JP6044158B2 - Vehicle travel support device and vehicle travel support method - Google Patents

Description

  The present invention relates to a vehicle travel support device and a vehicle travel support method.

  2. Description of the Related Art Conventionally, in a technology for recognizing an image around a vehicle, it is known to cope with a change in brightness of the surrounding environment by controlling exposure of a camera. However, when the light and dark portions are repeatedly passed by the shadow of the three-dimensional object, the camera exposure control cannot be performed correctly and hunting may occur.

  On the other hand, for example, Patent Document 1 describes that the road surface brightness is controlled to approach the target pixel value. According to this control, by limiting the exposure control amount to the limit value, the degree of image recognition hunting is suppressed even in a situation where the sun and the shade repeat.

JP 2005-148309 A

  However, even when the brightness of the image is adjusted by exposure control as in the technique of Patent Document 1, if the brightness of the sun and the shade is greatly different, temporary recognition may occur.

  By the way, in a situation where a long shadow boundary extending in the traveling direction of the vehicle exists in the vicinity of the center in front of the travel path, there is a case where the position near the shadow boundary is set as the target travel position and the lane keeping control is performed. In this case, the camera repeats entering the sun or entering the shade due to a subtle shift in the traveling position of the vehicle. At that time, there is a possibility that hunting is caused without appropriate camera exposure control, or that temporary unrecognition may occur even when the camera exposure control is appropriately performed.

  Then, this invention is proposed in view of the above-mentioned situation, and it aims at providing the vehicle travel support apparatus and vehicle travel support method which can suppress the unrecognition of a travel environment.

In order to solve the above-described problem, the present invention detects a shadow edge caused by a shadow extending in the vehicle traveling direction from an image captured in front of the vehicle, and the length of the shadow edge is longer than a predetermined value. The travel of the vehicle is controlled so as to travel in a region away from the shadow edge. The shadow edge is an edge of a building shadow.

  According to the present invention, when the length of the shadow edge is longer than the predetermined value, the travel of the vehicle is controlled so as to travel in a region away from the shadow edge. The vicinity of the boundary can be avoided, and unrecognition of the driving environment can be suppressed.

It is a block diagram which shows the structure of the vehicle travel assistance apparatus shown as embodiment of this invention. (A) is explanatory drawing of the yaw angle of a camera, (b) is explanatory drawing of the pitch angle and height of a vehicle. It is explanatory drawing about a road parameter. It is a flowchart which shows the calculation process of the road parameter in the vehicle travel assistance apparatus shown as embodiment of this invention. It is explanatory drawing of a white line model. It is a figure explaining the initial setting of a white line candidate point detection area. It is a figure explaining the setting of the white line candidate point detection area | region in case the road white line is detected. It is explanatory drawing which sets a white line candidate point detection area with respect to a front image. It is a figure which shows the deviation | shift amount of the point on the white line model calculated | required last time, and the candidate point of the road white line detected this time. 5 is a flowchart showing a shadow edge calculation process by a shadow edge detection unit in the vehicle travel support apparatus shown as the embodiment of the present invention. In the vehicle travel support device shown as an embodiment of the present invention, it is a top view showing a scene where a vehicle is traveling on a travel path. In the vehicle travel support device shown as an embodiment of the present invention, it is a perspective view showing a scene where a vehicle is traveling on a travel path. 5 is a flowchart showing a travel position setting process by a travel position setting unit in the vehicle travel support apparatus shown as the embodiment of the present invention. 4 is a flowchart showing a steering control process by a steering control unit in the vehicle travel support apparatus shown as the embodiment of the present invention. It is a top view which shows the result of having changed the target travel position of the vehicle with the vehicle travel assistance apparatus shown as embodiment of this invention.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

  A vehicle travel support apparatus shown as an embodiment of the present invention is configured as shown in FIG. 1, for example. This vehicle travel support device detects a shadow edge caused by a shadow extending in the vehicle traveling direction from an image obtained by capturing the front of the vehicle, and moves away from the shadow edge when the length of the shadow edge is longer than a predetermined value. The vehicle is controlled to travel in the area. This shadow edge includes, for example, a shadow that includes a traveling direction component of a vehicle that appears due to a shadow that occurs in the vicinity of the center in the lateral direction ahead of the travelable region, and that extends in the traveling direction of the vehicle whose length is equal to or greater than a predetermined value. The vehicle travel support device includes, for example, a camera 1, an image recognition unit 2, a sensor unit 3, a travel control unit 4, and a steering actuator 5.

  The camera 1 is attached to the upper part of the front window in the vehicle interior at the center position in the vehicle width direction, for example. As shown in FIGS. 2 and 3, the camera 1 captures a road surface several meters to several tens meters ahead of the vehicle 10. The camera 1 supplies the captured image data to the image recognition unit 2.

  The image recognition unit 2 includes a white line recognition unit 21 and a shadow edge detection unit 22. The white line recognition unit 21 detects the relative positional relationship between the vehicle 10 and the traveling lane line (white line) based on the image data captured by the camera 1. The shadow edge detection unit 22 detects a shadow edge that appears in front of the vehicle 10 as a shadow. The shadow edge detection unit 22 calculates the position of the extracted shadow edge.

  The white line recognition unit 21 detects white lines on the road by processing image data captured by the camera 1. Next, the white line recognition unit 21 uses a plurality of parameters (hereinafter referred to as road parameters) representing the road shape and vehicle behavior to express a white line model mathematically representing the shape of the road white line, and a road white line detection result. The road parameters are updated with time so as to match. As a result, the white line recognition unit 21 detects a white line on the road and estimates the road shape and vehicle behavior.

  The road parameters include the lateral displacement yr of the center of gravity of the vehicle 10 with respect to the lane centerline drawn on the road, the yaw angle φr of the vehicle relative to the lane centerline (see FIGS. 2A and 3), and the pitch angle of the vehicle 10. η, the height h from the road surface of the camera (see FIG. 2B), road curvature (reciprocal of curvature radius) ρ, traveling lane width w, and the like. These road parameters estimated by the white line recognition unit 21 are supplied to the travel control unit 4.

  The shadow edge detection unit 22 specifies a travelable area based on the road parameter detected by the white line recognition unit 21. The shadow edge detection unit 22 extracts a shadow edge due to a shadow extending in the vehicle traveling direction in at least the travelable region. The shadow edge detection unit 22 supplies the position of the shadow edge to the travel control unit 4 as shadow edge information. The shadow edge is acquired based on the camera image. The shadow edge detection unit 22 may determine a shadow edge based on building information extending along a road such as a sound barrier near the road based on the navigation information.

  The sensor unit 3 detects the state of the vehicle 10. The sensor unit 3 includes, for example, a vehicle speed sensor, a steering angle sensor, and a current sensor for the steering actuator 5. The sensor unit 3 may additionally use a yaw rate sensor. For example, the vehicle speed sensor detects the vehicle speed by measuring the number of rotations on the output side of the transmission and the number of rotations of the wheels. The steering angle sensor amplifies the rotational displacement of the steering shaft directly or by a gear mechanism or the like, and then detects the steering angle as a steering angle detection signal by an angle detection mechanism such as a rotary encoder or a potentiometer. These sensor signals are supplied to the traveling control unit 4.

  The travel control unit 4 performs overall control in the vehicle travel support device. The traveling control unit 4 controls the vehicle so as to travel by selecting a lateral position away from a shadow edge having a length equal to or longer than a predetermined value. The travel control unit 4 includes a travel position setting unit 41 and a steering control unit 42.

  The travel position setting unit 41 sets a target travel position of the vehicle 10 based on road parameters and shadow edge information input from the image recognition unit 2. This target travel position is a lateral position in the lateral travelable area on the travel path. Next, the travel position setting unit 41 calculates the steering control amount based on the sensor signal including the vehicle speed, the steering angle, and the current of the steering actuator 5 input from the sensor unit 3.

  The steering control unit 42 sends a current command to the steering actuator 5 according to the steering control amount. Thereby, the traveling control unit 4 performs control so that the vehicle 10 travels at the target traveling position. Normally, the steering control unit 42 assists the vehicle 10 to travel along the white line based on white line recognition by a monocular camera, for example. When there is a shadow edge, the steering control unit 42 controls the traveling position of the vehicle 10 as will be described later.

[Calculation of road parameters]
Next, road parameter calculation processing by the white line recognition unit 21 in the vehicle travel support device described above will be described with reference to FIG.

First, in step S1, the white line recognition unit 21 initially sets road parameters representing road shapes and vehicle behavior. For example, on the screen coordinate system of the forward image 100 as shown in FIG. 5, the white line model is expressed by the following equation 1 using road parameters.

In the above formula 1, a to e are road parameters. If the height h of the camera 1 from the road surface is constant, each road parameter represents the following road and white line shape or vehicle behavior. That is, a corresponds to the lateral displacement amount y _cr of the _host vehicle in the lane. b corresponds to the road curvature ρ. c corresponds to the yaw angle phi _r with respect to the road of the vehicle (the optical axis of the camera 1). d corresponds to the pitch angle η with respect to the road of the host vehicle (the optical axis of the camera 1). e corresponds to the lane width W of the road. Since the shape of the road and the white line and the vehicle behavior are unknown in the initial state, for example, a value corresponding to the median is set as the initial value for each road parameter. For example, the lane center is set as the road parameter corresponding to the lateral displacement amount of the vehicle 10 in the travelable area. A straight line is set for the road parameter corresponding to the road curvature. Zero degree is set to the road parameter corresponding to the yaw angle to be in the lane. The degree of the stop state is set to the road parameter corresponding to the pitch angle with respect to the lane. A general road lane width is set as the road parameter corresponding to the lane width.

A detailed description of Equation 1 is given below. When an arbitrary point on the real coordinate system X (vehicle left-right direction), Y (vehicle vertical direction), and Z (vehicle front-back direction) fixed to the vehicle is projected onto the screen coordinate system x, y, the following equation is obtained. Like 2,

It becomes. Here, f is a lens parameter. This lens parameter is a coefficient corresponding to the focal length of the lens. Here, it is assumed that the road curvature ρ is not so large and the road surface is a flat surface. Accordingly, the coordinates of the road white line with respect to the vehicle center line (camera center line) ahead of Z [m] are expressed by the following expression 4 in the horizontal direction and the following expression 5 in the vertical direction. However, this assumption is set for simplification of the model. If the order of the model is increased, a more general condition can be established.

By eliminating X, Y, and Z from the above formulas 2 and 3, the following formula 4 is obtained.

The above equation 1 is obtained by normalizing the road parameters using the following equation 5 while keeping the height of the camera 1 having the smallest fluctuation among the variables.

  Next, in step S2, the white line recognition unit 21 performs initial setting of the white line candidate point detection areas 102L and 102R as small areas for detecting candidate points of the road white lines 101L and 101R as shown in FIG. In the initial state, it is expected that there is a large gap between the white line model in which the initial value is set as the road parameter and the road white lines 101L and 101R on the actual front image 100. Accordingly, it is desirable to set the white line candidate point detection areas 102L and 102R as large as possible. In the example shown in FIG. 6, a total of ten white line candidate point detection areas 102L and 102R are set on each of the left and right road white lines 101L and 101R. If the road white lines 101L and 101R have already been detected by the previous process, the difference between the actual road white line and the white line model is considered to be small. In this case, as shown in FIG. 7, setting as small white line candidate point detection regions 102L and 102R as possible is less likely to erroneously detect other than white lines, and the processing speed can be improved. .

Next, in step S <b> 3, the white line recognition unit 21 inputs the image data captured by the camera 1.
Next, in step S4, the white line recognition unit 21 sets white line candidate point detection areas 102L and 102R on the front image 100 of the image data input from the camera 1 in step S3. At this time, based on the white line candidate point detection regions 102L and 102R calculated in step S2 and the white line model based on the road parameters corrected in step S1 or step S9 described later, as shown in FIG. New white line candidate point detection areas 102L and 102R are set so that the white line model is the center of the area. In the example shown in FIG. 8, a total of ten white line candidate point detection areas 102L and 102R are set on each of the left and right white lines. Note that the white line candidate point detection regions 102L and 102R may be set at positions offset in the change direction of the white line model based on the past changes in the white line model.

  Next, in step S5, the white line recognition unit 21 detects white line candidate points from the edge of the front image 100 in the white line candidate point detection regions 102L and 102R.

  Next, in step S6, the white line recognition unit 21 determines whether or not the number of white line candidate points detected from all the white line candidate point detection areas 102L and 102R is equal to or greater than a predetermined value. If the number of white line candidate points is less than the predetermined value, it is determined that the road white line 101L, 101R is not included in the white line candidate point detection areas 102L, 102R, and the process returns to step S2. On the other hand, if a white line candidate point is detected at a predetermined value or more, the process proceeds to step S7.

  In step S7, as shown in FIG. 9, the white line recognition unit 21 calculates a deviation amount between the white line candidate point 103 detected this time and the point 101 on the white line model obtained in the previous process for each point.

  Next, in step S8, the white line recognizing unit 21 calculates road parameter fluctuation amounts Δa to Δe based on the deviation amount obtained in step S7. This fluctuation amount is calculated by, for example, a known least square method as disclosed in JP-A-8-5388.

  Next, in step S9, the white line recognition unit 21 corrects the road parameters a to e based on the road parameter fluctuation amounts Δa to Δe calculated in step S8. For example, in the case of the white line model shown in Equation 1 above, the road parameters a to e are corrected by Equation 5.

Then, the corrected road parameters a to e are stored in a predetermined storage area as road parameters of a new white line model, and values obtained by converting the road parameters a to e into actual physical quantities using the following formula 6 are also stored. To do. And it returns to step S3 and performs the said process repeatedly.

  As described above, the white line recognition unit 21 determines the relative positional relationship between the vehicle 10 and the white road lines 101L and 101R based on the white line model road parameters a to e detected from the front image 100 captured by the camera 1. Is detected.

[Shading edge calculation]
Next, shadow edge calculation processing by the shadow edge detection unit 22 in the vehicle travel support apparatus described above will be described with reference to FIG.

  First, in step S <b> 11, the shadow edge detection unit 22 captures image data captured by the camera 1.

  In the next step S <b> 12, the shadow edge detection unit 22 inputs the road parameter calculated by the white line recognition unit 21. Further, the shadow edge detection unit 22 inputs the forward gaze distance Ls (see FIG. 11) calculated by the travel control unit 4. A method for calculating the forward gazing point distance Ls will be described later. If the forward gaze distance is not used, only the road parameters need be input in step S12.

In the next step S <b> 13, the shadow edge detection unit 22 calculates the following expression 7 representing the position of the predetermined width t from the road center line 201 based on the road parameters, and sets the shadow edge search range 202. As shown in FIGS. 11 and 12, the shadow edge search range 202 is a region parallel to the lane inside the two lines. The shadow edge search range 202 is set around the road center line 201 as the target lateral position.

  In the next step S14, the shadow edge detection unit 22 detects an image edge (shadow edge 302) extending in the vertical vehicle traveling direction caused by the shadow 301 within the shadow edge search range 202 set in step S13. . This vertical direction is the vertical direction of the front image 100 and corresponds to the traveling direction of the vehicle 10. The shadow edge detection unit 22 performs clustering processing on the detected shadow edge 302. As a result, the shadow edge detection unit 22 identifies the shadow edge 302 in the traveling direction that is connected. Moreover, the shadow edge detection part 22 distinguishes each shadow edge 302, when a some shadow exists.

  In the next step S25, when the shadow edge 302 is detected in step S14, the shadow edge detector 22 determines the horizontal position yss and the traveling direction length xss of each shadow edge 302 as shown in FIG. calculate. Here, the horizontal position yss of the shadow edge 302 represents the horizontal distance between the road center line 201 and the shadow edge 302 at the forward gazing point distance Ls. The length xss of the shadow edge 302 represents the length of the shadow edge 302 ahead of the forward gazing point distance Ls.

  In such shadow edge calculation processing, the shadow edge 302 is detected by narrowing the shadow edge search range 202 in the width direction from the road center line 201, and the length of the shadow edge 302 is calculated. Thereby, the deviation of the inclination between the road center line 201 and the shadow edge 302 is indirectly evaluated.

  Note that the shadow edge detection unit 22 may directly calculate a deviation in inclination between the road center line 201 and the shadow edge 302.

[Setting processing of travel position by travel position setting unit 41]
Next, in the vehicle travel support apparatus described above, the travel position setting process by the travel position setting unit 41 will be described with reference to FIG.

  First, in step S21, the travel position setting unit 41 inputs the road parameter calculated by the image recognition unit 2, the length xss of the shadow edge 302 calculated by the shadow edge detection unit 22, and the horizontal position yss of the shadow edge 302. To do.

  In the next step S22, the traveling position setting unit 41 has not corrected the target lateral position of the vehicle 10 from the road center line 201 based on the shadow edge 302 detected in the previous shadow edge calculation process. Determine whether. If the target lateral position of the vehicle 10 has not been corrected, the process proceeds to step S23. If the target lateral position of the vehicle 10 has been corrected, the process proceeds to step S25.

  In step S <b> 23, the traveling position setting unit 41 determines whether or not a shadow edge 302 extending in the vehicle traveling direction having a length equal to or longer than a predetermined value (distance) in the traveling direction of the vehicle 10 has been detected. If there is a shadow edge 302 having a length equal to or longer than the predetermined value, the process proceeds to step S24, and if not, the process proceeds to step S29. The length (distance) of the predetermined value is set such that when the vehicle 10 travels in the vicinity of the shadow edge 302, the sun and the shade can appear repeatedly in the camera image due to the lateral blur of the vehicle 10. That is, the length of the shadow edge 302 is set such that hunting occurs in image recognition (for example, white line recognition) by the image recognition unit 2 when the vehicle 10 travels substantially along the shadow edge 302.

  In step S24, the traveling position setting unit 41 sets a lateral position that is a predetermined distance away from the shadow edge 302 having a length equal to or greater than a predetermined value and closer to the road center line 201 as a target lateral position. Specifically, in the scenes shown in FIGS. 11 and 12, the traveling position setting unit 41 has the shadow edge 302 on the right side of the road traveling direction with respect to the road center line 201. A position separated by a predetermined distance in the left direction on the side is set as the target lateral position. As described above, when there is a shadow edge 302 having a length equal to or longer than a predetermined value, the travel position setting unit 41 corrects the target lateral position so as to travel in a region away from the shadow edge 302.

  When a plurality of shadow edges 302 having a length equal to or greater than a predetermined value are detected in the horizontal direction, the traveling position setting unit 41 sets the target horizontal position at a position that is separated from both shadow edges 302 by a predetermined distance in the horizontal direction. Set. The range of the lateral position where the target lateral position can be set is preferably calculated on the basis of the width of the traveling path and the width of the vehicle 10, and it is desirable that a certain margin is secured from the white line to fall within a possible traveling range. Moreover, in order to suppress the rapid behavior of the vehicle 10, it is desirable to change the target lateral position so that the target lateral position is gradually moved according to the required time for changing the target lateral position or the distance traveled by the vehicle 10.

  In step S29, the traveling position setting unit 41 sets the road center line 201 to the target lateral position because there is no shadow edge 302 having a length equal to or longer than the predetermined value.

  In step S25 when the target lateral position was corrected last time in step S22, the traveling position setting unit 41 continuously detects the shadow edge 302 because the shadow edge 302 continues to exist in front of the vehicle 10. It is determined whether or not. If the shadow edge 302 continues to exist, the process proceeds to step S26. If the shadow edge 302 does not continue to exist, the target lateral position is set to the road center line 201 in step S29.

  In step S <b> 26, the travel position setting unit 41 calculates a separation distance between the previous target lateral position and the lateral position yss of the shadow edge 302, and determines whether or not the separation distance is a predetermined value or more. If the separation distance is greater than or equal to the predetermined value, the process proceeds to step S27. On the other hand, if the separation distance is not greater than or equal to the predetermined value, the process proceeds to step S28.

  In step S27, the travel position setting unit 41 holds the previous target lateral position. Thereby, when the shadow edge 302 has not changed much, it is possible to prevent the target lateral position of the vehicle 10 from being frequently corrected.

  In step S <b> 28, the traveling position setting unit 41 corrects the target lateral position to a lateral position that is separated from the shadow edge 302 by a predetermined value. As a result, once the target lateral position is corrected, the set lateral position is maintained while the distance to the shadow edge 302 is maintained at a certain distance or more without finely correcting the lateral position. On the other hand, the target lateral position is corrected only when the distance between the shadow edge 302 and the target lateral position becomes narrower than a certain value. Thereby, the repetition of unnecessary fine orbit correction is suppressed.

  In step S23 described above, a difference in inclination between the shadow edge 302 and the target lateral position may be calculated. The traveling position setting unit 41 proceeds to step S <b> 24 when the inclination deviation is small, and sets the target lateral position so as to be away from the shadow edge 302. On the other hand, when the deviation of the inclination is large, the road center line 201 is set to the target lateral position in step S29.

  In step S24, the traveling position setting unit 41 may correct the target lateral position so that the lane is changed to another lane having the same traveling direction. When the lane change is performed, the vehicle travel support device needs to set the shadow edge search range 202 over a plurality of lanes.

[Steering control processing by the steering control unit 42]
Next, steering control processing by the steering control unit 42 in the vehicle travel support device described above will be described with reference to FIG.

  First, in step S <b> 31, the steering control unit 42 acquires various sensor signals from the sensor unit 3. Specifically, the steering control unit 42 acquires signals from a vehicle speed sensor, a steering angle sensor, and a current sensor of the steering actuator 5.

  In the next step S32, the steering control unit 42 calculates a forward gazing distance according to the vehicle speed acquired in step S31. The steering control unit 42 performs calculation so that the forward gazing point distance becomes farther than the vehicle 10 as the vehicle speed increases. Note that the steering control unit 42 may calculate the forward gaze distance using the road curvature calculated by the image recognition unit 2.

  In the next step S <b> 33, the steering control unit 42 inputs the target travel position calculated by the above-described process from the travel position setting unit 41.

  In the next step S34, the steering control unit 42 calculates a target curve that connects the target travel position that is a target lateral position away from the road center line 201 at the forward gazing distance and the lateral position of the vehicle 10 with a constant curvature.

  In the next step S35, the steering control unit 42 calculates a steering control amount corresponding to the target curve calculated in step S34.

  In the next step S36, the steering control unit 42 drives the steering actuator 5 based on the steering control amount calculated in step S35.

  By performing the steering control process by the steering control unit 42 in this way, the vehicle travel support device can control the lateral position of the vehicle 10 to be the target travel position. Specifically, as shown in FIG. 15, the lateral position of the vehicle 10 can be controlled to become the target travel position along a trajectory 400 that travels to the left of the road center line 201. Thereby, the vehicle travel support device can control the travel of the vehicle 10 so as to travel in a region away from the shadow edge 302 extending in the vehicle traveling direction in the travelable region 202.

[Effect of the embodiment]
As described above, when the length of the shadow edge 302 caused by the shadow extending in the vehicle traveling direction is longer than a predetermined value, the traveling of the vehicle 10 is controlled so as to travel in a region away from the shadow edge 302. Thereby, when the vehicle 10 is traveling, the vicinity of the boundary of the shadow edge 302 can be avoided, and unrecognition of the traveling environment can be suppressed. In other words, by avoiding the vicinity of the shadow boundary, even if the driving position fluctuates or the shadow boundary position fluctuates slightly, the light environment can be kept constant and no unrecognized state occurs. Highly accurate recognition state can be maintained. Further, since the target lateral position is corrected only when the length of the shadow edge 302 is equal to or longer than the predetermined distance, fine trajectory correction can be suppressed.

  In addition, since this vehicle travel support device calculates the difference in inclination between the shadow edge 302 and the target lateral position and corrects the target lateral position in accordance with the difference in inclination, the shadow edge 302 is parallel to the target route. It is determined whether or not it is extended, and the target lateral position can be changed only in the case of parallelism. That is, if the shadow edge 302 and the travel route are close to each other temporarily and there is no fear of traveling around the shadow edge 302 for a long time, the target lateral position can be prevented from being changed. Thereby, generation | occurrence | production of the behavior of the vehicle 10 is suppressed and smooth driving | running | working is attained.

  Furthermore, according to this vehicle travel support device, the target lateral position is corrected by a predetermined distance in the lateral direction from the shadow edge 302 and is corrected to a position close to the road center line 201. A target lateral position passing through the one closer to the road center line 201 out of two routes passing through the separated positions can be selected. Therefore, it can suppress that the vehicle 10 leaves | separates from the road center line 201. FIG.

  The above-described embodiment is an example of the present invention. For this reason, the present invention is not limited to the above-described embodiment, and various modifications can be made depending on the design and the like as long as the technical idea according to the present invention is not deviated from this embodiment. Of course, it is possible to change.

  That is, although the vehicle travel support apparatus described above has described the vehicle 10 that detects a white line and travels within the white line, the present invention is not limited to this.

DESCRIPTION OF SYMBOLS 1 Camera 2 Image recognition part 3 Sensor part 4 Travel control part 5 Steering actuator 10 Vehicle 21 White line recognition part 22 Shadow edge detection part 41 Travel position setting part 42 Steering control part

Claims (4)

Edge detection means for detecting a shadow edge caused by a shadow extending in the vehicle traveling direction from an image obtained by imaging the front of the vehicle;
Wherein when the edge length of the shadow edges detected by the detecting means is longer than a predetermined value, e Bei and running control means for controlling the travel of the vehicle so that the vehicle travels a region away from the shadow edge,
The vehicle running support apparatus , wherein the shadow edge is a shadow edge of a building . The travel control unit, according to claim 1 which calculates a difference of the slope of a straight line extending in the vehicle traveling direction and the shadow edge extending in a straight line, characterized by correcting the target lateral position according to the difference of the slope The vehicle travel support device according to claim 1.   2. The vehicle travel support apparatus according to claim 1, wherein the travel control unit changes the target lateral position to a position that is spaced apart from the shadow edge by a predetermined distance in the lateral direction and is close to the center of the travel path. Detecting a shadow edge caused by a shadow extending in the vehicle traveling direction from an image of the front of the vehicle,
When the length of the shadow edge is longer than a predetermined value, the vehicle is controlled to travel in a region away from the shadow edge ,
The vehicle running support method , wherein the shadow edge is a shadow edge of a building .

Images