, the expected recognition rate ER is set regardless of the image recognition result at each time point of the feature 50 constituting the recognition feature unit 60 to be determined. Based on this, the recognition rate R is determined. In the present embodiment, the normal recognition rate determination processing unit 32 performs a calculation based on the predicted recognition rate ER acquired by the predicted recognition rate acquisition unit 31 and determines the recognition rate R of the recognized feature unit 60.

  Specifically, the normal recognition rate determination processing unit 32 derives the recognition rate R by multiplying the expected recognition rates ER of all the features 50 constituting the recognized feature unit 60 with each other. That is, the recognition rate R of the recognized feature unit 60 determined in the normal recognition rate determination process other than the specific recognition rate determination process is equal to the expected recognition rate ER of all the features 50 constituting the recognized feature unit 60. A value obtained by multiplication is uniquely determined based on the type and number of the features 50 constituting the recognized feature unit 60. When the recognized feature unit 60 is composed of a single feature 50, the recognition rate R of the recognized feature unit 60 is equal to the expected recognition rate ER of the feature 50.

  Specifically, referring to FIG. 2 and FIG. 3, the recognition rate R determined by the normal recognition rate determination process is “ER1” for the first recognized feature unit 61 composed of one pedestrian crossing sign 51. “ER2 × ER2” for the second recognized feature unit 62 composed of two pedestrian crossing warning signs 52, and “ER3 × for the third recognized feature unit 63 composed of two stop line markings 53”. ER3 ".

2-7-3. Configuration of Specific Recognition Rate Determination Processing Unit The specific recognition rate determination processing unit 33 is a functional unit that executes specific recognition rate determination processing. The specific recognition rate determination process is a process of determining the recognition rate R of the specific recognition feature unit 60a that is the specific recognition feature unit 60. When the recognition rate R is determined (re-determined) by the specific recognition rate determination processing unit 33 for the specific recognition feature unit 60a for which the recognition rate R has already been determined by the normal recognition rate determination processing unit 32 The recognition rate R determined by the specific recognition rate determination processing unit 33 is replaced with the recognition rate R determined by the normal recognition rate determination processing unit 32 to obtain a new recognition rate R.

  Here, the “specific recognition feature unit 60a” is a recognition feature unit 60 including a group of features arranged separately in the road length direction L. Specifically, the specific recognition feature unit 60a is composed of a plurality of features 50 of the same type arranged separately in the road length direction L. More specifically, as described above, the road length It is composed of a plurality of features 50 of the same type that are divided in the direction L and arranged close to each other.

  In the example shown in FIG. 2, the second recognized feature unit 62 is a specific recognized feature unit 60a composed of two features 50 of the same type (specifically, a pedestrian crossing warning sign 52). In the example shown in FIG. 3, the third recognized feature unit 63 is a specific recognized feature unit 60a composed of two features 50 (specifically, stop line markings 53) of the same type. As can be seen from these specific examples, the plurality of features 50 constituting the specific recognition feature unit 60a may be arranged on the same lane (see FIG. 2) or in different lanes (for example, adjacent lanes). In some cases (see FIG. 3). In addition, there are cases where a plurality of features 50 constituting the specific recognition feature unit 60a are continuously arranged in the road length direction L (see FIG. 2), and there are other features 50 and intersections (node N). ) May be provided on both sides of the road length direction L (see FIG. 3).

  The specific recognition rate determination processing unit 33 constituting the recognition rate determination unit 26 grasps the image recognition result of each feature 50 constituting the specific recognition feature unit 60a at each time point based on the recognition result by the image processing unit 22. When a part of the plurality of features 50 constituting the specific recognition feature unit 60a is image-recognized, the specific recognition rate determination process is executed. In the specific recognition rate determination process, the recognition rate R is determined based on the expected recognition rate ER of the remaining features 50 constituting the specific recognition feature unit 60a. In the present embodiment, the specific recognition rate determination processing unit 33 performs a calculation based on the predicted recognition rate ER acquired by the predicted recognition rate acquisition unit 31, and determines the recognition rate R of the specific recognition feature unit 60a.

  Specifically, the specific recognition rate determination processing unit 33 predicts the recognition rates ER of all the remaining features 50 excluding the image-recognized features 50 among the features 50 constituting the specific recognition feature unit 60a. Is multiplied by each other to derive the recognition rate R. That is, the recognition rate R of the specific recognition feature unit 60a determined in the specific recognition rate determination process is a value obtained by multiplying the expected recognition rates ER of all the remaining features 50 by one another, and the remaining feature 50 It is uniquely determined based on the type and number. In other words, the recognition rate R determined in the specific recognition rate determination process is the recognition rate determined in the normal recognition rate determination process when the expected recognition rate ER of the image-recognized feature 50 is replaced with “1.0”. It becomes equal to the rate R.

  The specific recognition rate determination process is executed only after a part of the plurality of features 50 constituting the specific recognition feature unit 60a is image-recognized. Therefore, the specific recognition rate determination process is basically performed in a state before the specific recognition rate determination process is executed. Furthermore, the recognition rate R determined by the normal recognition rate determination process is set as the recognition rate R of the specific recognition feature unit 60a. Since the expected recognition rate ER is set to a value of 1 or less as described above, the recognition rate R determined by the specific recognition rate determination process is equal to or higher than the recognition rate R determined by the normal recognition rate determination process. It becomes. Thereby, the recognition feature unit selected before re-determination of the recognition rate R by the recognition target selection processing executed by the recognition target selection unit 25 after the re-determination of the recognition rate R by the specific recognition rate determination processing unit 33 A recognized feature unit 60 different from 60 may be selected.

  A specific description will be given with reference to the example shown in FIG. Here, the first expected recognition rate ER1 that is the expected recognition rate ER of the pedestrian crossing sign 51 is “0.7”, and the second expected recognition rate ER2 that is the expected recognition rate ER of the pedestrian crossing notice sign 52 is “0”. .8 ”will be described as an example. When the estimated vehicle position EP has not entered either the first recognition request range A1 or the second recognition request range A2, the recognition of the first recognition feature unit 61 determined by the normal recognition rate determination processing unit 32 is performed. The rate R is “0.7”, and the recognition rate R of the second recognition feature unit 62 determined by the normal recognition rate determination processing unit 32 is “0.64 (= 0.8 × 0.8)”. As a result, the first recognized feature unit 61 is selected (provisionally determined) as the recognized feature unit 60 to be recognized in the overlapping region B.

  When the estimated vehicle position EP enters the second recognition required range A2 (state shown in FIG. 2D), the second recognized feature unit 62 (crosswalk notice) until the vehicle enters the overlapping area B. Image recognition processing is performed on the continuously acquired captured image PG with the sign 52) as a recognition target. If the pedestrian crossing warning sign 52 is image-recognized before the estimated vehicle position EP enters the overlap area B, the recognition rate R is determined again by the specific recognition rate determination processing unit 33, and the second recognition feature The recognition rate R of the unit 62 is changed from “0.64” to “0.8 (= 1.0 × 0.8)”. Then, the re-selection processing of the recognized feature unit 60 is executed by the recognition target selecting unit 25, and the second recognized feature unit 62 is selected as the recognized feature unit 60 to be recognized in the overlapping region B. In this case, even after the estimated own vehicle position EP enters the overlapping area B, the image recognition process is continuously performed on the second recognized feature unit 62 (the pedestrian crossing notice sign 52) as a recognition target. Therefore, the image recognition process for which the first recognized feature unit 61 is a recognition target can be executed only in a state where the estimated own vehicle position EP is located in a non-overlapping area excluding the overlapping area B in the first recognition request range A1. .

  On the other hand, when the estimated own vehicle position EP enters the overlap area B without image recognition of the pedestrian crossing warning sign 52, the recognition rate R is re-determined by the specific recognition rate determination processing unit 33 and the recognition target is selected. The re-selection processing of the recognized feature unit 60 by the unit 25 is not executed, and the recognized feature unit 60 to be recognized is selected according to the selection of the recognized feature unit 60 based on the recognition rate R determined by the normal recognition rate determination processing unit 32. Is switched from the second recognized feature unit 62 (pedestrian crossing warning sign 52) to the first recognized feature unit 61 (pedestrian crossing sign 51). Then, in the first recognition request range A1 including the overlapping region B, the image recognition process is performed with the first recognition feature unit 61 as a recognition target.

  In the present embodiment, when the image recognition of any one recognized feature unit 60 is successful with respect to a plurality of recognized feature units 60 having overlapping recognition request ranges A, the other recognized feature units 60 are changed. It is configured not to perform image recognition processing as a recognition target. Therefore, at least one pedestrian crossing warning sign 52 is image-recognized until the estimated own vehicle position EP enters the overlapping area B, and the estimated own vehicle position EP is located within the first recognition request range A1. When the two pedestrian crossing warning signs 52 are image-recognized in the state, the feature recognition information of the second recognized feature unit 62 is not executed without executing the image recognition processing for the first recognized feature unit 61 as a recognition target. Correction processing of the estimated own vehicle position EP based on the above is executed.

  The same applies to the example shown in FIG. 3. The first expected recognition rate ER1 that is the expected recognition rate ER of the pedestrian crossing sign 51 is “0.7”, and the third is the expected recognition rate ER of the stop line sign 53. Assuming that the predicted recognition rate ER3 is “0.8”, the third recognized feature unit 63 (stop line marking 53) is image-recognized before the estimated own vehicle position EP enters the overlapping area B. In this case, even after the estimated own vehicle position EP enters the overlapping area B, the image recognition process is continuously executed with the third recognized feature unit 63 as a recognition target.

  On the other hand, when the estimated host vehicle position EP enters the overlap area B without the image of the stop line marking 53 being recognized, the recognized feature unit 60 to be recognized is the third recognized feature unit 63 (stop line). The sign recognition 53) is switched to the first recognition feature unit 61 (the pedestrian crossing sign 51), and the image recognition processing is performed in the overlap region B with the first recognition feature unit 61 as a recognition target. In the example shown in FIG. 3, since the first recognition request range A1 forms a part of the third recognition request range A3, the pedestrian crossing sign 51 is present in the overlapping region B (same as the first recognition request range A1). If the image is not recognized, the image recognition process is performed again with the third recognition feature unit 63 as the recognition target in the third recognition request range A3 located on the forward direction D1 side from the overlapping region B. In this case, since it is substantially difficult to recognize the two stop line markings 53 constituting the third recognized feature unit 63, the crossing is performed in the overlapping region B (same as the first recognition request range A1). It is good also as a structure which complete | finishes the image recognition process with respect to these 1st recognition feature units 61 and the 3rd recognition feature unit 63 at the time of the sidewalk marking 51 not being recognized.

  By the way, in this embodiment, since the specific recognition feature unit 60a is composed of a plurality of features 50 of the same type, the one feature 50 is most advanced in a state where one feature 50 is image-recognized. It is not easy to determine whether or not the feature 50 is located on the direction rear side D2. For example, in the example illustrated in FIG. 2, when one pedestrian crossing warning sign 52 is image-recognized on the rear direction D2 side from the overlapping region B in the second recognition request range A2, the image-recognized pedestrian crossing warning sign 52 is recognized. Even if it is actually the pedestrian crossing warning sign 52 located on the front side D1 in the traveling direction, it is not easy to recognize this fact. When the specific recognition rate determination process is executed when the image-recognized pedestrian crossing warning sign 52 is the pedestrian crossing warning sign 52 located on the front side D1 in the traveling direction, another pedestrian crossing warning is displayed in the overlap area B. The recognition target in the overlap region B is switched from the first recognized feature unit 61 to the second recognized feature unit 62 depending on the magnitude of the expected recognition rate ER, although the sign 52 is not likely to be image-recognized. It will be.

  As described above, when the specific recognition rate determination process is executed only on the condition that a part of the plurality of features 50 constituting the specific recognition feature unit 60a is image-recognized, the other recognition feature units 60 are recognized. There is a possibility that the recognized feature unit 60 that is less likely to succeed in the image recognition than is selected as a recognition target in the overlapping region B.

  Therefore, in the present embodiment, the first determination region R1 is set inside the recognition request range A of the specific recognition feature unit 60a, and the recognition target feature 50 constituting the specific recognition feature unit 60a is the first determination. When the image is recognized in the region R1, the specific recognition rate determination process is executed as it is, and the feature 50 to be recognized is recognized in the second determination region R2 that is a region other than the first determination region R1 in the recognition request range A. When the image is recognized, the specific recognition rate determination process is prohibited from being executed. The first determination region R1 is set so as to include an end portion on the rear direction D2 side in the traveling direction in the feature-specific required range AF.

  In the present embodiment, as shown in FIG. 2C and FIG. 3C, the first determination region R1 travels in the feature-specific required range AF for the feature 50 that is located closest to the rearward direction D2 in the traveling direction. The position of the end of the first determination region R1 on the front direction D1 side is set to include the end of the first determination region R1, and the end of the first feature region required range AF on the front direction D1 side is set. Is set to the same position as or a position on the rear side D2 side in the traveling direction from the position. By setting the first determination region R1 in this way, there is a possibility that an image of the same type of feature 50 other than the feature 50 located closest to the rearward direction D2 in the traveling direction is recognized in the first determination region R1. The recognition feature unit 60 that can be suppressed to a low level and suppresses the occurrence of the above-described problem, that is, has a low possibility of succeeding in image recognition compared to other recognition feature units 60, is a recognition target in the overlapping region B. It is possible to suppress the occurrence of a situation selected as.

  In the example shown in FIGS. 2 and 3, the position of the end portion of the first determination region R1 on the front direction D1 side is the road length of the recognition request range A in which the first determination region R1 is set. It is set at the center in the direction L. The position of the end portion on the front direction D1 side in the traveling direction in the first determination region R1 is set to the center portion in the road length direction L of the feature-specific required range AF for the feature 50 located on the most rearward direction D2 side. It is also possible to do.

  Further, in the present embodiment, the specific recognition rate determination process is performed with other recognized feature units 60 and recognition request ranges, such as the second recognized feature unit 62 in FIG. 2 and the third recognized feature unit 63 in FIG. The specific recognition feature unit 60a in which A is a specific recognition feature unit 60a that overlaps each other, and has the feature 50 arranged on the rear direction D2 side with respect to the feature 50 constituting the other recognition feature unit 60 It is configured to be executed only for the unit 60a. Thereby, it is possible to suppress the calculation load by suppressing the determination process of the recognition rate R from being performed more than necessary. This is because when the specific recognition feature unit 60a does not satisfy the above-described requirements, the feature 50 constituting the specific recognition feature unit 60a is substantially image-recognized. When the EP is located in a region where the overlapping region B does not exist on the forward direction D1 side in the recognition request range A, or when the specific recognition feature unit 60a is selected as the recognition feature unit 60 to be recognized, This is limited to the case where the vehicle position EP is located within the overlap region B. In such a case, it is not necessary to select the recognized feature unit 60, or the same specific recognized feature unit 60a is selected again even if the re-selection processing of the recognized feature unit 60 is performed. Because.

  In order to further suppress that the determination process of the recognition rate R by the specific recognition rate determination processing unit 33 is performed more than necessary, the expected recognition rate ER of the feature 50 alone constituting the specific recognition feature unit 60a is a recognition request. When the range A is smaller than the recognition rate R of the other recognized feature units 60 that overlap each other, it is possible to prohibit the execution of the specific recognition rate determination process. For example, in the example shown in FIG. 2, when the first expected recognition rate ER1 is “0.9” and the second expected recognition rate ER2 is “0.8”, the normal recognition rate determination process and the specific recognition Even if the recognition rate R determined by any of the rate determination processes is used, the recognition feature unit 60 selected by the recognition target selection unit 25 becomes the first recognition feature unit 61, and therefore the specific recognition rate determination process Is prohibited. That is, the specific recognition feature unit 60a to be subjected to the specific recognition rate determination process is a specific recognition feature unit 60a in which the recognition request range A overlaps with another recognition feature unit 60, and the other recognition feature unit 60a. It can be limited to the specific recognition feature unit 60 a having the feature 50 having the predicted recognition rate ER larger than the recognition rate R of the feature unit 60.

  Further, when the recognition rate R determined by the normal recognition rate determination process for the specific recognition feature unit 60a is larger than the recognition rate R of other recognition feature units 60 whose recognition request ranges A overlap each other, It is possible to adopt a configuration that prohibits execution of the recognition rate determination process. For example, in the example illustrated in FIG. 2, the first predicted recognition rate ER1 that is the expected recognition rate ER of the pedestrian crossing sign 51 is “0.6”, and the second prediction that is the expected recognition rate ER of the pedestrian crossing notice sign 52. When the recognition rate ER2 is “0.8”, the recognition target selection unit 25 selects the recognition rate R determined by any of the normal recognition rate determination processing and the specific recognition rate determination processing. Since the recognized feature unit 60 becomes the second recognized feature unit 62, execution of the specific recognition rate determination process is prohibited. That is, the specific recognition feature unit 60a to be subjected to the specific recognition rate determination process is a specific recognition feature unit 60a in which the recognition request range A overlaps with another recognition feature unit 60, and the other recognition feature unit 60a. It can be limited to the specific recognition feature unit 60a whose recognition rate R determined by the normal recognition rate determination process is smaller than the recognition rate R of the feature unit 60.

3. Procedure of Operation Process Next, with reference to FIGS. 5 to 7, a procedure of the vehicle position recognition process executed in the vehicle position recognition unit 2 according to the present embodiment, that is, a vehicle position recognition method will be described. . The procedure of the vehicle position recognition process described below is executed by hardware and / or software (program) or both constituting each functional unit of the navigation device 1 (vehicle position recognition unit 2). When each of the above function units is configured by a program, the arithmetic processing device included in the navigation device 1 operates as a computer that executes the program that configures each of the above function units. FIG. 6 is a flowchart showing the procedure of the estimated host vehicle position correction process in step # 04 of FIG. 5, and FIG. 7 is a flowchart showing the procedure of the image recognition process in step # 17 of FIG.

3-1. Overall Procedure of Own Vehicle Position Recognition Processing As shown in FIG. 5, when the estimated own vehicle position acquisition unit 21 acquires the estimated own vehicle position EP (step # 01), the road information acquisition unit 23 displays the estimated own vehicle position. The road information RD within the search range set in front of the vehicle 3 based on the EP is acquired, and the recognition feature unit 60 is searched within the search range, and can be a target of image recognition processing by the image processing unit 22. A recognition feature unit 60 as a processing candidate is extracted (step # 02). If there is a recognized feature unit 60 as a processing candidate within the search range (step # 03: Yes), an estimated vehicle position correction process described below based on FIG. 6 is executed (step # 04). ). On the other hand, if there is no recognition feature unit 60 as a candidate for processing within the search range (step # 03: No), the processing ends. This own vehicle position recognition process is repeatedly executed at a predetermined timing.

3-2. Procedure of Estimated Vehicle Position Correction Process Next, the procedure of the estimated vehicle position correction process in step # 04 of FIG. 5 will be described with reference to FIG. When the recognition request range acquisition unit 27 acquires the recognition request range A for each recognition feature unit 60 as a processing candidate (step # 10), each of the acquired recognition request ranges A overlaps with other recognition request ranges A. It is determined whether or not there is an overlapping area B to be performed (step # 11). If none of the recognition request ranges A has the overlapping area B (step # 11: No), the process proceeds to step # 15.

  On the other hand, when at least one of the recognition request ranges A includes the overlapping area B (step # 11: Yes), the recognition feature unit 60 selection process is executed for each of the single or plural overlapping areas B. Specifically, the predicted recognition rate acquisition unit 31 acquires the predicted recognition rate ER for the constituent feature 50 for each recognition feature unit 60 in which the recognition request range A overlaps with each other in the overlapping region B (step S31). # 12) Based on the acquired expected recognition rate ER, the normal recognition rate determination processing unit 32 determines the recognition rate R for each recognized feature unit 60 (step # 13). Then, based on the determined recognition rate R, the recognition target selection unit 25 selects a recognition feature unit 60 to be subjected to image recognition in the overlapping region B (step # 14). When the selection process of the recognized feature unit 60 in step # 14 is completed for all overlapping regions B, the process proceeds to step # 15.

  The estimated own vehicle position EP (step # 15) acquired by the estimated own vehicle position acquisition unit 21 is within the recognition request range A that is located closest to the rearward direction D2 in the recognition request range A acquired in step # 10. When entering (step # 16: Yes), an image recognition process described below based on FIG. 7 is executed (step # 17).

3-3. Image Recognition Processing Procedure Next, the image recognition processing procedure in step # 17 of FIG. 6 will be described with reference to FIG. When the image processing unit 22 acquires the captured image PG (step # 20), an image recognition process for the target feature is executed (step # 21). Here, the “target feature” is the feature 50 constituting the recognized feature unit 60 determined according to the estimated own vehicle position EP, and the “recognized feature unit 60 determined according to the estimated own vehicle position EP” is When the estimated own vehicle position EP is located within the recognition request range A other than the overlap region B, the recognition feature unit 60 corresponding to the recognition request range A is set, and the estimated own vehicle position EP is within the overlap region B. If the recognized feature unit 60 selected in step # 14 in FIG. 6 or the processing in step # 28 described later is executed, it is reselected in this processing. The recognition feature unit 60 is used.

  When the target feature is image-recognized by the image recognition processing by the image processing unit 22 (step # 22: Yes), the recognized feature unit 60 is configured with respect to the recognized feature unit 60 formed by the target feature. A determination is made as to whether or not all the features 50 to be recognized have been recognized (step # 23). And when all the features 50 which comprise the recognition feature unit 60 are image-recognized (step # 23: Yes), the estimated own vehicle position correction | amendment part 24 based on the feature information of the said recognition feature unit 60 concerned. Executes a correction process for the estimated vehicle position EP (step # 24). In the present embodiment, when the correction process of the estimated vehicle position EP is executed based on the feature information of any recognized feature unit 60, the other recognized feature unit 60 extracted in step # 02 of FIG. Since the correction process based on is not executed, the process ends when the process of step # 24 is executed.

  On the other hand, when the target feature has not been recognized by the image recognition process in step # 21 (step # 22: No), the estimated own vehicle position EP acquired by the estimated own vehicle position acquisition unit 21 (step # 29) ) Is not positioned on the forward direction D1 side from all the recognition request ranges A acquired in step # 10 of FIG. 6 (step # 30: No), the estimated own vehicle position EP is within the recognition request range A. On the condition that it is located (step # 31: Yes), the processing from step # 20 is repeatedly executed. It should be noted that the process of one round of the vehicle position recognition process shown in FIG. 5 ends directly from the process of step # 30 (step # 30: Yes), and all the recognition locations extracted in step # 02 of FIG. This is a case where the object unit 60 is not recognized. Further, the process returns from the process of step # 31 to the process of step # 29 when the estimated own vehicle position EP is at a position sandwiched between two recognition request ranges A on both sides in the road length direction L. It is.

  If the target feature has been image-recognized by the image recognition process of step # 21 (step # 22: Yes), but not all the features 50 constituting the recognized feature unit 60 have been image-recognized (step #) 23: No), the process proceeds to step # 25. The process proceeds to step # 25 when the target feature recognized in step # 22 constitutes the specific recognized feature unit 60a. In step # 25, it is determined whether or not there is an overlapping area B in front of the estimated own vehicle position EP in the recognition request range A where the estimated own vehicle position EP is currently located (step # 25). If there is (step # 25: Yes), it is determined whether or not the target feature has been recognized in the first determination region R1 (step # 26). When the target feature is image-recognized in the first determination region R1 (step # 26: Yes), the specific recognition rate determination processing unit 33 executes the recognition rate R redetermination processing (step #). 27) The recognition target selection unit 25 executes a reselection process of the recognized feature unit 60 to be recognized in the overlap region B (step # 28), and the process proceeds to step # 29.

  On the other hand, in the recognition request range A where the estimated vehicle position EP is currently located, when there is no overlap area B in front of the estimated vehicle position EP (step # 25: No), the target area is within the first determination area R1. If the object has not been recognized (step # 26: No), the process proceeds to step # 29 without passing through the processes of step # 27 and step # 28.

4). Other Embodiments Finally, other embodiments of the vehicle position recognition system according to the present invention will be described. Note that the configurations disclosed in the following embodiments can be applied in combination with the configurations disclosed in other embodiments as long as no contradiction arises.

(1) In the above embodiment, when there is an overlapping area B that overlaps with another recognition request range A in the recognition request range A, the estimated host vehicle position EP is within the recognition request range A that overlaps with the overlap area B. In the state before entering, the recognition feature unit 60 to be recognized in the overlap area B is selected in advance (provisionally determined) based on the recognition rate R determined by the normal recognition rate determination process. Described as an example. However, the embodiment of the present invention is not limited to this, and the recognition target selection unit 25 selects the recognized feature unit 60 for the first time in accordance with the timing when the estimated host vehicle position EP enters the overlapping region B. It can also be configured to be executed. For example, in the example illustrated in FIG. 2, the recognition feature unit 60 is selected for the first time for the overlapping area B in the portion behind the overlapping area B in the second recognition request range A2 in the traveling direction rear D2 side. Can do. In this case, when the pedestrian crossing warning sign 52 is image-recognized at the time of the selection, the recognition rate R of the second recognized feature unit 62 is not determined by the normal recognition rate determination processing unit 32. The specific recognition rate determination processing unit 33 determines for the first time.

(2) In the above embodiment, the recognition rate R determined by the normal recognition rate determination process is a value that is uniquely determined based on the type and number of the features 50 constituting the recognized feature unit 60, and the specific recognition rate. The recognition rate R determined by the determination process is uniquely based on the type and number of all the remaining features 50 excluding the image-recognized features 50 among the features 50 constituting the specific recognition feature unit 60a. The configuration having a fixed value has been described as an example. However, the embodiment of the present invention is not limited to this, and the normal recognition rate determination processing unit 32 and the specific recognition rate determination processing unit 33 correct the value uniquely determined based on the type and number of the features 50. Thus, the recognition rate R can be determined. In such a configuration, correction can be performed in consideration of various factors that affect the success rate of image recognition. For example, the state of fading of the feature 50 and the state of sunshine with respect to the feature 50 (for example, Hyuga) Or in the shade, etc.), or in accordance with weather conditions, time, and the like. Various factors can be acquired by a sensor or the like, and correction information such as a correction coefficient corresponding to such a factor is provided in the road information storage unit 10 as in the position information of the feature 50, for example. It can be set as the structure acquired from the road information storage part 10. FIG.

(3) In the above embodiment, a configuration in which the normal recognition rate determination processing unit 32 and the specific recognition rate determination processing unit 33 determine the recognition rate R by calculation based on the predicted recognition rate ER acquired by the predicted recognition rate acquisition unit 31. Was described as an example. However, the embodiment of the present invention is not limited to this, and a recognition rate map that defines the relationship between the type and number of the features 50 and the recognition rate R is stored in the storage device, and the normal recognition rate determination is performed. The processing unit 32 and the specific recognition rate determination processing unit 33 may be configured to acquire the corresponding recognition rate R based on the type and number of the features 50.

(4) In the above embodiment, when the image recognition of any one recognized feature unit 60 is successful with respect to a plurality of recognized feature units 60 with the recognition request range A overlapping, other recognized feature units As an example, a configuration in which the image recognition process with 60 as a recognition target is not performed has been described. However, the embodiment of the present invention is not limited to this, and after a plurality of recognized feature units 60 having the same recognition request range A overlap after image recognition of any one recognized feature unit 60 is successful. It can be set as the structure which performs the image recognition process which makes another recognition feature unit 60 recognition object. In this case, when there are a plurality of recognized feature units 60 that have not been successfully image-recognized, the same recognition target selection process as that before the successful image recognition of any one recognized feature unit 60 is performed. It may be performed by excluding one recognized feature unit 60. And when the image recognition of the some recognition feature unit 60 succeeds, it can be set as the structure by which the correction process of the estimated own vehicle position EP is performed in multiple times.

(5) In the above embodiment, the configuration in which the recognition rate R is determined by the recognition rate determination unit 26 is described as an example only for the recognized feature unit 60 in which the recognition request range A has the overlapping region B. However, the embodiment of the present invention is not limited to this, and the recognition rate R is determined for the recognition feature unit 60 whose recognition request range A does not have the overlapping region B, and the recognition rate R Depending on the size, whether or not to execute the image recognition processing for the recognition feature unit 60 as a recognition target may be determined.

(6) In the above-described embodiment, the configuration in which the size of the feature-specific required range AF is set to the same value for all feature types has been described as an example. However, the embodiment of the present invention is not limited to this, and the size of the required range AF for each feature in the road length direction L is set to a different value depending on the feature type. You can also. Moreover, even if it is the same feature type, the size of the required range AF for each feature may be set to a different value according to the size of the feature 50.

(7) In the above embodiment, the positional relationship between the feature-based required range AF and the setting target feature 50 is the same positional relationship for all feature types, and the feature-specific required range AF. However, a description will be given by taking as an example a configuration that is set with the same length on both sides in the road length direction L with respect to the feature 50 so that the feature 50 to be set is located in the center of the range. did. However, the embodiment of the present invention is not limited to this, and the feature 50 to be set is arranged at a position where the required range AF for each feature is different from the central portion of the range in the road length direction L. Thus, it is also possible to adopt a configuration in which different lengths are set on both sides in the road length direction L with respect to the feature 50. In this case, for example, the setting target feature 50 can be configured to be located on the front side D1 in the traveling direction with respect to the center portion of the feature-specific required range AF. Moreover, it can also be set as the structure by which the positional relationship between the required range AF for every feature and the feature 50 to be set is different depending on the feature type.

(8) In the above embodiment, the recognition request range A is set as the minimum range including all the feature-specific request ranges AF for all the features 50 constituting the recognition feature unit 60 to be set. Was described as an example. However, the embodiment of the present invention is not limited to this, and the configuration in which the recognition requirement range A is larger than the minimum range, that is, the feature-specific requirement range AF is included. It is also possible to adopt a configuration in which the recognition request range A has no area.

(9) In the above embodiment, the configuration in which the recognition request range acquisition unit 27 sets and acquires the recognition request range A based on the setting rule for the recognition request range A has been described as an example. However, the embodiment of the present invention is not limited to this. The recognition request range A is associated with the recognition feature unit 60 and stored in the road information storage unit 10, and the recognition request range acquisition unit 27 is connected to the road. A configuration in which the recognition request range A is acquired with reference to the information storage unit 10 may be employed. Similarly, for the first determination region R1 and the second determination region R2, the recognition request range acquisition unit 27 may be configured to acquire and set based on a predetermined setting rule. A configuration in which the recognition request range acquisition unit 27 refers to and acquires the stored information may be employed.

(10) In the above embodiment, the first determination region R1 is set within the recognition request range A of the specific recognition feature unit 60a, and the recognition target feature 50 constituting the specific recognition feature unit 60a is the first. The configuration in which the specific recognition rate determination process is executed only when an image is recognized within one determination region R1 has been described as an example. However, the embodiment of the present invention is not limited to this, and the specific recognition rate determination process is always executed when the recognition target feature 50 is image-recognized within the recognition request range A. It is also possible.

(11) In the above embodiment, as the specific recognition feature unit 60a, the second recognition feature unit 62 including the pedestrian crossing warning sign 52 and the third recognition feature unit 63 including the stop line marking 53 are taken as examples. As mentioned above, it is also possible to use the specific recognized feature unit 60a composed of other road markings (for example, a forward priority road marking indicating that there is a priority road ahead) for correcting the estimated vehicle position EP. is there. In the above embodiment, the specific recognition feature unit 60a including two features 50 has been described as an example. However, the specific recognition feature unit 60a including three or more features 50 is naturally estimated. It can also be used to correct the vehicle position EP. In such a configuration, when the second and subsequent features 50 constituting the specific recognition feature unit 60a are image-recognized, the specific recognition feature unit 60a has already been selected by the recognition target selection unit 25. If so, the configuration for prohibiting the execution of the specific recognition rate determination process can be adopted. This is because even if the specific recognition rate determination process is executed, a value equal to or higher than the current recognition rate R is determined, so that the same specific recognition feature unit 60a is selected again even if the recognition feature unit 60 is reselected. This is because that.

(12) In the above embodiment, the configuration in which the target feature 50 in the image recognition for correcting the estimated host vehicle position EP is a road marking provided on the road surface has been described as an example. However, the embodiment of the present invention is not limited to this, and a three-dimensional feature 50 such as a traffic light can be used for correcting the estimated host vehicle position EP. In this case, the installation mode of the camera 90 on the vehicle 3 is set so that the image of the three-dimensional feature 50 can be recognized.

(13) In the above embodiment, the configuration in which the camera 90 is a back camera that captures the rear of the vehicle 3 has been described as an example. However, the embodiment of the present invention is not limited to this, and the camera 90 may be configured as a front camera that captures the front of the vehicle 3 or a side camera that captures the side of the vehicle 3. It is.

(14) In the above embodiment, the case where the vehicle position recognition system according to the present invention is applied to the in-vehicle navigation device 1 has been described as an example. However, such a navigation device 1 is fixed to the vehicle 3. The portable navigation device is not limited to the one that is mounted, and may be a portable navigation device that can be arbitrarily moved, and may be brought into the vehicle 3 only at the time of use.

(15) In the above-described embodiment, the case where the vehicle position recognition system according to the present invention is applied to the navigation device 1 has been described as an example. It is also possible to apply to a device (travel control device or the like).

(16) The assignment of the functional units described in the above embodiment is merely an example, and a plurality of functional units can be combined or one functional unit can be further divided. Further, in the above-described embodiment, each functional unit constituting the own vehicle position recognition unit 2 and each storage unit 10 and 11 have been described as an example of a configuration provided in the vehicle 3, but at least the own vehicle position recognition unit 2 is included. A configuration in which some of the functional units and at least a part of the storage units 10 and 11 are provided outside the vehicle 3 (for example, a server device or the like), and information is transmitted and received via a communication network such as the Internet. You can also

(17) Regarding other configurations as well, the embodiments disclosed herein are illustrative in all respects, and embodiments of the present invention are not limited thereto. In other words, configurations that are not described in the claims of the present application can be modified as appropriate without departing from the object of the present invention.

  INDUSTRIAL APPLICABILITY The present invention can be suitably used for a host vehicle position recognition system, a host vehicle position recognition program, and a host vehicle position recognition method for recognizing a host vehicle position using an image captured by a camera provided in the host vehicle.

3: Vehicle (own vehicle)
21: Estimated vehicle position acquisition unit 22: Image processing unit 23: Road information acquisition unit 24: Estimated vehicle position correction unit 25: Recognition target selection unit 26: Recognition rate determination unit 27: Recognition request range acquisition unit 50: Feature 60: recognized feature unit 60a: specific recognized feature unit 90: camera A: recognition required range AF: required range for each feature D1: forward direction D2: backward direction EP: estimated own vehicle position ER: expected recognition rate L : Road length direction PG: Captured image R: Recognition rate R1: First determination area R2: Second determination area RD: Road information

Claims (6)

An estimated host vehicle position acquisition unit that acquires an estimated host vehicle position that is an estimated position of the host vehicle, and a captured image captured by a camera provided in the host vehicle are acquired, and an image of a feature included in the captured image An image processing unit that performs a recognition process, a road information acquisition unit that acquires road information including position information of the feature, a recognition result of the feature by the image recognition process, and a position information of the feature included in the road information; An estimated vehicle position correcting unit that corrects the estimated vehicle position based on the vehicle position recognition system,
A feature group composed of a single feature or a plurality of predetermined features as a recognized feature unit, and for each recognized feature unit along the road length direction as a range for performing the image recognition processing A recognition request range acquisition unit for acquiring a set recognition request range;
A recognition rate determination unit that determines a recognition rate, which is a rate of successful image recognition, for each recognized feature unit based on an expected recognition rate predetermined for each type of feature;
Based on the recognition rate of each recognized feature unit, the recognized feature unit to be recognized in the image recognition process is selected from the plurality of recognized feature units whose recognition request ranges overlap each other. A recognition target selection unit,
The recognition rate determination unit, for the specific recognition feature unit that is the recognition feature unit consisting of the feature group arranged separately in the road length direction, each location constituting the specific recognition feature unit at each time point The predicted recognition of the remaining features constituting the specific recognition feature unit when a part of the plurality of features constituting the specific recognition feature unit is image-recognized according to the image recognition result of the feature A host vehicle position recognition system that executes a specific recognition rate determination process for determining the recognition rate based on a rate. The recognition request range is set based on a feature-specific request range set for each feature constituting the recognition feature unit,
The recognition rate determination unit, when determining the recognition rate of the specific recognition feature unit, within the first determination region including the end portion of the feature-required range on the rear side in the traveling direction, When the corresponding feature is image-recognized, a specific recognition rate determination process is executed, and the feature in the second determination region other than the first determination region in the recognition request range formed by the feature-specific request range The vehicle position recognition system according to claim 1, wherein execution of the specific recognition rate determination process is prohibited when an image of a feature corresponding to each requested range is recognized.   The recognition rate determination unit is the specific recognition feature unit in which the recognition request range overlaps with the other recognition feature unit, and proceeds with respect to the feature constituting the other recognition feature unit. The own vehicle position recognition system according to claim 1 or 2, wherein the specific recognition rate determination process is executed only for the specific recognition feature unit having a feature arranged on the rear side in the direction.   In the specific recognition rate determination process, the recognition rate determination unit sets the predicted recognition rates of all the remaining features other than the image-recognized features in the features constituting the specific recognition feature unit to each other. The multiplied value is determined as the recognition rate of the specific recognition feature unit, and in the normal recognition rate determination process other than the specific recognition rate determination process, the expected recognition rate of all the features constituting the specific recognition feature unit The own vehicle position recognition system according to any one of claims 1 to 3, wherein a value obtained by multiplying the two is determined as a recognition rate of the specific recognition feature unit. An estimated own vehicle position acquisition function for acquiring an estimated own vehicle position that is an estimated position of the own vehicle, and a photographed image taken by a camera provided in the own vehicle, and an image of a feature included in the photographed image An image processing function for performing recognition processing, a road information acquisition function for acquiring road information including position information of the features, a recognition result of the features by the image recognition processing, and position information of the features included in the road information; An estimated vehicle position correcting function for correcting the estimated vehicle position based on the vehicle position recognition program,
A feature group composed of a single feature or a plurality of predetermined features as a recognized feature unit, and for each recognized feature unit along the road length direction as a range for performing the image recognition processing A recognition request range acquisition function for acquiring a set recognition request range;
A recognition rate determination function for determining a recognition rate, which is a rate of successful image recognition, for each recognition feature unit based on an expected recognition rate predetermined for each type of feature;
Based on the recognition rate of each recognized feature unit, the recognized feature unit to be recognized in the image recognition process is selected from the plurality of recognized feature units whose recognition request ranges overlap each other. Realize recognition target selection function on computer,
The recognition rate determination function is configured so that the specific recognition feature unit at each time point constitutes the specific recognition feature unit with respect to the specific recognition feature unit that is the recognition feature unit including the feature group arranged separately in the road length direction. The predicted recognition of the remaining features constituting the specific recognition feature unit when a part of the plurality of features constituting the specific recognition feature unit is image-recognized according to the image recognition result of the feature A vehicle position recognition program which is a function for executing a specific recognition rate determination process for determining the recognition rate based on a rate. An estimated vehicle position acquisition step for acquiring an estimated vehicle position that is an estimated position of the vehicle, a captured image captured by a camera provided in the vehicle, and an image of a feature included in the captured image An image processing step for performing recognition processing, a road information acquisition step for acquiring road information including position information of the features, a recognition result of the features by the image recognition processing, and position information of the features included in the road information; An estimated vehicle position correcting step for correcting the estimated vehicle position based on the vehicle position recognition method,
A feature group composed of a single feature or a plurality of predetermined features as a recognized feature unit, and for each recognized feature unit along the road length direction as a range for performing the image recognition processing A recognition request range acquisition step for acquiring a set recognition request range;
A recognition rate determination step for determining a recognition rate, which is a rate of successful image recognition, for each recognized feature unit based on an expected recognition rate predetermined for each type of feature;
Based on the recognition rate of each recognized feature unit, the recognized feature unit to be recognized in the image recognition process is selected from the plurality of recognized feature units whose recognition request ranges overlap each other. A recognition object selection step,
In the recognition rate determining step, for each specific recognition feature unit that is the recognition feature unit composed of a group of features arranged separately in the road length direction, various locations constituting the specific recognition feature unit at each time point The predicted recognition of the remaining features constituting the specific recognition feature unit when a part of the plurality of features constituting the specific recognition feature unit is image-recognized according to the image recognition result of the feature A vehicle position recognition method for executing a specific recognition rate determination process for determining the recognition rate based on a rate.

Images