JP2011018166A - Travel safety device for vehicle - Google Patents

Abstract

An object of the present invention is to appropriately detect an intersection and to secure desired traveling safety of the vehicle at the intersection.
A traveling safety device for a vehicle includes a first camera and a second camera that are provided in a front portion of the host vehicle and output an image obtained by capturing an image of an external environment in the left-right direction of the host vehicle. Based on the image data output from the cameras 21 and 22, a boundary line extraction unit 34 that extracts a line segment at the upper end of the road surface as a plane boundary line, and an empty area where no structures on the road surface and the road surface exist, A proximity point extraction unit 35 that extracts a proximity point closest to the plane boundary line from an empty region, a distance calculation unit 36 that calculates a distance between the plane boundary line and the proximity point, and a distance between the plane boundary line and the proximity point And an intersection determination unit 37 that determines that the vehicle is located at a point facing the intersection when the vehicle is equal to or less than the predetermined distance.
[Selection] Figure 1

Description

  The present invention relates to a vehicle travel safety device.

  Conventionally, for example, a driving support device that predicts the state of a traffic signal at an intersection through which the vehicle passes and suppresses the vehicle from entering the intersection when the traffic signal when the vehicle passes through the intersection is yellow or red. It is known (see, for example, Patent Document 1).

JP 2009-67314 A

By the way, according to the driving support device according to the above-described prior art, when there is no traffic light at the intersection and the traveling path of the own vehicle is a non-priority road, etc., it is effective to suppress the approach of the own vehicle to the intersection. There is a problem that the desired travel safety cannot be ensured without acting.
In addition, in the method of determining the presence of an intersection according to the state of the direction indicator of the own vehicle, the suppression of entering the intersection of the own vehicle does not work effectively when the own vehicle goes straight through the intersection. There arises a problem that traveling safety cannot be ensured.
The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a vehicle travel safety device capable of ensuring the desired travel safety of the host vehicle at an intersection.

  In order to solve the above-described problems and achieve the object, the vehicle travel safety device according to the first aspect of the present invention is provided at the front portion of the host vehicle and images the external world in the left-right direction of the host vehicle. Based on the image pickup means (for example, the first camera 21 and the second camera 22 in the embodiment) that outputs the image and the image output from the image pickup means, the line segment at the upper end of the road surface is extracted as a boundary line. Based on the boundary line extraction means (for example, the boundary line extraction unit 34 in the embodiment) and the image output from the imaging means, the road surface and an empty region where no structures on the road surface exist are extracted. A proximity point extracting unit that extracts a proximity point closest to the boundary line from the sky region (for example, the proximity point extracting unit in the embodiment), and the boundary line extracted by the boundary line extracting unit. And the proximity point extraction means When the distance calculation unit (for example, the distance calculation unit 36 in the embodiment) that calculates the distance to the extracted proximity point and the distance calculated by the distance calculation unit is equal to or less than a predetermined distance, A determination unit (for example, an intersection determination unit 37 in the embodiment) that determines that the host vehicle is located at a point facing an intersection is provided.

  Furthermore, in the vehicle travel safety device according to the second aspect of the present invention, the imaging means outputs a first image obtained by imaging the external environment of the left front of the host vehicle (for example, implementation). A first camera 21) in the form and a second imaging means (for example, the second camera 22 in the embodiment) for outputting a second image obtained by imaging the right front outside of the host vehicle, The distance calculating unit calculates a distance between the boundary line and the proximity point for each of the first image output from the first imaging unit and the second image output from the second imaging unit. The determination unit is located at a point where the host vehicle faces an intersection when the distances to the first image and the second image calculated by the distance calculation unit are equal to or less than a predetermined distance. Is determined.

  Furthermore, the vehicle travel safety device according to the third aspect of the present invention includes a host vehicle route prediction means (for example, host vehicle track prediction unit 31 in the embodiment) for predicting the route of the host vehicle, Crossing vehicle detection means (for example, a crossing vehicle detection unit 32 in the embodiment) that detects a crossing vehicle that runs on a crossing road that intersects the driving road, and the path of the crossing vehicle detected by the crossing vehicle detection means Predicted by the crossing vehicle course prediction means (for example, the crossing car course prediction unit 33 in the embodiment), the course of the own vehicle predicted by the own vehicle course prediction means, and the crossing vehicle course prediction means Collision possibility determination means (for example, collision possibility determination unit 38 in the embodiment) for determining presence or absence of collision possibility between the own vehicle and the intersection vehicle based on the course of the intersection vehicle; The traveling path of the host vehicle Control means for executing a predetermined warning or avoidance control when the collision possibility determination means determines that there is a possibility of collision between the own vehicle and the intersection vehicle at an intersection with a difference road (for example, implementation) Vehicle control unit 39) in the form of, and when the determination means determines that the host vehicle is located at a point facing an intersection, the predetermined alarm or the avoidance Execute control.

  According to the travel safety device for a vehicle according to the first aspect of the present invention, it is accurately determined whether or not the host vehicle is facing an intersection without requiring communication with, for example, a roadside machine or another vehicle. can do.

  Furthermore, according to the vehicle travel safety device of the second aspect of the present invention, it is possible to improve the accuracy and reliability of the determination result as to whether or not the host vehicle is facing an intersection.

  Furthermore, according to the travel safety device for a vehicle according to the third aspect of the present invention, for example, an alarm for notifying that there is a possibility of collision between the crossing vehicle and the host vehicle, or suppressing the approach of the host vehicle to the intersection, for example. It is possible to prevent the travel control and the like from being executed excessively, and to appropriately operate the alarm and the travel control.

1 is a configuration diagram of a vehicle travel safety device according to an embodiment of the present invention. It is a figure which shows the example of arrangement | positioning of each camera of the travel safety apparatus of the vehicle which concerns on embodiment of this invention. Feature point extraction processing, planar boundary line vicinity region extraction processing, and planar boundary line performed on image data obtained by imaging of each camera of the vehicle travel safety device according to the embodiment of the present invention It is a figure explaining the process of an extraction, and the process of an empty area | region extraction. 4A is an example of image data obtained by imaging the first camera of the host vehicle facing the intersection, and FIG. 4B is an image of the first camera of the host vehicle not facing the intersection. It is an example of the image data obtained by this. It is a flowchart which shows the operation | movement of the traveling safety apparatus of the vehicle which concerns on embodiment of this invention, especially the process which determines whether the own vehicle is facing the intersection.

Hereinafter, a vehicle travel safety apparatus according to an embodiment of the present invention will be described with reference to the accompanying drawings.
The vehicle travel safety device 10 according to the present embodiment transmits the driving force of the internal combustion engine (E) to the driving wheels (not shown) of the vehicle via a transmission (T / M), for example, as shown in FIG. The vehicle is mounted on a vehicle and includes an external sensor 11, a vehicle state sensor 12, a processing device 13, a throttle actuator 14, a brake actuator 15, a steering actuator 16, and a notification device 17.

The external sensor 11 includes, for example, an imaging device and a radar device 23 using an electromagnetic wave such as an infrared laser or millimeter wave.
For example, as shown in FIG. 2, the imaging apparatus includes a first camera 21 having an imaging area RA as an area with a predetermined angle θ in the right front of the external environment of the host vehicle, and an area with a predetermined angle θ in the left front of the external environment of the own vehicle. Is image-capturing area LA, image processing is performed on images obtained by the cameras 21 and 22, image data is generated, and output to the processing device 13.
Further, for example, the radar device 23 divides a detection target region (for example, right front and left front) set in the external environment of the host vehicle into a plurality of angle regions, and scans each angle region so as to scan the electromagnetic wave. Send the outgoing signal. Then, each of the transmission signals receives a reflection signal generated by being reflected by an external object (for example, another vehicle or a structure) of the own vehicle, and a detection signal related to the distance from the radar device 23 to the external object. Is output to the processing device 13.

  The vehicle state sensor 12 includes, for example, a wheel speed sensor that detects the rotational speed (wheel speed) of the driving wheel of the host vehicle, an acceleration sensor that detects acceleration acting on the vehicle body, and a gyro that detects the posture and traveling direction of the vehicle body. Sensor, yaw rate (rotational angular velocity around the vertical axis of the center of gravity of the vehicle), and positioning signals such as GPS (Global Positioning System) signals for measuring the position of the vehicle using an artificial satellite, for example A positioning signal receiver that receives the signal and each sensor that detects the driving operation by the driver (for example, accelerator pedal depression amount, brake pedal depression amount, steering wheel steering angle, shift position, etc.) And outputs signals of detection results of various types of vehicle information of the host vehicle.

  The processing device 13 includes, for example, a host vehicle route prediction unit 31, an intersection vehicle detection unit 32, an intersection vehicle route prediction unit 33, a boundary line extraction unit 34, a proximity point extraction unit 35, a distance calculation unit 36, and an intersection. A determination unit 37, a collision possibility determination unit 38, and a vehicle control unit 39 are provided.

The host vehicle course prediction unit 31 calculates the traveling direction of the host vehicle based on, for example, signals output from the wheel speed sensor and the yaw rate sensor of the vehicle state sensor 12, and further, based on the traveling direction of the host vehicle. Predict the course.
The crossing vehicle detection unit 32 is based on, for example, a detection signal output from the radar device of the external sensor 11, and another vehicle (crossing) that moves in a traveling direction that intersects the course of the host vehicle predicted by the host vehicle path prediction unit 31 Vehicle).

  The crossing vehicle course prediction unit 33 determines the position of the crossing vehicle from a plurality of reflection points of electromagnetic waves transmitted from the radar device and reflected by the crossing vehicle based on, for example, detection signals sequentially output from the radar device of the external sensor 11. A representative representative point (for example, a reflection point closest to the host vehicle or the center of gravity of a plurality of reflection points) is calculated, and a course of the intersecting vehicle is predicted from a time series change of the representative point.

The boundary line extraction unit 34 extracts a line segment at the upper end of the road surface as a plane boundary line in the image data captured by the cameras 21 and 22.
For example, as shown in FIG. 3A, the boundary line extraction unit 34 performs feature point extraction processing on the image data output from the external sensor 11 by, for example, a Harris operator. Then, it is assumed that the feature point distribution is sparse in the plane area and the feature point distribution is dense in areas other than the plane area, and an area near the boundary of the plane area (plane boundary line vicinity area) is extracted.

Specifically, for example, as shown in FIG. 3B, a histogram of feature points distribution, that is, the total number (frequency) of feature points in the horizontal direction for each vertical position of the image data is created.
Then, for example, the lower half of the image data in the vertical direction is set as a planar area search area (lower image half area), and the image position (histogram maximum point) having the highest frequency in this search area is extracted.
Then, as shown in FIG. 3C, for example, a rectangular area in a predetermined range above and below the maximum point of the histogram (for example, a range of 20 pixels above and below) is set as a plane boundary vicinity area.
Then, for example, principal component analysis is performed on the feature point group in the region near the plane boundary line, and the first principal component straight line is set as the plane boundary line. This first principal component straight line includes the centroid of the feature point distribution and is a straight line having the eigenvector of the first principal component as an inclination. Note that, for example, if the boundary between the feature point distribution between the flat area and the non-planar area is unclear due to road surface unevenness, etc., the contribution ratio of the first principal component is small, so the contribution ratio is, for example, a predetermined value (for example, , 0.9, etc.) is considered to be successful in extracting the plane boundary line, and when the contribution rate is less than a predetermined value, it cannot be determined.

  The proximity point extraction unit 35 binarizes the image area above the plane boundary line, for example, as shown in FIG. 3D according to the plane boundary line extracted by the boundary line extraction unit 34. Processing is performed, and in the image data after the binarization processing, the maximum area is an empty area where no road surface and structures on the road surface exist. Then, a point (proximity point) closest to the plane boundary line in the empty area is extracted, and this adjacent point is set as the lower end of the empty area.

  For example, as shown in FIGS. 4A and 4B, the distance calculation unit 36 calculates the distance between the lower end (proximity point) of the sky region extracted by the proximity point extraction unit 35 and the plane boundary line. .

When the distance between the lower end (proximity point) of the sky region and the plane boundary line is equal to or less than a predetermined distance for each image data captured by the cameras 21 and 22, the intersection determination unit 37 Is determined to be located at a point facing the intersection.
That is, for example, as shown in FIG. 4 (A), when the host vehicle is located at a point where it faces an intersection, the intersections intersecting the traveling path of the host vehicle are imaged by the cameras 21 and 22. As a result, the distance between the lower end (proximity point) of the sky region and the plane boundary line decreases.
On the other hand, for example, as shown in FIG. 4B, when there is no crossing road that intersects the traveling road of the host vehicle, the distance between the lower end (proximity point) of the empty area and the plane boundary line increases. .

  The collision possibility determination unit 38, for example, when the intersection determination unit 37 determines that the host vehicle is located in the vicinity of the intersection, and the course of the host vehicle predicted by the host vehicle route prediction unit 31 and the intersection vehicle route prediction unit 33. Based on the predicted path of the intersecting vehicle, the possibility of collision between the host vehicle and the intersecting vehicle is determined in consideration of, for example, the deceleration required for collision avoidance.

The vehicle control unit 39 outputs a control signal for controlling the traveling state of the host vehicle according to the determination result by the collision possibility determination unit 38. This control signal includes, for example, a control signal for controlling the transmission operation of the transmission (T / M), a control signal for controlling the driving force of the internal combustion engine (E) by the throttle actuator 14, and a control signal for controlling the deceleration by the brake actuator 15. And a control signal for controlling the turning by the steering actuator 16.
Moreover, the vehicle control part 39 outputs the control signal which controls the alerting | reporting apparatus 17, when notifying the passenger | crew of the own vehicle various information.

The notification device 17 includes, for example, a tactile transmission device, a visual transmission device, and an auditory transmission device.
The tactile transmission device is, for example, a seat belt device, a steering control device, or the like, and generates a predetermined tension on the seat belt, for example, according to a control signal output from the vehicle control unit 39 so that the passenger of the host vehicle can sense the touch. The possibility of a collision with an approaching crossing vehicle by applying a perceptible tightening force or generating vibration (steering vibration) that can be perceived tactilely by the driver of the host vehicle on the steering wheel. Let the crew recognize that there is.
The visual transmission device is, for example, a display device and the like, for example, by displaying predetermined alarm information on the display device or blinking a predetermined alarm light in accordance with a control signal input from the vehicle control unit 39. The occupant is made aware that there is a possibility of a collision with the approaching crossing vehicle.
The auditory transmission device is, for example, a speaker and outputs a predetermined warning sound or voice according to a control signal input from the vehicle control unit 39, so that there is a possibility of occurrence of a collision with an approaching crossing vehicle. Let the crew recognize that there is.

  The vehicle travel safety apparatus 10 according to the present embodiment has the above-described configuration. Next, the operation of the vehicle travel safety apparatus 10, particularly the process for determining whether or not the host vehicle is facing an intersection. explain.

First, for example, in step S01 shown in FIG. 5, each image data obtained by the imaging of each camera 21, 22 is acquired.
Next, in step S02, feature point extraction processing is performed on each image data by, for example, a Harris operator.
Next, in step S03, a histogram of the feature point distribution is created, and a rectangular area in a predetermined range above and below the maximum histogram point (for example, a range of 20 pixels above and below) is set as a plane boundary vicinity area.
Next, in step S04, for example, a principal component analysis process is performed on the feature point group in the plane boundary line vicinity region.

In step S05, for example, it is determined whether or not the plane boundary line extraction is successful by determining whether or not the contribution rate is equal to or greater than a predetermined value (for example, 0.9).
If this determination is “NO”, the flow proceeds to step S 06, and in this step S 06, the determination is impossible and the flow proceeds to the end.
On the other hand, if this determination is “YES”, the flow proceeds to step S07.
In step S07, the binarization process is performed on the image area above the plane boundary, and the maximum area is set as an empty area in the image data after the binarization process. Then, a point (proximity point) closest to the plane boundary line in the empty area is extracted, and this adjacent point is set as the lower end of the empty area.
In step S08, it is determined whether or not the distance between the lower end (proximity point) of the sky region and the plane boundary is equal to or less than a predetermined distance.
If this determination is “YES”, the flow proceeds to step S 09, and in this step S 09, it is determined that the host vehicle is located at a point facing an intersection, and the flow proceeds to the end.
If this determination is “NO”, the flow proceeds to step S 10, and in this step S 10, it is determined that the host vehicle is not located at a point facing the intersection, and the flow proceeds to the end.

As described above, the vehicle travel safety device 10 according to the present embodiment does not require communication with, for example, a roadside machine or another vehicle, and does not require map data or the like of the navigation device. It is possible to accurately determine whether or not the host vehicle is facing an intersection.
Furthermore, when the distance between the lower end (proximity point) of the sky region and the plane boundary line is equal to or less than a predetermined distance for each image data captured by the cameras 21 and 22, the host vehicle faces an intersection. By determining that it is located at a point, for example, the distance between the lower end (proximity point) of the sky region and the plane boundary for only one image data captured by the first camera 21 or the second camera 22 The accuracy and reliability of the determination result as to whether or not the host vehicle faces an intersection can be improved as compared with the case where the vehicle is less than or equal to the predetermined distance. In other words, if the distance between the lower end of the sky area (proximity point) and the plane boundary line is less than or equal to a predetermined distance in only one of the image data, the host vehicle is not on an intersection but on a curve or a curved road. You can determine that you are facing.
Then, when it is determined that the host vehicle is located near the intersection, by determining whether or not there is a possibility of collision between the host vehicle and the intersection vehicle, for example, it is notified that there is a possibility of collision between the intersection vehicle and the host vehicle. It is possible to prevent alarms and, for example, traveling control that suppresses the entry of the vehicle to the intersection from being performed excessively, and to appropriately activate the alarm and traveling control.

DESCRIPTION OF SYMBOLS 10 Vehicle travel safety device 11 External sensor 12 Vehicle state sensor 17 Notification device 21 First camera (imaging means, first imaging means)
22 Second camera (imaging means, second imaging means)
31 Own vehicle course prediction unit (own car course prediction means)
32 Crossing vehicle detection unit (crossing vehicle detection means)
33 Crossing vehicle route prediction unit (crossing vehicle route prediction means)
34 Boundary line extraction unit (Boundary line extraction means)
35 Proximity point extraction unit (proximity point extraction means)
36 Distance calculation part (distance calculation means)
37 Intersection determination unit (determination means)
38 Collision possibility determination unit (collision possibility determination means)
39 Vehicle control unit (control means)

Claims (3)

An imaging means that is provided in a front portion of the host vehicle and outputs an image obtained by imaging the external world in the left-right direction of the host vehicle;
Boundary line extraction means for extracting a line segment at the upper end of the road surface as a boundary line based on the image output from the imaging means;
Based on the image output from the imaging unit, the road surface and a sky area where no structure on the road surface exists are extracted, and a proximity point closest to the boundary line is extracted from the sky area. Means,
Distance calculating means for calculating a distance between the boundary line extracted by the boundary line extracting means and the proximity point extracted by the proximity point extracting means;
A vehicle travel safety comprising: a determination unit that determines that the host vehicle is located at a point facing an intersection when the distance calculated by the distance calculation unit is equal to or less than a predetermined distance. apparatus. The imaging means outputs a first image obtained by taking an image of the outside world on the left front of the host vehicle and a second image obtained by taking an image of the outside world on the right front of the host vehicle. An imaging means,
The distance calculating unit calculates a distance between the boundary line and the proximity point for each of the first image output from the first imaging unit and the second image output from the second imaging unit. And
The determination means is located at a point where the host vehicle faces an intersection when the distances to the first image and the second image calculated by the distance calculation means are not more than a predetermined distance. The vehicle travel safety device according to claim 1, wherein the determination is made. Own vehicle course prediction means for predicting the course of the own vehicle;
Crossing vehicle detection means for detecting a crossing vehicle that runs on a crossing that crosses the traveling road of the host vehicle;
Crossing vehicle course prediction means for predicting the course of the crossing vehicle detected by the crossing vehicle detection means;
Presence / absence of possibility of collision between the own vehicle and the intersecting vehicle based on the course of the own vehicle predicted by the own vehicle route predicting unit and the course of the intersecting vehicle predicted by the intersecting vehicle route predicting unit A collision possibility determination means for determining
When the collision possibility determining means determines that there is a possibility of collision between the own vehicle and the intersecting vehicle at an intersection between the traveling road of the own vehicle and the intersection, a predetermined warning or avoidance control is performed. Control means to execute,
2. The control device according to claim 1, wherein the control unit executes the predetermined alarm or the avoidance control when the determination unit determines that the host vehicle is located at a point facing an intersection. The travel safety device for a vehicle according to claim 2.

Images