System and method for advanced highway lane detection

Patent metadata

Field	Value
Publication number	US-10614320-B2
Application number	US-201815944363-A
Country	US
Kind code	B2
Filing date	Apr 3, 2018
Priority date	Apr 3, 2018
Publication date	Apr 7, 2020
Grant date	Apr 7, 2020

Abstract

A computer-implemented method for lane detection includes receiving a road image from an image capture device, detecting a first solid line marking and a second solid line marking outside of the first solid line marking in the binary road image. The first solid line marking and the second solid line marking are non-parallel lines. The method includes calculating a first distance between a first point of the first solid line marking and a first point of the second solid line marking. The first points being in a top portion of the binary road image. The method includes calculating a second distance between a second point of the first solid line marking and a second point of the second solid line marking. The second points being in a bottom portion of the binary road image. Further, the method includes determining a merging lane based the first distance and the second distance.

First claim

The invention claimed is:

1. A computer-implemented method for lane detection, comprising:
receiving a road image from an image capture device;
processing the road image to a binary road image;
detecting a first solid line marking in the binary road image;
detecting a second solid line marking outside of the first solid line marking in the binary road image, wherein the first solid line marking and the second solid line marking are non-parallel lines;
calculating a first distance between a first point of the first solid line marking and a first point of the second solid line marking, wherein the first point of the first solid line marking and the first point of the second solid line marking are in a top portion of the binary road image;
calculating a second distance between a second point of the first solid line marking and a second point of the second solid line marking, wherein the second point of the first solid line marking and the second point of the second solid line marking are in a bottom portion of the binary road image; and
determining a type of a merging lane based the first distance and the second distance.

2. The computer-implemented method of claim 1 , wherein processing the road image to the binary road image includes transforming the binary road image according to a perspective transform.

3. The computer-implemented method of claim 1 , including defining a first search area including the first solid line marking and segmenting the binary road image within the first search area into a plurality of vertical sections.

4. The computer-implemented method of claim 3 , including calculating a first histogram of the plurality of vertical sections and wherein detecting the first solid line marking in the binary road image is based on the first histogram with parabolic fitting.

5. The computer-implemented method of claim 4 , wherein upon detecting the first solid line marking in the binary road image, defining a second search area in a rightward direction of the first solid line marking.

6. The computer-implemented method of claim 5 , including segmenting the binary road image within the second search area into a plurality of vertical sections.

7. The computer-implemented method of claim 6 , including calculating a second histogram of the plurality of vertical sections and wherein detecting the second solid line marking outside of the first solid line marking in the binary road image is based on the second histogram with parabolic fitting.

8. The computer-implemented method of claim 1 , wherein determining the type of the merging lane includes classifying the merging lane as an entrance lane or an exit lane based on a difference between the first distance and the second distance.

9. The computer-implemented method of claim 8 , wherein upon determining the first distance is less than the second distance, the merging lane is classified as the entrance lane.

10. The computer-implemented method of claim 8 , wherein upon determining the first distance is greater than the second distance, the merging lane is classified as the exit lane.

11. A system for lane detection, comprising:
an image capture device captures a road image of an area surrounding a vehicle; and
a processor operably connected for computer communication to the image capture device, wherein the processor receives the road image from the image capture device and processes the road image into a binary road image, wherein the processor detects a first solid line marking in the binary road image and a second solid line marking outside of the first solid line marking in the binary road image, wherein the first solid line marking and the second solid line marking are non-parallel lines,
wherein the processor calculates a first distance between a first point of the first solid line marking and a first point of the second solid line marking, wherein the first point of the first solid line marking and the first point of the second solid line marking are in a top portion of the binary road image, the processor calculates a second distance between a second point of the first solid line marking and a second point of the second solid line marking, wherein the second point of the first solid line marking and the second point of the second solid line marking are in a bottom portion of the binary road image, and the processor determines a type of a merging lane based the first distance and the second distance.

12. The system of claim 11 , wherein the processor defines a second search area in the binary road image positioned in a rightward direction outside of the first solid line marking.

13. The system of claim 11 , wherein the processor detects the first solid line marking and the second solid line marking based on an intensity value analysis and parabolic fitting.

14. The system of claim 11 , wherein the processor determines the merging lane is an entrance lane when the first distance is less than the second distance.

15. The system of claim 11 , wherein the processor determines the merging lane is an exit lane when the first distance is greater than the second distance.

16. A non-transitory computer-readable storage medium including instructions that when executed by a processor, cause the processor to:
receive a road image from an image capture device;
process the road image to a binary road image;
detect a first solid line marking in the binary road image;
detect a second solid line marking outside of the first solid line marking in the binary road image, wherein the first solid line marking and the second solid line marking are non-parallel lines;
calculate a first distance between a first point of the first solid line marking and a first point of the second solid line marking, wherein the first point of the first solid line marking and the first point of the second solid line marking are in a top portion of the binary road image;
calculate a second distance between a second point of the first solid line marking and a second point of the second solid line marking, wherein the second point of the first solid line marking and the second point of the second solid line marking are in a bottom portion of the binary road image; and
determine a type of a merging lane based the first distance and the second distance.

17. The non-transitory computer-readable storage medium of claim 16 , including causing the processor to detect the first solid line marking and the second solid line marking based on an intensity value analysis and parabolic fitting.

18. The non-transitory computer-readable storage medium of claim 16 , including causing the processor to classify the merging lane as an exit lane or an entrance lane.

19. The non-transitory computer-readable storage medium of claim 18 , wherein upon determining the first distance is less than the second distance, the merging lane is classified as the entrance lane.

20. The non-transitory computer-readable storage medium of claim 18 , wherein upon determining the first distance is greater than the second distance, the merging lane is classified as the exit lane.

Assignees

• Honda Motor Co Ltd

Inventors

• Yang Shuowei

Classifications

• G06T2207/20048

  Transform domain processing · CPC title

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title

• G06T7/529

  from texture · CPC title

• G06T2207/30256

  Lane; Road marking · CPC title

• G06T7/11

  Region-based segmentation · CPC title