JP2019133445A - Section line detection device, section line detection system, and section line detection method - Google Patents

Abstract

To provide a section line detection technology capable of reducing such a situation that a detected section line becomes unfollowable.SOLUTION: A section line detection device comprises: a detection part for detecting first and second section lines from a camera photographic image; an endpoint coordinate calculation part for calculating first and second endpoint coordinates corresponding to vehicle side ends of the first and second section lines; a storage part for storing the first and second endpoint coordinates calculated by the endpoint coordinate calculation part; and a correction part for correcting the first and second endpoint coordinates stored by the storage part on the basis of an estimated moving amount of the vehicle from the previous detection time. The detection part sets a first endpoint coordinate region including the first endpoint coordinates and a second endpoint region including the second endpoint coordinates on the basis of the first and second endpoint coordinates corrected by the correction part.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a technique for detecting a marking line indicating a parking section.

  In order to reduce the calculation load, the parking assistance device proposed in Patent Literature 1 sets an area estimated to have a lane marking as a region of interest and executes image recognition processing. When a lane line is detected, the parking assistance device proposed in Patent Document 1 recognizes and sets the parking area based on the detected lane line. After the setting of the parking area, the parking assistance device proposed in Patent Document 1 further reduces the detection of the lane line and the recognition process of the parking area by further narrowing down the attention area.

JP 2008-296697 A

  In Patent Document 1, there is no specific disclosure regarding how to further narrow down the attention area when further narrowing down the attention area after setting the parking area. For this reason, when the attention area is further narrowed down after the parking section is set, the attention area cannot be set to an appropriate position, and the detected section line may not be tracked.

  In view of the above problems, an object of the present invention is to provide a lane marking detection technique capable of reducing the inability to follow a detected lane marking.

  The lane marking detection apparatus according to the present invention includes a detection unit that detects a first lane line and a second lane line from a captured image obtained by a camera that captures the periphery of a vehicle, and the first lane line. An end point coordinate calculating unit that calculates a first end point coordinate corresponding to an end on the vehicle side and a second end point coordinate corresponding to the end on the vehicle side of the second lane marking; and the end point coordinate calculating unit A storage unit that stores the first end point coordinates and the second end point coordinates calculated by the above, and a first detection of the first end point coordinates and the second end point coordinates stored by the storage unit. A correction unit that corrects based on the estimated amount of movement of the vehicle from, the detection unit based on the first end point coordinates and the second end point coordinates corrected by the correction unit, A first end point coordinate area including a first end point coordinate and the second end point coordinate region; A configuration (first configuration) for setting the second end point coordinate region including the point coordinates.

  Further, in the lane marking detection device having the first configuration, a target parking position is calculated based on a traveling direction detection unit that detects a traveling direction of the vehicle, the first lane line, and the second lane line. A position calculation unit that performs the rotation of the vehicle in a turning direction, the detection unit is based on the first end point coordinates and the second end point coordinates corrected by the correction unit. When the first end point coordinate area including the first end point coordinates and the second end point coordinate area including the second end point coordinates are set and the traveling direction of the vehicle is straight, the correction unit Corrects the target parking position based on the estimated movement amount of the vehicle from the previous detection, and the detection unit calculates the first end point coordinates and the target parking position from the target parking position corrected by the correction unit. Before calculating the second endpoint coordinates A configuration in which a first endpoint coordinate area including the first endpoint coordinates and a second endpoint coordinate area including the second endpoint coordinates are set based on the first endpoint coordinates and the second endpoint coordinates. (2nd structure) may be sufficient.

  Further, in the lane marking detection device of the second configuration, the traveling direction detection unit determines that the vehicle is turning when the steering angle integrated amount of the vehicle is larger than a threshold, and the steering angle of the vehicle A configuration (third configuration) that determines that the vehicle is traveling straight when the integrated amount is equal to or less than a threshold value may be employed.

  In the lane marking detection device having any one of the first to third configurations, the target parking is performed based on a vehicle control unit that controls parking of the vehicle, the first lane line, and the second lane line. A position calculation unit that calculates a position, wherein the vehicle control unit controls the vehicle to the target parking position based on the first end point coordinates and the second end point coordinates (fourth point) Configuration).

  Further, in the lane marking detection device having any one of the first to fourth configurations, a position calculation unit that calculates a target parking position based on the first lane line and the second lane line, an update unit, The update unit is calculated based on the captured image when the detection unit detects a first new lane line at a position straddling the first lane line from the target parking position. If the value obtained by subtracting the reliability of the first lane marking calculated based on the captured image from the reliability of the first new lane marking is equal to or less than a first predetermined value, the first A configuration (fifth configuration) in which the lane line is not updated to the first new lane line may be employed.

  A lane marking detection system according to the present invention has a configuration (sixth configuration) including a camera that captures the periphery of a vehicle and the lane marking detection device having any one of the first to fifth configurations.

  The lane marking detection method according to the present invention includes a detection step of detecting a first lane line and a second lane line from a captured image obtained by a camera that images the periphery of a vehicle, and the first lane line An end point coordinate calculating step for calculating a first end point coordinate corresponding to the end portion on the vehicle side and a second end point coordinate corresponding to the end portion on the vehicle side of the second lane marking; and the end point coordinate calculating step Storing the first end point coordinates and the second end point coordinates calculated by the step, and the first end point coordinates and the second end point coordinates stored by the storing step at the time of previous detection. A correction step of correcting based on the estimated amount of movement of the vehicle from, wherein the detection step is based on the first end point coordinates and the second end point coordinates corrected by the correction step, First endpoint coordinates including first endpoint coordinates It is configured to set the second end point coordinate region including the the band second end point coordinates (seventh configuration).

  According to the lane marking detection technique of the present invention, the calculation error can be limited only to the error due to the estimated movement amount of the vehicle from the previous detection time, so the first endpoint coordinate area including the first endpoint coordinates And the second end point coordinate area including the second end point coordinates can be reduced from being shifted from the correct position. Therefore, it is possible to reduce the inability to follow the detected marking line.

The figure which shows the structural example of a lane marking detection apparatus Top view of parking area Flowchart showing an operation example of the lane marking detection ECU Flow chart showing calculation procedure of target parking position A top view showing the relationship between the first and second end point coordinates and the candidate coordinates of the target parking position The flowchart which shows the other operation example of lane marking detection ECU The figure which shows the other structural example of a lane marking detection apparatus Flow chart showing calculation procedure of first and second end point coordinates

  Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the drawings. In the following description, the direction in which the vehicle travels straight and is directed from the driver's seat to the steering is referred to as “front direction”. Further, the direction in which the vehicle travels straight and is directed from the steering to the driver's seat is referred to as “rearward direction”. Also, the direction from the right side to the left side of the driver who faces the forward direction and is the direction perpendicular to the straight traveling direction of the vehicle and the vertical line is referred to as “left direction”. Further, the direction from the left side to the right side of the driver who faces the forward direction and is the direction perpendicular to the straight traveling direction of the vehicle and the vertical line is referred to as “right direction”.

  In the present embodiment, a coordinate system (world coordinate system) having a specific point of the vehicle on which the lane marking detection device is mounted as an origin is used. The specific point of the vehicle is a point that is separated from the front end of the vehicle by an effective length (the length obtained by subtracting the rear overhang from the full length of the vehicle) and is the center in the left-right direction of the vehicle. The front-rear direction of the vehicle is the Z-axis direction (the rear direction is the positive direction of the Z-axis), and the left-right direction of the vehicle is the X-axis direction (the left direction is the positive direction of the X-axis).

<1. Configuration of lane marking detector>
FIG. 1 is a diagram illustrating a configuration example of a lane marking detection apparatus. In the present embodiment, the lane marking detection device includes a lane marking detection ECU (Electric Control Unit) 1 and a vehicle control ECU 3. The lane marking detection ECU 1 is connected to the imaging unit 2 and is connected to the vehicle control ECU 3 and the like via an in-vehicle network 4 such as a CAN (Controller Area Network). The lane marking detection system includes the lane marking detection ECU 1, the imaging unit 2, and the vehicle control ECU 3. Unlike the present embodiment, the lane marking detection device does not include the vehicle control ECU 3 and may not have a function of controlling the parking of the vehicle. Further, unlike the present embodiment, the lane marking detection ECU 1 and the vehicle control ECU 3 may be integrated into one ECU instead of separate ECUs.

  The photographing unit 2 includes three cameras 21 to 23. The camera 21 is provided at the rear end of the vehicle. For this reason, the camera 21 is also referred to as a back camera 21. The optical axis of the back camera 21 is along the front-rear direction of the vehicle when viewed from above. The back camera 21 captures the rear direction of the vehicle. The mounting position of the back camera 21 is preferably the left and right center of the vehicle, but may be slightly shifted from the left and right center in the left and right direction.

  The camera 22 is provided on the left door mirror of the vehicle. For this reason, the camera 22 is also referred to as a left side camera 22. When the vehicle is a so-called door mirrorless vehicle, the left side camera 22 is attached to the periphery of the rotation shaft (hinge portion) of the left side door without a door mirror. The optical axis of the left side camera 22 is along the left-right direction of the vehicle when viewed from above. The left side camera 22 captures the left direction of the vehicle. The camera 23 is provided on the right door mirror of the vehicle. For this reason, the camera 23 is also referred to as a right side camera 23. When the vehicle is a so-called door mirrorless vehicle, the right side camera 23 is attached to the periphery of the rotation shaft (hinge portion) of the right side door without a door mirror. The optical axis of the right side camera 23 is along the left-right direction of the vehicle when viewed from above. The right side camera 23 captures the right direction of the vehicle.

  In the present embodiment, the lane line detection ECU 1 acquires the captured images of the cameras 21 to 23, but the lane line detection ECU 1 excludes the left side camera 22 and the right side camera 23 from the imaging unit 2 and only the captured image of the back camera 21. You may make it the structure which acquires.

  The lane marking detection ECU 1 includes a video acquisition unit 10, a detection unit 11, an end point coordinate calculation unit 12, a storage unit 13, a correction unit 14, a position calculation unit 15, and an update unit 16. The lane marking detection ECU 1 can be configured by, for example, a control unit and a nonvolatile storage unit. The control unit is a computer including a CPU (Central Processing Unit), a RAM (Random Access Memory), and a ROM (Read Only Memory). The non-volatile storage unit stores a computer program and data necessary for the lane marking detection ECU 1 to operate as the image acquisition unit 10, the detection unit 11, the position calculation unit 15, the update unit 16, and the end point coordinate calculation unit 12 in a non-volatile manner. Remember. As the nonvolatile storage unit, for example, an EEPROM, a flash memory, or the like can be used.

  The video acquisition unit 10 acquires analog or digital captured images from each of the cameras 21 to 23 continuously in a predetermined cycle (for example, 1/30 second cycle). Then, when the acquired temporally continuous captured images (acquired video) are analog, the video acquisition unit 10 converts the analog captured image into a digital captured image (A / D conversion).

  The detection unit 11 detects the first lane line and the second lane line indicating the parking lot from the captured image output from the video acquisition unit 10 using image processing such as edge extraction. The first lane line and the second lane line are drawn with white lines on the road surface of the parking lot. In the top views of the parking sections illustrated in FIGS. 2A to 2D, ideally, the portion surrounded by the gray dotted line D1 is detected as the first partition line and is surrounded by the gray dotted line D2. A portion is detected as the second lane marking.

  In the first detection, the detection unit 11 sets the entire area of the captured image as a region of interest (a range in which a lane line can be detected), and corresponds to the vehicle-side end of the first lane line in the second and subsequent detections. The region of interest is set based on the first end point coordinates and the second end point coordinates corresponding to the end of the second lane marking on the vehicle side. Thereby, the detection part 11 can track and detect the 1st division line and the 2nd division line in the detection after the 2nd time.

  The detection unit 11 uses the first end point coordinate corresponding to the end of the first lane line on the vehicle side as a reference, and detects the first new lane line detection range (for example, the first end point coordinate as the center). And a second new lane marking detection range (for example, the second endpoint) with reference to the second endpoint coordinates corresponding to the end of the second lane marking on the vehicle side. A square area of a predetermined size centered on the coordinates) is set. In this way, by reducing the detection range of the first new lane line and the detection range of the second new lane line, false detection of the first new lane line and the first new lane line is reduced. can do.

  The end point coordinate calculation unit 12 calculates a first end point coordinate corresponding to the vehicle-side end of the first lane marking and a second end point coordinate corresponding to the vehicle-side end of the second lane marking.

  The storage unit 13 has a first end point coordinate corresponding to the end on the vehicle side of the first lane marking calculated by the end point coordinate calculation unit 12 and a second end corresponding to the end on the vehicle side of the second lane marking. The end point coordinates of are stored.

  The correction unit 14 has a first end point coordinate corresponding to the end of the first lane marking stored in the storage unit 13 on the vehicle side and a second end corresponding to the end of the second lane marking on the vehicle side. The end point coordinates are corrected based on the estimated movement amount of the vehicle from the previous detection performed by the detection unit 11.

  The position calculation unit 15 performs target parking based on the first end point coordinates corresponding to the end of the first lane marking on the vehicle side and the second end point coordinates corresponding to the end of the second lane marking on the vehicle side. Calculate the position. When the first dividing line is detected as a line having a width, for example, the center position in the width direction of the end portion on the vehicle side may be set as the first end point coordinate. Similarly, when the second division line is detected as a line having a width, for example, the center position in the width direction of the end portion on the vehicle side may be set as the second end point coordinate.

  When the detection unit 11 detects the first new lane line, the update unit 16 updates the first lane line to the first new lane line if the predetermined condition is satisfied. When two new lane markings are detected, the second lane marking is updated to the second new lane marking if a predetermined condition is satisfied.

  The vehicle control ECU 3 controls, for example, the direction and speed of the vehicle according to the operation by the driver, and controls the direction of the vehicle, for example, according to information sent from the lane marking detection ECU 1 via the in-vehicle network 4.

  The position calculation unit 15 of the lane marking detection ECU 1 has a function of outputting information related to the target parking position to the vehicle control ECU 3. In the present embodiment, the position calculation unit 15 outputs the coordinates of the target parking position to the vehicle control ECU 3. Thereby, for example, when the vehicle is moved to the parking section, the vehicle control ECU 3 can automatically control the direction of the vehicle (the steering angle) and the amount of movement of the vehicle. That is, the vehicle control ECU 3 can control parking of the vehicle. Specifically, the vehicle control ECU 3 sets the first end point coordinates corresponding to the end of the first lane marking on the vehicle side and the second end point coordinates corresponding to the end of the second lane marking on the vehicle side. Based on this, the vehicle can be controlled to the target parking position. As a result, the vehicle is parked in the parking space between the first lane line and the second lane line without protruding outside the first lane line or outside the second lane line. it can. The control signal generated when the vehicle control ECU 3 controls the vehicle to the target parking position is an acceleration parameter corresponding to an accelerator pedal operation amount that is variable according to the driver's driving operation during manual driving, and the driver during manual driving. This corresponds to the deceleration parameter corresponding to the brake pedal operation amount that is variable according to the driving operation, the steering angle parameter that corresponds to the steering operation amount that is variable according to the driver operation during manual operation, and the vehicle shift lever operation content by the driver Includes shift parameters.

<2. Operation of lane marking detector>
FIG. 3 is a flowchart showing an operation example of the lane marking detection ECU 1 which is an example of the lane marking detection device. When the operation start event of the lane marking detection ECU 1 occurs, the lane marking detection ECU 1 starts the operation of the flowchart shown in FIG. As an operation start event of the lane marking detection ECU 1, for example, the position of the shift lever of the vehicle is switched to the reverse range. Note that the photographing unit 2 also starts to operate simultaneously with the start of the operation of the lane marking detection ECU 1.

  First, the detection unit 11 tries to detect the first lane marking and the second lane marking with the entire region of the captured image as the region of interest (step S10).

  When the first lane line and the second lane line are detected, the end point coordinate calculation unit 12 has the first end point coordinates corresponding to the end of the first lane line on the vehicle side and the second lane line vehicle. The second end point coordinate corresponding to the side end is calculated (step S20), and the storage unit 13 stores the calculation result (step S30).

  In step S40 following step S30, the position calculation unit 15 uses the first end point coordinates corresponding to the end of the first lane line calculated by the end point coordinate calculation unit 12 and the vehicle of the second lane line. The target parking position is calculated based on the second end point coordinates corresponding to the side end. The specific processing content of step S40 will be described with reference to the flowchart shown in FIG. 4 and the top view shown in FIG.

  First, the position calculation unit 15 calculates a first coordinate A1 that is away from the first end point coordinate EP1 by an effective length L0 (a length obtained by subtracting the rear overhang from the total length of the vehicle) toward the opposite side of the vehicle. (Step S40_1). Next, the position calculation unit 15 calculates a second coordinate A2 that is separated from the second end point coordinate EP2 by an effective length L0 toward the opposite side of the vehicle (step S40_2).

  Next, the position calculation unit 15 calculates the first end point coordinate EP1 and the second lane line in the direction perpendicular to the longitudinal direction of the first lane line from the first coordinate A1 toward the second lane line. A third coordinate A3, which is half the distance W, is calculated, and the distance of the distance W from the first coordinate A1 toward the opposite side of the second lane line in the direction perpendicular to the longitudinal direction of the first lane line is calculated. A fourth coordinate A4 that is half apart is calculated (step S40_3). Furthermore, the position calculation unit 15 calculates a fifth coordinate A5 that is half the distance W from the second coordinate A2 toward the first lane line in the direction perpendicular to the longitudinal direction of the second lane line. Then, a sixth coordinate A6 that is half the distance W from the second coordinate A2 toward the opposite side of the first lane line in a direction perpendicular to the direction of the second lane line is calculated (step S40_4). ).

  And the position calculation part 15 selects two coordinates from which the distance between two points becomes the minimum among the third coordinates A3 to the sixth coordinates A6 (step S40_5), and is close to the vehicle among the selected two coordinates. The coordinate of the target (position with the smaller distance from the origin) is set as the coordinate of the target parking position (step S40_6), and the calculation processing of the coordinate of the target parking position is ended.

  By the processing of the flowchart shown in FIG. 4, the coordinates of the target parking position are moved by the effective length L0 from the end of the first lane line and the second lane line on the vehicle side (the entrance to the parking area) in the depth direction of the parking area. And a position that is the center of the first and second lane markings.

  Returning to FIG. 3, the operation after the calculation processing of the coordinates of the target parking position is completed will be described. In step S50 subsequent to step S40, the correction unit 12 has the first end point coordinates corresponding to the vehicle side end of the first lane marking stored in the storage unit 13 and the vehicle side of the second lane marking. The second end point coordinate corresponding to the end is corrected based on the estimated movement amount of the vehicle. Specifically, the end point coordinate calculation unit 12 has passed a predetermined time (for example, several hundred ms) from the timing at which the first lane line and the second lane line were detected based on the information acquired from the vehicle control ECU 3. The estimated movement amount of the vehicle at the time is obtained, and based on the estimated movement amount, the first end point coordinates and the second division corresponding to the vehicle side end portion of the first division line stored in the storage unit 13 The second end point coordinate corresponding to the end of the line on the vehicle side is corrected. The first end point coordinates corresponding to the end of the first lane marking on the vehicle side obtained by the correction of the correction section 12 and the end of the second lane marking on the vehicle side are the first lane marking and the first lane marking. The first end point coordinates corresponding to the end of the first lane line on the vehicle side and the vehicle side of the second lane line when a predetermined time (for example, several hundred ms) has elapsed from the timing when the second lane line is detected This is the second end point coordinate corresponding to the end.

  In step S60 following step S50, the detection unit 11 includes the first end point coordinate area including the first end point coordinate and the second end point coordinate based on the first end point coordinate and the second end point coordinate calculated by the correction unit 14. The second end point coordinate area including the end point coordinates is set, and the first end point coordinate area and the second end point coordinate area are set as the region of interest. Thereby, since the range of the region of interest can be narrowed, false detection by the detection unit 11 can be reduced. In addition, since the calculation error related to the setting of the region of interest can be limited only to the error due to the estimated movement amount of the vehicle from the previous detection, it is possible to reduce the region of interest from shifting from the correct position. Therefore, it is possible to reduce the inability to follow the detected marking line.

  The detection unit 11 sets a first region of interest that includes the first end point coordinate calculated by the end point coordinate calculation unit 12, and the second end point that includes the second end point coordinate calculated by the end point coordinate calculation unit 12 Set the region of interest. That is, the first region of interest corresponds to the first end point coordinate region, and the second region of interest corresponds to the second end point coordinate region.

  Note that the first region of interest and the second region of interest are preferably separated from each other. Thereby, since the range of the region of interest can be further narrowed, erroneous detection by the detection unit 11 can be further reduced. In order to effectively reduce erroneous detection by the detection unit 11, the top view area of the first region of interest and the top view area of the second region of interest are each made smaller than at least the top view area of the vehicle. It is desirable to keep it. The top view shape of the first region of interest is a rectangle, the longitudinal direction of the first region of interest is made to coincide with the longitudinal direction of the first partition line, the top view shape of the second region of interest is a rectangle, It is desirable to match the longitudinal direction of the two regions of interest with the longitudinal direction of the second partition line. By devising this shape, it is possible to reduce the top view area of the first region of interest and the top view area of the second region of interest.

  In step S70 following step S60, the detection unit 11 tries to detect the first lane line, the second lane line, the first new lane line, and the second new lane line.

  When the detection unit 11 detects the first new lane line in step S70, the update unit 16 determines whether or not to update the first lane line to the first new lane line (step S80). . Similarly, when the detection unit 11 detects the second new lane line in step S70, the update unit 16 determines whether or not to update the second lane line to the second new lane line ( Step S80). If the detection unit 11 detects neither the first new lane line nor the second new lane line in step S70, the update unit 16 determines not to update (step S80). It is determined whether or not to update the first lane line to the first new lane line and to determine whether or not to update the second lane line to the second new lane line. The predetermined value and the predetermined angle used as a reference may be shared or may be different values.

  Hereinafter, the process of step S80 will be described by taking as an example the case where the detection unit 11 detects the first new lane marking in step S70.

  When the detection unit 11 detects the first new lane line at a position that does not cross the first lane line from the target parking position, the update unit 16 determines the first new line from the reliability of the first lane line. If the value obtained by subtracting the reliability of the lane marking is less than or equal to the predetermined value V1, the first lane marking is updated to the first new lane marking, and the first new lane marking is updated from the reliability of the first lane marking. If the value obtained by subtracting the reliability of the lane marking is larger than the predetermined value V1, the first lane marking is not updated to the first new lane marking.

  The reliability of the first lane line can be obtained from a captured image obtained by a camera that captures the periphery of the vehicle. For example, the reliability is calculated based on the luminance, contrast, shape, and the like of the first lane line. And the reliability of a 1st division line should just be set so that it may decrease with time passage after it calculates. Similarly, the reliability of the first new lane marking can be obtained from a captured image obtained by a camera that captures the periphery of the vehicle. For example, the brightness, contrast, shape, etc. of the first new lane marking. Is calculated based on And the reliability of a 1st new division line should just be set so that it may reduce with progress of time after calculating.

  When the detection unit 11 detects the first new lane line at a position straddling the first lane line from the target parking position, the update unit 16 determines the first division from the reliability of the first new lane line. If the value obtained by subtracting the reliability of the line is equal to or less than the predetermined value V1, the first division line is not updated to the first new division line, and the first division is determined based on the reliability of the first new division line. If the value obtained by subtracting the line reliability is greater than the predetermined value V1, the first lane line is updated to the first new lane line. If the value obtained by subtracting the reliability of the first lane line from the reliability of the first new lane line is larger than the predetermined value V1, the first lane line is not changed. It may not be updated to one new lane marking.

  When the detection unit 11 detects the first new lane line at a position that does not cross the first lane line from the target parking position by the process of step S80 described above, the first lane line is changed to the first new line. When the detection unit 11 detects the first new lane line at a position straddling the first lane line from the target parking position, the first lane line is changed to the first new lane line. It becomes difficult to update to lane markings. Therefore, it can reduce that a parking section is set widely accidentally.

  In step S90 following step S80, the lane marking detection ECU 1 checks whether an end event of the lane marking detection ECU 1 has occurred. Examples of the operation end event of the lane marking detection ECU 1 include that the distance between the coordinates of the target parking position and the origin is equal to or less than a predetermined value that is substantially zero, and the position of the shift lever of the vehicle is changed from the reverse range to another range. It can be mentioned that it has been switched.

  If the operation end event of the lane marking detection ECU 1 has not occurred, the process returns to step S20. On the other hand, if the operation end event of the lane marking detection ECU 1 has occurred, the lane marking detection ECU 1 ends the operation of the flowchart shown in FIG.

  Instead of performing step S90, the lane line detection ECU 1 constantly monitors whether the operation end event of the lane line detection ECU 1 has occurred, and the operation end event of the lane line detection ECU 1 is generated. For example, the operation of the flowchart may be immediately terminated. In this case, when the process of step S80 ends, the process may return to step S20.

<3. Notes>
Various technical features disclosed in the present specification can be variously modified within the scope of the technical creation in addition to the above-described embodiment. That is, the above-described embodiment is an example in all respects and should not be considered as limiting, and the technical scope of the present invention is not the description of the above-described embodiment, but the claims. It should be understood that all modifications that come within the meaning and range of equivalents of the claims are included.

  For example, the lane line detection ECU 1 outputs information related to the first lane line and the second lane line to the display device, and the display device displays the first lane line and the second lane line in the camera image. The parking frame set based on the first lane line and the second lane line may be displayed in a superimposed manner. This superimposed display allows the vehicle driver to clearly recognize the parking area.

  Further, for example, the lane marking detection ECU 1 may perform the operation of the flowchart shown in FIG. 6 instead of the operation of the flowchart shown in FIG. In this case, the lane marking detection ECU 1 includes a traveling direction detection unit 17 as shown in FIG. The traveling direction detection unit 17 detects the traveling direction of the vehicle based on, for example, information acquired from the vehicle control ECU 3 or information acquired from various sensors provided in the vehicle such as a steering angle sensor.

  The flowchart shown in FIG. 6 is obtained by adding steps S41 and S51 to the flowchart shown in FIG.

  In the flowchart shown in FIG. 6, after step S <b> 40, the traveling direction detection unit 17 calculates the steering angle integration amount of the vehicle until a predetermined time elapses from the timing when the first lane line and the second lane line are detected last time. It is determined whether or not it is larger than the threshold (step S41). When the integrated steering angle is larger than the threshold value, the vehicle turns and travels, that is, travels while turning. Further, when the steering angle integrated amount is equal to or less than the threshold value, the vehicle is traveling straight ahead. Based on the information acquired from the vehicle control ECU 3, the traveling direction detection unit 17 obtains the steering angle integrated amount of the vehicle until a predetermined time elapses from the timing when the first lane line and the second lane line are detected last time. If the rudder angle integration amount is larger than the threshold value, the process proceeds to step S50, and if the rudder angle integration amount is equal to or less than the threshold value, the process proceeds to step S51.

  In step S51, the end point coordinate calculation unit 12 corresponds to the vehicle-side end of the first lane marking when a predetermined time has elapsed since the previous detection of the first lane marking and the second lane marking. The second end point coordinates corresponding to the end point coordinates and the end of the second lane marking on the vehicle side are calculated from the coordinates of the target parking position. The specific processing content of step S51 will be described with reference to the flowchart shown in FIG.

  First, the end point coordinate calculation unit 12 corrects the coordinates of the target parking position (step S51_1). Specifically, the end point coordinate calculation unit 12 is based on the information acquired from the vehicle control ECU 3, and the estimated movement of the vehicle when a predetermined time has elapsed from the timing when the first lane line and the second lane line were detected last time. The amount is obtained, and the coordinates of the target parking position are corrected based on the estimated movement amount.

  Next, the end point coordinate calculation unit 12 is separated from the target parking position by the effective length L0 from the target parking position toward the vehicle side in the longitudinal direction of the first lane line and the second lane line from the corrected target parking position coordinates. Point coordinates are calculated (step S51_2).

  Next, the end point coordinate calculation unit 12 is separated by half of the above-described distance W from the middle point coordinate toward the first lane line in the direction perpendicular to the longitudinal direction of the first lane line and the second lane line. The first end point coordinates are calculated (step S51_3).

  Next, the end point coordinate calculation unit 12 is separated by a half of the above-described distance W from the middle point coordinate toward the second lane line in the direction perpendicular to the longitudinal direction of the first lane line and the second lane line. The second end point coordinates are calculated (step S51_4), and the end point coordinate calculation processing is terminated. When the longitudinal direction of the first lane line and the longitudinal direction of the second lane line are slightly different, the longitudinal direction of the first lane line, the longitudinal direction of the second lane line, and the first partition line Either the longitudinal direction of the average longitudinal direction of the line and the second partition line may be the longitudinal direction of the first partition line and the second partition line.

  When the process proceeds from step S51 to step S60, in step S60, the detection unit 11 sets a region of interest based on the first end point coordinates and the second end point coordinates calculated by the end point coordinate calculation unit 12.

  In the flowchart shown in FIG. 6, when the integrated steering angle of the vehicle until the predetermined time elapses from the timing when the first lane line and the second lane line were detected last time, Since the calculation error is small even if the first end point coordinates and the second end point coordinates are obtained by calculation, the first end point coordinates and the second end point coordinates are obtained by calculation from the target parking position. Thereby, when the steering angle integrated amount of the vehicle until the predetermined time elapses from the timing at which the first lane line and the second lane line were detected last time is equal to or less than the threshold value, the process of step S50 can be omitted. , The processing load can be reduced.

1 lane marking detection ECU
3 Vehicle control ECU
DESCRIPTION OF SYMBOLS 10 Image | video acquisition part 11 Detection part 12 Endpoint coordinate calculation part 13 Memory | storage part 14 Correction | amendment part 15 Position calculation part 16 Update part 17 Travel direction detection part 2 Imaging | photography part 21-23 Camera 3 Vehicle control ECU
4 In-vehicle network

Claims (7)

A detection unit for detecting a first lane marking and a second lane marking from a captured image obtained by a camera that images the periphery of the vehicle;
End point coordinate calculation for calculating a first end point coordinate corresponding to the vehicle-side end of the first lane marking and a second end point coordinate corresponding to the vehicle-side end of the second lane marking And
A storage unit for storing the first end point coordinates and the second end point coordinates calculated by the end point coordinate calculation unit;
A correction unit that corrects the first end point coordinates and the second end point coordinates stored by the storage unit based on the estimated movement amount of the vehicle from the previous detection time;
With
The detection unit includes a first end point coordinate area including the first end point coordinate and the second end point coordinate based on the first end point coordinate and the second end point coordinate corrected by the correction unit. A lane marking detection apparatus that sets a second end point coordinate area including: A traveling direction detector for detecting a traveling direction of the vehicle;
A position calculation unit that calculates a target parking position based on the first lane line and the second lane line; and
When the traveling direction of the vehicle is turning,
The detection unit includes a first end point coordinate area including the first end point coordinate and the second end point coordinate based on the first end point coordinate and the second end point coordinate corrected by the correction unit. And a second end point coordinate area including
When the traveling direction of the vehicle is straight,
The correction unit corrects the target parking position based on an estimated movement amount of the vehicle from the previous detection time,
The detection unit calculates the first end point coordinate and the second end point coordinate from the target parking position corrected by the correction unit, and calculates the calculated first end point coordinate and the second end point coordinate. The lane marking detection device according to claim 1, wherein a first endpoint coordinate area including the first endpoint coordinates and a second endpoint coordinate area including the second endpoint coordinates are set based on the first endpoint coordinates area.   The advancing direction detection unit determines that the vehicle is turning when the steering angle integrated amount of the vehicle is greater than a threshold value, and the vehicle travels straight when the steering angle integrated amount of the vehicle is equal to or less than the threshold value. The lane marking detection apparatus according to claim 2, wherein the lane marking detection apparatus determines that the A vehicle control unit for controlling parking of the vehicle;
A position calculation unit that calculates a target parking position based on the first lane line and the second lane line; and
The lane marking detection device according to any one of claims 1 to 3, wherein the vehicle control unit controls the vehicle to the target parking position based on the first end point coordinates and the second end point coordinates. . A position calculation unit that calculates a target parking position based on the first lane line and the second lane line; and an update unit;
The update unit
The first new lane marking calculated based on the captured image when the detection unit detects a first new lane marking at a position across the first lane marking from the target parking position. If the value obtained by subtracting the reliability of the first lane marking calculated based on the captured image from the reliability of the first lane is equal to or less than a first predetermined value, the first lane marking is changed to the first new lane marking. The lane marking detection apparatus according to any one of claims 1 to 4, which is not updated to a lane marking. A camera that captures the area around the vehicle,
A lane marking detection system comprising the lane marking detection device according to any one of claims 1 to 5. A detection step of detecting a first lane marking and a second lane marking from a captured image obtained by a camera that images the periphery of the vehicle;
End point coordinate calculation for calculating a first end point coordinate corresponding to the vehicle-side end of the first lane marking and a second end point coordinate corresponding to the vehicle-side end of the second lane marking Process,
A storage step of storing the first end point coordinates and the second end point coordinates calculated by the end point coordinate calculating step;
A correction step of correcting the first end point coordinates and the second end point coordinates stored by the storage step based on an estimated movement amount of the vehicle from the previous detection time;
With
The detection step includes a first end point coordinate area including the first end point coordinate and the second end point coordinate based on the first end point coordinate and the second end point coordinate corrected by the correction step. A lane marking detection method for setting a second end point coordinate area including: