Verification module system and method for motion-based lane detection with multiple sensors

Patent metadata

Field	Value
Publication number	US-11874130-B2
Application number	US-202318158974-A
Country	US
Kind code	B2
Filing date	Jan 24, 2023
Priority date	Aug 22, 2017
Publication date	Jan 16, 2024
Grant date	Jan 16, 2024

Abstract

A method of lane detection for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs include instructions, which when executed by a computing device, cause the computing device to perform the following steps comprising: generating a ground truth associated with lane markings expressed in god's view; receiving features from at least one of a hit-map image and a fitted lane marking, wherein the hit-map image includes a classification of pixels that hit a lane marking, and the fitted lane marking includes pixels optimized based on the hit-map image; and training a confidence module based on the features and the ground truth, the confidence module configured to determine on-line whether a fitted lane marking is reasonable, using parameters that express a lane marking in an arc.

First claim

What is claimed is:

1. A method for lane detection, comprising:
generating, based on a lane detection algorithm, a hit-map image in response to a current view, wherein the hit-map image includes a classification of pixels that hit a lane marking;
receiving a fitted lane marking associated with the current view;
extending, in a post processing module, the fitted lane marking;
generating a lane template, using a set of parameters that express the fitted lane marking in an arc, that includes features of the lane marking associated with the current view and features of an extended lane marking; and
feeding the lane template associated with the current view for detection of a next view.

2. The method according to claim 1 , wherein the extending includes: extending a fitted lane marking based on a high-definition map.

3. The method according to claim 1 , further comprising:
generating, based on a lane detection algorithm, a hit-map image in response to the current view, the hit-map image including a classification of pixels that hit a lane marking.

4. The method according to claim 3 further comprising:
generating a fitted lane marking based on the hit-map image and a lane template associated with an immediately previous view.

5. The method according to claim 4 , wherein generating a fitted lane marking includes:
optimizing, based on priors or constraints, the lane template associated with the immediately previous view to obtain a local optimal.

6. The method according to claim 4 further comprising:
determining that a confidence level of the fitted lane marking is reasonable, using the set of parameters; and
outputting the fitted lane marking to a post-processing module.

7. The method according to claim 4 further comprising: determining that a confidence level of the fitted lane marking is unreasonable, using the set of parameters; and rejecting the fitted lane marking.

8. The method according to claim 4 further comprising: removing an incorrect line from the fitted lane marking.

9. The method according to claim 6 , after extending the fitted lane marking, further comprising:
fitting, in the post-processing module, the lane marking in an arc by using the set of parameters.

10. A system for lane detection, the system comprising:
a memory;
one or more processing units; and
one or more programs stored in the memory and configured for execution by the one or more processing units, the one or more programs comprising instructions to cause at least:
generating, based on a lane detection algorithm, a hit-map image in response to a current view, the hit-map image including a classification of pixels that hit a lane marking;
receiving a fitted lane marking associated with a current view;
extending, in a post processing module, the fitted lane marking;
generating a lane template, using a set of parameters that express the lane marking in an arc, the lane template including features of the lane marking associated with the current view and features of an extended lane marking; and
feeding the lane template associated with the current view for detection of a next view.

11. The system according to claim 10 , wherein the extending includes: extending a fitted lane marking based on a high-definition map.

12. The system according to claim 10 , wherein the one or more programs comprises instructions to further cause at least:
generating a fitted lane marking based on the hit-map image and a lane template associated with an immediately previous view.

13. The system according to claim 12 , wherein generating a fitted lane marking includes:
optimizing, based on priors or constraints, the lane template associated with the immediately previous view to obtain a local optimal.

14. The system according to claim 12 further comprising:
determining that a confidence level of the fitted lane marking is reasonable, using the set of parameters; and
outputting the fitted lane marking to a post-processing module.

15. The system according to claim 14 , wherein the one or more programs comprises instructions to further cause at least: determining that a confidence level of the fitted lane marking is unreasonable, using the set of parameters; and rejecting the fitted lane marking.

16. The system according to claim 14 , wherein the one or more programs comprises instructions to further cause removing an incorrect line from the fitted lane marking.

17. The system according to claim 14 , wherein the one or more programs comprises instructions to further cause at least: after extending the fitted lane marking, further comprising:
fitting, in the post-processing module, the lane marking in an arc by using the set of parameters.

18. A device for controlling a vehicle, comprising:
a processor configured to:
generate, based on a lane detection algorithm, a hit-map image in response to a current view, the hit-map image including a classification of pixels that hit a lane marking;
receive a fitted lane marking associated with a current view;
extend, in a post processing module, the fitted lane marking;
generate a lane template, using a set of parameters that express the lane marking in an arc, the lane template including features of the lane marking associated with the current view and features of an extended lane marking; and
feed the lane template associated with the current view for detection of a next view.

19. The device according to claim 18 , wherein the extending includes: extending a fitted lane marking based on a high-definition map.

Assignees

• Tusimple Inc

Inventors

• Liu Siyuan
• Wang Mingdong
• Hou Xiaodi

Classifications

• G01C21/3658 Primary

  Lane guidance · CPC title

• G06V20/588 Primary

  Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road · CPC title

• G01S17/86

  Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders · CPC title

• G01S17/89

  for mapping or imaging · CPC title

• G06V2201/10

  Recognition assisted with metadata · CPC title