JP5109413B2 - Object detection device - Google Patents

Description

  The present invention relates to an object detection device that detects an object.

  2. Description of the Related Art Conventionally, an apparatus for detecting surrounding objects has been used for driving support for vehicles. For example, it is suitably used for determining the preceding vehicle for automatic driving by grasping the inter-vehicle distance and the relative speed with surrounding vehicles. As such a device, an object detection device having a function of transmitting a radio wave to an object, receiving a reflected wave reflected by the object, detecting the presence and position of a surrounding object, and identifying the object is known. (For example, refer to Patent Document 1).

This apparatus has a function of identifying an object based on the intensity of a reflected wave from the object. Specifically, if the intensity of the reflected wave is greater than a first predetermined value, the object is a vehicle. An object detection device that identifies and identifies an object as a pedestrian when the intensity of the reflected wave is less than a first predetermined value and greater than a second predetermined value.
JP 2004-191131 A

  However, in the conventional apparatus, when the intensity of the reflected wave from the object becomes unstable, there is a risk of erroneous detection or identification. For example, when the intensity of the reflected wave is small, specifically, when an object such as a motorcycle or a bicycle having a small intensity of the reflected wave is detected, the detected object may be frequently lost. In addition, for example, in the case of a car with a round shape that hardly reflects transmitted radio waves, the intensity of the reflected wave may change, and there is a risk of re-identifying an object that has been identified as a car in the past as a motorcycle or a bicycle. is there.

  Accordingly, the present invention has been made to solve such a technical problem, and an object of the present invention is to provide an object detection apparatus with improved object identification accuracy.

  That is, the object detection apparatus according to the present invention is an object detection apparatus that identifies whether or not the object is a specific object based on the reception intensity of a reflected wave that is transmitted to the object and reflected by the object. A specific object history recording unit configured to record a specific object history for the object when the object is identified as a specific object under a predetermined condition; and Identification means for determining that the object is the specific object candidate when the specific object history is recorded in the object when the specific object history is recorded when the object is not equal to or greater than the first threshold. Composed.

  According to the present invention, when an object is identified as a specific object under a predetermined condition, a history of the identification result of the object is recorded, and the intensity of the reflected wave from the object becomes a first threshold value or more for a certain time or more. When the threshold value is not greater than or equal to the first threshold, the object having the history of the specific object can be identified as the specific object candidate regardless of the intensity of the reflected wave. As a result, when the intensity of the reflected wave from the object is unstable and the intensity of the reflected wave from the object does not currently exceed the first threshold, the object is further identified by referring to the past history. Therefore, it is possible to suppress misidentification due to the instability of the reflected wave intensity and improve the identification accuracy of the object detection apparatus.

  Here, in the object detection apparatus according to the present invention, when the intensity of the reflected wave from the object is not less than the first threshold after the intensity of the reflected wave from the object is not less than the first threshold after a certain time or more, When the specific object history is not recorded for the object, it is preferable to determine that the object is not the specific object candidate.

  According to the present invention, when an object is identified as a specific object under a predetermined condition, a history of the identification result of the object is recorded, and the intensity of the reflected wave from the object becomes a first threshold value or more for a certain time or more. When it is not greater than or equal to the first threshold after the recording, an object that does not have a specific object history can not be identified as a specific object candidate. Thus, for example, even when a so-called ghost target generated by detecting road surface reflection or the like as an object has exceeded a first threshold for a certain time or more, the object is further identified with reference to the past history. Therefore, it is possible to suppress erroneous identification of a ghost target as a specific object.

  ADVANTAGE OF THE INVENTION According to this invention, the identification accuracy of an object can be improved in an object detection apparatus.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same elements are denoted by the same reference numerals, and redundant description is omitted.

  FIG. 1 is a schematic configuration diagram of a driving support system including an object detection device according to this embodiment. This object detection apparatus is preferably used as a preceding vehicle detection means in a system such as ACC that automatically controls the distance between the host vehicle and the preceding vehicle, for example. Here, ACC (Adaptive Cruise Control) is a system that automatically follows when there is a preceding vehicle.

  As shown in FIG. 1, the object detection device 1 according to the present embodiment includes, for example, a millimeter wave sensor and an object detection ECU 10 which are vehicle periphery monitoring means. The object detection ECU 10 is connected to the travel control ECU 30 to constitute a travel support system. Here, the ECU (Electronic Control Unit) is a computer of an automobile device that is electronically controlled, and includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), an input / output interface, and the like. Configured.

  The millimeter wave sensor 20 used as a monitoring unit of the object detection device 1 is a sensor that acquires information on an object existing around the host vehicle. For example, the millimeter wave sensor 20 transmits radio waves and receives reflected waves from the objects. The function of measuring the presence or absence of the preceding vehicle, the distance between the preceding vehicle and the host vehicle, and the relative speed is provided. Moreover, it has the function to output the measured data to ECU10.

  The object detection ECU 10 connected to the monitoring means has a function of performing calculation processing for detecting a specific object, and determines a reflected wave information input unit 11, an intensity determination unit 12, and a preceding vehicle candidate (specific object). A processing unit 13 is provided.

  The reflected wave information input unit 11 is an input unit that inputs information related to a reflected wave from an object. For example, the reflected wave information input unit 11 has a function of inputting reflected wave information including the position, relative velocity, and intensity information of an object from the millimeter wave sensor 20. ing. In addition, a function of outputting the reflected wave information to the intensity determination unit 12 is provided.

  The intensity determination unit 12 is a determination unit that determines whether or not the input reflected wave is reflected from the vehicle. For example, the reflected wave information is input from the reflected wave information input unit 11, and A function is provided for determining whether the intensity is greater than the first threshold. Here, the first threshold value may be set to the minimum value of the intensity of the reflected wave assumed to be reflected by the vehicle, for example. In addition, a function of outputting the determined result to the preceding vehicle candidate determination processing unit 13 is provided.

  The preceding vehicle candidate determination processing unit 13 is a processing unit that determines a preceding vehicle (specific object) candidate, and has a function of determining a preceding vehicle candidate based on, for example, a determination result of the strength determination unit 12. Moreover, the function which outputs the determined candidate to travel control ECU30 is provided.

  The travel control ECU 30 connected to the object detection ECU 10 includes a preceding vehicle determination processing unit 31 and a travel control unit 32. The preceding vehicle determination processing unit 31 is a processing unit that determines the preceding vehicle based on the preceding vehicle candidate, and has a function of outputting the preceding vehicle determination result to the travel control unit 32. The travel control unit 32 has a function of outputting a signal for controlling each actuator of the host vehicle so as to follow the determined preceding vehicle.

  With the above configuration, a preceding vehicle candidate is selected based on the intensity of the reflected wave from the object, and it is determined whether the selected preceding vehicle candidate can be a preceding vehicle. As a result, automatic driving can be performed while following.

  Here, in particular, the object detection apparatus 1 according to this embodiment includes an intensity history record processing unit 14, an intensity history DB 15, an intensity history determination unit 16, a preceding vehicle history record processing unit 17, and a preceding vehicle history DB 18 in the object detection ECU 10. I have.

  The intensity history recording processing unit 14 is a processing unit that records the intensity of the reflected wave as a history, and has a function of acquiring the intensity of the reflected wave from, for example, the reflected wave information input unit 11 and recording it in the intensity history DB 15. . The intensity history DB 15 is a database that records, for example, the reflection intensity for each detected object in time series.

  The intensity history determination unit 16 is a determination unit that determines whether or not the reflection intensity has been equal to or higher than the first threshold value continuously for a predetermined period in the past. It has. Further, the strength history determination unit 16 has a function of outputting a determination result to the preceding vehicle candidate determination processing unit 13.

  The preceding vehicle history record processing unit 17 is a processing unit that records a vehicle set as the preceding vehicle as a history. For example, when the traveling control ECU 30 determines that the preceding vehicle is a preceding vehicle, the preceding vehicle history DB 18 stores the preceding vehicle in the preceding vehicle history DB 18. It has a function to record history. The preceding vehicle history DB 18 is a database that records, for example, whether or not each detected object has become a preceding vehicle. The preceding vehicle history DB 18 becomes an input source of the preceding vehicle candidate determination processing unit 13.

  By configuring in this way, the preceding vehicle candidate determination processing unit 13 described above not only determines a preceding vehicle candidate based on the determination result of the strength determination unit 12, but also the determination result of the strength history determination unit 16 and A preceding vehicle candidate is determined with reference to the preceding vehicle history DB 18 as well.

  Next, the operation of the travel control system including the object detection device according to the present embodiment will be described. In the following description, the specific object detected by the object detection device is referred to as a preceding vehicle.

  FIG. 2 is a flowchart showing the operation of the travel control system 2 according to the present embodiment. The flowchart shown in FIG. 2 is repeatedly executed at predetermined intervals, for example, when a travel control switch or the like is provided and the user presses the control start switch until the user presses the control end switch.

  The traveling control system 2 starts processing from the millimeter wave information input processing shown in FIG. 2 (S10). The process of S10 is executed by the reflected wave information input unit, and is a process for inputting information of a reflected wave from a certain object. For example, information including the intensity information of the reflected wave, the position of the reflected object, and the relative velocity is input from the millimeter wave sensor 20. Hereinafter, an object to be identified will be referred to as an object A for explanation. When the process of S10 ends, the process proceeds to an intensity history input process (S12).

  The process of S12 is executed by the intensity history determination unit 16 and is a process for inputting history information related to the object A from the intensity history DB 15. When the process of S12 ends, the process proceeds to an intensity history determination process (S14).

  The process of S14 is executed by the intensity history determination unit 16 and refers to the time-series intensity history of the object A input in S12. In the past, the intensity of the reflected wave is the first threshold value continuously for a certain time, for example, 1 second. It is determined whether or not this is the case. Here, the first threshold value may be set to the minimum value of the intensity of the reflected wave assumed to be reflected by the vehicle, for example. In the process of S14, when it is determined that the intensity of the reflected wave is equal to or greater than the first threshold value for a certain period of time, that is, when there is a high possibility that the object A is a vehicle, the process proceeds to a threshold flag setting process (S16 ).

  The process of S16 is executed by the intensity history determination unit 16 and is a process of turning on the threshold flag on the assumption that the object A whose reflected wave intensity is equal to or higher than the first threshold continuously for a certain time is likely to be a vehicle. is there. When the process of S16 ends, the process proceeds to the current reflected wave determination process (S18).

  The process of S18 is a process that is executed by the preceding vehicle candidate determination processing unit 13 and determines whether or not the intensity of the current reflected wave from the object A is equal to or higher than the first threshold value. In the process of S18, when it is determined that the value is equal to or greater than the first threshold value, the process proceeds to a preceding vehicle candidate determination process in order to make the object A a preceding vehicle candidate (S20).

  The process of S20 is a process that is executed by the preceding vehicle candidate determination processing unit 13 and determines the preceding vehicle candidate. In this process, the object A is determined as a preceding vehicle candidate. When the process of S20 ends, the process proceeds to a preceding vehicle determination process (S22).

  The process of S22 is a process that is executed by the preceding vehicle determination processing unit 31 and determines whether the preceding vehicle candidate input in S20, that is, the object A is suitable as the preceding vehicle. For example, whether or not the vehicle is a preceding vehicle is determined depending on whether or not the position of the object A obtained in the process of S10 is on the lane on which the host vehicle is traveling. When the object A is set as the preceding vehicle in the process of S22, the process proceeds to the following traveling process (S24).

  The process of S24 is a process that is executed by the travel control unit 32 and controls the inter-vehicle distance based on the behavior of the preceding vehicle determined in S22, that is, the object A, and follows the vehicle. When the process of S24 is completed, the process proceeds to the preceding vehicle recording process (S26).

  The process of S26 is a process executed by the preceding vehicle history recording processing unit 17 and records in the preceding vehicle history DB 18 that the object A has become a preceding vehicle. When the process of S26 ends, the control process of FIG. 2 ends.

  On the other hand, in the process of S14, when it is determined that the intensity of the reflected wave from the object A is not equal to or greater than the first threshold value for a certain period of time, the process proceeds to the current reflected wave determination process described above (S18), and after S18. Execute the process.

  In the process of S18, when it is determined that the current reflected wave intensity from the object A is not greater than or equal to the first threshold value, that is, the current reflected wave intensity from the object A is within a range that can be recognized as a car. If it is lower, the process proceeds to threshold flag confirmation processing (S28).

  The process of S28 is executed by the intensity history determination unit 16, and at present, the reflection intensity from the object A is small, but in order to confirm whether there is a case where it is equal to or more than the first threshold continuously for a certain time in the past, This is processing for determining whether or not the threshold flag for the object A is turned on. When the threshold flag is turned on, that is, when the reflected wave from the object A has been continuously equal to or greater than the first threshold for a certain period in the past, the process proceeds to the preceding vehicle history confirmation process (S30).

  The process of S30 is a process that is executed by the preceding vehicle candidate determination processing unit 13 and determines whether or not the object A has been a preceding vehicle in the past based on the information in the preceding vehicle history DB18. If the vehicle is a preceding vehicle in the past, the process proceeds to a preceding vehicle candidate determination process (S20), and the processes after S20 are executed.

  On the other hand, if the threshold flag is not turned on in S28, that is, if the reflected wave from the object A has not been equal to or more than the first threshold for a certain period in the past, the object A is regarded as the preceding vehicle. Is not set, the process proceeds to the constant speed running process (S32).

  The process of S32 is executed by the travel control unit 32, and is performed when it is determined that there is no preceding vehicle that follows the vehicle, that is, when it is determined that the object A is not a preceding vehicle. This process is, for example, a process of releasing a command to automatically follow the vehicle and outputting a command to travel while maintaining a constant speed to each actuator of the host vehicle. When the process of S32 ends, the control process of FIG. 2 ends.

  On the other hand, in the process of S30, the object A is the first threshold value or more continuously for a certain period in the past, but the object A is a ghost target when it has never become a preceding vehicle. Since there is a high possibility, the process shifts to the constant speed running process so as not to set the object A as the preceding vehicle (S32), and after executing the process of S32, the control process of FIG.

  Furthermore, in the process of S22, when it is determined that the object A does not exist in the same lane as the own vehicle, the object A is not set as the preceding vehicle, so the process proceeds to the constant speed travel process (S32), and the process of S32 After execution, the control process of FIG. 2 ends.

  When the object detection device 1 operates as shown in FIG. 2, the identification accuracy of the object detection device 1 is improved. For example, in the conventional object detection device, the vehicle is determined only by whether or not the reflection intensity exceeds the first threshold value. Therefore, the reflected wave that temporarily exceeds the first threshold value due to the reflection angle, noise, or the like is also determined as the vehicle. And he was a candidate for a preceding vehicle. For this reason, there is a possibility that a vehicle that is not a vehicle is a preceding vehicle candidate.

  On the other hand, the object detection apparatus 1 of the present embodiment determines whether or not the reflection intensity is an object having a value equal to or higher than the first threshold value for a certain time in the past, and temporarily exceeds the first threshold value. Such a reflected wave can not be a preceding vehicle candidate. Further, when the vehicle becomes a preceding vehicle, the history is acquired in the preceding vehicle history DB 18 and used for the determination of the next preceding vehicle candidate, thereby realizing more accurate object detection.

  As described above, according to the object detection device 1 of the present embodiment, an object A that has a reflection intensity equal to or higher than the first threshold value continuously for a certain time in the past and that is on a lane on which the host vehicle travels is detected as a preceding vehicle. Is recorded, and when the intensity of the reflected wave from the object A is not less than the first threshold after the intensity of the reflected wave from the object A is not less than the first threshold after a certain time, The object A having the history of the preceding vehicle can be identified as a preceding vehicle candidate regardless of the intensity of the reflected wave. As a result, when the intensity of the reflected wave from the object A is unstable and the intensity of the reflected wave from the object A does not currently exceed the first threshold value, the past history of the object A is further referred to. Therefore, it is possible to identify whether or not the vehicle is a preceding vehicle. Therefore, it is possible to suppress misidentification caused by the instability of the reflected wave intensity and improve the identification accuracy of the object detection device 1.

  Further, according to the object detection apparatus 1 of the present embodiment, the object A that has a reflection intensity equal to or higher than the first threshold continuously in the past for a certain period of time and that is on the lane on which the host vehicle travels is a preceding vehicle. When recognized, the history of the identification result of the object A is recorded, and when the intensity of the reflected wave from the object A is not less than the first threshold after the intensity is not less than the first threshold for a certain time or more, the preceding vehicle's An object having no history can not be identified as a preceding vehicle candidate. Thereby, for example, even when the object A is a so-called ghost target such as road surface reflection and the first threshold is not less than a certain time, the preceding history of the object A is further referred to. Since it can identify whether it was a vehicle, it can suppress misidentifying a ghost target as a preceding vehicle candidate.

  The above-described embodiment shows an example of the object detection apparatus according to the present invention. The object detection device according to the present invention is not limited to the above, and the object detection device according to the embodiment is modified or applied to others so as not to change the gist described in each claim. It may be a thing.

  For example, in the embodiment, the monitoring unit has been described as a millimeter wave sensor, but the distance and relative velocity of the object are measured based on reflection from the object, such as a sensor using a microwave or a submillimeter wave, and the object Any sensor can be used.

1 is a schematic configuration diagram of a driving support system including an object detection device according to an embodiment. It is a flowchart which shows operation | movement of the driving assistance system of FIG.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 ... Object detection apparatus, 2 ... Travel control system, 10 ... Object detection ECU, 11 ... Reflected wave information input part, 12 ... Intensity determination part, 13 ... Predecessor vehicle candidate determination process part, 14 ... Intensity history recording process part, 15 ... intensity history DB, 16 ... intensity history determination unit, 17 ... preceding vehicle history recording processing unit, 18 ... preceding vehicle history, 20 ... millimeter wave sensor, 30 ... travel control ECU, 31 ... preceding vehicle determination processing unit, 32 ... travel Control unit.

Claims (2)

An object detection device for identifying whether or not the object is a specific object based on the intensity of a reflected wave transmitted from the object and reflected by the object,
A specific object history recording means for recording a specific object history for the object when the object is identified as a specific object under a predetermined condition;
When the specific object history is recorded in the object when the intensity of the reflected wave from the object is not less than the first threshold after the intensity is not less than the first threshold for a certain time or more, the object Identifying means for determining that is a specific object candidate;
An object detection apparatus comprising: When the intensity of the reflected wave from the object is not less than the first threshold after the intensity of the reflected wave from the object is not more than the first threshold, the specific object history is not recorded in the object. Determining that the object is not the specific object candidate,
The object detection apparatus according to claim 1.

Images