JP2008040819A - Obstacle recognition device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an obstacle recognition device capable of reducing false detection further and recognizing the obstacle. <P>SOLUTION: A drive assist system 1 consists of an ECU10, and the ECU10 is equipped with a navigation system 12 and an object detection part 100 to which a forward millimeter-wave radar 30, and the like, is connected. A travelling lane recognition part 110 recognizes the travelling lane where its own vehicle is traveling from a measurement result of the navigation system 12 and decides a possibility in which other vehicles exist in either side of the own vehicle, when the traveling lane recognition part 110 decides that there are no possibilities in which other vehicles exist at the either side of the own vehicle, a radar wave detection part 102 extracts the object as the obstacle when reflectance of the forward millimeter-wave radar 30 and a short range millimeter-wave radar 32 are not less than a second threshold value which is higher than a usual first threshold value with respect to the side concerned. Consequently, the possibility of the falsely detecting the roadside objects, such as a guardrail and a side wall as the vehicles, is reduced, the false detection is further lessened and the obstacle can be recognized. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an object detection device, and more particularly to an obstacle recognition device that detects an obstacle such as an overtaking vehicle or an interrupting vehicle on a road.

As one of the vehicle driving support devices, a driving support device that detects an overtaking vehicle or an interrupting vehicle existing on the side of the vehicle and gives a warning to the driver has been put into practical use. Japanese Patent Application Laid-Open No. 2004-133867 describes a device that arranges a distance measuring sensor that detects a distance to an object on the side of the vehicle and issues an alarm when the distance to the detected object is smaller than a predetermined value. In the device described in Patent Document 1, a guardrail that is not related to lane change is suppressed by suppressing the occurrence of an alarm for the presence of an object that does not interfere with the lane change of the host vehicle based on the detection result by the distance measuring sensor. And roadside objects such as side walls are not erroneously detected.
JP 2005-145196 A

  However, in the above technique, since the obstacle is detected based only on the detection result by the distance measuring sensor, it may be insufficient to determine whether the detected object is a vehicle or a roadside object. There are cases where roadside objects such as guardrails and side walls are not erroneously detected as vehicles.

  The present invention has been made in view of such circumstances, and an object of the present invention is to provide an obstacle recognition apparatus that can recognize an obstacle with fewer erroneous detections.

  The present invention relates to a navigation device capable of measuring the position of the host vehicle, a travel lane in which the host vehicle is traveling from the measurement result of the navigation device, and another vehicle on either the left side or the right side of the host vehicle. A vehicle lane recognizing means for judging the possibility of existence of an object, a detecting means capable of detecting an object existing outside the host vehicle, and an object detected by the detecting means according to the degree to which the object can become an obstacle. The obstacle extraction means, and the obstacle extraction means, when the traveling lane recognition means determines that there is a possibility that another vehicle exists on either the left side or the right side of the own vehicle, When the object detected by the detection means has a degree of obstacle that is greater than or equal to the first degree, the object is extracted as an obstacle, and the travel lane recognition means is on either the left or right side of the vehicle Other cars If it is determined that there is no possibility that the object is present, the object is extracted as an obstacle when the degree of the object detected by the detection means is higher than the first degree and higher than the first degree. It is an obstacle recognition device.

  According to this configuration, the travel lane recognition means recognizes the travel lane in which the host vehicle is traveling from the measurement result of the navigation device, and there may be another vehicle on either the left side or the right side of the host vehicle. For example, when the host vehicle is traveling in the rightmost lane, it can be determined that there is no possibility that another vehicle exists on the right side of the host vehicle.

  In addition, when the obstacle lane recognition unit determines that there is a possibility that another vehicle exists on either the left side or the right side of the own vehicle, the obstacle extraction unit is detected by the detection unit. When the degree that an object can become an obstacle is greater than or equal to the first degree, the object is extracted as an obstacle, and there is no possibility that the traveling lane recognition means has another vehicle on either the left side or the right side of the own vehicle. When the determination is made, the object is extracted as an obstacle when the degree to which the object detected by the detection means can be an obstacle is equal to or higher than the second degree higher than the first degree. For this reason, for example, when the vehicle is traveling in the rightmost lane, the threshold for extracting an object as an obstacle is increased on the right side, and there is a possibility that roadside objects such as guardrails and side walls are erroneously detected as vehicles. It is possible to reduce the number of false detections and recognize obstacles.

  In this case, the detection means is a radar that can detect an object by radiating an electromagnetic wave to an object existing outside the host vehicle and measuring the reflected wave of the electromagnetic wave, and the obstacle extraction means is a lane recognition means. When it is determined that there is a possibility that another vehicle exists on either the left side or the right side of the own vehicle, the object is reflected when the reflectance of the reflected wave measured by the radar is equal to or higher than the first threshold value on the side. Is detected as an obstacle, and the lane recognition means determines that there is no possibility of another vehicle on either the left or right side of the host vehicle. When the reflectance is equal to or higher than the second threshold value higher than the first threshold value, the object can be extracted as an obstacle.

  According to this configuration, since the detection means is a radar, the detection means is not easily affected by the weather, and the obstacle extraction means extracts the obstacle based on the threshold value of the reflected wave measured by the radar. It can be configured.

  The detecting means is a monocular image sensor capable of detecting an object by imaging an object existing outside the own vehicle, and the obstacle extracting means is configured such that the travel lane recognizing means is either the left side or the right side of the own vehicle. If it is determined that there is a possibility that another vehicle exists on the side of the object, the object is obstructed when the number of edge points obtained by performing edge processing on the image picked up by the monocular image sensor is equal to or more than the first threshold. When it is determined that there is no possibility that another vehicle exists on either the left side or the right side of the host vehicle, the captured image of the monocular image sensor is edge-processed for that side. When the number of edge points obtained in this way is equal to or higher than the second threshold value higher than the first threshold value, the object can be extracted as an obstacle.

  According to this configuration, the detection unit is a monocular image sensor, and the obstacle extraction unit extracts the obstacle based on the threshold of the number of edge points obtained by performing edge processing on the captured image of the monocular image sensor. Obstacles can be detected based on the reference, and a relatively simple device configuration can be obtained.

  The detecting means is a stereo image sensor capable of detecting an object by imaging an object existing outside the host vehicle, and the obstacle extracting means is configured such that the traveling lane recognition means is either the left side or the right side of the host vehicle. If it is determined that there is a possibility that another vehicle exists on the side of the object, the object is obstructed when the number of edge points obtained by performing edge processing on the image captured by the stereo image sensor is equal to or greater than the first threshold value. When it is determined that there is no possibility that another vehicle exists on either the left side or the right side of the host vehicle, the captured image of the stereo image sensor is edge-processed for that side. When the number of edge points obtained in this way is equal to or higher than the second threshold value higher than the first threshold value, the object can be extracted as an obstacle.

  According to this configuration, the detection means is a stereo image sensor, and the obstacle extraction means extracts the obstacle based on the threshold of the number of edge points obtained by performing edge processing on the captured image of the stereo image sensor. It is easy to detect the distance and speed, and the detection accuracy can be improved.

  Alternatively, the detecting means radiates an electromagnetic wave to an object existing outside the host vehicle and measures the reflected wave of the electromagnetic wave, and images the object existing outside the host vehicle by imaging the radar. The obstacle extraction means, when the lane recognition means determines that there is a possibility that another vehicle exists on either the left side or the right side of the own vehicle, When the coincidence between the detection results of the radar and the image sensor is greater than or equal to the first threshold, the object is extracted as an obstacle, and the traveling lane recognition means is on the left side or the right side of the own vehicle. When it is determined that there is no possibility that the object exists, the object is extracted as an obstacle when the degree of coincidence between the detection results of the radar and the image sensor is equal to or higher than the second threshold higher than the first threshold. And can.

  According to this configuration, since the obstacle is extracted by both the radar and the image sensor having different detection principles, the obstacle detection accuracy is further improved.

  According to the obstacle recognition apparatus of the present invention, it is possible to recognize an obstacle with fewer erroneous detections.

  Hereinafter, an obstacle recognition apparatus according to an embodiment of the present invention will be described with reference to the accompanying drawings.

  FIG. 1 is a block diagram showing the driving support system according to the first embodiment, and shows a configuration example when the obstacle recognition device of the present invention is applied to the driving support system.

  The driving support system 1 mainly includes an ECU 10. The ECU 10 is a system control in which an in-vehicle system 14 is connected to an object detection unit 100 to which a navigation system (navigation device) 12, a forward millimeter wave radar (detection means) 30, and a short-range millimeter wave radar (detection means) 32 are connected. Part 20.

  The navigation system 12 is for measuring the position of the host vehicle by GPS (Global Positioning System) or the like, and at least with an accuracy capable of recognizing at least the current travel lane (lane) on which the host vehicle is traveling. The position of the car can be measured. The measurement result of the navigation system 12 is output to the object detection unit 100 of the ECU 10.

  The forward millimeter wave radar 30 irradiates the front of the vehicle while scanning the millimeter wave band radio wave in the horizontal direction, receives the radio wave reflected on the object surface such as the vehicle, and reflects the reflectance (the radio wave intensity and the irradiation of the received wave). The ratio of the signal strength to the wave intensity), the presence / absence of the preceding vehicle, the distance between the preceding vehicle and the host vehicle, the relative speed, the lateral displacement (lateral position) from the host vehicle, etc. To the ECU 10.

  The short-range millimeter-wave radar 32 irradiates the front, side, and rear of the vehicle while scanning the millimeter-wave radio waves in the horizontal direction, receives the radio waves reflected by the object surface such as the vehicle, and reflects and receives the reflectance. Parameters such as the presence / absence of a parallel running vehicle, an overtaking vehicle and an interrupting vehicle, the distance between the vehicle and the own vehicle, the relative speed, the lateral displacement (lateral position) from the own vehicle are obtained from the change in the frequency of the signal, and the ECU 10 is used as the detection result. Output to.

  The object detection unit 100 includes a travel lane recognition unit (travel lane recognition unit) 110 and a radar wave detection unit (obstacle extraction unit) 102.

  Based on the measurement result from the navigation system 12, the travel lane recognition unit 110 recognizes whether the travel lane in which the vehicle is currently traveling is the left lane or the right lane. In addition, the travel lane recognition unit 110 determines whether there is a possibility that another vehicle exists on either the left side or the right side of the host vehicle. The determination result is output to the radar wave detection unit 102.

  The radar wave detection unit 102 extracts an obstacle from the detection results of the front millimeter wave radar 30 and the short-range millimeter wave radar 32. When the traveling wave recognition unit 110 determines that there is a possibility that another vehicle exists on either the left side or the right side of the own vehicle, the radar wave detection unit 102 determines that the front millimeter wave radar 30 When the reflectance of the reflected wave of the short-range millimeter wave radar 32 is equal to or higher than the first threshold, the object related to the reflected wave is extracted as an obstacle. On the other hand, when the traveling lane recognition unit 110 determines that there is no possibility that another vehicle exists on either the left side or the right side of the host vehicle, the radar wave detection unit 102 When the reflectance of the reflected wave of the radar 30 and the short-range millimeter wave radar 32 is equal to or higher than the second threshold value that is higher than the first threshold value, the object related to the reflected wave is extracted as an obstacle. Information regarding the extracted obstacle is output to the system control unit 30.

  The system control unit 30 is for outputting a control amount and a flag to the in-vehicle system 14 in accordance with the information regarding the obstacle from the object detection unit 100. The system control unit 30 includes a driving load reduction system unit 22 and a safety system unit 24. The driving load reduction system unit 22 controls a system for reducing the driving load of a driver such as ACC, LKA, and IPA. The safety system 24 includes PCS / FCAAS, PB, PSB, PBA, suspension control, warning, steering avoidance support, headrest control, seat control, active hood, active bumper, etc. Control the system to ensure safety.

  The in-vehicle system 14 performs operations such as predetermined steering, acceleration / deceleration, alarm notification, and the like based on the control amount and flag from the system control unit 30.

  In addition, a sonar 50, a vehicle motion state sensor 60, and a face direction sensor 70 are connected to the object detection unit 100 of the ECU 10, and information from these is used for recognition of an obstacle. The output information of the vehicle motion state sensor 60 is processed by the own vehicle motion state estimation unit 62 and then sent to the object detection unit 100. The output information of the face direction sensor 70 is processed by the driver state estimation unit 72 and then the object detection unit. 100. The processing information from the vehicle motion state estimation unit 62 and the driver state estimation unit 72 is directly output to the system control unit 20 and used for system control. Sensors such as the forward millimeter wave radar 30 and the short-range millimeter wave radar 32 connected to the object detection unit 100 are connected to each other, and control the operation of each sensor.

  Next, the operation of the driving support system 1 will be described with reference to FIG. FIG. 2 is a flowchart showing a processing procedure in the driving support system according to the first embodiment. In the following description, a case where an obstacle present on the right side of the own vehicle is detected will be described as an example.

  First, the reflected wave of the object in the right side of the own vehicle is detected by the front millimeter wave radar 30 and the short-range millimeter wave radar 32 (S101). Next, the traveling lane recognition unit 110 acquires information on the current traveling lane position of the host vehicle based on the measurement result from the navigation system 12, and there is a possibility that an overtaking vehicle and an interrupting vehicle exist on the right side of the own vehicle. Whether or not there is is determined (S102).

  As shown in FIG. 3A, for example, when the host vehicle 200 is currently traveling in the left lane L of a road with two lanes, the other vehicle 300 may travel in the right lane R. It is determined that there is a possibility that another vehicle 300 exists. On the other hand, as shown in FIG. 3B, when the host vehicle 200 is currently traveling on the right lane R of a road with two lanes, there is no lane on the right side of the host vehicle 200. Judge that there is no possibility of a car.

  Returning to FIG. 2, when the traveling lane recognition unit 110 determines that there is no possibility that an overtaking vehicle and an interruption vehicle exist on the right side of the own vehicle, the radar wave detection unit 102 sets the reflectance threshold of the reflected wave to the first value. A second threshold value greater than one threshold value is set (S103, S104). On the other hand, when the traveling lane recognition unit 110 determines that there is a possibility that an overtaking vehicle and an interruption vehicle exist on the right side of the host vehicle, the radar wave detection unit 102 sets the lower threshold value of the reflectance of the reflected wave. One threshold value is set (S103).

  Finally, when the reflectance of the reflected wave is equal to or greater than the set threshold, the radar wave detection unit 102 extracts an object related to the reflected wave as an obstacle (S104).

  According to the present embodiment, the travel lane recognition unit 110 recognizes the travel lane in which the host vehicle 200 is traveling from the measurement result of the navigation system 12, and the other vehicle is placed on either the left side or the right side of the host vehicle. For example, when the host vehicle is traveling on the right lane R of a two-lane road as shown in FIG. 3B, the other vehicle 300 may be present on the right side of the host vehicle 200. It can be determined that there is no sex.

  Further, according to the present embodiment, when the radar wave detection unit 102 determines that the other vehicle 200 may exist on either the left side or the right side of the own vehicle 200 when the traveling lane recognition unit 110 determines that the other vehicle 200 exists. The object is extracted as an obstacle when the reflectance of the reflected waves of the front millimeter wave radar 30 and the short-range millimeter wave radar 32 is equal to or higher than the first threshold, and the traveling lane recognition unit 110 is on the left side of the own vehicle 200. When it is determined that there is no possibility that the other vehicle 300 exists on either side of the right side, the reflectance of the reflected wave of the front millimeter wave radar 30 and the short-range millimeter wave radar 32 is the first threshold value on the side. An object is extracted as an obstacle when it is equal to or higher than a higher second threshold. Therefore, as shown in FIG. 3B, when the host vehicle 200 is traveling on the right lane R of a two-lane road, the threshold value for extracting an object as an obstacle is increased on the right side, such as a guardrail or a side wall. The possibility of erroneously detecting a roadside object as a vehicle can be reduced, and an obstacle can be recognized with fewer erroneous detections.

  Furthermore, according to the present embodiment, the detection means are the front millimeter wave radar 30 and the short-range millimeter wave radar 32, and the radar wave detection unit 102 is the reflected wave measured by the front millimeter wave radar 30 and the short-range millimeter wave radar 32. Since the threshold value is changed, it is difficult to be affected by the weather and the like, and a relatively simple device configuration can be obtained.

  Hereinafter, a second embodiment of the present invention will be described. FIG. 4 is a block diagram showing a driving support system according to the second embodiment. As shown in FIG. 4, in this embodiment, instead of the front millimeter wave radar 30 and the short-range millimeter wave radar 32, the front image monocular camera 40 that is a monocular image sensor and the rear / side / periphery are used as detection means. An image monocular camera 42 is provided. In this embodiment, an edge processing unit 104 is provided instead of the radar wave detection unit 102 as an obstacle extraction unit.

  The front image monocular camera 40 is a CCD camera that acquires an image in front of the vehicle. The rear / side / peripheral image monocular camera 42 is a CCD camera that acquires images of the rear, side, and periphery of the vehicle, and a wide-angle lens such as a fish-eye lens is appropriately mounted according to the situation.

  The edge processing unit 104 performs edge processing on the images acquired from the front image monocular camera 40 and the rear / side / peripheral image monocular camera 42 and recognizes an object from the shape of the edge point, the velocity vector of the edge point, the optical flow, and the like. To do. In addition, when the traveling lane recognition unit 110 determines that there is a possibility that another vehicle exists on either the left side or the right side of the own vehicle, the edge processing unit 104 determines that the front image monocular camera for the side. 40 and the rear / side / peripheral image When the number of edge points of an object in the image of the monocular camera 42 is equal to or greater than the first threshold, the object is extracted as an obstacle. On the other hand, when the driving lane recognition unit 110 determines that there is no possibility that another vehicle exists on either the left side or the right side of the own vehicle, the edge processing unit 104 uses the front image monocular camera for that side. 40 and the rear / side / peripheral image When the number of edge points of an object in the image of the monocular camera 42 is equal to or greater than a second threshold value that is higher than the first threshold value, the object is extracted as an obstacle.

  FIG. 5 is a flowchart showing a processing procedure in the driving support system according to the second embodiment. In the following description, as in the first embodiment, a case where an obstacle present on the right side of the own vehicle is detected will be described as an example.

  First, the front image monocular camera 40 and the rear / side / peripheral image monocular camera 42 acquire an image of an object that can be placed on the right side of the vehicle, and the edge processing unit 104 performs edge processing on the image to obtain an edge image ( S201). Next, as in the first embodiment, the traveling lane recognition unit 110 acquires information on the current traveling lane position of the own vehicle based on the measurement result from the navigation system 12 and passes the vehicle to the right side of the own vehicle. It is determined whether or not there is a possibility that a vehicle and an interrupted vehicle exist (S202).

  If the traveling lane recognition unit 110 determines that there is no possibility that an overtaking vehicle or an interrupting vehicle exists on the right side of the host vehicle, the edge processing unit 104 sets the threshold value for the number of edge points to a second threshold value greater than the first threshold value. (S203, S204). On the other hand, when the travel lane recognition unit 110 determines that there is a possibility that an overtaking vehicle and an interruption vehicle exist on the right side of the host vehicle, the edge processing unit 104 keeps the threshold value of the number of edge points as the lower first threshold value. (S203).

  Finally, the edge processing unit 104 extracts an object related to the image as an obstacle when the number of edge points is equal to or greater than a set threshold (S204).

  In this embodiment, since a monocular image sensor is used as the detection means, there is an advantage that an obstacle can be detected based on an image and the structure of the apparatus can be made relatively simple.

  Hereinafter, a third embodiment of the present invention will be described. FIG. 6 is a block diagram showing a driving support system according to the second embodiment. As shown in FIG. 6, in this embodiment, instead of the front image monocular camera 40 and the rear / side / peripheral image monocular camera 42 that are monocular image sensors, the front image stereo that is a stereo image sensor is used as detection means. A camera 44 and a rear / side / peripheral image stereo camera 46 are provided.

  The front image stereo camera 44 is a pair of CCD cameras that acquire an image ahead of the vehicle. The rear / side / peripheral image stereo camera 46 is a pair of CCD cameras that acquire images of the rear, side, and periphery of the vehicle, and a wide-angle lens such as a fish-eye lens is appropriately mounted according to the situation.

  In the present embodiment, the edge processing unit 104 performs edge processing on the images of the front image stereo camera 44 and the rear / side / peripheral image stereo camera 46 in the same manner as in the second embodiment, and the determination is made by the traveling lane recognition unit 110. Obstacles are extracted based on the threshold of the number of edge points set based on the above. In addition, the edge processing unit 104 according to the present embodiment performs triangulation based on the difference in the position of the object in the acquired image of the CCD camera that forms a pair of the front image stereo camera 44 and the rear / side / peripheral image stereo camera 46. According to the method, the distance to the object and the lateral displacement from the own vehicle are obtained, and the relative speed is obtained from the amount of change with respect to the distance obtained at the previous frame.

  FIG. 7 is a flowchart showing a processing procedure in the driving support system according to the third embodiment. FIG. 7 shows an example in which an obstacle present on the right side of the host vehicle is detected as in the first embodiment. In step S301, the front image stereo camera 44 and the rear / side / peripheral image stereo camera are detected. The following steps S302 to S305 are performed in the same manner as steps S202 to S205 in the second embodiment, except that an image of an object that can be placed on the right side of the vehicle is acquired by 46.

  In the present embodiment, since a stereo image sensor is used as the detection means, there are advantages in that it is easy to detect the distance and speed of the object more accurately, and the detection accuracy of the obstacle can be further improved.

  The fourth embodiment of the present invention will be described below. FIG. 8 is a block diagram showing a driving support system according to the fourth embodiment. As shown in FIG. 8, in this embodiment, the front millimeter wave radar 30 and the short-range millimeter wave radar 32, and the front image camera 48 and the rear / side / peripheral image camera 49, which are image sensors, are used as detection means. I have. The information from the front millimeter wave radar 30 and the short-range millimeter wave radar 32 is processed by the radar wave detection unit 102 as in the first embodiment, and from the front image camera 48 and the rear / side / peripheral image camera 49. This information is processed by the edge processing unit 104 as in the second embodiment. The front image camera 48 and the rear / side / peripheral image camera 49 can be applied to either a monocular camera or a stereo camera.

  In the present embodiment, the object detection unit 100 further includes a coincidence degree detection unit 106 as an obstacle extraction unit. The degree of coincidence detection unit 106 determines the degree of coincidence of detection results from the radar wave detection unit 102 and the edge processing unit 104 based on, for example, the degree of coincidence between the distance and position of the object. In this case, the degree-of-match detection unit 106 sets a threshold for the reciprocal of the object distance or position difference, and matches according to whether the reciprocal of the distance or position difference in the detection result is equal to or greater than the set threshold. Determine the degree. When the coincidence detection unit 106 determines that there is a possibility that another vehicle may exist on either the left side or the right side of the own vehicle, the coincidence degree detection unit 106 matches the above detection results for that side. If the degree is equal to or greater than the first threshold, the object is extracted as an obstacle. On the other hand, when the coincidence detection unit 106 determines that there is no possibility that another vehicle is present on either the left side or the right side of the own vehicle, the coincidence degree detection unit 106 performs the detection result on the side. Is equal to or higher than a second threshold value higher than the first threshold value, the object is extracted as an obstacle.

  FIG. 9 is a flowchart showing a processing procedure in the driving support system according to the fourth embodiment. In the following description, as in the first embodiment, a case where an obstacle present on the right side of the own vehicle is detected will be described as an example.

  First, an object on the side of the vehicle is detected by the front millimeter wave radar 30 and the short-range millimeter wave radar 32, the front image camera 48, and the rear / side / peripheral image camera 49 (S401). Next, as in the first embodiment, the traveling lane recognition unit 110 acquires information on the current traveling lane position of the own vehicle based on the measurement result from the navigation system 12 and passes the vehicle to the right side of the own vehicle. It is determined whether or not there is a possibility that a vehicle and an interrupted vehicle exist (S402).

  When the traveling lane recognition unit 110 determines that there is no possibility that an overtaking vehicle and an interrupting vehicle are present on the right side of the host vehicle, the coincidence degree detection unit 106 sets the coincidence degree threshold to a second threshold greater than the first threshold. Set (S403, S404). On the other hand, when the traveling lane recognition unit 110 determines that there is a possibility that an overtaking vehicle and an interruption vehicle exist on the right side of the host vehicle, the coincidence degree detection unit 106 sets the coincidence degree threshold value to the lower first threshold value. The setting is made as it is (S403).

  Finally, the coincidence degree detection unit 106 extracts the object as an obstacle when the coincidence degree is equal to or greater than the set threshold (S404). That is, the coincidence degree detection unit 106 extracts an object as an obstacle when, for example, the reciprocal of the difference in the distance or position of the object in the detection result is equal to or greater than a set threshold value.

  Here, although the millimeter wave radar has high detection accuracy of the distance to the object and the relative speed with the object, the detection accuracy of the lateral displacement and the object width is inferior to that of a camera such as a stereo camera. On the other hand, although a camera such as a stereo camera has high detection accuracy of the lateral displacement and the object width, the detection accuracy of the distance to the object and the relative speed with the object is inferior to that of the millimeter wave radar 10. Therefore, according to the present embodiment, the parameters of the front millimeter wave radar 30 and the short-range millimeter wave radar 32 having different detection principles, the front image camera 48, and the rear / side / peripheral image camera 49 are merged to obstruct the obstacle. Therefore, the obstacle detection accuracy is further improved.

  Although the embodiment of the present invention has been described above, the present invention is not limited to the above embodiment, and various modifications can be made. In the present embodiment, the case where the obstacle recognition apparatus is applied to the driving support system has been mainly described, but the application field of the obstacle recognition apparatus of the present invention is not limited to this.

It is a block diagram which shows the driving assistance system which concerns on 1st Embodiment. It is a flowchart which shows the process sequence in the driving assistance system which concerns on 1st Embodiment. (A) (b) is a figure which shows recognition of the obstruction on the right side in each right and left driving lane. It is a block diagram which shows the driving assistance system which concerns on 2nd Embodiment. It is a flowchart which shows the process sequence in the driving assistance system which concerns on 2nd Embodiment. It is a block diagram which shows the driving assistance system which concerns on 3rd Embodiment. It is a flowchart which shows the process sequence in the driving assistance system which concerns on 3rd Embodiment. It is a block diagram which shows the driving assistance system which concerns on 4th Embodiment. It is a flowchart which shows the process sequence in the driving assistance system which concerns on 4th Embodiment.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Driving assistance system, 10 ... ECU, 12 ... Navigation system, 14 ... In-vehicle system, 20 ... System control part, 22 ... Driving load reduction system part, 24 ... Safety system part, 30 ... Forward millimeter wave radar, 32 ... Near Distance millimeter-wave radar, 40 ... front image monocular camera, 42 ... rear / side / peripheral image monocular camera, 44 ... front image stereo camera, 46 ... rear / side / peripheral image stereo camera, 48 ... front image camera, 49 ... rear / side / peripheral image camera, 50 ... sonar, 60 ... vehicle motion state sensor, 62 ... own vehicle motion state estimation unit, 70 ... face orientation detection sensor, 72 ... driver state estimation unit, 100 ... object detection unit, DESCRIPTION OF SYMBOLS 102 ... Radar wave detection part, 104 ... Edge processing part, 106 ... Matching degree detection part, 110 ... Travel lane recognition part, 200 ... Own vehicle, 300 ... Other vehicle.

Claims (5)

A navigation device capable of measuring the position of the vehicle,
A traveling lane recognition means for recognizing a traveling lane in which the host vehicle is traveling from the measurement result of the navigation device and determining the possibility that another vehicle exists on either the left side or the right side of the host vehicle;
Detection means capable of detecting an object existing outside the vehicle;
Obstacle extraction means for extracting the object as an obstacle according to the degree to which the object detected by the detection means can become an obstacle,
With
The obstacle extracting means includes
When the travel lane recognition unit determines that there is a possibility that another vehicle exists on either the left side or the right side of the host vehicle, the degree to which the object detected by the detection unit may become an obstacle for the side. Is extracted as an obstacle when is greater than or equal to the first degree,
When the travel lane recognition unit determines that there is no possibility that another vehicle exists on either the left side or the right side of the host vehicle, the degree to which the object detected by the detection unit may become an obstacle for the side. The object is extracted as an obstacle when is equal to or higher than a second degree higher than the first degree;
Obstacle recognition device. The detection means is a radar capable of detecting the object by radiating an electromagnetic wave to an object existing outside the vehicle and measuring a reflected wave of the electromagnetic wave,
The obstacle extracting means includes
When the traveling lane recognition means determines that there is a possibility that another vehicle exists on either the left side or the right side of the own vehicle, the reflectance of the reflected wave measured by the radar is the first for the side. When the threshold is exceeded, the object is extracted as an obstacle,
When the travel lane recognition means determines that there is no possibility of another vehicle on either the left or right side of the host vehicle, the reflectance of the reflected wave measured by the radar is the first The object is extracted as an obstacle when the threshold value is equal to or higher than a second threshold value higher than one threshold value;
The obstacle recognition apparatus according to claim 1. The detection means is a monocular image sensor capable of detecting the object by imaging an object existing outside the host vehicle,
The obstacle extracting means includes
When the travel lane recognition unit determines that there is a possibility that another vehicle exists on either the left side or the right side of the host vehicle, the captured image of the monocular image sensor is obtained by performing edge processing on the side. When the obtained edge score is equal to or greater than the first threshold, the object is extracted as an obstacle,
When the travel lane recognition means determines that there is no possibility that another vehicle exists on either the left side or the right side of the host vehicle, the captured image of the monocular image sensor is obtained by performing edge processing on the side. Extracting the object as an obstacle when the obtained edge score is equal to or higher than a second threshold value higher than the first threshold value;
The obstacle recognition apparatus according to claim 1. The detection means is a stereo image sensor capable of detecting the object by imaging an object existing outside the host vehicle,
The obstacle extracting means includes
When the travel lane recognition unit determines that there is a possibility that another vehicle exists on either the left side or the right side of the host vehicle, the captured image of the stereo image sensor is obtained by performing edge processing on the side. When the obtained edge score is equal to or greater than the first threshold, the object is extracted as an obstacle,
When the travel lane recognition means determines that there is no possibility that another vehicle exists on either the left side or the right side of the host vehicle, the captured image of the stereo image sensor is obtained by performing edge processing on that side. Extracting the object as an obstacle when the obtained edge score is equal to or higher than a second threshold value higher than the first threshold value;
The obstacle recognition apparatus according to claim 1. The detection means captures a radar capable of detecting the object by radiating an electromagnetic wave to an object existing outside the host vehicle and measuring the reflected wave of the electromagnetic wave, and an object existing outside the host vehicle. An image sensor capable of detecting the object by
The obstacle extracting means includes
When the travel lane recognition means determines that there is a possibility that another vehicle exists on either the left side or the right side of the host vehicle, the degree of coincidence of detection results between the radar and the image sensor for that side When the value is equal to or greater than the first threshold, the object is extracted as an obstacle,
When the travel lane recognition means determines that there is no possibility that another vehicle exists on either the left side or the right side of the host vehicle, the degree of coincidence of detection results between the radar and the image sensor for that side The object is extracted as an obstacle when is equal to or higher than a second threshold value higher than the first threshold value,
The obstacle recognition apparatus according to claim 1.

Images