JP2008143387A - Surrounding area monitoring device and surrounding area monitoring method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a surrounding area monitoring device and a surrounding area monitoring method for restricting/prohibiting an application of non-required information or an operation control in view of external circumstances around an automobile. <P>SOLUTION: A walker recognition unit 18 acknowledges walking persons in reference to input images photographed by a camera 31 and processed by a pre-processing unit 11, and at the same time even if a specified environment sensing unit 19 acknowledges the walking persons, but there is a less possibility that collision against the walking persons takes place due to stopping before signals, stopping before a cross walk, states of sidewalk, type of roads and inside lane or the like, a specific situation showing a low necessity of providing information or performing a vehicle control is detected. Then, in the case that the specific situation is detected, information to a driver or control of vehicle operation is prohibited and restricted. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a periphery monitoring device and a periphery monitoring method for recognizing the presence of a pedestrian and performing notification to a driver or operation control of a host vehicle.

  2. Description of the Related Art In recent years, various technologies for assisting driving operations have been devised by determining the situation around the host vehicle, providing information to the driver, and controlling the operation of the vehicle.

  Among such driving assistance technologies, technology for preventing accidents with pedestrians is particularly important. Therefore, it is required to recognize pedestrians with high accuracy and to provide information and control operations. For example, Patent Document 1 discloses a technique for providing information to a driver when the vehicle passes a pedestrian crossing that a pedestrian is crossing.

Japanese Patent Laid-Open No. 2001-134891

  By the way, if all the pedestrians in the vicinity of the own vehicle are notified to the driver, information about pedestrians that have no possibility of colliding with the own vehicle will be provided, which may be troublesome for the driver. As a result, the driver's attention and confidence in the information provided in general declines, and when the driver really provides the necessary information, the driver does not pay attention to the information and the original purpose cannot be achieved. there is a possibility. Therefore, it has been an important issue to select and provide only necessary information for the driver.

  Considering the possibility of a pedestrian colliding with the host vehicle, a technology for selectively recognizing and notifying a pedestrian in the direction of the host vehicle has already been considered. In such a case, it is expected that the driver will stop after confirming the signal even if the driver is not aware of the pedestrian, so the risk of collision with the pedestrian is low.

  As described above, even if a pedestrian is recognized in certain situations, information provision and vehicle control may not be necessary, but such situations have not been sufficiently studied in the past, and appropriate driving assistance can be performed. There was a problem that it was not possible.

  The present invention has been made in order to solve the above-described problems in the prior art and to solve the problems, and a peripheral monitoring device and a peripheral that suppress and prohibit unnecessary information provision and operation control in view of the external situation The purpose is to provide a monitoring method.

  In order to solve the above-described problems and achieve the object, the periphery monitoring device and the periphery monitoring method according to the present invention provide notification to the driver of the host vehicle or the host vehicle when the presence of a pedestrian around the host vehicle is recognized. On the other hand, when a specific external environment is detected, notification and control are prohibited / suppressed.

  According to the present invention, the periphery monitoring device and the periphery monitoring method suppress / prohibit notification to the driver and vehicle operation control in a specific situation with low risk of collision even if the presence of a pedestrian is recognized. There is an effect that it is possible to obtain a pedestrian recognition device and a pedestrian recognition method that perform appropriate driving support according to the situation.

  Hereinafter, a periphery monitoring device and a periphery monitoring method according to the present invention will be described in detail with reference to the accompanying drawings.

  FIG. 1 is a schematic configuration diagram showing a schematic configuration of a vehicle-mounted periphery monitoring device 10 that is an embodiment of the present invention. As shown in the figure, the periphery monitoring device 10 mounted on the vehicle is connected to a navigation device 30, a camera 31, a radar 34, a communication device 32, a vehicle speed sensor 33, and a pre-crash ECU 40.

  The navigation device 30 is an in-vehicle device that sets and guides a travel route using the position of the host vehicle specified by communicating with a GPS (Global Positioning System) artificial satellite and map data 30a stored in advance. In addition, the navigation device 30 provides the periphery monitoring device 10 with position information of the own vehicle, surrounding map information, information regarding roads, and the like.

  The camera 31 captures the periphery of the host vehicle and inputs the captured result to the periphery monitoring device 10. Further, the radar 34 radiates, for example, millimeter waves to the periphery of the own vehicle, detects surrounding objects from the reflected waves, and inputs them to the periphery monitoring device 10. The communication device 32 inputs information acquired by performing communication with other vehicles and roadside communication terminals to the periphery monitoring device 10. Further, the vehicle speed sensor 33 acquires the traveling speed of the host vehicle and changes thereof and inputs the acquired traveling speed to the periphery monitoring device 10.

  When the image recognition unit 10 predicts a collision of the host vehicle, the pre-crash ECU 40 is an electronic device that performs notification to the occupant by the display 43 and the speaker 44, control of the vehicle operation by the brake 41, and the engine control device (EFI) 42. It is a control device and functions as a vehicle control device.

  The periphery monitoring device 10 includes a preprocessing unit 11, a vehicle recognition unit 16, a white line recognition unit 17, a pedestrian recognition unit 18, a specific environment detection unit 19, a collision determination unit 20, and a risk correction unit 21 therein. Here, the vehicle recognition unit 16, the white line recognition unit 17, the pedestrian recognition unit 18, the specific environment detection unit 19, the collision determination unit 20, and the risk level correction unit 21 are, for example, a single microcomputer 10 a (CPU, ROM, RAM). It is preferable to realize it by an arithmetic processing unit comprising a combination.

  The preprocessing unit 11 performs processing such as filtering, edge detection, and contour extraction on the image captured by the camera 31, and then outputs the image to the vehicle recognition unit 16, the white line recognition unit 17, and the pedestrian recognition unit 18.

  The vehicle recognition unit 16 recognizes the vehicle by performing pattern matching on the image output from the preprocessing unit 11, recognizes the vehicle from the output of the radar 34, and outputs the recognition result to the collision determination unit 20. Similarly, the white line recognition unit 17 performs pattern matching on the image output from the preprocessing unit 11 to recognize a white line, and outputs the recognition result to the collision determination unit 20.

  The pedestrian recognition unit 18 detects an area where a pedestrian may exist from the image output by the preprocessing unit 11 as a pedestrian candidate area, and recognizes the pedestrian by image processing on the image of the pedestrian candidate area. In addition, the pedestrian is recognized from the output of the radar 34 and the recognition result is output to the collision determination unit 20.

  The collision determination unit 20 uses the vehicle recognition unit 16, the white line recognition unit 17, the recognition result by the pedestrian recognition unit 18, the position information output from the navigation device 30, and the like to detect a collision between the pedestrian and other vehicles and the host vehicle. Predict and output the prediction result to the pre-crash ECU 40.

  The pre-crash ECU 40 performs notification control on the driver through the display 43, the speaker 44, and the like if there is a possibility of a collision based on a prediction result (a pedestrian is present ahead and the distance is close to several meters). Depending on the degree of risk of collision, vehicle travel control (brake control, accelerator control, etc.) is performed to realize avoidance support control that supports avoidance of contact with a pedestrian.

  The specific environment detection unit 19 is an external environment detection unit that detects a specific external environment using information obtained by image recognition and radar detection. Here, the specific external environment is a situation in which even if a pedestrian is recognized, the possibility of collision with the pedestrian is low, and the need for information provision and vehicle control is small.

  Specifically, the specific environment detection unit 19 detects a stop before a signal, a stop before a pedestrian crossing, a sidewalk state, a road type, and a traveling lane.

  The stop before the signal is a state in which the host vehicle is expected to stop before the signal, such as when there is a traffic signal on the course of the host vehicle and the state of the signal is a red signal. In order to detect this pre-signal stop, it is necessary to detect the presence or absence of a signal as shown in FIG. 2, and to detect the state when a signal exists. Furthermore, it is preferable that it is possible to detect that the speed of the host vehicle is decelerating so that it can stop before the traffic light.

  The presence / absence of a traffic light can be detected by image recognition of the result of photographing by the camera 31, communication with the outside by the communication device 32, provision of information from the navigation device 30, and output of the radar 34.

  The signal state can also be recognized by image processing, external communication, a color sensor that detects the color of the traffic light, and the like. Further, when detecting the speed of the host vehicle, the output from the vehicle speed sensor 33 may be used.

  The stop before the pedestrian crossing is a situation where there is a pedestrian crossing in the course of the host vehicle and the host vehicle is decelerating to be able to stop before the pedestrian crossing. In order to detect this stop in front of a pedestrian crossing, as shown in FIG. 2, the presence or absence of a pedestrian crossing is detected, and if there is a pedestrian crossing, the vehicle must be decelerating so that it can stop before that. Need to be detected.

  The presence / absence of a pedestrian crossing can be detected by image recognition of the result of photographing by the camera 31, communication with the outside by the communication device 32, and provision of information from the navigation device 30. And when detecting the speed of the own vehicle, the output from the vehicle speed sensor 33 may be used.

  The sidewalk state is the state of the sidewalk on the road on which the host vehicle is traveling. Even if there are pedestrians at the same position with respect to the host vehicle, the pedestrian will go to the side of the road and there will be a situation where there is no sidewalk and there is a sidewalk where it is difficult for the pedestrian to enter the road. The risk of collision with is very different.

  Therefore, as shown in FIG. 2, the specific environment detection unit 19 detects the presence or absence of a sidewalk by image processing or communication. If there is a sidewalk, the specific environment detection unit 19 detects the width of the sidewalk and the height of the roadway, Presence / absence, and if there is a guardrail, its height is detected by image processing, communication, or radar.

  And the presence or absence of the sidewalk, the width of the sidewalk, the height of the sidewalk, the presence or absence of the guardrail, whether the state of the sidewalk is good from the height of the guardrail, that is, how much pedestrians do not come out to the roadside Determine if you can expect.

  For the road type, the specific environment detection unit 19 detects a situation where the type of road on which the host vehicle is traveling is dedicated to the vehicle as a specific external environment. This is because the risk of collision with a pedestrian is small when traveling on a road dedicated to vehicles such as an expressway or a bypass. This road type can be acquired from the navigation device 30.

  For the traveling lane, the specific environment detection unit 19 detects a situation in which another lane exists on the left side of the lane in which the host vehicle is traveling as a specific external environment. For example, as shown in FIG. 3, in a road with three lanes on the left side and two lanes on the right side, lanes L1 and lane R1 have no other lanes on the left in the traveling direction, so there is a high possibility that pedestrians will appear. However, since it is necessary for the lane L2 and the lane R2 to pass through the lane L1 and the lane R1 before the pedestrian appears, the possibility of the pedestrian coming out is lower than the lane L1 and the lane R1. The lane L3 has a lower possibility of a pedestrian coming out than the lane L2.

  In this way, the possibility that a collision with a pedestrian will occur depends on which lane of the lane the host vehicle is traveling, so the specific environment detection unit 19 uses the navigation device 30 to determine the lane of the host vehicle. Get from.

  The specific environment detection unit 19 outputs the detection result of the specific environment to the risk correction unit 21. The risk correction unit 21 functions as a prohibition suppression unit by performing a process of correcting the risk calculated by the collision determination unit 20 based on the detection result of the specific environment.

  For example, if the collision determination unit 20 determines the possibility of a collision with a pedestrian as shown in FIG. 4 in six stages of risk 0 to 5, and associates notification and vehicle control, the specific environment detection When the unit 19 detects a specific external environment, the risk correction unit 21 corrects the risk value based on the detected external environment.

  Specifically, in FIG. 4, there is no notification and no vehicle control at risk level 0, notification by navigation screen display at risk level 1, notification by display with warning at risk level 2, display with warning at risk level 3 and voice notification Deceleration preparations such as reducing notification and brake play, warning display with warning 4 and warning notification and acceleration prohibition and preparation for deceleration, warning display with warning and voice notification and warning deceleration at risk 5 .

  Here, for example, if the specific environment detection unit 19 detects a stop before a signal or a stop before a pedestrian crossing, the risk level correction unit 21 sets the risk level to 0 and prohibits notification and control. In addition, when the sidewalk state is good, when the vehicle is traveling on a vehicle-only road, or when another lane exists on the left side of the travel lane, the risk correction unit 21 sets the risk value to 1 to 4. By lowering the level, notification and control are suppressed. Note that it is preferable to set how much the degree of danger is to be reduced in a stepwise manner depending on the content of the detected situation.

  Next, the processing operation of the entire periphery monitoring apparatus 10 shown in FIG. 1 will be described with reference to FIG. The processing flow shown in the figure is started when a power switch (which may be linked to an ignition switch or the like) is turned on and the camera 31 captures an image, and for each processing of an image frame (for example, every several msec). This process is repeatedly executed.

  First, the periphery monitoring apparatus 10 performs processing such as filtering, edge detection, and contour extraction by the preprocessing unit 11 on the image captured by the camera 31 (step S101). Next, the white line recognition process (step S102) by the white line recognition part 16 and the vehicle recognition process (step S103) by the vehicle recognition part 16 are performed.

  Thereafter, the pedestrian recognition unit 18 performs pedestrian recognition (step S104), the collision determination unit 20 performs collision determination (step S105), and outputs the determination result to the pre-crash ECU 40 (step S106). finish.

  Further, FIG. 6 shows processing operations of the specific environment detection unit 19 and the risk level correction unit 21. As shown in the figure, the specific environment detection unit 19 first determines whether or not the road type is dedicated to the vehicle (step S201).

  If the road type is not dedicated to the vehicle (step S201, No), it is determined whether or not the vehicle is in the stop state before the signal (step S202). If the road type is not in the stop state before the signal (step S202, No), It is determined whether or not the vehicle is in a stop before a pedestrian crossing (step S203).

  Furthermore, if it is not the state before a pedestrian crossing (step S203, No), it is determined whether the traveling lane is not the left end (step S204), and if the traveling lane is the left end (step S204, No), which sidewalk state is It is determined whether the degree is good (step S205).

  If there is no sidewalk (step S205, No), the risk level correction unit 21 does not correct the risk level (step S206), but if any of steps S201 to S205 is yes, the risk level The correction unit 21 corrects the degree of risk so as to suppress / prohibit notification and vehicle control based on the pedestrian recognition result (step S207).

  As described above, the periphery monitoring device 10 according to the present embodiment recognizes the presence of a pedestrian by image processing or radar detection, and stops before a signal, stops before a pedestrian crossing, a sidewalk state, a road type, a driving lane, and the like. Even if a pedestrian is recognized, it is unlikely that a collision with the pedestrian will occur, and if the driver detects a specific situation with little need for information provision or vehicle control, Since the notification and control of the vehicle operation are prohibited / suppressed, it is possible to prevent unnecessary notification and control from occurring, thereby effectively supporting the driving operation.

  In addition, a present Example is an example to the last, and this invention can be implemented by changing a structure suitably. For example, in the present embodiment, when a specific environment is detected, an example of a configuration in which notification or control is prohibited / suppressed by correcting the degree of risk calculated by the collision determination unit 20 has been described. As shown, the output suppression unit 22 that has received the detection result of the specific environment detection unit 19 may be configured to intervene in the operation of the pre-crash ECU 40 and directly prohibit / suppress notification and operation control.

  As described above, the periphery monitoring device and the periphery monitoring method according to the present invention are useful for driving support by pedestrian recognition, and realize effective pedestrian recognition that suppresses unnecessary notification and control depending on the situation. Is suitable.

It is a schematic block diagram which shows schematic structure of the periphery monitoring apparatus concerning the Example of this invention. It is explanatory drawing explaining the detection of a specific environment. It is explanatory drawing explaining the change of the collision risk with the pedestrian based on a travel lane. It is explanatory drawing explaining the correspondence of a danger level, alerting | reporting, and vehicle control. It is a flowchart explaining the processing operation of the periphery monitoring apparatus shown in FIG. It is a flowchart explaining the process of specific environment detection and a risk correction. It is a schematic block diagram explaining the structure in the case of intervening directly in alerting | reporting or vehicle control based on the detection result of a specific environment.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Perimeter monitoring apparatus 10a Microcomputer 11 Pre-processing part 16 Vehicle recognition part 17 White line recognition part 18 Pedestrian recognition part 19 Specific environment detection part 20 Collision judgment part 21 Risk level correction part 22 Output suppression part 30 Navigation apparatus 30a Map data 31 Camera 32 Communication device 33 Vehicle speed sensor 34 Radar 40 Pre-crash ECU
41 Brake 42 EFI
43 Display 44 Speaker

Claims (11)

A surrounding monitoring device that performs avoidance support control for assisting avoidance of contact with the pedestrian by notifying a driver of the own vehicle and / or controlling the operation of the own vehicle when a pedestrian around the own vehicle is recognized. ,
An external environment detection means for detecting a specific external environment of the host vehicle;
A prohibition suppressing means for prohibiting and / or suppressing the crisis avoidance support control when the external environment detecting means detects a specific external environment outside the vehicle;
A peripheral monitoring device comprising:   The periphery monitoring device according to claim 1, wherein the external environment detection unit detects, as the specific external environment, a situation in which a stop signal for the vehicle is present in the course of the host vehicle.   The external environment detection means detects, as the specific external environment, a situation in which a pedestrian crossing exists in the course of the host vehicle and the host vehicle is decelerating so as to stop before the pedestrian crossing. The periphery monitoring apparatus according to 1 or 2.   The periphery monitoring device according to claim 1, 2 or 3, wherein the external environment detection means detects a situation in which the type of road on which the host vehicle is traveling is dedicated to the vehicle as the specific external environment.   The said external environment detection means detects the condition where the other lane exists in the left side of the lane in which the own vehicle is driving | running | working as said specific external environment, The any one of Claims 1-4 characterized by the above-mentioned. Perimeter monitoring device.   The external environment detection unit detects a sidewalk width and / or a sidewalk height when a sidewalk exists, and the prohibition suppression unit performs the avoidance support control based on the sidewalk width and / or the sidewalk height. The periphery monitoring device according to any one of claims 1 to 5, which is prohibited and / or suppressed.   The external environment detection unit further detects the presence or absence of a guardrail, and the prohibition suppression unit prohibits and / or suppresses the avoidance support control stepwise based on a state of the guardrail. Perimeter monitoring device as described in 1.   The prohibition suppression means prohibits the avoidance support control by correcting the collision risk when the avoidance support control performs notification and / or operation control based on a collision risk between the pedestrian and the host vehicle. The perimeter monitoring device according to claim 1, wherein the perimeter monitoring device is suppressed.   The periphery monitoring device according to any one of claims 1 to 7, wherein the prohibition suppressing unit directly intervenes in notification and / or operation control by the avoidance support control.   The periphery monitoring device according to any one of claims 1 to 9, wherein a pedestrian around the host vehicle is recognized by image processing. A surrounding monitoring method for performing avoidance support control for assisting avoidance of contact with the pedestrian by notifying a driver of the own vehicle and / or operation control of the own vehicle when a pedestrian around the own vehicle is recognized. ,
An external environment detection process for detecting the external environment of the vehicle;
A prohibition suppressing step for prohibiting and / or suppressing the crisis avoidance support control when the external environment detecting step detects a specific external environment outside the vehicle;
A peripheral monitoring method characterized by comprising

Images