WO2019065411A1 - Vehicle sensing system - Google Patents

Vehicle sensing system Download PDF

Info

Publication number
WO2019065411A1
WO2019065411A1 PCT/JP2018/034649 JP2018034649W WO2019065411A1 WO 2019065411 A1 WO2019065411 A1 WO 2019065411A1 JP 2018034649 W JP2018034649 W JP 2018034649W WO 2019065411 A1 WO2019065411 A1 WO 2019065411A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
detection
radar
camera
degrees
Prior art date
Application number
PCT/JP2018/034649
Other languages
French (fr)
Japanese (ja)
Inventor
平山 義幸
Original Assignee
日立オートモティブシステムズ株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 日立オートモティブシステムズ株式会社 filed Critical 日立オートモティブシステムズ株式会社
Priority to JP2019545007A priority Critical patent/JP6818902B6/en
Publication of WO2019065411A1 publication Critical patent/WO2019065411A1/en

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/86Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88Radar or analogous systems specially adapted for specific applications
    • G01S13/93Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/16Anti-collision systems

Definitions

  • the present invention relates to a vehicle detection system for continuously detecting a vehicle to be detected (hereinafter referred to as a detection vehicle).
  • Patent Document 1 outputs an image capturing means for capturing a situation ahead of the vehicle as an image, and position information of an object to be noticed by the vehicle.
  • an external world recognition apparatus comprising an object of interest output means, and an image processing means for performing image processing on a region based on an output of the object of interest output means in the image capturing means and detecting the object
  • the image processing means detects the position of the object And a second method of tracking the object, and when the object can not be detected by the first method, the object is detected by the second method.
  • a safety support travel system which controls a vehicle so as to prevent occurrence of a collision with a vehicle etc. in advance or reduce the damage at the time of a collision.
  • the sensor used for detection differs depending on the position of the detection vehicle. This is because it depends on the characteristics of the sensor.
  • a detection point changes with positions of a detection vehicle
  • a detection point also changes with directions of a detection vehicle.
  • the detection point is the front center of the detection vehicle.
  • the detection point is the front end or the side center of the detection vehicle.
  • the detection point is either the rear end of the detection vehicle or the rear center.
  • the orientation of a detection vehicle can be obtained from a change in detected coordinates.
  • the direction can be obtained from the velocity in the X direction and the Y direction.
  • FIG. 1 is a diagram showing the result of analyzing the direction of a detected vehicle by a stereo camera
  • FIG. 2 is a diagram showing the result of analyzing the direction of a detected vehicle by a millimeter wave radar.
  • the detection vehicle 2000 passes straight in the vicinity of the host vehicle 1000 at a constant speed (relative speed 20 km / h)
  • the detection vehicle 2000 is analyzed using the detection value of the stereo camera.
  • the relative velocity Vx in the longitudinal direction of the vehicle is detected as about 15 to 20 km / h as shown in FIG. 1 (2), and the direction of the detection vehicle is detected as about 0 degree as shown in FIG. Ru.
  • the detection vehicle 1000 when the same scene is analyzed using the detection value of the millimeter wave radar, although the detection vehicle is traveling straight at a constant speed (relative speed 20 km / h), the own vehicle 1000
  • the relative velocity Vx in the longitudinal direction of the detection vehicle 2000 when passing near is detected to be about 10 km / h or less as shown in FIG. 2 (2), and as shown in FIG. 2 (3) It was revealed that the direction was detected as -50 to 0 degrees.
  • the millimeter wave radar may detect “speed decrease” by mistake in front of the host vehicle and calculate “incorrect direction of detected vehicle”. It became clear by examination of this inventor.
  • the present invention has been made in view of the above problems, and provides a vehicle detection system capable of highly accurately determining the direction of a detection vehicle traveling around the host vehicle and performing tracking with high accuracy.
  • the purpose is to
  • the present invention includes a plurality of means for solving the above problems, and an example thereof is a vehicle detection system for detecting the position and direction of a detection vehicle traveling around the host vehicle.
  • a sensor group including a radar installed near a front corner and a camera installed on the side of the vehicle, and an arithmetic device for calculating the direction of the detection vehicle based on the detection result of the sensor group,
  • the detection angle range of the radar is in the range of 105 degrees or less outward with respect to the front of the vehicle
  • the detection angle range of the camera is 65 degrees to 115 degrees outward with respect to the front of the vehicle. It is characterized by including an angle range of
  • the forward direction of the host vehicle means the traveling direction when the host vehicle travels straight ahead, and the angle is defined as 0 degrees ahead of the host vehicle.
  • FIG. 3 is a block diagram showing an example of a system configuration of the vehicle detection system of the present embodiment.
  • FIG. 4 is a view showing a detection angle range of the millimeter wave radar with respect to the host vehicle.
  • FIG. 5 is a view showing a detection angle range of the camera with respect to the host vehicle.
  • FIG. 6 is a diagram showing the relationship between the error rate of detection of the direction of the vehicle of the millimeter wave radar and the detection angle in the present invention.
  • FIG. 7 is a diagram showing the relationship between the error rate for detecting the direction of the vehicle of the millimeter wave radar and the maximum angle of the detection range in the present invention.
  • FIG. 8 is a flowchart for explaining the flow of processing of the vehicle detection system in the present embodiment.
  • a vehicle detection system 1 for detecting the position and the direction of a detection vehicle traveling around the host vehicle 1000 includes a radar 10, a camera 20, and an arithmetic device 100.
  • the radar 10 is a radar that detects a detection vehicle by a millimeter wave and calculates its position and velocity, and uses a millimeter wave with a wavelength of about 1 to 10 mm and a frequency of 30 G to 300 GHz (gigahertz) for radio waves to be emitted It is a radar.
  • the details thereof are not particularly limited, and as a detection method of distance and relative velocity, for example, a known FM-CW (Friquency-Modulated Continuous Wave) method, a two-frequency CW (Continuous Wave) method, a spread spectrum method, a pulse method, etc. Any scheme may be applied.
  • the details of the direction detection method are not particularly limited, and the direction detection method may be applied to a known method such as an electronic scan method, a mechanical scan method, or a monopulse method. Also, publicly known processing can be used for calculation processing of the position and speed of the detection vehicle.
  • the radar 10 is mounted on the left and right front corners of the vehicle 1000 as shown in FIG. 4, and the detection angle range thereof is a range of 105 degrees or less outward with respect to the forward direction of the vehicle 1000.
  • the mounting angle is 45 degrees
  • the detection angle range is a range (100 degrees) from -5 degrees to 95 degrees with reference to the forward direction of the host vehicle.
  • the mounting angle in the present embodiment means an angle corresponding to the center of the outward minimum value and the maximum value with reference to the forward direction of the vehicle 1000 in the detection angle range of the radar 10.
  • the detection angle range can be calculated by measuring the relationship between the position of the detection vehicle and the possibility of detection when the detection vehicle travels around the host vehicle.
  • the camera 20 captures an image of the detected vehicle by an imaging element, and calculates the position and speed of the detected vehicle from the imaging results. Even when there are a plurality of detection vehicles around the host vehicle 1000, the camera 20 can detect the detection vehicles separately for each vehicle.
  • the details of the camera 20 are also not particularly limited, and a stereo camera having a known configuration in which information in the depth direction can also be recorded can be appropriately applied by simultaneously photographing an object from a plurality of different directions. Also, publicly known processing can be used for calculation processing of the position and speed of the detection vehicle.
  • the camera 20 is mounted on the left and right side surfaces of the vehicle 1000, and the detection angle range is an angle range of 65 degrees to 115 degrees outward with reference to the forward direction of the vehicle 1000.
  • the mounting angle is 90 degrees
  • the detection angle range is a range (50 degrees) of 65 degrees to 115 degrees with reference to the forward direction of the host vehicle.
  • the radar 10 erroneously detects "speed reduction” obliquely ahead of the host vehicle and calculates "incorrect direction”.
  • the present inventors have further intensively studied the false detection area. The examination results will be described below with reference to FIGS. 6 and 7.
  • the measurement was performed while changing the mounting angle from 15 degrees to 120 degrees (detection angle And the attachment angle made the forward direction of the own vehicle 0 degree).
  • the graph which plotted the error rate of direction detection of the detection vehicle measured on this condition with respect to the detection angle is FIG.
  • the plot points are mean values, and the maximum and minimum values are indicated by error bars.
  • the detection angle range of the radar 10 is the direction detection of the detection vehicle by the millimeter wave radar in the range of 65 degrees to 115 degrees outward when based on the forward direction of the host vehicle 1000 It was found that the error rate of In particular, it has been found that the error rate is high when the angle is in the range of 75 degrees to 105 degrees. Therefore, it has become clear that it is necessary to cover the angle range of 65 degrees to 115 degrees, which the radar 10 is not good at, with the camera 20.
  • a vehicle traveling in the vicinity of the host vehicle is detected to check the accuracy of the detection result of the detected vehicle, and the error rate average value of the detection angle range (The angle is 0 degrees in the forward direction of the host vehicle).
  • tracking processing is included. That is, the newly detected data was judged by comparing the predicted value from the past data and the newly detected data. In other words, the newly detected data is not adopted as suspicious.
  • FIG. 7 shows a diagram in which the error rate of the direction detection of the vehicle is plotted against the maximum angle of the detection range.
  • the results of using five types of millimeter wave radars having different detection angle ranges are indicated by different marks.
  • the error rate can be reduced by setting the detection angle range of the millimeter wave radar to 105 degrees or less.
  • the detection angle range of the radar 10 is set to a range of 105 degrees or less outward with respect to the forward direction of the host vehicle 1000, and the detection angle range of the camera 20 is based on the forward direction of the host vehicle 1000. And include an angle range of 65 degrees to 115 degrees outward.
  • the sensor group of the present embodiment is configured of the radar 10 installed at the front corner of the host vehicle 1000 and the camera 20 installed on the side surface of the host vehicle 1000.
  • the sensor group is not limited to the case where it is configured by two radars 10 and two cameras 20, and may be configured by one or more radars 10 and one or more cameras 20. .
  • different types of known sensors can be further included.
  • detection ranges of the radar 10 and the camera 20 be overlapped.
  • the arithmetic unit 100 is an arithmetic processing unit that calculates the direction of the detection vehicle based on the detection result of the sensor group, and is configured by a computer having a CPU, a memory, an I / O, and the like.
  • the computing device 100 includes an input unit 110, an angle determination unit 120, a computing unit 130, and an output unit 140.
  • the input unit 110 is a portion that receives an input of data on the position and velocity of a detection vehicle output from the radar 10 or the camera 20.
  • the input data of each sensor is output to the angle determination unit 120.
  • the angle determination unit 120 calculates how many positions of the detection vehicle exist outward when the forward direction of the host vehicle 1000 is a reference. Then, when it is determined that the detection vehicle exists outward at 65 degrees or less with reference to the forward direction of the host vehicle 1000, the angle determination unit 120 causes the calculation unit 130 to calculate the calculation result of the radar 10 Output. Further, when it is determined that the detection vehicle is present at an angle larger than 65 degrees, the angle determination unit 120 outputs the calculation result of the camera 20 to the calculation unit 130. The output of these calculation results is executed for each detected vehicle.
  • the boundary angle is not limited to 65 degrees and can be changed as appropriate.
  • the boundary angle may be 75 degrees or 80 degrees at which the detection error rate of the radar 10 sharply rises, and may be 105 degrees which is the maximum angle range.
  • the calculation unit 130 calculates the direction of the detection vehicle from the calculation result of the radar 10 input from the angle determination unit 120 or the calculation result of the camera 20 and the calculation result of the position and speed of the detection vehicle in the past. . If there are a plurality of detection vehicles, the calculation unit 130 calculates the direction for each detection vehicle. The calculation result is output to the vehicle control ECU 200 via the output unit 140.
  • the calculation unit 130 When calculating the direction of the detection vehicle, the calculation unit 130 according to this embodiment does not distinguish whether the detection information in the past is a detection value based on the radar 10 or a detection value based on the camera 20.
  • the radar vehicle takes over and utilizes the information on the position and direction of the detection vehicle calculated based on the detection result of the camera 20 when it is at a position larger than 65 degrees.
  • the position and direction of the detection vehicle are calculated based on the 10 detection results.
  • the information on the position and the direction of the detected vehicle calculated based on the detection result of the radar 10 when it exists at 65 degrees or less is inherited and used,
  • the position and the direction of the detected vehicle calculated based on the detection result of the camera 20 using it are calculated. Thereby, it is comprised so that a detection vehicle may be tracked continuously.
  • Vehicle control ECU Electronic Control Unit
  • the vehicle control ECU 200 executes control for supporting automatic driving of the host vehicle 1000.
  • the target steering angle is output to the steering device 230 to control the traveling direction of the host vehicle 1000.
  • the required driving force is output to the driving force control ECU 210 that controls the driving force of the host vehicle 1000
  • the required braking force is output to the braking force control ECU 220 that controls the braking force, thereby controlling the speed of the host vehicle 1000.
  • the shift range of the own vehicle 1000 is controlled by issuing a request for the drive range, the reverse range or the parking range to the shift by wire control device 240 that controls the shift range of the automatic transmission.
  • the vehicle detection system 1 of the present embodiment repeatedly executes the processing shown in FIG. 8 while the engine of the host vehicle is ON.
  • the vehicle detection system 1 measures the surroundings of the host vehicle 1000 by the radar 10 and the camera 20, and calculates the position and speed of the detection vehicle if it exists (step S100).
  • the position and speed thereof are calculated for each detection vehicle. Also, when there is no detected vehicle, a flag indicating that there is no detected vehicle is set.
  • the vehicle detection system 1 inputs the calculation result of the radar 10 and the camera 20 calculated in step S100 to the calculation device 100 (step S110).
  • the vehicle detection system 1 determines the position of the detection vehicle (how many positions outward with respect to the forward direction of the host vehicle 1000 exist) in the angle determination unit 120 (step S120).
  • the angle determination unit 120 calculates the calculation unit among the calculation results input in step S110.
  • the calculation result of the radar 10 is output to 130.
  • the angle determination unit 120 outputs the calculation result of the camera 20 to the calculation unit 130 among the calculation results input in step S110.
  • the angle determination unit 120 outputs a processing signal to the arithmetic unit 130 to skip the next steps S130 and S140 with no detected vehicle.
  • the vehicle detection system 1 determines in the calculation unit 130 whether there is a past detection value of the detection vehicle (step S130).
  • step S140 If it is determined in this step that there is a past detected value of the detected vehicle, the process proceeds to step S140. On the other hand, when it is determined that there is no past detected value of the vehicle, the process proceeds to step S150.
  • the detected vehicle in the past does not distinguish whether it is a detected value based on the radar 10 or a detected value based on the camera 20 in a pure manner. And / or detected by the camera 20, it is determined whether or not there is a calculation result of position and velocity.
  • the vehicle detection system 1 calculates the direction of the detection vehicle based on the past detection result of the detection vehicle and the information output in step S120 in the calculation unit 130 (step S140).
  • step S140 similarly to step S130, when calculating the direction of the detection vehicle, it is not distinguished whether the detection information in the past is a detection value based on the radar 10 or a detection value based on the camera 20. It shall be.
  • the vehicle detection system 1 determines whether or not the directions of all the detected vehicles have been calculated based on the detection results of the radar 10 and the camera 20 in the calculation unit 130 (step S150).
  • step S120 If it is determined in this step that the directions of all the detected vehicles have been calculated, the processing is ended. On the other hand, when it is determined that the directions of all the detected vehicles are not calculated, the process returns to step S120, and the calculation of all the detected vehicles is ended.
  • the vehicle detection system 1 of the present embodiment described above detects a sensor group including the radar 10 installed at the front corner of the host vehicle 1000 and the camera 20 installed at the side surface of the host vehicle 1000 and detection results of the sensor group
  • the detection angle range of the radar 10 is in the range of 105 degrees or less outward with respect to the forward direction of the host vehicle 1000
  • the detection angle range of the camera 20 is An angle range of 65 degrees to 115 degrees is included outward with reference to the forward direction of the host vehicle 1000.
  • the direction of the detection vehicle is calculated using the detection result of the camera 20 in the area where the “speed decrease” is detected by mistake in front of the host vehicle 1000 and the “incorrect direction” is calculated.
  • the direction of the detection vehicle can be calculated using the detection result of the radar 10 outside the region. Therefore, the accuracy of the calculation of the direction of the detection vehicle can be improved as compared with the conventional case, and the tracking of the detection vehicle present around the host vehicle 1000 can be accurately and stably performed in the automatic driving.
  • the computing device 100 uses information on the position and orientation of the detected vehicle calculated based on the detection result of the radar 10 when calculating the position and orientation of the detected vehicle based on the detection result of the camera 20, and the camera 20
  • the information on the position and direction of the detected vehicle calculated on the basis of the detection result of is used to calculate the position and the direction of the detected vehicle on the basis of the detection result of the radar 10 to continuously track the detected vehicle.
  • the information (position, speed, acceleration, vehicle size, direction of the vehicle) of the surrounding vehicles detected by 10 can be delivered to the camera 20 which is a video system sensor, and the recognition rate and recognition when recognizing the detected vehicle from the image Accuracy can be improved.
  • the detection accuracy of the direction of the detection vehicle can be made more accurate, and the tracking accuracy can be further improved.
  • the detection information of the camera 20 is not used to determine the direction of the detection vehicle detected in an angle range of 65 degrees to 115 degrees outward with reference to the forward direction of the host vehicle 1000.
  • the radar 10 erroneously detects the “speed decrease” obliquely ahead of the host vehicle 1000 and detects the detection vehicle more reliably excluding the area where the “incorrect detection vehicle direction” is calculated. This enables more accurate tracking of the detected vehicle.
  • the information of the plurality of detection vehicles is used when computing the direction of the detection vehicles by the radar 10, so that the camera 20 is excellent in detection of a plurality of vehicles. It becomes possible to detect that there are a plurality of vehicles with higher accuracy and to take over the information to the radar 10, and even when there are a plurality of vehicles around the host vehicle 1000, with high accuracy It can track.
  • the position and the speed of the detection vehicle are calculated by the radar 10 and the camera 20

Abstract

Provided is a vehicle sensing system enabling highly precise locating and tracking of a target vehicle travelling in the surroundings of a host vehicle. A vehicle sensing system 1 for detecting the position and orientation of a target vehicle travelling in the surroundings of a host vehicle 1000 has: a sensor array comprising radars 10 disposed near the front corners of the host vehicle 1000 and cameras 20 disposed on the side surfaces of the host vehicle 1000; and a calculation device 100 for calculating the orientation of the target vehicle on the basis of sensing results from the sensor array. The sensing angle range of radar 10 is equal to or less than 105° in the outward direction with respect to the direction of travel when the host vehicle 1000 is travelling forward. The sensing angle range of camera 20 is between 65° and 115° in the outward direction with respect to the direction of travel when the host vehicle 1000 is travelling forward.

Description

車両検知システムVehicle detection system
 本発明は、検知対象となる車両(以下、検知車両)を継続して検知するための車両検知システムに関する。 The present invention relates to a vehicle detection system for continuously detecting a vehicle to be detected (hereinafter referred to as a detection vehicle).
 位置検知と追跡を両立できる車両用外界認識装置の一例として、特許文献1には、自車前方の状況を画像として撮り込む画像取り込み手段と、自車にとって注目すべき物体の位置情報を出力する注目物体出力手段と、画像取り込み手段における注目物体出力手段の出力に基づく領域を画像処理し、物体を検知する画像処理手段と、を備える外界認識装置において、画像処理手段は、物体の位置を検知する第1の手法と、物体の追跡を行う第2の手法を備え、第1の手法により物体が検知できないとき、第2の手法により物体を検知する、ことが記載されている。 As an example of a vehicle external world recognition device capable of achieving both position detection and tracking, Patent Document 1 outputs an image capturing means for capturing a situation ahead of the vehicle as an image, and position information of an object to be noticed by the vehicle. In an external world recognition apparatus comprising an object of interest output means, and an image processing means for performing image processing on a region based on an output of the object of interest output means in the image capturing means and detecting the object, the image processing means detects the position of the object And a second method of tracking the object, and when the object can not be detected by the first method, the object is detected by the second method.
特開2005-038407号公報JP, 2005-038407, A
 近年、自車両周辺に存在する物体を検出するレーダ装置や、自車両周辺の画像を撮像する撮像装置等を車両に搭載し、これらレーダ装置や撮像装置等で検出された情報に基づいて、他車両等との衝突事故等の発生を未然に防止したり、衝突時の被害を軽減したりするように車両を制御する安全支援走行システムが提案されている。 In recent years, a radar device that detects an object present around the vehicle, an imaging device that captures an image of the periphery of the vehicle, and the like are mounted on the vehicle, and other information is detected based on the information detected by the radar device and the imaging device. A safety support travel system has been proposed which controls a vehicle so as to prevent occurrence of a collision with a vehicle etc. in advance or reduce the damage at the time of a collision.
 このようなシステムを実現するためには、自車両の周囲を走行する検知車両の位置検知と追跡を高精度に行うことが求められる。このような技術の一環として、上述した特許文献1に記載のような技術がある。 In order to realize such a system, it is required to perform position detection and tracking of a detection vehicle traveling around the host vehicle with high accuracy. As part of such a technique, there is a technique as described in Patent Document 1 mentioned above.
 ここで、自動運転において検知車両のトラッキングを精度良く安定して行うためには、「車両の向き」から検出点を判断して検知車両の正しい位置を求める必要がある。 Here, in order to perform tracking of a detection vehicle accurately and stably in automatic driving, it is necessary to determine a detection point from "the direction of the vehicle" to obtain a correct position of the detection vehicle.
 しかし、複数の検知手段を用いて検知車両を検知する場合、検知車両の位置によって検知に用いるセンサが異なる。これはセンサの特徴に依存するためである。 However, when detecting a detection vehicle using a plurality of detection means, the sensor used for detection differs depending on the position of the detection vehicle. This is because it depends on the characteristics of the sensor.
 また、検知車両の位置によって検出点が異なるとともに、検知車両の向きによっても検出点が異なる。 Moreover, while a detection point changes with positions of a detection vehicle, a detection point also changes with directions of a detection vehicle.
 例えば、自車両後方を検知する後側方レーダであれば、検知点は検知車両の前面中心となる。自車両横方向周辺を検知するサラウンドカメラであれば、検知点は検知車両の前面端部あるいは側面中心となる。また、自車両前方を検知する前側方レーダや前方カメラであれば、検知点は検知車両の背面端部あるいは背面中心のいずれかとなる。 For example, in the case of a rear side radar that detects the rear of the host vehicle, the detection point is the front center of the detection vehicle. In the case of a surround camera that detects the periphery of the host vehicle in the lateral direction, the detection point is the front end or the side center of the detection vehicle. In addition, in the case of a front side radar or a front camera that detects the front of the host vehicle, the detection point is either the rear end of the detection vehicle or the rear center.
 また、検出値からの検知車両の向きの求め方も、センサによって異なる。 Moreover, how to obtain | require the direction of the detection vehicle from a detected value also changes with sensors.
 例えば、ステレオカメラ等の撮像装置では、検出した座標の変化から検知車両の向きが得られる。一方、ミリ波レーダでは、X方向とY方向の速度から向きが得られる。 For example, in an imaging device such as a stereo camera, the orientation of a detection vehicle can be obtained from a change in detected coordinates. On the other hand, in the millimeter wave radar, the direction can be obtained from the velocity in the X direction and the Y direction.
 ここで、検知車両の向きを求める際に、センサによっては異常な値を検知するケースがあり、誤った向きを算出することがあることが本発明者の検討によって明らかとなった。 Here, when finding the direction of the detection vehicle, depending on the sensor, there are cases where an abnormal value is detected, and it has become clear by the study of the inventor that the wrong direction may be calculated.
 以下、自車両の近傍を真直ぐに一定速度で走行する検知車両の検知結果から検知車両の向きを解析した場合を例に、図1および図2を用いて説明する。図1はステレオカメラによって検知車両の向きを解析した結果を示す図、図2はミリ波レーダによって検知車両の向きを解析した結果を示す図である。 Hereinafter, the case where the direction of the detection vehicle is analyzed from the detection results of the detection vehicle traveling straight at a constant speed in the vicinity of the own vehicle will be described using FIGS. 1 and 2 as an example. FIG. 1 is a diagram showing the result of analyzing the direction of a detected vehicle by a stereo camera, and FIG. 2 is a diagram showing the result of analyzing the direction of a detected vehicle by a millimeter wave radar.
 図1(1)に示すように、自車両1000の近傍を真直ぐに一定速度(相対速度20km/h)で検知車両2000が通り過ぎる場合、ステレオカメラの検出値を使用して解析すると、検知車両2000の縦方向の相対速度Vxは図1(2)に示すように約15~20km/hと検知され、検知車両の向きについては図1(3)に示すように約0度であると検出される。 As shown in FIG. 1 (1), when the detection vehicle 2000 passes straight in the vicinity of the host vehicle 1000 at a constant speed (relative speed 20 km / h), the detection vehicle 2000 is analyzed using the detection value of the stereo camera. The relative velocity Vx in the longitudinal direction of the vehicle is detected as about 15 to 20 km / h as shown in FIG. 1 (2), and the direction of the detection vehicle is detected as about 0 degree as shown in FIG. Ru.
 これに対し、同じ場面をミリ波レーダの検出値を使用して解析した場合には、検知車両は真直ぐに一定速度(相対速度20km/h)で走行しているにもかかわらず、自車両1000近くを通過する際の検知車両2000の縦方向の相対速度Vxが図2(2)に示すように約10km/h以下であると検出され、図2(3)に示すように検知車両2000の向きについては-50~0度であると検出されることが明らかとなった。 On the other hand, when the same scene is analyzed using the detection value of the millimeter wave radar, although the detection vehicle is traveling straight at a constant speed (relative speed 20 km / h), the own vehicle 1000 The relative velocity Vx in the longitudinal direction of the detection vehicle 2000 when passing near is detected to be about 10 km / h or less as shown in FIG. 2 (2), and as shown in FIG. 2 (3) It was revealed that the direction was detected as -50 to 0 degrees.
 図1および図2に示すように、ミリ波レーダは、ステレオカメラと違い、自車両の斜め前方で誤って「速度低下」を検出し、「誤った検知車両の向き」を算出することがあることが本発明者の検討によって明らかとなった。 As shown in FIG. 1 and FIG. 2, unlike a stereo camera, the millimeter wave radar may detect “speed decrease” by mistake in front of the host vehicle and calculate “incorrect direction of detected vehicle”. It became clear by examination of this inventor.
 この誤って速度低下を検出する領域は、自車両から検知車両までの距離の変化が小さい領域、すなわち検知車両の速度の半径方向成分が小さい領域で発生することが本発明者の検討によって明らかとなった。 It is apparent from the study of the present inventor that this erroneously detected speed reduction area occurs in an area where the change in distance from the host vehicle to the detection vehicle is small, that is, an area where the radial component of the speed of the detection vehicle is small. became.
 本発明は、上述のような問題に鑑みなされたものであって、自車両の周囲を走行する検知車両の向きを高精度に判定し、追跡を高精度に行うことができる車両検知システムを提供することを目的とする。 The present invention has been made in view of the above problems, and provides a vehicle detection system capable of highly accurately determining the direction of a detection vehicle traveling around the host vehicle and performing tracking with high accuracy. The purpose is to
 本発明は、上記課題を解決する手段を複数含んでいるが、その一例を挙げるならば、自車両の周辺を走行する検知車両の位置と向きを検知する車両検知システムであって、自車両のフロントのコーナー近傍に設置されたレーダおよび自車両側面に設置されたカメラを含むセンサ群と、前記センサ群の検出結果に基づいて前記検知車両の向きを演算する演算装置と、を有し、前記レーダの検知角度範囲が、自車両の前方を基準にして外向きに105度以下の範囲にあり、前記カメラの検知角度範囲が、自車両の前方を基準にして外向きに65度~115度の角度範囲を含むことを特徴とする。 The present invention includes a plurality of means for solving the above problems, and an example thereof is a vehicle detection system for detecting the position and direction of a detection vehicle traveling around the host vehicle. A sensor group including a radar installed near a front corner and a camera installed on the side of the vehicle, and an arithmetic device for calculating the direction of the detection vehicle based on the detection result of the sensor group, The detection angle range of the radar is in the range of 105 degrees or less outward with respect to the front of the vehicle, and the detection angle range of the camera is 65 degrees to 115 degrees outward with respect to the front of the vehicle. It is characterized by including an angle range of
 本発明によれば、自車両の周囲を走行する検知車両の向きを高精度に判定し、追跡を高精度に行うことができる。上記した以外の課題、構成および効果は、以下の実施例の説明により明らかにされる。 According to the present invention, it is possible to determine with high accuracy the direction of the detection vehicle traveling around the host vehicle, and to perform tracking with high accuracy. Problems, configurations and effects other than those described above will be clarified by the description of the following embodiments.
ステレオカメラによって検知車両を検知した場合の解析結果の一例を示す図である。It is a figure which shows an example of the analysis result at the time of detecting a detection vehicle by a stereo camera. ミリ波レーダによって検知車両を検知した場合の解析結果の一例を示す図である。It is a figure which shows an example of the analysis result at the time of detecting a detection vehicle by a millimeter wave radar. 本実施例の車両検知システムのシステム構成の一例を示すブロック図である。It is a block diagram showing an example of a system configuration of a vehicle detection system of this example. 本実施例における自車両に対するミリ波レーダの検知角度範囲を示す図である。It is a figure which shows the detection angle range of the millimeter wave radar with respect to the own vehicle in a present Example. 本実施例における自車両に対するカメラの検知角度範囲を示す図である。It is a figure which shows the detection angle range of the camera with respect to the own vehicle in a present Example. 本発明におけるミリ波レーダの車両の向き検知の誤り率と検知角度との関係を示す図である。It is a figure which shows the relationship of the error rate and detection angle of a direction detection of the vehicle of the millimeter wave radar in this invention. 本発明におけるミリ波レーダの車両の向き検知の誤り率と検知範囲の最大角度との関係を示す図である。It is a figure which shows the relationship between the error rate of direction detection of the vehicle of the millimeter wave radar in this invention, and the largest angle of a detection range. 本実施例における車両検知システムの処理の流れを説明するフローチャート図である。It is a flowchart figure explaining the flow of processing of the vehicle detection system in this example.
 本発明の車両検知システムの実施例について図3乃至図8を用いて説明する。なお、本発明における「自車両の前方方向」とは自車両が前方に直進するときの進行方向を意味し、角度については、自車両の前方を0度として定義されるものである。 An embodiment of a vehicle detection system of the present invention will be described with reference to FIGS. 3 to 8. In the present invention, “the forward direction of the host vehicle” means the traveling direction when the host vehicle travels straight ahead, and the angle is defined as 0 degrees ahead of the host vehicle.
 図3は本実施例の車両検知システムのシステム構成の一例を示すブロック図である。図4は自車両に対するミリ波レーダの検知角度範囲を示す図である。図5は自車両に対するカメラの検知角度範囲を示す図である。図6は本発明におけるミリ波レーダの車両の向き検知の誤り率と検知角度との関係を示す図である。図7は本発明におけるミリ波レーダの車両の向き検知の誤り率と検知範囲の最大角度との関係を示す図である。図8は本実施例における車両検知システムの処理の流れを説明するフローチャート図である。 FIG. 3 is a block diagram showing an example of a system configuration of the vehicle detection system of the present embodiment. FIG. 4 is a view showing a detection angle range of the millimeter wave radar with respect to the host vehicle. FIG. 5 is a view showing a detection angle range of the camera with respect to the host vehicle. FIG. 6 is a diagram showing the relationship between the error rate of detection of the direction of the vehicle of the millimeter wave radar and the detection angle in the present invention. FIG. 7 is a diagram showing the relationship between the error rate for detecting the direction of the vehicle of the millimeter wave radar and the maximum angle of the detection range in the present invention. FIG. 8 is a flowchart for explaining the flow of processing of the vehicle detection system in the present embodiment.
 図3において、自車両1000(図4,5参照)の周辺を走行する検知車両の位置と向きを検知する車両検知システム1は、レーダ10、カメラ20、演算装置100を備えている。 In FIG. 3, a vehicle detection system 1 for detecting the position and the direction of a detection vehicle traveling around the host vehicle 1000 (see FIGS. 4 and 5) includes a radar 10, a camera 20, and an arithmetic device 100.
 レーダ10は、ミリ波により検知車両を検知してその位置や速度を演算するレーダであり、放射する電波に波長が1~10mm程度で、周波数が30G~300GHz(ギガヘルツ)のミリ波を利用するレーダである。その詳細は特に限定されず、距離・相対速度の検出方式としては、例えばFM-CW(Friquency-Modulated Continuous Wave)方式や2周波CW(Continuous Wave)方式、スペクトル拡散方式、パルス方式などの公知の方式が用いられるものを適用することができる。また、方位検知方式についてもその詳細は特に限定されず、電子スキャン方式やメカスキャン方式、モノパルス方式などの公知の方式が用いられるものと適用することができる。また、検知車両の位置および速度の演算処理についても、公知の処理を用いることができる。 The radar 10 is a radar that detects a detection vehicle by a millimeter wave and calculates its position and velocity, and uses a millimeter wave with a wavelength of about 1 to 10 mm and a frequency of 30 G to 300 GHz (gigahertz) for radio waves to be emitted It is a radar. The details thereof are not particularly limited, and as a detection method of distance and relative velocity, for example, a known FM-CW (Friquency-Modulated Continuous Wave) method, a two-frequency CW (Continuous Wave) method, a spread spectrum method, a pulse method, etc. Any scheme may be applied. The details of the direction detection method are not particularly limited, and the direction detection method may be applied to a known method such as an electronic scan method, a mechanical scan method, or a monopulse method. Also, publicly known processing can be used for calculation processing of the position and speed of the detection vehicle.
 レーダ10は、図4に示すように、自車両1000の左右のフロントコーナにそれぞれ搭載されており、その検知角度範囲は自車両1000の前方方向を基準にして外向きに105度以下の範囲となっており、本実施例では取付角度は45度、検知角度範囲は自車両の前方方向を基準にして-5度~95度の範囲(100度)となっている。レーダの取付位置は自車両のフロントの中央ではなく、フロントのコーナー近傍とすることにより、自車前方だけでなく自車前側方の周辺車両を検知することができる。 The radar 10 is mounted on the left and right front corners of the vehicle 1000 as shown in FIG. 4, and the detection angle range thereof is a range of 105 degrees or less outward with respect to the forward direction of the vehicle 1000. In the present embodiment, the mounting angle is 45 degrees, and the detection angle range is a range (100 degrees) from -5 degrees to 95 degrees with reference to the forward direction of the host vehicle. By setting the mounting position of the radar not in the center of the front of the host vehicle but in the vicinity of the front corner, it is possible to detect not only the host vehicle front but also surrounding vehicles on the front side of the host vehicle.
 なお、本実施例における取付角度とは、レーダ10の検知角度範囲の自車両1000の前方方向を基準にして外向きの最小値と最大値の中央に相当する角度のことを意味する。また、検知角度範囲は自車両の周辺を検知車両が走行した場合の検知車両の位置と検知可否の関係を測定することにより算出することができる。 The mounting angle in the present embodiment means an angle corresponding to the center of the outward minimum value and the maximum value with reference to the forward direction of the vehicle 1000 in the detection angle range of the radar 10. In addition, the detection angle range can be calculated by measuring the relationship between the position of the detection vehicle and the possibility of detection when the detection vehicle travels around the host vehicle.
 カメラ20は検知車両を撮像素子により撮像し、それらの撮像結果から検知車両の位置および速度を演算するものである。カメラ20は、自車両1000の周囲に複数台の検知車両が存在する場合にも、検知車両を車両ごとに区別して検知することが可能である。 The camera 20 captures an image of the detected vehicle by an imaging element, and calculates the position and speed of the detected vehicle from the imaging results. Even when there are a plurality of detection vehicles around the host vehicle 1000, the camera 20 can detect the detection vehicles separately for each vehicle.
 カメラ20の詳細についても特に限定されず、対象物を複数の異なる方向から同時に撮影することにより、その奥行き方向の情報も記録できるようにした公知の構成のステレオカメラを適宜適用することができる。また、検知車両の位置および速度の演算処理についても、公知の処理を用いることができる。 The details of the camera 20 are also not particularly limited, and a stereo camera having a known configuration in which information in the depth direction can also be recorded can be appropriately applied by simultaneously photographing an object from a plurality of different directions. Also, publicly known processing can be used for calculation processing of the position and speed of the detection vehicle.
 カメラ20は、図5に示すように、自車両1000の左右の側面に搭載されており、その検知角度範囲は自車両1000の前方方向を基準にして外向きに65度~115度の角度範囲を含むものであり、本実施例では取付角度は90度、検知角度範囲は自車両の前方方向を基準にして65度~115度の範囲(50度)となっている。 As shown in FIG. 5, the camera 20 is mounted on the left and right side surfaces of the vehicle 1000, and the detection angle range is an angle range of 65 degrees to 115 degrees outward with reference to the forward direction of the vehicle 1000. In the present embodiment, the mounting angle is 90 degrees, and the detection angle range is a range (50 degrees) of 65 degrees to 115 degrees with reference to the forward direction of the host vehicle.
 ここで、上述したように、レーダ10では、自車両の斜め前方で誤って「速度低下」を検出して「誤った向き」を算出することが本発明者の検討によって初めて明らかとなった。 Here, as described above, it has become clear for the first time by the inventor of the present invention that the radar 10 erroneously detects "speed reduction" obliquely ahead of the host vehicle and calculates "incorrect direction".
 この誤検出領域について本発明者は更に鋭意検討を行った。以下その検討結果について図6および図7を用いて説明する。 The present inventors have further intensively studied the false detection area. The examination results will be described below with reference to FIGS. 6 and 7.
 最初に、レーダ検知角度と車両の向き検知の誤り率との関係について検討した。 First, the relationship between the radar detection angle and the error rate of the direction detection of the vehicle was examined.
 条件は、自車両前方のコーナーに取り付けたミリ波レーダを用いて、自車両近傍を走行する検知車両を検知して、検知角度毎に車両の向き検知結果の正誤について調べた。 As the conditions, using a millimeter wave radar attached to a corner in front of the host vehicle, a detected vehicle traveling in the vicinity of the host vehicle is detected, and whether the direction detection result of the vehicle is true or false is checked for each detection angle.
 この際、検知角度範囲が60度,80度,100度,120度,140度と変化させたミリ波レーダを使用して、取付角度を15度から120度まで変化させて測定した(検知角度および取付角度は自車両の前方方向を0度とした)。 At this time, using a millimeter wave radar in which the detection angle range was changed to 60 degrees, 80 degrees, 100 degrees, 120 degrees, and 140 degrees, the measurement was performed while changing the mounting angle from 15 degrees to 120 degrees (detection angle And the attachment angle made the forward direction of the own vehicle 0 degree).
 この条件で測定した検知車両の向き検知の誤り率を検知角度に対してプロットしたグラフが図6である。図6において、プロット点は平均値であり、最大値と最小値をエラーバーで表示した。 The graph which plotted the error rate of direction detection of the detection vehicle measured on this condition with respect to the detection angle is FIG. In FIG. 6, the plot points are mean values, and the maximum and minimum values are indicated by error bars.
 その結果、図6に示すように、レーダ10の検知角度範囲は、自車両1000の前方方向を基準にした時に外向きに65度~115度の範囲において、ミリ波レーダによる検知車両の向き検知の誤り率が上昇することがわかった。特に、角度が75度~105度の範囲では誤り率が高くなることが分かった。そこで、このレーダ10が不得意とする65度~115度の角度範囲については、カメラ20でカバーする必要があることが明らかとなった。 As a result, as shown in FIG. 6, the detection angle range of the radar 10 is the direction detection of the detection vehicle by the millimeter wave radar in the range of 65 degrees to 115 degrees outward when based on the forward direction of the host vehicle 1000 It was found that the error rate of In particular, it has been found that the error rate is high when the angle is in the range of 75 degrees to 105 degrees. Therefore, it has become clear that it is necessary to cover the angle range of 65 degrees to 115 degrees, which the radar 10 is not good at, with the camera 20.
 更に、レーダの取付角度と誤り率の関係についても検討を行った。 Furthermore, the relationship between the mounting angle of the radar and the error rate was also studied.
 条件は、自車両前方のコーナーに取り付けたミリ波レーダを用いて、自車近傍を走行する車両を検知して検知車両の向き検知結果の正誤を調べ、検知角度範囲の誤り率平均値を求めた(角度は自車両前方方向を0度とした)。 As the condition, using a millimeter wave radar attached to the corner in front of the host vehicle, a vehicle traveling in the vicinity of the host vehicle is detected to check the accuracy of the detection result of the detected vehicle, and the error rate average value of the detection angle range (The angle is 0 degrees in the forward direction of the host vehicle).
 この検討では、トラッキング処理を入れるものとした。すなわち、過去のデータからの予測値と新たに検出したデータを比較して、新たに検出したデータの判定を行った。すなわち、新たに検出したデータで疑わしいものは採用しない方式とした。 In this study, tracking processing is included. That is, the newly detected data was judged by comparing the predicted value from the past data and the newly detected data. In other words, the newly detected data is not adopted as suspicious.
 この結果、ミリ波レーダの取付角度によって車両の向き検知の誤り率が大幅に異なることが明らかとなった。 As a result, it has become clear that the error rate for detecting the direction of the vehicle is significantly different depending on the mounting angle of the millimeter wave radar.
 更に、この検討結果をまとめて、レーダの最大検知角度と誤り率の関係についても検討した。図7に、車両の向き検知の誤り率を検知範囲の最大角度に対してプロットした図を示す。図7では、検知角度範囲の異なる5種類のミリ波レーダを用いた結果を異なるマークで示してある。 Furthermore, the study results were summarized, and the relationship between the maximum detection angle of the radar and the error rate was also studied. FIG. 7 shows a diagram in which the error rate of the direction detection of the vehicle is plotted against the maximum angle of the detection range. In FIG. 7, the results of using five types of millimeter wave radars having different detection angle ranges are indicated by different marks.
 図7に示すように、ミリ波レーダの検知角度範囲を105度以下の範囲にすることで、誤り率低減が可能なことが明らかとなった。 As shown in FIG. 7, it has become clear that the error rate can be reduced by setting the detection angle range of the millimeter wave radar to 105 degrees or less.
 これら図6および図7に示す検討結果の解釈は以下の通りである。 The interpretation of the examination results shown in FIGS. 6 and 7 is as follows.
 図6から、ミリ波レーダの誤り率の高い角度範囲(65度~115度)を含まないことが最も良いことが明らかとなった。また、例えその角度範囲(65度~115度)を含んだとしても、図7に示すように、検知範囲の端近傍の場合(検知角度範囲が105度以下)はトラッキングによって修正可能であることも明らかとなった。 It is clear from FIG. 6 that it is best not to include the angular range (65 degrees to 115 degrees) where the error rate of the millimeter wave radar is high. Also, even if the angle range (65 degrees to 115 degrees) is included, as shown in FIG. 7, the case near the end of the detection range (detection angle range of 105 degrees or less) can be corrected by tracking It also became clear.
 そこで、レーダ10の検知角度範囲は、上述のように、自車両1000の前方方向を基準にして外向きに105度以下の範囲とし、カメラ20の検知角度範囲は自車両1000の前方方向を基準にして外向きに65度~115度の角度範囲を含むものとする。 Therefore, as described above, the detection angle range of the radar 10 is set to a range of 105 degrees or less outward with respect to the forward direction of the host vehicle 1000, and the detection angle range of the camera 20 is based on the forward direction of the host vehicle 1000. And include an angle range of 65 degrees to 115 degrees outward.
 これら自車両1000のフロントコーナーに設置されたレーダ10と自車両1000側面に設置されたカメラ20とから本実施例のセンサ群は構成される。なお、センサ群は2台のレーダ10および2台のカメラ20とから構成される場合に限られず、1台以上のレーダ10と1台以上のカメラ20とから構成されるものとすることができる。また、異なる種類の公知のセンサを更に含むものとすることができる。 The sensor group of the present embodiment is configured of the radar 10 installed at the front corner of the host vehicle 1000 and the camera 20 installed on the side surface of the host vehicle 1000. The sensor group is not limited to the case where it is configured by two radars 10 and two cameras 20, and may be configured by one or more radars 10 and one or more cameras 20. . In addition, different types of known sensors can be further included.
 また、本実施例のように、レーダ10とカメラ20との検知範囲は重複させるものとすることが望ましい。 Further, as in the present embodiment, it is desirable that detection ranges of the radar 10 and the camera 20 be overlapped.
 また、自車両1000の進行方向の右側のレーダ10の検知範囲と左側のレーダ10の検知範囲とについても重複させることが望ましい。 In addition, it is desirable to overlap the detection range of the radar 10 on the right side of the traveling direction of the host vehicle 1000 and the detection range of the radar 10 on the left side.
 これらのようにカメラ20とレーダ10およびレーダ10同士の冗長系とすることにより、自車両1000の自動運転にとって最も重要である正面側の検知をより確実に実行することができる。 By providing a redundant system of the camera 20, the radar 10, and the radars 10 as described above, it is possible to more reliably execute the front side detection that is most important for the automatic driving of the vehicle 1000.
 図3に戻り、演算装置100は、センサ群の検出結果に基づいて検知車両の向きを演算する演算処理装置であり、CPUやメモリ、I/O等を有するコンピュータによって構成されている。演算装置100は、入力部110、角度判定部120、演算部130、出力部140を有している。 Returning to FIG. 3, the arithmetic unit 100 is an arithmetic processing unit that calculates the direction of the detection vehicle based on the detection result of the sensor group, and is configured by a computer having a CPU, a memory, an I / O, and the like. The computing device 100 includes an input unit 110, an angle determination unit 120, a computing unit 130, and an output unit 140.
 入力部110は、レーダ10やカメラ20から出力される検知車両の位置および速度のデータの入力を受ける部分である。入力されたそれぞれのセンサのデータを角度判定部120に出力する。 The input unit 110 is a portion that receives an input of data on the position and velocity of a detection vehicle output from the radar 10 or the camera 20. The input data of each sensor is output to the angle determination unit 120.
 角度判定部120は、自車両1000の前方方向を基準にしたときに検知車両が外向きに何度の位置に存在するかを演算する。その上で、角度判定部120は、検知車両が自車両1000の前方方向を基準にして外向きに65度以下に存在すると判定されたときは、演算部130に対してレーダ10の演算結果を出力する。また、角度判定部120は、65度より大きい角度に検知車両が存在すると判定されたときは、演算部130に対してカメラ20の演算結果を出力する。これらの演算結果の出力は、検知車両ごとに実行する。 The angle determination unit 120 calculates how many positions of the detection vehicle exist outward when the forward direction of the host vehicle 1000 is a reference. Then, when it is determined that the detection vehicle exists outward at 65 degrees or less with reference to the forward direction of the host vehicle 1000, the angle determination unit 120 causes the calculation unit 130 to calculate the calculation result of the radar 10 Output. Further, when it is determined that the detection vehicle is present at an angle larger than 65 degrees, the angle determination unit 120 outputs the calculation result of the camera 20 to the calculation unit 130. The output of these calculation results is executed for each detected vehicle.
 なお、レーダ10の演算結果を用いる場合とカメラ20の演算結果を用いる場合の境界を65度に設ける場合について説明したが、境界角度は65度に限定されず、適宜変更することができる。 Although the case of using the calculation result of the radar 10 and the case of providing the boundary in the case of using the calculation result of the camera 20 at 65 degrees have been described, the boundary angle is not limited to 65 degrees and can be changed as appropriate.
 例えば、境界角度としては、レーダ10の検知誤り率が急上昇する75度や80度とすることができ、また最大角度範囲である105度とすることができる。 For example, the boundary angle may be 75 degrees or 80 degrees at which the detection error rate of the radar 10 sharply rises, and may be 105 degrees which is the maximum angle range.
 演算部130は、角度判定部120から入力されたレーダ10の演算結果、またはカメラ20の演算結果と、過去の当該検知車両の位置および速度の演算結果の情報から、検知車両の向きを演算する。演算部130は、検知車両が複数存在するときは、検知車両ごとにその向きを演算する。その演算結果は出力部140を介して車両制御ECU200に出力する。 The calculation unit 130 calculates the direction of the detection vehicle from the calculation result of the radar 10 input from the angle determination unit 120 or the calculation result of the camera 20 and the calculation result of the position and speed of the detection vehicle in the past. . If there are a plurality of detection vehicles, the calculation unit 130 calculates the direction for each detection vehicle. The calculation result is output to the vehicle control ECU 200 via the output unit 140.
 本実施例の演算部130では、検知車両の向きの演算の際に、過去の検知情報はレーダ10に基づく検出値であるかカメラ20に基づく検出値であるかの区別はしないものとする。 When calculating the direction of the detection vehicle, the calculation unit 130 according to this embodiment does not distinguish whether the detection information in the past is a detection value based on the radar 10 or a detection value based on the camera 20.
 すなわち、検知車両が65度以下に存在する場合も、65度より大きい位置に存在した際にカメラ20の検出結果に基づいて演算した検知車両の位置と向きの情報を引き継いで利用して、レーダ10の検出結果に基づいて検知車両の位置と向きを演算する。同様に、検知車両が65度より大きい位置に存在する場合も、65度以下に存在した際にレーダ10の検出結果に基づいて演算した検知車両の位置と向きの情報を引き継いで利用して、利用してカメラ20の検出結果に基づいて演算した検知車両の位置と向きを演算する。これにより、検知車両を継続的にトラッキングするように構成されている。 That is, even when the detection vehicle is at 65 degrees or less, the radar vehicle takes over and utilizes the information on the position and direction of the detection vehicle calculated based on the detection result of the camera 20 when it is at a position larger than 65 degrees. The position and direction of the detection vehicle are calculated based on the 10 detection results. Similarly, even when the detected vehicle is at a position larger than 65 degrees, the information on the position and the direction of the detected vehicle calculated based on the detection result of the radar 10 when it exists at 65 degrees or less is inherited and used, The position and the direction of the detected vehicle calculated based on the detection result of the camera 20 using it are calculated. Thereby, it is comprised so that a detection vehicle may be tracked continuously.
 車両検知システム1で求められた、自車両1000周辺を走行したり、停車したりしている検知車両の向きや速度の情報は車両制御ECU(Electronic Control Unit)200に対して出力され、自動運転制御や自動駐車制御、駐車支援制御等の各種制御を実行する際に利用する。 Information on the direction and speed of a detected vehicle traveling around the vehicle 1000 or stopped, obtained by the vehicle detection system 1, is output to a vehicle control ECU (Electronic Control Unit) 200 for automatic driving. It is used when performing various controls such as control, automatic parking control, and parking assistance control.
 車両制御ECU200では、自車両1000の自動運転を支援する制御を実行する。例えば、ステアリング装置230に目標操舵角を出力して自車両1000の進行方向を制御する。また、自車両1000の駆動力を制御する駆動力制御ECU210に要求駆動力を出力し、制動力を制御する制動力制御ECU220に要求制動力を出力することにより自車両1000の速度を制御する。更に、自動変速機のシフトレンジを制御するシフトバイワイヤ制御装置240にドライブレンジまたはリバースレンジまたはパーキングレンジの要求を出すことにより、自車両1000のシフトレンジを制御する。 The vehicle control ECU 200 executes control for supporting automatic driving of the host vehicle 1000. For example, the target steering angle is output to the steering device 230 to control the traveling direction of the host vehicle 1000. Further, the required driving force is output to the driving force control ECU 210 that controls the driving force of the host vehicle 1000, and the required braking force is output to the braking force control ECU 220 that controls the braking force, thereby controlling the speed of the host vehicle 1000. Furthermore, the shift range of the own vehicle 1000 is controlled by issuing a request for the drive range, the reverse range or the parking range to the shift by wire control device 240 that controls the shift range of the automatic transmission.
 次に、本実施例の車両検知システム1による検知車両の検知の処理の流れについて図8を参照して説明する。 Next, the flow of processing of detection of a detection vehicle by the vehicle detection system 1 of the present embodiment will be described with reference to FIG.
 本実施例の車両検知システム1は、自車両のエンジンがONとなっている間、図8に示す処理を繰り返し実行する。 The vehicle detection system 1 of the present embodiment repeatedly executes the processing shown in FIG. 8 while the engine of the host vehicle is ON.
 まず、車両検知システム1は、レーダ10、およびカメラ20によって自車両1000の周囲を計測し、検知車両が存在する場合にはその位置および速度を演算する(ステップS100)。カメラ20の演算結果において、自車両1000の周囲に検知車両が複数存在すると判断される場合には、検知車両ごとにその位置および速度を演算する。また、検知車両が存在しないときは、検知車両無しのフラグを立てる。 First, the vehicle detection system 1 measures the surroundings of the host vehicle 1000 by the radar 10 and the camera 20, and calculates the position and speed of the detection vehicle if it exists (step S100). When it is determined in the calculation result of the camera 20 that there are a plurality of detection vehicles around the host vehicle 1000, the position and speed thereof are calculated for each detection vehicle. Also, when there is no detected vehicle, a flag indicating that there is no detected vehicle is set.
 次いで、車両検知システム1は、ステップS100で演算したレーダ10、およびカメラ20の演算結果を演算装置100に入力する(ステップS110)。 Next, the vehicle detection system 1 inputs the calculation result of the radar 10 and the camera 20 calculated in step S100 to the calculation device 100 (step S110).
 次いで、車両検知システム1は、角度判定部120において、検知車両の位置(自車両1000の前方方向を基準にして外向きに何度の位置に存在するか)を判定する(ステップS120)。 Next, the vehicle detection system 1 determines the position of the detection vehicle (how many positions outward with respect to the forward direction of the host vehicle 1000 exist) in the angle determination unit 120 (step S120).
 本ステップにおいて検知車両が自車両1000の前方方向を基準にして外向きに65度以下に存在すると判定されたときは、角度判定部120は、ステップS110で入力された演算結果のうち、演算部130に対してレーダ10の演算結果を出力する。これに対し、65度より大きい角度に存在すると判定されたときは、角度判定部120は、ステップS110で入力された演算結果のうち、演算部130に対してカメラ20の演算結果を出力する。更に、ステップS110において検知車両無しのフラグが入力されたときは、角度判定部120は、検知車両無しとして次のステップS130,S140を飛ばすような処理信号を演算部130に対して出力する。 When it is determined in this step that the detection vehicle is present at 65 degrees or less outward with reference to the forward direction of the host vehicle 1000, the angle determination unit 120 calculates the calculation unit among the calculation results input in step S110. The calculation result of the radar 10 is output to 130. On the other hand, when it is determined that the angle is greater than 65 degrees, the angle determination unit 120 outputs the calculation result of the camera 20 to the calculation unit 130 among the calculation results input in step S110. Furthermore, when the flag indicating no detected vehicle is input in step S110, the angle determination unit 120 outputs a processing signal to the arithmetic unit 130 to skip the next steps S130 and S140 with no detected vehicle.
 次いで、車両検知システム1は、演算部130において、当該検知車両の過去の検出値があるか否かを判定する(ステップS130)。 Next, the vehicle detection system 1 determines in the calculation unit 130 whether there is a past detection value of the detection vehicle (step S130).
 本ステップにおいて当該検知車両の過去の検出値があると判定されたときは処理をステップS140に進める。これに対して、当該車両の過去の検出値がないと判定されたときは処理をステップS150進める。 If it is determined in this step that there is a past detected value of the detected vehicle, the process proceeds to step S140. On the other hand, when it is determined that there is no past detected value of the vehicle, the process proceeds to step S150.
 このステップS130では、当該検知車両の過去の検出値は、レーダ10に基づく検出値であるかカメラ20に基づく検出値であるかの区別はせずに、純粋に当該検知車両が過去にレーダ10および/またはカメラ20によって検知され、位置、速度の演算結果があるか否かを判定する。 In this step S130, the detected vehicle in the past does not distinguish whether it is a detected value based on the radar 10 or a detected value based on the camera 20 in a pure manner. And / or detected by the camera 20, it is determined whether or not there is a calculation result of position and velocity.
 次いで、車両検知システム1は、演算部130において、当該検知車両の過去の検知結果とステップS120で出力された情報に基づいて検知車両の向きを演算する(ステップS140)。 Next, the vehicle detection system 1 calculates the direction of the detection vehicle based on the past detection result of the detection vehicle and the information output in step S120 in the calculation unit 130 (step S140).
 本ステップS140においても、ステップS130と同様に、検知車両の向きを演算する際には、過去の検知情報はレーダ10に基づく検出値であるかカメラ20に基づく検出値であるかの区別はしないものとする。 Also in step S140, similarly to step S130, when calculating the direction of the detection vehicle, it is not distinguished whether the detection information in the past is a detection value based on the radar 10 or a detection value based on the camera 20. It shall be.
 次いで、車両検知システム1は、演算部130において、レーダ10、カメラ20における検出結果を基に、全ての検知車両の向きを演算したか否かを判定する(ステップS150)。 Next, the vehicle detection system 1 determines whether or not the directions of all the detected vehicles have been calculated based on the detection results of the radar 10 and the camera 20 in the calculation unit 130 (step S150).
 本ステップにおいて全ての検知車両の向きを演算したと判定されたときは処理を終了する。これに対して全ての検知車両の向きを演算していないと判定されたときは処理ステップS120に戻し、全ての検知車両の演算を終了させる。 If it is determined in this step that the directions of all the detected vehicles have been calculated, the processing is ended. On the other hand, when it is determined that the directions of all the detected vehicles are not calculated, the process returns to step S120, and the calculation of all the detected vehicles is ended.
 次に、本実施例の効果について説明する。 Next, the effects of this embodiment will be described.
 上述した本実施例の車両検知システム1は、自車両1000のフロントコーナーに設置されたレーダ10および自車両1000側面に設置されたカメラ20を含むセンサ群と、センサ群の検出結果に基づいて検知車両の向きを演算する演算装置100と、を有し、レーダ10の検知角度範囲が、自車両1000前方方向を基準にして外向きに105度以下の範囲にあり、カメラ20の検知角度範囲が、自車両1000前方方向を基準にして外向きに65度~115度の角度範囲を含むものである。 The vehicle detection system 1 of the present embodiment described above detects a sensor group including the radar 10 installed at the front corner of the host vehicle 1000 and the camera 20 installed at the side surface of the host vehicle 1000 and detection results of the sensor group The detection angle range of the radar 10 is in the range of 105 degrees or less outward with respect to the forward direction of the host vehicle 1000, and the detection angle range of the camera 20 is An angle range of 65 degrees to 115 degrees is included outward with reference to the forward direction of the host vehicle 1000.
 このような構成によって、自車両1000の斜め前方で誤って「速度低下」を検出して「誤った向き」を算出する領域についてはカメラ20の検出結果を用いて検知車両の向きを演算することができ、またその領域以外ではレーダ10の検出結果を用いて検知車両の向きを演算することができる。従って、従来に比べて検知車両の向きの演算の精度を向上させることができ、自動運転において自車両1000の周囲に存在する検知車両のトラッキングを精度良く安定して行うことができるようになる。 With such a configuration, the direction of the detection vehicle is calculated using the detection result of the camera 20 in the area where the “speed decrease” is detected by mistake in front of the host vehicle 1000 and the “incorrect direction” is calculated. The direction of the detection vehicle can be calculated using the detection result of the radar 10 outside the region. Therefore, the accuracy of the calculation of the direction of the detection vehicle can be improved as compared with the conventional case, and the tracking of the detection vehicle present around the host vehicle 1000 can be accurately and stably performed in the automatic driving.
 また、演算装置100は、レーダ10の検出結果に基づいて演算した検知車両の位置と向きの情報をカメラ20の検出結果に基づいて検知車両の位置と向きを演算する際に用い、かつカメラ20の検出結果に基づいて演算した検知車両の位置と向きの情報をレーダ10の検出結果に基づいて検知車両の位置と向きを演算する際に用いて、検知車両を継続的にトラッキングするため、レーダ10によって検知した周辺車両の情報(位置、速度、加速度、車両サイズ、車両の向き)を映像系センサであるカメラ20に受け渡すことができ、映像から検知車両を認識する際の認識率や認識精度を向上させることができる。一般的な映像は平面的な情報に過ぎないが、上述の引き継ぎ処理のように立体的な形状に関する情報を加えることで、認識の誤り率をより低減し、より精度の高い検知を実現することが可能となる。一方で、カメラ20によって検知した自車両1000の周辺の検知車両の情報がレーダ10に受け渡されることによって、車種や車両サイズを知った上での検知となるため、より精度の高い検知が可能となる。このように、周辺車両情報の受け渡しを行うことで、レーダ10とカメラ20の間の滑らかなトラッキングが可能となる。 Further, the computing device 100 uses information on the position and orientation of the detected vehicle calculated based on the detection result of the radar 10 when calculating the position and orientation of the detected vehicle based on the detection result of the camera 20, and the camera 20 The information on the position and direction of the detected vehicle calculated on the basis of the detection result of is used to calculate the position and the direction of the detected vehicle on the basis of the detection result of the radar 10 to continuously track the detected vehicle. The information (position, speed, acceleration, vehicle size, direction of the vehicle) of the surrounding vehicles detected by 10 can be delivered to the camera 20 which is a video system sensor, and the recognition rate and recognition when recognizing the detected vehicle from the image Accuracy can be improved. Although a general image is only planar information, adding information on a three-dimensional shape as in the above-mentioned handover processing further reduces the recognition error rate and realizes more accurate detection. Is possible. On the other hand, by passing information of the detection vehicle around the host vehicle 1000 detected by the camera 20 to the radar 10, detection can be performed after knowing the vehicle type and the vehicle size, so detection with higher accuracy is possible. It becomes. As described above, by exchanging the peripheral vehicle information, smooth tracking between the radar 10 and the camera 20 becomes possible.
 更に、検知車両の向きをセンサ群によって検知された車両の速度情報を用いて判定することで、検知車両の向きの検出精度をより高精度にすることができ、トラッキングの精度をより向上させることができる。 Furthermore, by determining the direction of the detection vehicle using the speed information of the vehicle detected by the sensor group, the detection accuracy of the direction of the detection vehicle can be made more accurate, and the tracking accuracy can be further improved. Can.
 また、自車両1000の前方方向を基準にして外向きに65度~115度の角度範囲で検知された検知車両の向きの判定には、レーダ10の検知情報は用いずにカメラ20の検知情報を用いることにより、レーダ10が自車両1000の斜め前方で誤って「速度低下」を検出して「誤った検知車両の向き」を算出する領域をより確実に除外して検知車両を検出することができ、より高精度な検知車両のトラッキングが可能となる。 Further, the detection information of the camera 20 is not used to determine the direction of the detection vehicle detected in an angle range of 65 degrees to 115 degrees outward with reference to the forward direction of the host vehicle 1000. The radar 10 erroneously detects the “speed decrease” obliquely ahead of the host vehicle 1000 and detects the detection vehicle more reliably excluding the area where the “incorrect detection vehicle direction” is calculated. This enables more accurate tracking of the detected vehicle.
 更に、カメラ20で同時に複数の検知車両が検知されたときは、複数の検知車両の情報をレーダ10による検知車両の向きを演算する際に用いることで、複数車両の検知に優れたカメラ20で車両が複数存在することをより高精度に検知して、その情報をレーダ10に引き継ぐことができるようになり、自車両1000の周囲に車両が複数存在する場合であっても、高い精度でのトラッキングを行うことができる。 Furthermore, when a plurality of detection vehicles are simultaneously detected by the camera 20, the information of the plurality of detection vehicles is used when computing the direction of the detection vehicles by the radar 10, so that the camera 20 is excellent in detection of a plurality of vehicles. It becomes possible to detect that there are a plurality of vehicles with higher accuracy and to take over the information to the radar 10, and even when there are a plurality of vehicles around the host vehicle 1000, with high accuracy It can track.
 <その他> 
 なお、本発明は上記の実施例に限られず、種々の変形、応用が可能なものである。上述した実施例は本発明を分かりやすく説明するために詳細に説明したものであり、必ずしも説明した全ての構成を備えるものに限定されない。
<Others>
The present invention is not limited to the above-described embodiment, and various modifications and applications are possible. The embodiments described above are described in detail to explain the present invention in an easy-to-understand manner, and the present invention is not necessarily limited to those having all the configurations described.
 例えば、レーダ10やカメラ20で検知車両の位置および速度を演算する場合について説明したが、演算装置100内で検知車両の位置および速度を演算することも可能である。 For example, although the case where the position and the speed of the detection vehicle are calculated by the radar 10 and the camera 20 has been described, it is also possible to calculate the position and the speed of the detection vehicle in the arithmetic device 100.
1…車両検知システム
10…レーダ
20…カメラ
100…演算装置
110…入力部
120…角度判定部
130…演算部
140…出力部
200…車両制御ECU
210…駆動力制御ECU
220…制動力制御ECU
230…ステアリング装置
240…シフトバイワイヤ制御装置
1000…自車両
2000…検知車両
DESCRIPTION OF SYMBOLS 1 ... Vehicle detection system 10 ... Radar 20 ... Camera 100 ... Arithmetic device 110 ... Input part 120 ... Angle determination part 130 ... Arithmetic part 140 ... Output part 200 ... Vehicle control ECU
210 ... driving force control ECU
220 ... braking force control ECU
230: Steering device 240: Shift-by-wire control device 1000: Vehicle 2000: Detection vehicle

Claims (5)

  1.  自車両の周辺を走行する検知車両の位置と向きを検知する車両検知システムであって、
     自車両のフロントのコーナー近傍に設置されたレーダおよび自車両側面に設置されたカメラを含むセンサ群と、
     前記センサ群の検出結果に基づいて前記検知車両の向きを演算する演算装置と、を有し、
     前記レーダの検知角度範囲が、自車両が前方に直進するときの進行方向を基準にして外向きに105度以下の範囲にあり、
     前記カメラの検知角度範囲が、自車両が前方に直進するときの進行方向を基準にして外向きに65度~115度の角度範囲を含む
     ことを特徴とする車両検知システム。
    A vehicle detection system for detecting a position and a direction of a detection vehicle traveling around a host vehicle, the vehicle detection system comprising:
    A sensor group including a radar installed near the front corner of the vehicle and a camera installed on the side of the vehicle;
    An arithmetic device for calculating the direction of the detection vehicle based on the detection result of the sensor group;
    The detection angle range of the radar is in the range of 105 degrees or less outward based on the traveling direction when the host vehicle travels straight ahead,
    A vehicle detection system, wherein a detection angle range of the camera includes an angle range of 65 degrees to 115 degrees outward with reference to a traveling direction when the host vehicle goes straight ahead.
  2.  請求項1に記載の車両検知システムにおいて、
     前記検知車両の向きを前記レーダの検出結果に基づいて演算する場合に、前記検知車両の向きを前記レーダによって検知された車両の速度情報を用いて判定する
     ことを特徴とする車両検知システム
    In the vehicle detection system according to claim 1,
    When calculating the direction of the detection vehicle based on the detection result of the radar, the direction of the detection vehicle is determined using the speed information of the vehicle detected by the radar.
  3.  請求項2に記載の車両検知システムにおいて、
     前記演算装置は、
     前記レーダの検出結果に基づいて演算した前記検知車両の位置と向きの情報を前記カメラの検出結果に基づいて前記検知車両の位置と向きを演算する際に用い、かつ前記カメラの検出結果に基づいて演算した前記検知車両の位置と向きの情報を前記レーダの検出結果に基づいて前記検知車両の位置と向きを演算する際に用いることにより、前記検知車両を継続的にトラッキングする
     ことを特徴とする車両検知システム。
    In the vehicle detection system according to claim 2,
    The arithmetic device is
    Information on the position and orientation of the detected vehicle calculated based on the detection result of the radar is used when calculating the position and orientation of the detected vehicle based on the detection result of the camera, and based on the detection result of the camera The detection vehicle is continuously tracked by using the information of the position and direction of the detection vehicle calculated in the above calculation when calculating the position and direction of the detection vehicle based on the detection result of the radar. Vehicle detection system.
  4.  請求項2に記載の車両検知システムにおいて、
     前記自車両が前方に直進するときの進行方向を基準にして外向きに65度~115度の角度範囲で検知された検知車両の向きの判定には、前記レーダの検知情報は用いずに前記カメラの検知情報を用いる
     ことを特徴とする車両検知システム。
    In the vehicle detection system according to claim 2,
    The detection information of the radar is not used to determine the direction of the detection vehicle detected in an angle range of 65 degrees to 115 degrees outward with reference to the traveling direction when the host vehicle travels straight ahead. A vehicle detection system characterized by using detection information of a camera.
  5.  請求項2に記載の車両検知システムにおいて、
     前記カメラで同時に複数の検知車両が検知されたときは、前記複数の検知車両の情報を前記レーダによる前記検知車両の向きを演算する際に用いる
     ことを特徴とする車両検知システム。
    In the vehicle detection system according to claim 2,
    A vehicle detection system characterized by using information of the plurality of detection vehicles when calculating a direction of the detection vehicle by the radar when a plurality of detection vehicles are simultaneously detected by the camera.
PCT/JP2018/034649 2017-09-29 2018-09-19 Vehicle sensing system WO2019065411A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2019545007A JP6818902B6 (en) 2017-09-29 2018-09-19 Vehicle detection system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2017189677 2017-09-29
JP2017-189677 2017-09-29

Publications (1)

Publication Number Publication Date
WO2019065411A1 true WO2019065411A1 (en) 2019-04-04

Family

ID=65901409

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/034649 WO2019065411A1 (en) 2017-09-29 2018-09-19 Vehicle sensing system

Country Status (2)

Country Link
JP (1) JP6818902B6 (en)
WO (1) WO2019065411A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7388971B2 (en) 2020-04-06 2023-11-29 トヨタ自動車株式会社 Vehicle control device, vehicle control method, and vehicle control computer program

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008002818A (en) * 2006-06-20 2008-01-10 Alpine Electronics Inc Vehicle identification system
US20110144859A1 (en) * 2009-12-14 2011-06-16 Electronics And Telecommunications Research Institue Apparatus and method for preventing collision of vehicle
WO2012039012A1 (en) * 2010-09-24 2012-03-29 トヨタ自動車株式会社 Object detector and object detecting program
JP2015064795A (en) * 2013-09-25 2015-04-09 日産自動車株式会社 Determination device and determination method for parking place
CN106553655A (en) * 2016-12-02 2017-04-05 深圳地平线机器人科技有限公司 Hazardous vehicles detection method and system and the vehicle including the system
JP2017132285A (en) * 2016-01-25 2017-08-03 日立オートモティブシステムズ株式会社 Vehicle traveling control system and vehicle traveling control method
WO2018030102A1 (en) * 2016-08-08 2018-02-15 日立オートモティブシステムズ株式会社 Object detection device and vehicle control system comprising object detection device

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008002818A (en) * 2006-06-20 2008-01-10 Alpine Electronics Inc Vehicle identification system
US20110144859A1 (en) * 2009-12-14 2011-06-16 Electronics And Telecommunications Research Institue Apparatus and method for preventing collision of vehicle
WO2012039012A1 (en) * 2010-09-24 2012-03-29 トヨタ自動車株式会社 Object detector and object detecting program
JP2015064795A (en) * 2013-09-25 2015-04-09 日産自動車株式会社 Determination device and determination method for parking place
JP2017132285A (en) * 2016-01-25 2017-08-03 日立オートモティブシステムズ株式会社 Vehicle traveling control system and vehicle traveling control method
WO2018030102A1 (en) * 2016-08-08 2018-02-15 日立オートモティブシステムズ株式会社 Object detection device and vehicle control system comprising object detection device
CN106553655A (en) * 2016-12-02 2017-04-05 深圳地平线机器人科技有限公司 Hazardous vehicles detection method and system and the vehicle including the system

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7388971B2 (en) 2020-04-06 2023-11-29 トヨタ自動車株式会社 Vehicle control device, vehicle control method, and vehicle control computer program

Also Published As

Publication number Publication date
JPWO2019065411A1 (en) 2020-10-22
JP6818902B2 (en) 2021-01-27
JP6818902B6 (en) 2021-03-17

Similar Documents

Publication Publication Date Title
CN111398924B (en) Radar installation angle calibration method and system
US9784829B2 (en) Wheel detection and its application in object tracking and sensor registration
US10922561B2 (en) Object recognition device and vehicle travel control system
CN108238056B (en) Vehicle-mounted warning device
US9599706B2 (en) Fusion method for cross traffic application using radars and camera
US11069241B2 (en) Driving support device and driving support method
US9053554B2 (en) Object detection device using an image captured with an imaging unit carried on a movable body
US10054671B2 (en) On-vehicle radar apparatus capable of recognizing radar sensor mounting angle
US10583737B2 (en) Target determination apparatus and driving assistance system
US10967857B2 (en) Driving support device and driving support method
US9470790B2 (en) Collision determination device and collision determination method
JP2015155878A (en) Obstacle detection device for vehicle
US20180015923A1 (en) Vehicle control device and vehicle control method
US9002630B2 (en) Road shape estimation apparatus
US20190061748A1 (en) Collision prediction apparatus
WO2017170799A1 (en) Object recognition device and object recognition method
CN106605153B (en) Shaft offset diagnostic device
JP3925285B2 (en) Road environment detection device
US20210190934A1 (en) Object-detecting device
JP2002296350A (en) Object detector
JP6818902B6 (en) Vehicle detection system
WO2019003631A1 (en) Object detection device for vehicle and method for determining horizontal axial deviation of object detection device for vehicle
JP2021511507A (en) Methods and devices for checking the validity of lateral movement
CN113126077B (en) Target detection system, method and medium for blind spot area
CN114502433A (en) Control device

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18863443

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2019545007

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18863443

Country of ref document: EP

Kind code of ref document: A1