JP2007237930A - Driving support device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a driving support device free to more easily drive a vehicle in a status of being difficult to retreat by supporting vehicle operation in retreating on the basis of a travelling hysteresis of the vehicle in advancing. <P>SOLUTION: This driving support device is constituted to detect a characteristic point 60 of an obstruction from a picked-up picture image 50 picked up by a rear camera 3 when the vehicle 2 enters a narrow street road or a parking area and to detect and store a travelling locus 75 of the vehicle 2 on the basis of a detected result (S2 to S5) and to control the vehicle so that the vehicle 2 retreats along the stored travelling locus 75 when the vehicle 2 retreats in the narrow street road or the parking area (S17). <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a driving support device that supports a vehicle operation performed by a driver when the vehicle is moved backward, and in particular, by performing vehicle operation support during backward movement based on a traveling history of the vehicle when moving forward, The present invention relates to a driving support device that enables easier driving of a vehicle under difficult circumstances.

Conventionally, the road information obtained from the map data of the navigation device, and various information related to the traveling of the vehicle such as the current position specified by GPS, etc. are acquired, and notification to the user, driving assistance, and further driving A driving assistance device for intervention is proposed.
In such a driving assistance device, driving assistance is often performed at the time of reverse, in which driving is more difficult than at the time of forward movement. For example, Japanese Patent Application Laid-Open No. 11-334470 describes a parking assist device that supports a driver's parking operation with respect to a vehicle by displaying a camera image obtained by imaging a rear environment of the vehicle during parking. According to such a parking assistance device, while displaying an image of the situation in the backward direction with respect to the vehicle, the vehicle progress prediction curve is calculated based on the signal from the steering angle sensor, and the calculated progress prediction curve is By superimposing and displaying on the captured camera image as described above, it is possible to assist the driver's parking operation with respect to the vehicle.
Japanese Patent Laid-Open No. 11-334470 (pages 3 to 5, FIG. 13)

However, the parking assist device described in Patent Document 1 is sufficient for performing a normal parking operation, but only displays a predicted travel curve on the display, so that it is particularly difficult to move backward. Under circumstances, it was insufficient as driving assistance. Here, for example, when it is difficult to retreat, for example, when you park in a narrow parking lot and then start again while retreating, or when you pass or stop with other vehicles on narrow streets or narrow mountain roads, etc. There are cases where it is necessary to retreat. Under the circumstances as described above, in addition to the difficulty of visually recognizing the environment behind the vehicle, vehicle operations such as a brake operation and a steering operation at an appropriate timing are required.
In addition, conventionally, it has been proposed to support driving by detecting the shape and position of a road surface or an obstacle using an image captured by a camera, a millimeter wave radar, or the like, and controlling a steering or a brake. . However, even if the shape and position of the road surface and the obstacle can be detected, it is difficult to control the vehicle so that the vehicle travels appropriately when reversing from only the detection result.

  The present invention has been made in order to solve the above-described conventional problems, and when the vehicle is parked forward in a narrow parking lot and then re-starts while retreating, or passing with another vehicle on a narrow street or a narrow mountain road. An object of the present invention is to provide a driving support device that enables easier driving of a vehicle even when the vehicle travels in a situation where it is difficult to perform reverse operation such as when there is a dead end and it is necessary to reverse.

In order to achieve the above object, a driving support apparatus (1) according to claim 1 of the present application is a driving support apparatus that supports a vehicle operation performed by a driver when the vehicle (2) is moved backward. A travel information detection means (4) for detecting the travel information of the vehicle, a travel history storage means (10) for storing the travel information of the vehicle detected by the travel information detection means as a travel history, and whether or not the vehicle moves backward A reverse determination means (4) for determining whether or not the vehicle is backed by the reverse determination means and assisting vehicle operation based on the travel history stored in the travel history storage means It is characterized by.
Note that “travel information” refers to information on what speed and route the vehicle has traveled, as well as vehicle operations performed by the driver during travel (for example, steering operation, accelerator operation, brake operation, Information on mirror operation, vehicle height operation, etc.).

  Further, the driving support device (1) according to claim 2 is the driving support device according to claim 1, wherein the travel information is a travel locus (75, 103) of the vehicle (2) when moving forward. Features.

  Further, the driving support device (1) according to claim 3 is the driving support device according to claim 2, wherein the travel information detecting means (4) is an obstacle (52 to 57) around the vehicle (2). ) Based on the detection result of the position detection means (4), the position detection means (4) for detecting the relative position of the obstacle detected by the obstacle detection means to the vehicle, and the position detection means. And a traveling locus detecting means (4) for detecting a traveling locus of the vehicle.

  Further, the driving support device (1) according to claim 4 is the driving support device according to claim 2 or 3, wherein the vehicle (2) is determined to move backward by the reverse determination means (4). It has a vehicle control means (4) which controls a vehicle so that it may retreat along a running locus of a vehicle.

  Further, the driving support device (1) according to claim 5 is the driving support device according to claim 2 or claim 3, wherein the driving support device (1) is arranged on the vehicle (2) and has an imaging means (3) for imaging the surroundings of the vehicle. And an image superimposing unit that superimposes the traveling locus (103) of the vehicle detected by the traveling information detecting unit (4) on the image captured by the imaging unit when the reverse determining unit determines that the vehicle is reversing. 4) and image display means (5) for displaying the image superimposed by the image superimposing means.

  The driving support device (1) according to claim 6 is the driving support device according to claim 1, wherein the travel information is operation contents of a vehicle operation performed by the driver when moving forward. To do.

  The driving support device (1) according to claim 7 is the driving support device according to claim 6, wherein the driving history storage is performed when the reverse determination means (4) determines that the vehicle (2) is reverse. It has vehicle operation control means (4) which controls a vehicle so that vehicle operation based on the operation content memorize | stored in the means (10) is performed.

  Further, the driving support device (1) according to claim 8 is the driving support device according to claim 1, wherein the driving support device (1) is disposed on the vehicle (2), and the imaging means (3) for imaging the surroundings of the vehicle, and the traveling of the vehicle. Travel distance detecting means (12) for detecting a distance, and the travel information is a forward-time captured image captured by the image capturing means from the vehicle at predetermined distance intervals when traveling forward.

  The driving support device (1) according to claim 9 captures images from the vehicle at predetermined distance intervals in the driving support device according to claim 8, when the reverse determination means (4) determines that the vehicle is reverse. The vehicle is supported based on a comparison result between the forward-captured captured image and the backward-captured captured image captured from the point where the distance from the reverse start point is captured, To do.

  Furthermore, the driving assistance device (1) according to claim 10 detects in the driving assistance device according to any one of claims 1 to 9 that the vehicle (2) has entered a narrow street or a parking lot. An entry detecting means (8), and the running information detecting means (4) detects the running information of the vehicle when the entry detecting means detects that the vehicle has entered a narrow street or a parking lot. It is characterized by supporting the operation.

  In the driving support device according to claim 1 having the above-described configuration, when the vehicle moves forward, the driving information of the vehicle is detected and stored as a driving history, and the driver is based on the driving history stored when the vehicle moves backward. It is necessary to retreat after retreating after having parked forward in a narrow parking lot, or when there is a passing or dead end with other vehicles on narrow streets or narrow mountain roads, etc. Even when reversing in a situation where it is difficult to perform reversal, it is possible to perform appropriate travel based on the travel history during forward travel. Therefore, the driver can drive the vehicle more easily when reversing.

  In the driving support device according to claim 2, when the vehicle moves forward, the driving locus of the vehicle is detected and stored as a driving history, and the driving is performed by the driver based on the driving history stored when the vehicle moves backward. Supporting vehicle operation, such as when you park again in a narrow parking lot and then start again, or when you need to retreat due to passing or dead ends with other vehicles on narrow streets or narrow mountain roads, etc. Even when reversing in a situation where it is difficult to perform reversing, it is possible to perform appropriate traveling based on the traveling locus during forward traveling. Therefore, the driver can drive the vehicle more easily when reversing.

  In the driving support device according to the third aspect, the relative position of the obstacle around the vehicle with respect to the vehicle is detected, and the traveling locus of the vehicle is detected based on the detection result. An accurate travel locus can be detected.

  In the driving support device according to the fourth aspect, the vehicle is controlled so as to move backward along the traveling locus of the vehicle. Appropriate travel based on the travel trajectory during forward travel is possible even when traveling backwards in situations where it is difficult to perform reverse travel, such as when it is necessary to travel backward due to a passing or dead end with a narrow mountain road. It becomes possible to make it. Therefore, the driver can drive the vehicle more easily when reversing.

  In the driving support device according to the fifth aspect, the vehicle travel locus is superimposed on the image captured by the imaging means, and the superimposed image is displayed, so that the driver refers to the displayed vehicle travel locus. Thus, it is possible to perform appropriate traveling based on the traveling locus during forward travel.

  In the driving support device according to the sixth aspect, the operation contents of the vehicle operation performed by the driver when the vehicle moves forward are stored as a traveling history, and the driving is performed based on the traveling history stored when the vehicle moves backward. To support the vehicle operation performed by the person, so it is necessary to retreat after parked forward in a narrow parking lot or to retreat due to passing or dead ends with other vehicles on narrow streets or narrow mountain roads etc. Even when reversing in a situation where it is difficult to perform reversal, for example, in certain cases, it is possible to perform appropriate traveling based on vehicle operation during forward travel. Therefore, the driver can drive the vehicle more easily when reversing.

  In the driving support device according to the seventh aspect of the invention, the vehicle is controlled so that the vehicle operation based on the vehicle operation performed by the driver at the time of forward movement is performed. Vehicle operation when moving forward even when going backwards in situations where it is difficult to move backward, such as when leaving or when it is necessary to move backward due to passing or dead ends with narrow streets or narrow mountain roads, etc. It is possible to perform appropriate traveling based on the above. Therefore, the driver can drive the vehicle more easily when reversing.

  In the driving support device according to the eighth aspect, when the vehicle moves forward, the forward-time captured images captured by the imaging unit from the vehicle at predetermined distance intervals are stored as a travel history, and the travel stored when the vehicle moves backward is stored. Since the vehicle operation performed by the driver is assisted based on the history, it is possible to detect an accurate vehicle position and surrounding situation during forward movement based on the captured image. Therefore, when you park in a narrow parking lot and then start again while retreating, or when you need to retreat due to a passing or dead end with other cars on narrow streets or narrow mountain roads, etc. Even when the vehicle is traveling backward in a difficult situation, it is possible to perform appropriate traveling based on the traveling locus during forward traveling.

  In the driving support device according to the ninth aspect, since the vehicle operation is supported based on the comparison result between the forward-captured image and the reverse-captured image captured from the same distance from the reverse start point, the captured image is displayed. Based on this, it is possible to compare the vehicle position and the surrounding situation at the time of forward and reverse more accurately, and to perform optimal vehicle support.

  Furthermore, in the driving support device according to the tenth aspect, when the vehicle enters the narrow street or the parking lot, the vehicle driving information is detected and the vehicle operation is supported. In this case, it is possible to perform an appropriate travel based on the vehicle operation at the time of forward movement, and it is possible to reduce the processing load of the control unit except in a situation where it is difficult to perform the backward movement.

  Hereinafter, a driving support device according to the present invention will be described in detail with reference to the drawings based on first to third embodiments.

(First embodiment)
First, a schematic configuration of the driving support device 1 according to the first embodiment will be described with reference to FIGS. 1 and 2. FIG. 1 is a schematic configuration diagram of a driving support apparatus 1 according to the first embodiment, and FIG. 2 is a block diagram schematically showing a control system of a vehicle 2 constituting the driving support apparatus 1 according to the first embodiment.
As shown in FIGS. 1 and 2, the driving assistance apparatus 1 according to the first embodiment includes a rear camera (imaging means) 3 installed on a vehicle 2 and a driving assistance ECU (running information detection means, reverse determination). Means, obstacle detection means, position detection means, travel locus detection means, vehicle control means, image superimposing means, vehicle operation control means) 4, liquid crystal display (image display means) 5, touch panel 6, speaker 7, It comprises various sensors such as a vehicle speed sensor 12 connected to a current position detection unit (entrance detection means) 8, a vehicle DB 9, a travel history DB (travel history storage means) 10, a vehicle ECU 11, and a driving support ECU 4. .

  The rear camera 3 uses a solid-state image sensor such as a CCD, for example, and is installed near the upper center of the license plate mounted on the rear side of the vehicle 2 and installed with the line of sight 45 degrees below the horizontal. The Then, the rear side of the vehicle, which is the traveling direction of the vehicle 2 when moving backward, is imaged, and the captured image (hereinafter referred to as a BGM (back guide monitor) image) is displayed on the liquid crystal display 5 of the navigation device.

  The driving support ECU (Electronic Control Unit) 4 detects obstacles around the vehicle 2 from an image captured by the rear camera 3 when the vehicle 2 enters a narrow street or a parking lot. An electronic device that performs a process of detecting a travel locus of the vehicle 2 based on the relative position of the detected obstacle to the vehicle 2 and a process of estimating a predicted course of the vehicle 2 when reversing and superimposing the locus on the BGM image. Control unit. The driving assistance ECU 4 may also be used as an ECU used for controlling the navigation device. The detailed configuration of the driving support ECU 4 will be described later.

  The liquid crystal display 5 is provided on the center console or panel surface in the room of the vehicle 2 and superimposes and displays the trajectory of the predicted course of the own vehicle on the BGM image captured by the rear camera 3 when reversing. Note that the liquid crystal display 5 may also be used for a navigation device.

  The touch panel 6 is disposed on the front surface of the liquid crystal display 5 and specifies the coordinate position of the part touched by the user, where the user touched based on the specified coordinate position information, and in which direction the touched part moves. Can be determined. And in the driving assistance apparatus 1 which concerns on 1st Embodiment, it is used when selecting whether driving assistance by control of the vehicle 2 is performed when retreating in a narrow street or a parking lot, or interrupting driving assistance. . Instead of the touch panel 6, a keyboard, a mouse, a remote control device for remote operation, a joystick, a light pen, a stylus pen, or the like can be used.

  The speaker 7 is provided on the center console or the panel surface in the room of the vehicle 2 and outputs a guidance voice, a warning sound, etc. regarding driving support. For example, in the driving support device 1 according to the first embodiment, when the vehicle deviates from the travel locus at the time of forward movement when retreating in a narrow street or a parking lot, “the rightward shift occurs with respect to the travel locus. Will be output. "

  The current location detection unit 8 receives the radio wave generated by the artificial satellite, thereby detecting the current location and current time of the vehicle 2 on the earth, and the absolute direction of the vehicle 2 by measuring the geomagnetism. It comprises a geomagnetic sensor 26 to be detected and a map DB 27 in which map data is stored (see FIG. 2), and the current location and traveling direction of the vehicle 2 can be specified on the map.

The vehicle DB 9 is a storage unit that stores various parameter information related to the vehicle such as the shape design value and camera design value of the vehicle 2. The vehicle DB 9 stores, for example, the wheel radius, vehicle width, minimum turning radius, the optical axis direction of the rear camera 3 (downward 45 degrees in the first embodiment), the installation position of the rear camera 3 with respect to the vehicle 2, and the like. Has been.
Then, the driving assistance ECU 4 detects the travel locus of the vehicle 2 from the image captured by the rear camera 3 by using various parameter information stored in the vehicle DB 9 as will be described later, and also predicts the vehicle 2 when reversing. Estimate the course.

The travel history DB 10 is a DB that stores a travel history when the vehicle moves forward when the vehicle 2 enters a narrow street or a parking lot. Specifically, as a result of the three-dimensional reconstruction of the feature points of the obstacle detected from the image captured by the rear camera 3, the position coordinates and direction of the vehicle 2 (specifically, every second) (specifically, every second) , Information on the position coordinates and direction of the rear camera 3, and the operation details (operation type and timing of operation) of the vehicle operation performed when the driver changes the angle of the door mirror or the vehicle height of the vehicle 2. (S5, S6 in FIG. 3).
In the first embodiment, a hard disk is used as a storage medium for the vehicle DB 9 and the travel history DB 10, but a magnetic disk, memory card, magnetic tape, magnetic drum, CD, MD, DVD, optical disk, MO, IC card. An optical card or the like can also be used as an external storage device.

The driving assistance ECU 4 is connected with various sensors such as a vehicle speed sensor (travel distance detection means) 12, an accelerator sensor 13, a brake sensor 14, a steering sensor 15, a gyro sensor 16, and a shift lever switch 17. Here, the vehicle speed sensor 12 is a sensor that generates a vehicle speed pulse in accordance with the rotation of the vehicle wheel and detects the travel distance and the vehicle speed of the vehicle. The accelerator sensor 13 is a sensor that detects the amount of operation of the accelerator pedal by the driver. The brake sensor 14 is a sensor that detects the amount of operation of the brake pedal by the driver. The steering sensor 15 is attached to the inside of the steering device, and is a sensor that detects a steering angle when the steering wheel is steered. The gyro sensor 16 is a sensor that detects the turning angle of the vehicle 2. The shift lever switch 17 is built in a shift lever (not shown), and the shift position is “P (parking)”, “N (neutral)”, “R (reverse)”, “D (drive)”, It is detected whether the position is “2 (second speed)” or “L (low)”.
As a result, the driving assistance ECU 4 detects the current vehicle speed of the vehicle 2 based on the output signal of the vehicle speed sensor 12 and determines the driver's accelerator operation amount and brake operation amount based on the output signals of the accelerator sensor 13 and the brake sensor 14. The steering angle of the vehicle 2 is detected based on the output signal of the steering sensor 15. Further, the vehicle direction is detected by integrating the turning angle detected by the gyro sensor 16. Further, the current shift position of the vehicle 2 is detected by the shift lever switch 17.

The vehicle ECU 11 is an electronic control unit for the vehicle 2 that controls the operation of the engine, transmission, brake, and the like, and is connected to an accelerator 18, a brake 19, a steering 20, and an operation switch 21. Then, the vehicle ECU 11 operates the accelerator 18, the brake 19 and the steering 20 based on an instruction from the driving support ECU 4. As a result, the vehicle ECU 11 can control the vehicle so as to move backward along the traveling locus of the vehicle when moving forward, as will be described later.
The operation switch 21 is an operation means that is operated by the driver in order to adjust the angle of a door mirror (not shown) provided in the vehicle 2 and the vehicle height of the vehicle 2. Then, the vehicle ECU 11 controls a drive source such as a motor based on the operation information of the operation switch 21 to adjust the angle of the door mirror (not shown) and the vehicle height of the vehicle 2.

  Next, the details of the driving assistance ECU 4 will be described with reference to FIG. 2. The driving assistance ECU 4 is configured with the CPU 31 as a core, and a ROM 32 and a RAM 33 which are storage means are connected to the CPU 31. The ROM 32 detects a vehicle travel locus from the BGM image captured by the rear camera 3, and controls the vehicle 2 to move backward along the detected travel locus (see FIG. 3). In addition, various programs necessary for controlling the liquid crystal display 5 and the like are stored. The RAM 33 is a memory for temporarily storing various data calculated by the CPU 31.

  Next, a vehicle control processing program executed by the driving support ECU 4 of the driving support device 1 according to the first embodiment having the above-described configuration will be described with reference to FIG. FIG. 3 is a flowchart of the vehicle control processing program in the driving support device 1 according to the first embodiment. Here, the vehicle control processing program detects an obstacle from the BGM image picked up by the rear camera 3 at the time of forward movement, detects the traveling locus of the vehicle 2 based on the relative position of the detected obstacle to the vehicle 2, and When the vehicle is moving backward, the vehicle is controlled so as to move backward along the traveling locus detected when moving forward. 3 is stored in the ROM 32 and the RAM 33 provided in the driving support ECU 4, and is repeatedly executed by the CPU 31 at predetermined intervals (for example, every 4 ms).

  In the vehicle control processing program, first, in step (hereinafter abbreviated as S) 1, the CPU 31 performs matching processing based on the current position of the vehicle detected by the GPS 25 and the map data stored in the map DB 27. It is determined whether the car has entered a narrow street or a parking lot. The determination may be made based on the image recognition result by the rear camera 3 or the detection result of the millimeter wave radar.

  And when it determines with the own vehicle having entered the narrow street or the parking lot (S1: YES), it transfers to S2. On the other hand, when it is determined that the own vehicle has not entered the narrow street or the parking lot (S1: NO), the vehicle control processing program is terminated.

  In S2, an image analysis process for analyzing an image captured by the rear camera 3 is performed. Here, the image analysis processing takes an image of the rear environment of the vehicle 2 captured by the rear camera 3 and performs analysis processing, and an obstacle (for example, a building or a parked vehicle) located along the road on which the vehicle 2 travels. Etc.) are detected from the feature points in the image. Here, the feature point corresponds to an edge of an obstacle, a corner, or the like, and is an object having a feature that can be traced along an image sequence to be described later.

Hereinafter, the image analysis process of S2 will be described using a specific example. FIG. 4 is a perspective view showing the vehicle 2 moving forward on the narrow street at a predetermined timing. FIG. 5 is a diagram illustrating a captured image 50 captured by the rear camera 3 of the vehicle 2 at the timing illustrated in FIG. 4.
As shown in FIG. 4, obstacles 52 to 57 are located along the road 51 in the narrow street where the vehicle 2 travels. Then, in the captured image 50 captured by the rear camera 3 from the position 58 of the vehicle 2 illustrated in FIG. 4, the obstacles 52 to 55 are captured together with the rear bumper 59 as illustrated in FIG. 5. In the image analysis process of S2, the CPU 31 detects the feature points 60 of the obstacles 52 to 55 using automatic correlation using a determinant. Then, the position coordinates (u, v) of the detected feature points 60 in the captured image 50 are stored in the RAM 33. The details of the method of detecting the feature point 60 from the captured image 50 are already known techniques (see, for example, Japanese Patent Application Laid-Open No. 2004-297808, paragraphs (0041) to (0042)). Is omitted.

  Next, in S3, a tracking process for detecting a movement amount after a minute time is performed on the feature point 60 of the obstacle detected in S2. Here, in the feature point tracking process, if the sampling period is sufficiently short, it is assumed that the luminance value of the image after the minute time does not change, and the displacement vector of each feature point 60 after the minute time has elapsed is calculated. Then, the feature point 60 is tracked by comparing with the feature point 60 detected from the captured image 50 captured from the vehicle 2 thereafter.

Hereinafter, the feature point tracking process of S3 will be described using a specific example. FIG. 6 is a diagram showing a displacement vector 61 after the minute time (dt) of the feature point 60 in the captured image 50 captured by the rear camera 3 at the timing shown in FIG. The details of the method of calculating the displacement vector 61 after the minute time of the feature point 60 has already been known (see, for example, JP-A-2004-297808, paragraphs (0043) to (0045)). Description is omitted.
Then, the feature point 60 in the new captured image 50 captured by the rear camera 3 from the vehicle position 65 (see FIG. 4) after the minute time (dt) has elapsed is detected again, and the calculated feature shown in FIG. The feature point is tracked by determining whether or not the feature point 60 is located along the displacement vector 61 of the point 60.

  Subsequently, in S4, based on the position coordinates (u, v) of the feature point 60 in the captured image 50, the three-dimensional coordinates (x, y, z) of the feature point 60 with respect to the position of the rear camera 3 of the vehicle 2 are calculated. Further, in consideration of the displacement vector 61 of the feature point 60 calculated in S3, a three-dimensional feature point corresponding to the track of the feature point 60 on the captured image acquired a plurality of times is reconstructed. As a result, the position of the feature point 60 relative to the rear camera 3 of the vehicle 2 is specified, and an accurate travel locus traveled by the vehicle 2 is detected using the position of the feature point 60. Note that the reconstruction process of the three-dimensional feature point corresponding to the track of the feature point 60 is already known technology (see, for example, Japanese Patent Application Laid-Open No. 2004-297808, paragraphs (0047) to (0064)). Is omitted. Further, the processing of S2 and S3 corresponds to the processing of the obstacle detection means, the processing of S4 corresponds to the processing of the position detection means and the travel locus detection means, and the processing of S2 to S4 is the processing of the travel information detection means. It corresponds to.

  Next, in S5, the CPU 31 stores the reconstruction result of the three-dimensional feature points in S4 in the RAM 33, and also determines the position of the vehicle 2 (specifically, the rear camera 3) for each time (for example, every second). The direction is detected by the GPS 25 and the geomagnetic sensor 26 and stored in the RAM 33. As a result, a travel locus (travel information) when the vehicle 2 moves forward is stored as a travel history.

  Further, in S6, when a vehicle operation such as a mirror operation or an operation for changing the vehicle height of the vehicle 2 is performed by operating the operation switch 21, the current position of the vehicle at the time of operation (specifically, the rear In association with the position of the camera 3, operation details of the vehicle operation (for example, opening the door mirror by 30 degrees, raising the vehicle height by 10 cm, etc.) are stored as a travel history.

  Thereafter, in S7, the CPU 31 determines whether or not the own vehicle has escaped from the narrow street or the parking lot based on the current position of the own vehicle detected by the GPS 25 and the map data stored in the map DB 27. The determination may be based on the image recognition result by the rear camera 3 or the detection result of the millimeter wave radar.

  If it is determined that the vehicle has escaped from the narrow street or the parking lot (S7: YES), the travel history of the vehicle 2 stored in the RAM 33 in S5 or S6 is cleared (S8), and the vehicle The control processing program is terminated.

  On the other hand, if it is determined that the vehicle is traveling on the narrow street or the parking lot (S7: NO), the CPU 31 shifts the vehicle 2 based on the detection result of the shift lever switch 17 in S9. It is determined whether or not the lever is reverse, that is, whether or not the vehicle 2 has moved backward in the narrow street or the parking lot. Note that the process of S9 corresponds to the process of the reverse determination means.

If it is determined that the shift lever of the vehicle 2 is not reverse (S9: NO), the process returns to S2, and the travel information of the vehicle 2 is detected again and the detected travel information is stored in the RAM 33 as a travel history. . On the other hand, if it is determined that the vehicle is reverse (S9: YES), whether or not to perform control of the vehicle 2 at the time of reverse based on the saved travel history (that is, assistance to the driver's vehicle operation) is determined. An execution confirmation screen 70 is displayed on the liquid crystal display 5 (S10).
Here, FIG. 7 is a diagram showing an assist execution confirmation screen 70 displayed on the liquid crystal display 5. On the assist execution confirmation screen 70, as shown in FIG. 7, a character 71 “Would you like to assist when reversing?” Is displayed in the center, and icons 72 and 73 are displayed below the character 71. When the driver desires to perform control of the vehicle 2 at the time of reverse based on the saved traveling history, the driver selects the icon 72 with the touch panel 6. On the other hand, when it is not desired that the control of the vehicle 2 at the time of reverse based on the saved travel history is desired, the icon 73 is selected by the touch panel 6.

  Next, in S11, based on the selection of the icons 72 and 73 by the driver, it is determined whether or not to control the vehicle 2 at the time of reverse based on the saved travel history (that is, assisting the driver to operate the vehicle). Is done. As a result, when it is determined not to control the vehicle 2 (S11: NO), that is, when the icon 73 is selected on the assist execution confirmation screen 70, the vehicle 2 stored in the RAM 33 in S5 or S6. Is cleared (S8) and the vehicle control processing program is terminated.

On the other hand, when it is determined that the vehicle 2 is to be controlled (S11: YES), that is, when the icon 72 is selected on the assist execution confirmation screen 70, the process proceeds to S12.
In S12, an image analysis process for analyzing an image captured by the rear camera 3 is performed, and in S13, a tracking process for detecting a movement amount after a minute time is performed on the feature point 60 of the obstacle detected in S12. In S14, the three-dimensional feature point corresponding to the track of the feature point 60 on the captured image acquired a plurality of times is reconstructed in consideration of the displacement vector 61 of the feature point 60 calculated in S13. Note that the processing of S12 to S14 is the same as the processing of S2 to S4 that is performed when moving forward in a narrow street or a parking lot, and thus the description thereof is omitted here.

Next, in S15, the CPU 31 compares the reconstruction result of the three-dimensional feature point performed in S14 with the reconstruction result of the three-dimensional feature point stored in S5 when the vehicle 2 moves forward. When the vehicle is moving forward, the current position and direction of the vehicle are compared with the position and direction of the vehicle 2 stored in the RAM 33. Thereby, a deviation of the position and direction of the vehicle 2 when traveling backward (specifically, the position and direction of the rear camera 3) with respect to the traveling locus when traveling forward is calculated (S16). Thereafter, the CPU 31 calculates the operation amounts of the accelerator 18, the brake 19 and the steering 20 for eliminating the displacement of the calculated position and direction, and transmits a control instruction to the vehicle ECU 11 (S17). As a result, the control of the vehicle 2 is performed so that the vehicle 2 moves backward along the traveling locus during forward movement.
When the operation details of the vehicle operation are stored in S6, control is performed so that the corresponding vehicle operation is performed at the own vehicle position corresponding to the time of forward movement. For example, when an operation of closing the door mirror 30 degrees at a predetermined point at the time of forward movement is performed, control is performed so as to perform an operation of opening the door mirror 30 degrees at the same point at the time of backward movement. Further, when an operation for lowering the vehicle height by 10 cm is performed at a predetermined point during forward travel, control is performed so as to perform an operation for increasing the vehicle height by 10 cm at the same point during backward travel. The process of S17 corresponds to the process of the vehicle control means and the vehicle operation control means.

Here, the processing of S15 to S17 will be specifically described with reference to FIGS. FIG. 8 is a perspective view showing the vehicle 2 retreating the narrow street shown in FIG. 4 at a predetermined timing, and FIG. 9 is a top view showing the vehicle 2 retreating the narrow street shown in FIG. 4 at the same timing.
When the three-dimensional feature point corresponding to the track of the feature point 60 is reconstructed by the processing of S12 to S14, the feature point 60 is detected based on the image captured by the vehicle 2 with the rear camera 3 as shown in FIG. Is done. Then, as shown in FIG. 9, the deviation in the vehicle direction is calculated from the vehicle direction θ1 when the vehicle 2 moves forward and the vehicle direction θ2 when the vehicle moves backward. Further, the deviation of the vehicle position is calculated from the distance d between the travel locus 75 when moving forward and the current position of the vehicle 2 when moving backward (specifically, the position of the rear camera 3). Then, the vehicle is controlled so as to eliminate the deviation between the calculated vehicle direction and the vehicle position.

  Next, in S18, the CPU 31 determines whether or not a vehicle operation different from the traveling history of the vehicle 2 during forward movement stored in S5 and S6 has been performed. Here, the case where the vehicle operation different from the traveling history of the vehicle 2 at the time of forward is performed is, for example, when the vehicle travels straight at a predetermined point when traveling forward, but makes a right turn or a left turn at the same point when traveling backward Etc.

  When it is determined that a vehicle operation different from the travel history has been performed (S18: YES), the driver determines that the vehicle travels on a travel route different from the forward travel time, and stops the control of the vehicle. Then, the traveling history of the vehicle 2 stored in the RAM 33 in S5 or S6 is cleared (S8), and the vehicle control processing program is terminated.

  On the other hand, when the vehicle operation different from the travel history is not performed (S18: NO), the CPU 31 further determines based on the current position of the vehicle detected by the GPS 25 in S19 and the map data stored in the map DB 27. It is determined whether the vehicle has escaped from the narrow street or the parking lot. The determination may be based on the image recognition result by the rear camera 3 or the detection result of the millimeter wave radar.

  If it is determined that the vehicle has escaped from the narrow street or the parking lot (S19: YES), the travel history of the vehicle 2 stored in the RAM 33 in S5 or S6 is cleared (S8), and the vehicle The control processing program is terminated.

  On the other hand, when it is determined that the vehicle is continuously traveling on the narrow street or the parking lot (S19: NO), the process returns to S12, and again, the three-dimensional feature point is detected from the image captured by the rear camera 3. A reconstruction process is performed to calculate a deviation from the travel locus when the vehicle is moving forward.

As described above in detail, in the driving support device 1 according to the first embodiment, when the vehicle 2 enters the narrow street or the parking lot, the feature point 60 of the obstacle is detected from the captured image 50 captured by the rear camera 3. At the same time, the travel locus 75 of the vehicle 2 is detected and stored based on the detection result (S2 to S5), and when the vehicle 2 moves backward in the narrow street or the parking lot, it follows the saved travel locus 75. Since the vehicle is controlled so that the vehicle 2 moves backward (S17), when the vehicle is parked forward in a narrow parking lot and then departs while retreating, or when the vehicle 2 passes or stops on a narrow street or a narrow mountain road. Even when reversing in a situation where it is difficult to retreat, such as when there is a need to retreat, it is possible to perform appropriate traveling based on the traveling locus 75 of the vehicle during forward traveling. Therefore, the driver can drive the vehicle 2 more easily when reversing.
Further, the feature point 60 of the obstacle is detected by the rear camera 3, and the traveling locus of the vehicle 2 when the vehicle 2 moves forward is detected based on the relative position of the feature point 60 with respect to the own vehicle position. Compared with the case of detecting the locus, it is possible to detect the traveling locus more accurately.
Further, since the travel information of the vehicle 2 is detected and the vehicle operation is supported only when the vehicle 2 enters the narrow street or the parking lot, the processing load of the driving support ECU 4 is reduced except when it is difficult to move backward. It becomes possible to make it.

(Second Embodiment)
Next, the driving support device according to the second embodiment will be described with reference to FIGS. In the following description, the same reference numerals as those of the driving support apparatus 1 according to the first embodiment in FIGS. 1 to 9 denote the same or corresponding parts as those of the driving support apparatus 1 according to the first embodiment. It is shown.

The schematic configuration of the driving support apparatus according to the second embodiment is substantially the same as that of the driving support apparatus 1 according to the first embodiment. Various control processes are also substantially the same as the driving support apparatus 1 according to the first embodiment.
However, the driving assistance device 1 according to the first embodiment saves the traveling locus at the time of forward travel, and performs driving assistance of the driver by controlling the vehicle so as to move backward along the traveling locus at the time of forward travel. On the other hand, in the driving support device according to the second embodiment, the driving trajectory at the time of forward is stored, and the driving trajectory at the time of forward is superimposed on the BGM image to display the driving assistance of the driver. This is different from the driving support device 1 according to the embodiment.

  Below, the vehicle control processing program which driving assistance ECU4 of the driving assistance device which concerns on 2nd Embodiment performs is demonstrated based on FIG. FIG. 10 is a flowchart of a vehicle control processing program in the driving support apparatus according to the second embodiment. Note that the program shown in the flowchart of FIG. 10 is stored in the ROM 32 and RAM 33 provided in the driving support ECU 4 and is repeatedly executed by the CPU 31 at predetermined intervals (for example, every 4 ms).

  Here, the processes of S101 to S110 of the vehicle control processing program executed by the driving support device according to the second embodiment are the same as S1 of the vehicle control processing program executed by the driving support device 1 of the first embodiment. Since it is the same as the process of S5 and S7-S11, the description is abbreviate | omitted here.

  Next, in S111, the CPU 31 detects a BGM image captured by the rear camera 3 in S104 based on the reconstruction result of the three-dimensional feature points and the vehicle position information, and in S105, the RAM 31 detects the BGM image. Superimpose the saved travel trajectory during forward travel. The process of S111 corresponds to the process of the image superimposing means.

  Further, in S112, the CPU 31 calculates a predicted course when the vehicle 2 moves backward based on information related to the vehicle 2 stored in the vehicle DB 9 and detection results of various sensors of the vehicle speed sensor 12, the steering sensor 15, and the gyro sensor 16. .

  Subsequently, in S113, the CPU 31 superimposes the predicted course when the vehicle 2 moves backward in S112 on the BGM image captured by the rear camera 3.

In S <b> 114, the BGM image in which the traveling locus when the vehicle 2 moves forward and the predicted course when moving backward is superimposed is displayed on the liquid crystal display 5. Here, FIGS. 11 and 12 are views showing a BGM image 101 displayed on the liquid crystal display 5 when the vehicle 2 moves backward.
The BGM image 101 displays the rear environment of the vehicle 2 captured by the rear camera 3. For example, in FIG. 11 and FIG. Is done. Further, in the driving support apparatus according to the second embodiment, the BGM image 101 includes different types of lines (for example, the traveling locus 103 is a broken line) in the traveling path 103 when the vehicle 2 moves forward and the predicted course 104 when the vehicle moves backward. The predicted course 104 is indicated by a solid line). In particular, FIG. 11 shows a case where the predicted course 104 is deviated from the travel locus 103, and FIG. 12 shows that the predicted course 104 matches the travel locus 103 when the driver operates the steering wheel 20. It shows the case where it was made to do.
Therefore, by referring to the BGM image 101, the driver can easily grasp the traveling locus 103 that has traveled when moving forward, and further, the driver can operate the steering 20 to determine the predicted course 104 when the vehicle 2 moves backward. By making it coincide with the traveling locus 103 (see FIG. 12), it is possible to perform an appropriate traveling along the traveling locus during forward movement.

  Next, in S115, the CPU 31 determines whether or not a vehicle operation different from the traveling history of the vehicle 2 at the time of advance stored in S105 has been performed. Here, the case where the vehicle operation different from the traveling history of the vehicle 2 at the time of forward is performed is, for example, when the vehicle travels straight at a predetermined point when traveling forward, but makes a right turn or a left turn at the same point when traveling backward Etc.

  If it is determined that a vehicle operation different from the travel history is performed (S115: YES), the driver determines that the vehicle travels on a travel route different from the forward travel time, and the travel trajectory 103 during forward travel is displayed in the BGM image 101. Cancel. Then, the traveling history of the vehicle 2 stored in the RAM 33 in S105 is cleared (S107), and the vehicle control processing program is terminated.

  On the other hand, if a vehicle operation different from the travel history is not performed (S115: NO), the CPU 31 further determines in S116 based on the current position of the vehicle detected by the GPS 25 and the map data stored in the map DB 27. It is determined whether the vehicle has escaped from the narrow street or the parking lot. The determination may be based on the image recognition result by the rear camera 3 or the detection result of the millimeter wave radar.

  If it is determined that the vehicle has escaped from the narrow street or the parking lot (S116: YES), the display of the traveling locus 103 during forward movement is stopped in the BGM image 101 and stored in the RAM 33 in S105. The travel history of the vehicle 2 is cleared (S107), and the vehicle control processing program ends.

  On the other hand, when it is determined that the host vehicle is continuously traveling on the narrow street or the parking lot (S116: NO), the process returns to S112, and the predicted course when the vehicle 2 moves backward is calculated again. A newly calculated predicted course is displayed for the image 101.

As described above in detail, in the driving support device according to the second embodiment, when the vehicle 2 enters the narrow street or the parking lot, the feature point 60 of the obstacle is detected from the captured image 50 captured by the rear camera 3. At the same time, the traveling locus 103 of the vehicle 2 is detected and stored based on the detection result (S102 to S105). When the vehicle 2 moves backward in the narrow street or the parking lot, the saved traveling locus 103 is moved backward. Is displayed on the BGM image 101 together with the predicted course 104 (S114), so that the driver refers to the travel locus 103 of the displayed vehicle 2 to appropriately travel based on the travel locus 103 during forward travel. It becomes possible. Therefore, when you park in a narrow parking lot and then start again while retreating, or when you need to retreat due to a passing or dead end with other cars on narrow streets or narrow mountain roads, etc. Even when the vehicle is traveling backward in a difficult situation, it is possible to perform appropriate traveling based on the traveling locus 103 of the vehicle when traveling forward.
Further, the feature point 60 of the obstacle is detected by the rear camera 3, and the traveling locus of the vehicle 2 when the vehicle 2 moves forward is detected based on the relative position of the feature point 60 with respect to the own vehicle position. Compared with the case of detecting the locus, it is possible to detect the traveling locus more accurately.
Furthermore, since the traveling locus of the vehicle 2 when the vehicle 2 moves forward is superimposed on the BGM image 101 and displayed only when the vehicle 2 enters the narrow street or the parking lot, the driving assistance ECU 4 is used except when it is difficult to move backward. It is possible to reduce the processing load.

(Third embodiment)
Next, the driving assistance apparatus which concerns on 3rd Embodiment is demonstrated based on FIG. In the following description, the same reference numerals as those of the driving support apparatus 1 according to the first embodiment in FIGS. 1 to 9 denote the same or corresponding parts as those of the driving support apparatus 1 according to the first embodiment. It is shown.

The schematic configuration of the driving support apparatus according to the third embodiment is substantially the same as that of the driving support apparatus 1 according to the first embodiment. Various control processes are also substantially the same as the driving support apparatus 1 according to the first embodiment.
However, the driving support apparatus 1 according to the first embodiment is configured to detect the forward movement detected based on the reconstruction process result of the three-dimensional feature points based on the captured image captured by the rear camera 3, the own vehicle position, and the own vehicle direction. The driving support is provided by controlling the vehicle so as to store the traveling locus and to move backward along the traveling locus at the time of forward travel, whereas in the drive assistance device according to the third embodiment, the predetermined amount of time is determined at the time of forward travel. By comparing the image captured by the rear camera 3 at a distance interval and the image captured by the rear camera 3 at the same predetermined distance interval at the time of backward movement, a shift in the position and direction of the vehicle at the time of forward movement and backward movement is detected, and forward movement This is different from the driving support apparatus 1 according to the first embodiment in that the driving assistance of the driver is performed by controlling the vehicle so as to move backward along the same locus as the time.

  Below, the vehicle control processing program which driving assistance ECU4 of the driving assistance device which concerns on 3rd Embodiment performs is demonstrated based on FIG. FIG. 13 is a flowchart of a vehicle control processing program in the driving support apparatus according to the third embodiment. 13 is stored in the ROM 32 or RAM 33 provided in the driving support ECU 4, and is repeatedly executed by the CPU 31 at predetermined intervals (for example, every 4 ms).

  First, in S201, the CPU 31 performs matching processing based on the current position of the vehicle detected by the GPS 25 and the map data stored in the map DB 27, and determines whether or not the vehicle has entered a narrow street or a parking lot. Is done. The determination may be made based on the image recognition result by the rear camera 3 or the detection result of the millimeter wave radar.

  And when it determines with the own vehicle having entered into a narrow street or a parking lot (S201: YES), it transfers to S2. On the other hand, when it is determined that the own vehicle has not entered the narrow street or the parking lot (S201: NO), the vehicle control processing program ends.

  Subsequently, in S202, the CPU 31 determines whether or not a vehicle speed pulse generated from the vehicle speed sensor 12 has been detected. Here, since the vehicle speed pulse is generated by the vehicle speed sensor 12 every time the vehicle travels 200 mm, it is determined in S201 whether or not the vehicle has traveled a predetermined distance interval.

  As a result, when it is determined that a vehicle speed pulse has been detected (S202: YES), the rear camera 3 captures a BGM image behind the vehicle (hereinafter referred to as a forward-time captured image) (S203). Then, the captured forward-time captured image is stored in the RAM 33 (S204). As a result, forward-time captured images at predetermined distance intervals (specifically, 200 mm intervals) when the vehicle 2 moves forward are saved as a travel history. On the other hand, when it is determined that the vehicle speed pulse is not detected (S202: NO), the process waits until it is detected.

  In S205, when a vehicle operation such as a mirror operation or an operation for changing the vehicle height of the vehicle 2 is performed by operating the operation switch 21, the vehicle operation is performed in association with the forward-time captured image stored in S203. (For example, opening the door mirror 30 degrees, raising the vehicle height by 10 cm, etc.) is stored as a travel history.

  Thereafter, in S206, the CPU 31 determines whether or not the own vehicle has escaped from the narrow street or the parking lot based on the current position of the own vehicle detected by the GPS 25 and the map data stored in the map DB 27. The determination may be based on the image recognition result by the rear camera 3 or the detection result of the millimeter wave radar.

  If it is determined that the vehicle has escaped from the narrow street or the parking lot (S206: YES), the travel history of the vehicle 2 stored in the RAM 33 in S204 or S205 is cleared (S207), and the vehicle The control processing program is terminated.

  On the other hand, if it is determined that the vehicle is traveling on the narrow street or the parking lot (S206: NO), the CPU 31 shifts the vehicle 2 based on the detection result of the shift lever switch 17 in S208. It is determined whether or not the lever is reverse, that is, whether or not the vehicle 2 has started retreating in a narrow street or a parking lot.

  If it is determined that the shift lever of the vehicle 2 is not reverse (S208: NO), the process returns to S202, and the forward-time captured image captured based on the detection of the vehicle speed pulse is stored in the RAM 33 as a travel history again. On the other hand, if it is determined that the vehicle is reverse (S208: YES), whether or not to perform control of the vehicle 2 at the time of reversing based on the saved travel history (that is, assistance for driver's vehicle operation) is determined. An execution confirmation screen 70 is displayed on the liquid crystal display 5 (S209).

  Next, in S210, based on the selection by the driver, it is determined whether or not to control the vehicle 2 at the time of reverse based on the saved travel history (that is, support for the driver's vehicle operation). As a result, if it is determined that the vehicle 2 is not to be controlled (S210: NO), the traveling history of the vehicle 2 stored in the RAM 33 in S204 or S205 is cleared (S207), and the vehicle control processing program Exit.

  On the other hand, when it is determined to control the vehicle 2 (S210: YES), the process proceeds to S211. In S211, the CPU 31 determines whether or not a vehicle speed pulse generated from the vehicle speed sensor 12 has been detected. Here, since the vehicle speed pulse is generated from the vehicle speed sensor 12 every time the vehicle travels 200 mm, it is determined in S211 whether or not the vehicle has traveled a predetermined distance interval when reversing.

As a result, when it is determined that the vehicle speed pulse has been detected (S211: YES), the rear camera 3 captures a BGM image behind the vehicle (hereinafter referred to as a reverse captured image) (S212). Then, the backward captured image captured in S212 is compared with the forward captured image captured at the same distance from the backward start point in the forward captured image stored in the RAM 33 (S213). Here, since the driving support device 1 according to the present embodiment captures a BGM image by the rear camera 3 every time the vehicle 2 travels 200 mm at the time of forward movement and backward movement, from the time when it is determined in S208 that the vehicle moves backward. An image taken after the same number of images taken before the predetermined number is an image taken at the same distance from the reverse start point. Note that the image comparison in S213 is performed by detecting feature points in the forward picked-up image and the reverse picked-up image and comparing the positions of corresponding feature points among the detected feature points.
On the other hand, when it is determined that the vehicle speed pulse is not detected (S211: NO), the process waits until it is detected.

Next, in S214, the CPU 31 calculates the deviation of the position and direction of the vehicle 2 when traveling backward (specifically, the position and direction of the rear camera 3) with respect to the traveling locus when traveling based on the comparison result of the image of S213. To do. Thereafter, the CPU 31 calculates the operation amounts of the accelerator 18, the brake 19 and the steering 20 for eliminating the displacement of the calculated position and direction, and transmits a control instruction to the vehicle ECU 11 (S215). As a result, the control of the vehicle 2 is performed so that the vehicle 2 moves backward along the traveling locus during forward movement.
When the operation details of the vehicle operation are stored in S205, control is performed so that the corresponding vehicle operation is performed at the own vehicle position corresponding to the forward time. For example, when an operation of closing the door mirror 30 degrees at a predetermined point at the time of forward movement is performed, control is performed so as to perform an operation of opening the door mirror 30 degrees at the same point at the time of backward movement. Further, when an operation for lowering the vehicle height by 10 cm is performed at a predetermined point during forward travel, control is performed so as to perform an operation for increasing the vehicle height by 10 cm at the same point during backward travel.

  Next, in S216, the CPU 31 determines whether or not a vehicle operation different from the traveling history of the vehicle 2 during forward movement stored in S204 and S205 has been performed. Here, the case where the vehicle operation different from the traveling history of the vehicle 2 at the time of forward is performed is, for example, when the vehicle travels straight at a predetermined point when traveling forward, but makes a right turn or a left turn at the same point when traveling backward Etc.

  If it is determined that a vehicle operation different from the travel history has been performed (S216: YES), the driver determines that the vehicle travels on a travel route different from the forward travel time, and stops the control of the vehicle. Then, the traveling history of the vehicle 2 stored in the RAM 33 in S204 or S205 is cleared (S207), and the vehicle control processing program is terminated.

  On the other hand, if a vehicle operation different from the travel history is not performed (S216: NO), the CPU 31 further determines based on the current position of the vehicle detected by the GPS 25 in S217 and the map data stored in the map DB 27. It is determined whether the vehicle has escaped from the narrow street or the parking lot. The determination may be based on the image recognition result by the rear camera 3 or the detection result of the millimeter wave radar.

  If it is determined that the vehicle has escaped from the narrow street or the parking lot (S217: YES), the travel history of the vehicle 2 stored in the RAM 33 in S204 or S205 is cleared (S207), and the vehicle The control processing program is terminated.

  On the other hand, if it is determined that the host vehicle continues to travel on the narrow street or the parking lot (S217: NO), the process returns to S211 and travels again from the image captured by the rear camera 3 when traveling forward. The deviation from the locus is calculated.

As described above in detail, in the driving support device according to the third embodiment, when the vehicle 2 enters the narrow street or the parking lot, the rear camera 3 captures a forward-time captured image at a predetermined travel distance ( S203) The travel history is saved in the RAM 33 (S204), and after the vehicle starts to move backward, the backward captured image captured by the rear camera 3 at the same distance interval is included in the backward captured image stored in the RAM 33. Compared with the forward-captured image captured at the same distance from the start point (S213), the vehicle is controlled so that the vehicle 2 moves backward along the travel locus during forward travel (S215). Carry out a retreat when you parked forward in the parking lot and start again while retreating, or when you need to retreat on narrow streets or narrow mountain roads due to passing or dead ends with other cars. Even when retracted that in difficult situations, it is possible to perform appropriate driving based on the traveling locus 75 of the forward-movement of the vehicle. Therefore, the driver can drive the vehicle 2 more easily when reversing. In addition, since the travel locus at the time of forward movement is calculated based on the image captured by the rear camera 3, it is possible to detect the accurate vehicle position and the surrounding situation at the time of forward movement.
Since the vehicle operation is supported based on the comparison result between the forward image and the reverse image captured from the same distance from the reverse start point, it is more accurate based on the captured image. It becomes possible to compare the vehicle position and the surrounding situation and to perform the optimum vehicle support.

Note that the present invention is not limited to the above-described embodiment, and various improvements and modifications can be made without departing from the scope of the present invention.
For example, in the first embodiment and the second embodiment, the feature point 60 of the obstacle is detected by the rear camera 3, and the traveling locus when the vehicle 2 moves forward is detected based on the relative position of the feature point 60 with respect to the vehicle position. However, the traveling locus may be detected based only on GPS and map data.

  Further, in the first to third embodiments, when the vehicle 2 is operated in a vehicle different from the travel history, or when the vehicle 2 escapes the narrow street or the parking lot, the vehicle control based on the travel history and the display of the BGM image are performed. However, a control stop button may be provided, and when the control stop button is pressed, control of the vehicle based on the travel history and display of the BGM image may be ended. Furthermore, when an obstacle (for example, a pedestrian) different from that at the time of forward movement is detected during reverse, control of the vehicle based on the travel history and display of the BGM image may be terminated.

  In the first and second embodiments, the three-dimensional feature point reconstruction process is performed based on the captured image captured by the rear camera 3 to detect the position coordinates of the feature point 60 with respect to the vehicle position. However, two rear cameras may be installed at a predetermined interval with respect to the vehicle 2, and the position coordinates of the feature point 60 may be detected by stereoscopic viewing.

It is a schematic structure figure of a driving support device concerning a 1st embodiment. It is a block diagram showing typically a control system of vehicles which constitute a driving support device concerning a 1st embodiment. It is a flowchart of the vehicle control processing program in the driving assistance device concerning a 1st embodiment. It is the perspective view which showed the vehicle which advances ahead on a narrow street at the predetermined timing. It is the figure which showed the picked-up image imaged with the rear camera of the vehicle at the timing shown in FIG. It is the figure which showed the displacement vector after the micro time progress of the feature point in the picked-up image imaged with the rear camera at the timing shown in FIG. It is the figure which showed the assist execution confirmation screen displayed on the liquid crystal display. It is the perspective view which showed the vehicle which reverses the narrow street shown in FIG. 4 at the predetermined timing. It is the top view which showed the vehicle which reverses the narrow street shown in FIG. 4 at the predetermined timing. It is a flowchart of the vehicle control processing program in the driving assistance device concerning a 2nd embodiment. It is the figure which showed the BGM image displayed with respect to a liquid crystal display, when the prediction course at the time of reverse is deviating from the driving locus at the time of advance of vehicles. It is the figure which showed the BGM image displayed with respect to a liquid crystal display, when the predicted course at the time of reverse | coincidence with the driving | running | working locus | trajectory at the time of advance of a vehicle. It is a flowchart of the vehicle control processing program in the driving assistance device concerning a 3rd embodiment.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Driving assistance apparatus 2 Vehicle 3 Rear camera 4 Driving assistance ECU
5 Liquid crystal display 8 Current location detection unit 10 Travel history DB
11 Vehicle ECU
31 CPU
32 ROM
33 RAM
52-57 Obstacles 60 Features

Claims (10)

In a driving support device that supports a vehicle operation performed by a driver when the vehicle is moved backward,
Travel information detection means for detecting travel information of the vehicle when the vehicle moves forward;
Travel history storage means for storing the travel information of the vehicle detected by the travel information detection means as a travel history;
Reverse determination means for determining whether or not the vehicle moves backward,
A driving support device that assists vehicle operation based on a travel history stored in the travel history storage means when the reverse determination means determines that the vehicle is going backward.   The driving support device according to claim 1, wherein the travel information is a travel locus of the vehicle when moving forward. The travel information detecting means includes
Obstacle detection means for detecting obstacles around the vehicle;
Position detecting means for detecting a relative position of the obstacle detected by the obstacle detecting means with respect to the vehicle;
The driving support apparatus according to claim 2, further comprising traveling locus detection means for detecting a traveling locus of the vehicle based on a detection result of the position detection means.   4. The driving according to claim 2, further comprising vehicle control means for controlling the vehicle so that the vehicle moves backward along a traveling track of the vehicle when the reverse determination means determines that the vehicle is going backward. Support device. An imaging means disposed in the vehicle for imaging the surroundings of the vehicle;
An image superimposing unit that superimposes a travel locus of the vehicle detected by the travel information detecting unit on an image captured by the imaging unit when the reverse determination unit determines that the vehicle is reversing;
The driving support apparatus according to claim 2, further comprising: an image display unit that displays an image superimposed by the image superimposing unit.   The driving support apparatus according to claim 1, wherein the travel information is an operation content of a vehicle operation performed by a driver when moving forward.   And a vehicle operation control unit configured to control the vehicle so that a vehicle operation based on an operation content stored in the travel history storage unit is performed when the reverse determination unit determines that the vehicle is going back. The driving support device according to claim 6. An imaging means disposed in the vehicle for imaging the surroundings of the vehicle;
Mileage detection means for detecting the mileage of the vehicle,
The driving support device according to claim 1, wherein the traveling information is a forward-time captured image captured by an imaging unit from a vehicle at a predetermined distance interval when traveling forward. When it is determined by the reverse determination means that the vehicle is reverse, the picked-up images are picked up by the image pickup means from the vehicle at predetermined distance intervals,
The driving support device according to claim 8, wherein the vehicle operation is supported based on a comparison result between the forward-time captured image and the reverse-time captured image captured from the same distance from the reverse start point. . Having an entry detecting means for detecting that the vehicle has entered a narrow street or a parking lot;
The driving information detecting means detects driving information of the vehicle and assists the vehicle operation when the approach detecting means detects that the vehicle has entered a narrow street or a parking lot. The driving support device according to claim 9.

Images