JP5452518B2 - Vehicle white line recognition device - Google Patents

Description

  The present invention relates to a vehicle white line recognition device that recognizes a white line based on an image captured by an in-vehicle camera.

  In recent years, in order to improve the safety of vehicles, driving support devices that actively support driving operations of drivers have been developed. In general, in order to realize a lane departure prevention function or the like, this driving support device recognizes a white line based on a captured image or the like ahead of the host vehicle, and estimates a driving lane or the like based on the recognized white line. . As this type of white line recognition technology, for example, in Patent Document 1, a search is made for each line extending in the horizontal direction on an image obtained by imaging the front of the host vehicle, and a threshold value set for each of the luminance value and the luminance differential value is set. Is disclosed as a lane candidate point (white line candidate point), and a lane (white line) position is detected based on a plurality of white line candidate points detected by the search.

  By the way, when a curve with a large curvature exists far away on the own vehicle travel path, the left and right white lines on the own vehicle travel path may be imaged at positions where distant areas are as close as possible on the image. In such a case, in a distant place on the image, the search areas for the left and right white lines may be superimposed on each other and the white line candidate points may be detected in a mixed state. That is, for example, there is a possibility that a white line candidate point that should be detected as the left side is detected as the right side, or a white line candidate point that should be detected as the right side is detected as the left side. . When white line recognition is performed in a state where the left and right white line candidate points are not accurately separated, a large error may occur in the parameters of the calculated white line shape (curvature, inclination, etc.).

  To cope with this, for example, in Patent Document 2, when the estimated ranges of the left and right lane boundary positions projected on the imaging surface overlap, it is difficult to determine which of the left and right lane boundaries the line segment in the overlapped range is. Therefore, a technique is disclosed in which the edge (white line candidate point) line segment of the part is not adopted as a lane boundary candidate.

JP 2007-264955 A Japanese Patent No. 3288656

  However, if the white line candidate point is deleted as in the technique disclosed in Patent Document 2 described above, for example, in a curve with a large curvature such as a junction of an expressway, the white line is also at a relatively short distance from the vehicle. The candidate points will be rejected, and it may be difficult to realize suitable driving support.

  The present invention has been made in view of the above circumstances, and even in a state where the left and right white line candidate points are mixed at a distance, each candidate point can be correctly separated to the left and right, and the white line can be accurately recognized to the distance. An object of the present invention is to provide a vehicular white line recognition device.

  The white line recognition device for a vehicle according to one aspect of the present invention performs a change in luminance in the vehicle width direction for each search line extending in the horizontal direction within each of the left and right white line detection regions set on an image obtained by imaging the host vehicle travel path. A candidate point detecting means for detecting and detecting edge points whose luminance changes from dark to bright over a predetermined level as white line candidate points, and sequentially determining the continuity of the adjacent white line candidate points for each of the left and right white line detection areas Grouping means for grouping point groups of the white line candidate points that have a predetermined continuity and continue a predetermined number or more, and the white line candidates grouped for each of the left and right white line detection areas Temporary white line approximate line calculation means for calculating a temporary white line approximate line using only points, and candidate point selection areas based on the left and right temporary white line approximate lines are set, and all detected in the left and right white line detection areas The white line of Using candidate point selection means for selecting the white line candidate points existing in the candidate point selection areas from the complement points, and using the white line candidate points selected in the left and right candidate point selection areas, White line approximate line calculating means for calculating each white line approximate line.

  According to the vehicle white line recognition device of the present invention, each candidate point can be correctly separated to the left and right even in a state where the left and right white line candidate points are mixed at a distance, and the white line can be accurately recognized to a distance. .

Schematic configuration diagram of a vehicle driving support device Flow chart showing white line recognition routine Flowchart showing white line candidate point grouping processing subroutine Explanatory drawing which shows typically an example of the captured image of the environment outside the vehicle Explanatory drawing which shows the white line candidate point detected from the image of FIG. Explanatory drawing which shows an example of the change of the brightness | luminance on a search line Explanatory drawing which shows the relationship between the white line on the left and right and the white line detection area on the right side in the distance when the own vehicle travel path is sharp Explanatory drawing which shows the determination method of continuity based on the pixel on a captured image Explanatory drawing which shows an example of the white line candidate point projected on real space Explanatory drawing which shows an example of the grouped white line candidate point Explanatory drawing which shows temporary white line approximate line and candidate point selection area Explanatory drawing which shows the white line approximate line calculated using the selected white line candidate point, and the white line detection area used in the next frame

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. The drawings relate to an embodiment of the present invention, FIG. 1 is a schematic configuration diagram of a vehicle driving support device, FIG. 2 is a flowchart showing a white line recognition routine, and FIG. 3 is a flowchart showing a white line candidate point grouping subroutine. 4 is an explanatory view schematically showing an example of a captured image of the environment outside the vehicle, FIG. 5 is an explanatory view showing white line candidate points detected from the image of FIG. 4, and FIG. 6 shows an example of a change in luminance on the search line. FIG. 7 is an explanatory diagram showing the relationship between the left and right white lines and the right white line detection area in the distance when the vehicle traveling path is sharply curved, and FIG. 8 is a continuity based on pixels on the captured image. FIG. 9 is an explanatory diagram illustrating an example of white line candidate points projected in real space, FIG. 10 is an explanatory diagram illustrating an example of grouped white line candidate points, and FIG. 11 is a provisional white line approximation. Explanatory drawing and figure which show line and candidate point selection area 2 is an explanatory view showing a white detection region for use in white approximate line and the next frame, which is calculated using the white line candidate point selected.

  In FIG. 1, reference numeral 1 denotes a vehicle such as an automobile (own vehicle), and a driving support device 2 is mounted on the vehicle 1. The driving support device 2 includes, for example, a stereo camera 3 and a stereo image recognition device. 4, the control unit 5 and the like are included in the main part.

  The host vehicle 1 is connected to a vehicle speed sensor 11 that detects the host vehicle speed V, a yaw rate sensor 12 that detects the yaw rate γ, a main switch 13 that performs ON / OFF switching of each function of the driving support control, and the like, and a steering wheel. A steering angle sensor 14 that detects the steering angle θst that is opposed to the steering shaft, an accelerator opening sensor 15 that detects an accelerator pedal depression amount (accelerator opening) θacc by the driver, and the like are provided.

  The stereo camera 3 is constituted by a set of CCD cameras using a solid-state imaging device such as a charge coupled device (CCD) as a stereo optical system. These left and right CCD cameras are respectively mounted at a certain distance in front of the ceiling in the vehicle interior, take a stereo image of an object outside the vehicle from different viewpoints, and output image data to the stereo image recognition device 4. In the following description, one image (for example, the right image) of the stereo images is referred to as a reference image, and the other image (for example, the left image) is referred to as a comparative image.

  First, the stereo image recognition device 4 divides the reference image into small areas of 4 × 4 pixels, for example, compares the luminance or color pattern of each small area with the comparison image, finds a corresponding area, and performs the entire reference image. Find the distance distribution over. Further, the stereo image recognition device 4 examines the luminance difference between each pixel on the reference image and an adjacent pixel, extracts those whose luminance difference exceeds a threshold value as an edge point, and extracts the extracted pixel (edge A distance image (a distribution image of edge points having distance information) is generated by giving distance information to (point). Then, the stereo image recognition device 4 performs a well-known grouping process on the generated distance image and compares it with a pre-stored three-dimensional frame (window), so that a white line and a side wall in front of the vehicle Recognize three-dimensional objects.

  Here, the white line to be recognized in the present embodiment is, for example, a single lane line or a multiple line (double line or the like) in which a line of sight guide line is provided inside the lane line, Lines that extend on the road and divide the vehicle lane are collectively referred to, and the form of each line includes a solid line, a broken line, and the like, and further includes a yellow line and the like. In the white line recognition of this embodiment, even if the white line that exists on the road is a double white line or the like, the white line is approximated and recognized by a single straight line or a curved line.

  By the way, the white line laid on the actual road has various variations as described above, and the form of the white line changes with the branching or merging of the traveling road. In addition, there are various noises such as road surface repair marks, water pools and snow on the road. Therefore, it is difficult to accurately recognize the white line in all scenes by uniform processing. Therefore, the stereo image recognition device 4 complementarily performs white line recognition using various methods without relying only on white line recognition using pattern matching based on the distance image as described above, and comprehensively recognizes these recognition results. Judgment to recognize the final white line.

  As one of such white line recognition, the stereo image recognition device 4 recognizes left and right white lines based on a change in luminance in the horizontal direction on one image (for example, a reference image shown in FIG. 4) taken in front of the host vehicle. I do. More specifically, for example, as shown in FIG. 5, the stereo image recognition device 4 sets left and right white line detection areas A (Al, Ar) on the image, and horizontally in each white line detection area A. For a plurality of search lines 1 extending, a change in luminance is examined from the inside to the outside in the vehicle width direction for each search line l. Then, the stereo image recognition device 4 detects, as white line candidate points Pd (Pdl, Pdr), on the respective search lines 1 in the respective white line detection areas A, the first edge points whose luminance changes from dark to bright by a predetermined amount or more. To do.

  Here, when a curve with a large curvature exists in the distance on the vehicle traveling road, the left and right white line detection areas Al and Ar are superimposed on the image. For example, as shown in FIG. In the illustrated example, the right and left white lines may be included in the right white line detection area Al). In such a case, when the luminance change from the inner side to the outer side in the vehicle width direction is examined as in this embodiment, the edge point of the other white line may be erroneously detected as the white line candidate point Pd of one white line. . Accordingly, the stereo image recognition device 4 has white line candidate points P (Pl, Pr) that truly indicate the left and right white lines, respectively, among the white line candidate points Pdl, Pdr detected in the left and right white line detection areas Al, Ar. ) And a white line approximate line L is calculated based on the selected white line candidate point P.

  More specifically, the stereo image recognition device 4 sequentially determines the continuity of adjacent white line candidate points Pd from the front side (vehicle side) to the far side for each of the left and right white line detection areas A. To do. Then, when there are point groups of white line candidate points Pd having a preset continuity and continuing for a set number or more, the stereo image recognition device 4 groups the point groups as a first group, and continuously When the number of white line candidate points Pd having the characteristic is less than the set number, the point group is grouped as a second group (see FIG. 10). Here, in the present embodiment, when the white line candidate points Pd are grouped, the stereo image recognition device 4 projects each white line candidate point Pd onto the real space based on the distance information on the distance image (FIG. 9). Then, the stereo image recognition device 4 is based on, for example, an error amount in pixel units between the adjacent white line candidate points Pd on the captured image and an error amount of the distance between the adjacent white line candidate points Pd in the real space. Thus, the continuity between the white line candidate points Pd is comprehensively determined.

  When the grouping process for all white line candidate points Pd is performed, the stereo image recognition device 4 uses only the white line candidate points Pd grouped as the first group for each of the left and right white line detection areas A. The white line approximate line (temporary white line approximate line) Lt (Ltl, Ltr) is calculated (see FIG. 11). That is, since each white line candidate point Pd grouped as the first group has a predetermined continuity, it is highly reliable to indicate the left and right white lines, respectively. Therefore, the stereo image recognition device 4 calculates the provisional white line approximate line Lt using only these highly reliable white line candidate points, thereby obtaining a rough shape of the white line that does not greatly deviate from the actual white line shape. To grasp.

  Then, the stereo image recognition device 4 sets each candidate point selection area As (Asl, Asr) with reference to the left and right provisional white line approximate lines Lt, respectively, and detects all within the left and right white line detection areas Al and Ar. White line candidate points Pd existing in each candidate point selection region As are selected as final white line candidate points P (Pl, Pr) for the left and right white lines.

  Then, the stereo image recognition device 4 calculates the final left and right white line approximate lines L (Ll, Lr) using the white line candidate points P selected in the left and right candidate point selection regions As and performs the calculation. Based on each white line approximate line L, a white line detection area A in the next frame is set (see FIG. 12).

  As described above, in this embodiment, the stereo image recognition device 4 realizes functions as candidate point detection means, grouping means, provisional white line approximate line calculation means, candidate point selection means, and white line approximate line calculation means. To do.

  Note that the stereo image recognition device 4 can perform white line recognition by various other methods. Then, for example, the stereo image recognition apparatus 4 has a relationship between an approximate line of a white line recognized in each white line recognition and a white line candidate point such as an edge point used for the recognition (for example, dispersion of white line candidate points with respect to the approximate line, etc.) ) Is selected from the recognized approximate lines, and the approximate line is output to the control unit 5 as the final approximate line of the white line.

  The control unit 5 receives driving environment information in front of the host vehicle 1 recognized by the stereo image recognition device 4. Further, the vehicle speed V from the vehicle speed sensor 11, the yaw rate γ from the yaw rate sensor 12, and the like are input to the control unit 5 as travel information of the host vehicle 1, and operation input information by the driver from the main switch 13. An operation signal, a steering angle θst from the steering angle sensor 14, an accelerator opening θacc from the accelerator opening sensor 15, and the like are input.

  For example, when an execution of an ACC (Adaptive Cruise Control) function which is one of the functions of the driving support control is instructed through the operation of the main switch 13 by the driver, the control unit 5 recognizes the stereo image recognition device 4. The direction of the preceding vehicle is read, and it is identified whether or not the preceding vehicle to be followed is traveling on the own vehicle traveling path.

  As a result, when the preceding vehicle to be tracked is not detected, the constant speed traveling control for maintaining the vehicle speed V of the host vehicle 1 at the set vehicle speed set by the driver through the opening / closing control (engine output control) of the throttle valve 16. Execute.

  On the other hand, when a preceding vehicle that is a tracking target vehicle is detected and the vehicle speed of the preceding vehicle is equal to or lower than the set vehicle speed, the following traveling control is performed in which the following distance is converged to the target inter-vehicle distance. Executed. During this follow-up running control, the control unit 5 basically converges the inter-vehicle distance to the target inter-vehicle distance through the opening / closing control of the throttle valve 16 (engine output control). Furthermore, when it is determined that sufficient deceleration cannot be obtained only by controlling the throttle valve 16 due to sudden deceleration of the preceding vehicle, the control unit 5 controls the output hydraulic pressure from the active booster 17 (automatic braking intervention). Control) to converge the inter-vehicle distance to the target inter-vehicle distance.

  Further, when execution of the lane departure prevention function, which is one of the functions of the driving support control, is instructed through the operation of the main switch 13 by the driver, the control unit 5 will, for example, the left and right white lines that define the own vehicle traveling lane. A warning determination line is set based on (approximate white line recognized by the stereo image recognition device 4), and the own vehicle traveling path is estimated based on the vehicle speed V and the yaw rate γ of the own vehicle 1. Then, for example, when the control unit 5 determines that the host vehicle travel route crosses either the left or right alarm determination line within a set distance (for example, 10 to 16 [m]) ahead of the host vehicle, It is determined that the host vehicle 1 is likely to depart from the current host vehicle lane, and a lane departure warning is issued.

  Next, white line recognition based on the luminance change on the reference image, which is executed in the stereo image recognition device 4, will be described with reference to the white line recognition routine shown in FIG. In this routine, the same processing is performed separately for the left and right white line detection areas Al and Ar. However, to simplify the description, unless otherwise required in the following description. For example, the white line detection areas Al and Ar are collectively referred to as the white line detection area A, and the subscripts “l” and “r” indicating the left and right attributes are omitted as appropriate.

  When this routine starts, the stereo image recognition device 4 first detects a white line candidate point Pd for each search line l in the white line detection area A set in the process of step S107 for the image of the previous frame in step S101. I do. Specifically, for example, as illustrated in FIG. 6, the stereo image recognition device 4 performs edge detection on each search line l from the inner side to the outer side in the vehicle width direction, and detects pixels on the outer side in the vehicle width direction. A point (edge point) in which the luminance is relatively high with respect to the luminance of the inner pixel and the differential value of the luminance indicating the amount of change is equal to or greater than the set threshold on the plus side is detected. Then, the stereo image recognition device 4 extracts the edge point first detected as the white line candidate point Pd on each search line l in the white line detection area A (see FIGS. 5 and 7). In FIGS. 5 and 7, the search line l, the white line candidate point Pd, and the like are thinned out and displayed in a predetermined manner in order to simplify the description.

  In subsequent step S102, the stereo image recognition device 4 uses each white line candidate point Pd detected in step S101 as the distance information of the corresponding pixel on the distance image and the pixel position of the horizontal method of the corresponding pixel on the reference image. Based on the above, the image is projected onto the real space (see FIG. 9).

  Then, when the process proceeds from step S102 to step S103, the stereo image recognition device 4 performs a white line candidate point Pd grouping process for each white line candidate point Pd detected in the left and right white line detection areas Al.

  This grouping processing is performed, for example, according to a white line candidate point grouping processing subroutine shown in FIG. When the subroutine starts, the stereo image recognition device 4 first extracts and extracts the white line candidate point Pd positioned closest to the own vehicle 1 among the white line candidate points Pd that are not currently grouped in step S201. A new group is created in which the white line candidate point Pd is incorporated as the first white line candidate point Pd.

  Then, when the process proceeds from step S201 to step S202, the stereo image recognition apparatus 4 has a white line candidate point (next white line candidate point) Pd farther than the last white line candidate point Pd incorporated in the current group. Investigate whether or not to do.

If it is determined in step S202 that the next white line candidate point Pd exists, the stereo image recognition device 4 proceeds to step S203, and sets the next white line candidate point Pd as the white line candidate point Pd (n) of interest. The pixel-based error determination is performed by comparison with the white line candidate point Pd. That is, for example, as shown in FIG. 8, the stereo image recognizing device 4 has a horizontal direction on the image of the white line candidate point Pd (n) of interest and the previous white line candidate point Pd (n−1) ( The pixel shift amount (horizontal error Δi and vertical error Δj) in the i direction) and vertical direction (j direction) is calculated. Further, the stereo image recognition device 4 has a horizontal error Δi_old on the image of the previous white line candidate point Pd (n−1) and the previous white line candidate point Pd (n−2), and vertical. The direction error Δj_old is calculated, and the horizontal direction error change amount Δs is calculated using the following equation (1).
Δs = (Δi / Δj) − (Δi_old / Δj_old) (1)
Then, when all of the horizontal direction error Δi, the vertical direction error Δj, and the horizontal direction error change amount Δs are within a preset threshold, the stereo image recognition device 4 has one white line candidate point Pd (n). It is determined that the preceding white line candidate point Pd (n−1) has continuity on the image. On the other hand, when at least one of the horizontal direction error Δi, the vertical direction error Δj, and the horizontal direction error change amount Δs is not within a preset threshold, the white line candidate point Pd (n) is the previous white line candidate. It is determined that there is no continuity on the image with respect to the point Pd (n−1).

  When the process proceeds from step S203 to step S204, the stereo image recognition device 4 performs error determination based on the distance between the white line candidate point Pd (n) of interest and the previous white line candidate point Pd. That is, the stereo image recognition device 4 uses the horizontal direction (X direction) and the vertical direction (Z direction) in the real space between the target white line candidate point Pd (n) and the previous white line candidate point Pd (n−1). ) Distance deviation (horizontal distance error ΔX and vertical distance error ΔZ).

  Then, when all of the horizontal direction distance error ΔX and the vertical direction distance error ΔZ are within a preset threshold, the stereo image recognition device 4 determines that the white line candidate point Pd (n) is the previous white line candidate point. It is determined that Pd (n−1) has continuity on the real space distance. On the other hand, when at least one of the horizontal direction distance error ΔX and the vertical direction distance error ΔZ is not within a preset threshold, the white line candidate point Pd (n) is the previous white line candidate point Pd (n− In contrast to 1), it is determined that there is no continuity on the real space distance.

  When the process proceeds from step S204 to step S205, the stereo image recognition device 4 determines whether the white line candidate point Pd (n) to be noticed is in the error determination based on the pixel in step S203 and the error determination based on the distance in step S204. It is checked whether or not it is determined that the previous white line candidate point Pd (n−1) has continuity.

  If the white line candidate point Pd (n) is determined not to be continuous with the white line candidate point Pd (n−1) in at least one of step S203 and step S204, the stereo image recognition device 4 The process advances from step S205 to step S206 without incorporating the current white line candidate point Pd (n) of interest into the current group, and after classifying the current group as either the first group or the second group, step S201 is performed. Return to. That is, in step S206, when the number of white line candidate points Pd belonging to the current group is equal to or greater than a preset threshold value, the stereo image recognition device 4 recognizes each white line candidate point Pd as a current recognition target. It is determined that there is a high possibility that the vehicle 1 shows the white line on the right side of the own vehicle 1 or the white line on the left side, and the group is classified into the first group. On the other hand, when the number of white line candidate points Pd belonging to the current group is less than a preset threshold value, each white line candidate point Pd is not sufficient to determine that it indicates a white line currently focused on as a recognition target. It is determined that there is a group, and the group is classified into the second group (see FIG. 10).

  On the other hand, if the white line candidate point Pd (n) is determined to be continuous with the white line candidate point Pd (n−1) in both step S203 and step S204, the stereo image recognition device 4 After taking the noticed white line candidate point Pd (n) into the current group, the process returns from step S205 to step S202.

  If it is determined in step S202 that the next white line candidate point Pd does not exist, the stereo image recognition device 4 proceeds to step S207, and performs the same process as in step S206 described above to change the current group to the first group or After classification into any of the second group, the subroutine is exited.

In the main routine of FIG. 2, when the process proceeds from step S103 to step S104, the stereo image recognition device 4 applies only the white line candidate point Pd grouped as the first group in step S103 for each left and right white line detection region A. Then, a temporary white line approximate line Lt is calculated (see FIG. 11). Here, the provisional white line approximate line Lt of the present embodiment is the distance in the horizontal direction of the white line depending on the parameters a, b, and c with respect to the vertical Z distance to the vehicle 1 as shown in the following equation (2). X is identified.
X = aZ ² + bZ + c (2)
Here, the parameters a, b, and c of the provisional white line approximate line Lt shown in the equation (2) can be obtained by, for example, the least square method using the white line candidate points Pd belonging to the first group, The parameters a, b, and c are determined to values that minimize the variance of each white line candidate point Pd with respect to the provisional white line approximate line Lt. In the equation (2), for the sake of convenience, the parameters are represented by the left and right common symbols a, b, and c, but these are set individually for the left and right provisional white line approximate lines Ltl and Ltr. Needless to say.

In subsequent step S105, the stereo image recognition device 4 selects a final white line candidate point Pd for each of the left and right white lines based on the temporary approximate curve Lt calculated in step S104. That is, the stereo image recognition device 4 offsets the provisional white line approximate line Lt obtained in step S104 by ΔE to the inside and the outside in the vehicle width direction, respectively, so that the candidates defined by the following expressions (3) and (4) A point selection area As is set (see FIG. 11).
X1 = aZ ² + bZ + c−ΔE (3)
X2 = aZ ² + bZ + c + ΔE (4)
The stereo image recognition device 4 then selects the white line candidate points Pdl present in the left candidate point selection area Asl from among all the white line candidate points Pdl, Pdr detected in the left and right white line detection areas Al, Ar. Pdr is selected as the final white line candidate point Pl for the left white line, and the white line candidate points Pdl and Pdr existing in the right candidate point selection area Asr are the final white line candidate points for the right white line. Select as Pr (see FIG. 12).

In subsequent step S106, the stereo image recognition device 4 calculates the left and right white line approximate lines L using the white line candidate points P selected in the left and right candidate point selection regions As (see FIG. 12). Here, the white line approximate line L of the present embodiment is similar to the provisional white line approximate line Lt described above, with respect to the vertical Z distance with respect to the vehicle 1, as shown in the following equation (5). The vehicle horizontal direction distance X of the white line is identified by each parameter.
X = AZ ² + BZ + C (5)
Here, the parameters A, B, and C of the provisional white line approximate line Lt shown in the equation (2) can be obtained by, for example, the least square method using the final white line candidate point P. B and C are determined to be values that minimize the variance of each white line candidate point P with respect to the white line approximate line L. In the equation (5), for the sake of convenience, the parameters are represented by common symbols A, B, and C on the left and right, but these are set individually for the left and right provisional white line approximate lines Ltl and Ltr. Needless to say.

In step S107, the stereo image recognition device 4 offsets the white line approximate line L calculated in step S106 by ΔE to the inside and the outside in the vehicle width direction, so that the following equations (6) and (7) After setting the white line detection area A in the next frame defined by the equation (see FIG. 12), the routine is exited.
X1 = AZ ² + BZ + C−ΔE (6)
X2 = AZ ² + BZ + C + ΔE (7)
According to such an embodiment, the continuity of the white line candidate points Pd adjacent to each other is sequentially determined for each of the left and right white line detection areas A, and the white line candidates having a predetermined continuity and continuing for a predetermined number or more. A point group of points is grouped as a first group, and by calculating the provisional white line approximate line Lt using only the grouped white line candidate points, white line candidates that are highly reliable as indicating the left and right white lines respectively. By using only the point Pd, it is possible to grasp a white line shape that does not greatly deviate from the actual white line shape. Then, candidate point selection areas As are set with reference to the left and right temporary white line approximate lines Lt, respectively, and within each candidate point selection area As among all the white line candidate points Pd detected in the left and right white line detection areas A. By selecting the existing white line candidate points Pd as the final white line candidate points P, even when the left and right white line candidate points Pd are detected in a mixed manner, they can be separated with high accuracy. Then, by calculating the white line approximate line L based on the white line candidate points P separated right and left with high accuracy in this way, the white line can be accurately recognized far away even when there is a curve ahead of the host vehicle travel path. be able to.

  At this time, the determination of continuity is sequentially performed from the near side to the far side of the own vehicle 1 with high detection accuracy of the white line candidate point Pd, whereby an accurate determination result can be obtained.

  In the above-described embodiment, an example in which the distance information of each pixel is calculated using a stereo camera has been described. However, the present invention is not limited to this, and for example, the vehicle traveling road is a flat road. It is also possible to calculate the distance information of each white line candidate point from an image captured by a monocular camera.

1 ... Vehicle (own vehicle)
2 ... Driving support device 3 ... Stereo camera 4 ... Stereo image recognition device (candidate point detecting means, grouping means, provisional white line approximate line calculating means, candidate point selecting means, white line approximate line calculating means)
DESCRIPTION OF SYMBOLS 5 ... Control unit 11 ... Vehicle speed sensor 12 ... Yaw rate sensor 13 ... Main switch 14 ... Steering angle sensor 15 ... Accelerator opening sensor 16 ... Throttle valve 17 ... Active booster

Claims (1)

An edge where the luminance changes in the vehicle width direction for each search line extending in the horizontal direction within each of the left and right white line detection areas set on the image obtained by capturing the vehicle's driving path, and the luminance changes from dark to bright over a predetermined level. Candidate point detecting means for detecting each point as a white line candidate point;
For each of the white line detection areas on the left and right, the continuity of the white line candidate points adjacent to each other is sequentially judged, and the point groups of the white line candidate points having a predetermined continuity and continuing for a predetermined number or more are grouped respectively. Grouping means to
Temporary white line approximate line calculating means for calculating a temporary white line approximate line based on the grouped white line candidate points for each of the left and right white line detection areas;
Candidate point selection areas based on the left and right provisional white line approximate lines are respectively set, and the white line candidate points existing in the candidate point selection areas from the white line candidate points detected in the left and right white line detection areas Candidate point selection means for selecting each,
A white line recognition device for a vehicle, comprising: white line approximate line calculating means for calculating left and right white line approximate lines using the white line candidate points selected in the left and right candidate point selection regions.

Images