Adaptive lane marker detection for a vehicular vision system

• US 10,255,509 B2
• Filed: 04/16/2018
• Issued: 04/09/2019
• Est. Priority Date: 12/18/2014
• Status: Active Grant

• Current Assignee: Magna Electronics Incorporated (Magna International Incorporated)
• Original Assignee: Magna Electronics Incorporated (Magna International Incorporated)
• Inventors: Gupta, Nikhil, Djeziri, Salim, Corral-Soto, Eduardo R.
• Primary Examiner(s): Nawaz, Talha M
• Application Number:
  US15/953,656
• Publication Number:
  US 20180239970A1
• Time in Patent Office: 358 Days
• Field of Search: None
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/181 involving edge growing; involving edge linking
• CPC Class Codes: G06V 10/421 by analysing segments intersecting the pattern
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: H04N 7/188 Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position signal generation from motion picture films H04N5/253

Abstract

A method for determining lane markers includes providing a camera at a vehicle so as to have a field of view exterior of the vehicle. An image processor processes a frame of image data captured by the camera to determine intensity gradient information of captured image data and to determine lane markers. Contrast values at both sides of a center region of the determined lane marker are determined via processing of the intensity gradient information. An angle of the determined lane marker relative to the direction of travel of the vehicle is determined responsive to the determined contrast values. Processing of a subsequent frame of captured image data is adjusted responsive to the determined angle of the determined lane marker relative to the direction of travel of the vehicle.

Claims

1. A method for determining lane markers via a vision system of a vehicle, said method comprising:

providing a camera at a vehicle so as to have a field of view forward and exterior of the vehicle, wherein the field of view encompasses a road along which the vehicle is traveling, and wherein the camera comprises a pixelated imaging array having a plurality of photosensing elements;

capturing frames of image data via the camera;

providing a processor for processing frames of image data captured by the camera;

determining, via processing by the processor of a frame of image data captured by the camera with the camera disposed at the vehicle and with the vehicle traveling along the road, intensity gradient information of the frame of captured image data;

determining, via processing by the processor of the frame of image data captured by the camera with the camera disposed at the vehicle and with the vehicle traveling along the road, and responsive at least in part to the determined intensity gradient information of the frame of captured image data, a lane marker of the road along which the vehicle is traveling;

determining, via processing by the processor of intensity gradient information of the frame of captured image data, contrast values at both sides of a center region of the determined lane marker;

determining, at least in part responsive to the determined contrast values, an angle of the determined lane marker relative to the direction of travel of the vehicle; and

adapting processing by the processor of a subsequent frame of captured image data responsive to the determined angle of the determined lane marker relative to the direction of travel of the vehicle.

2. The method of claim 1, wherein determining the angle of the determined lane marker relative to the direction of travel of the vehicle is based at least in part on comparing the determined contrast values with contrast values stored in memory.

3. The method of claim 1, comprising utilizing a database of contrast values for central, left and right regions for typical angles of a lane marker relative to the direction of travel of the vehicle, and comparing the determined contrast values with database contrast values to determine the angle of the determined lane marker relative to the direction of travel of the vehicle.

4. The method of claim 3, wherein the database provides data for central, right and left regions around the determined lane marker.

5. The method of claim 1, wherein determining the lane marker is based at least in part on determining segments on the road along which the vehicle is traveling.

6. The method of claim 5, comprising grouping the segments to determine the angle of the determined lane marker relative to the direction of travel of the vehicle.

7. The method of claim 6, wherein determining segments is via processing by the processor of captured image data.

8. The method of claim 7, comprising deriving a direction of lane markers on the road by grouping determined segments.

9. The method of claim 8, comprising approximating a direction of a group of determined segments using linear regression.

10. The method of claim 7, comprising grouping, responsive to processing of the frame of captured image data, determined segments within respective bounding boxes that encompass determined points along the determined segments.

11. The method of claim 10, wherein determining the angle of the determined lane marker relative to the direction of travel of the vehicle comprises determining, responsive to grouping determined segments, the angle of the determined lane marker at least in part responsive to a determination that a gap between centers of adjacent bounding boxes is less than a width of the larger of both bounding boxes.

12. The method of claim 1, wherein the camera comprises a wide angle lens and wherein said camera has a wide angle field of view forward and exterior of the vehicle.

13. A method for determining lane markers via a vision system of a vehicle, said method comprising:

providing a camera at a vehicle so as to have a field of view forward and exterior of the vehicle, wherein the field of view encompasses a road along which the vehicle is traveling, and wherein the camera comprises a pixelated imaging array having a plurality of photosensing elements, and wherein the camera comprises a wide angle lens and, when provided at the vehicle, has a wide angle field of view forward and exterior of the vehicle;

capturing frames of image data via the camera;

providing a processor for processing frames of image data captured by the camera;

determining, via processing by the processor of a frame of image data captured by the camera with the camera disposed at the vehicle and with the vehicle traveling along the road, intensity gradient information of the frame of captured image data;

determining, via processing by the processor of the frame of image data captured by the camera with the camera disposed at the vehicle and with the vehicle traveling along the road, and responsive at least in part to the determined intensity gradient information of the frame of captured image data, a plurality of lane markers of the road along which the vehicle is traveling;

determining, via processing by the processor of intensity gradient information of the frame of captured image data, contrast values at both sides of a center region of the determined lane markers;

determining a maximum contrast value over a plurality of orientations of the determined lane markers relative to the direction of travel of the vehicle by using determined contrast values over a plurality of angles of the determined lane markers relative to the direction of travel of the vehicle;

determining an angle of a determined lane marker of the determined lane markers relative to the direction of travel of the vehicle by comparing, utilizing a database of contrast values for central, left and right regions for typical angles of a lane marker relative to the direction of travel of the vehicle, the determined contrast values with database contrast values; and

adapting processing by the processor of a subsequent frame of captured image data responsive to the determined angle of the determined lane marker relative to the direction of travel of the vehicle.

14. The method of claim 13, wherein the database provides data for central, right and left regions around the determined lane marker.

15. The method of claim 13, wherein determining the lane markers is based at least in part on determining segments on the road along which the vehicle is traveling, and wherein determining the angle of the determined lane markers relative to the direction of travel of the vehicle is based at least in part on grouping of the determined segments.

16. The method of claim 15, comprising approximating a direction of a group of determined segments using linear regression.

17. A method for determining lane markers via a vision system of a vehicle, said method comprising:

providing a camera at a vehicle so as to have a field of view forward and exterior of the vehicle, wherein the field of view encompasses a road along which the vehicle is traveling, and wherein the camera comprises a pixelated imaging array having a plurality of photosensing elements, and wherein the camera comprises a wide angle lens and, when provided at the vehicle, has a wide angle field of view forward and exterior of the vehicle;

capturing frames of image data via the camera;

providing a processor for processing frames of image data captured by the camera;

determining, via processing by the processor of frames of image data captured by the camera with the camera disposed at the vehicle and with the vehicle traveling along the road, intensity gradient information of the frame of captured image data;

determining, via processing by the processor of the frame of image data captured by the camera with the camera disposed at the vehicle and with the vehicle traveling along the road, and responsive at least in part to the determined intensity gradient information of the frame of captured image data, line segments on the road along which the vehicle is traveling;

determining, via processing by the processor of intensity gradient information of the frame of captured image data, contrast values at both sides of a center region of the determined line segments;

determining lane markers via processing by the processor of the frame of captured image data and responsive to the determined contrast values at both sides of the center region of the determined line segments;

deriving a direction of the determined lane markers on the road by grouping determined line segments; and

adapting processing by the processor of a subsequent frame of captured image data responsive to the derived direction of the determined lane markers.

18. The method of claim 17, comprising approximating a direction of a group of line segments using linear regression.

19. The method of claim 17, comprising grouping, responsive to processing of the frame of captured image data, determined line segments within respective bounding boxes that encompass determined points along the determined line segments.

20. The method of claim 19, wherein deriving the direction of the determined lane markers comprises deriving, responsive to grouping determined line segments, the direction of the determined lane markers responsive at least in part to a determination that a gap between centers of adjacent bounding boxes is less than a width of the larger of both bounding boxes.