Mitigation strategies for lane marking misdetection

Patent metadata

Field	Value
Publication number	US-12456309-B2
Application number	US-202217740625-A
Country	US
Kind code	B2
Filing date	May 10, 2022
Priority date	May 10, 2022
Publication date	Oct 28, 2025
Grant date	Oct 28, 2025

Abstract

A vehicle, and a system and method of navigating the vehicle. The system includes a camera and a processor. The camera obtains an image of a road upon which the vehicle is moving. The processor is configured to extract a feature of the road from the image, perform a lane detection algorithm to detect a set of lane markers in the road using the image and the feature, and move the vehicle along the road by tracking the set of lane markers.

First claim

What is claimed is:

1. A method of navigating a vehicle, comprising:
obtaining, at a camera on the vehicle, an image of a road upon which the vehicle is moving;
determining a first set of lane markers by segmenting the image using pixel colors;
determining a first confidence value for the first set of lane markers;
determining a feature from the image that includes a shape of the road;
determining a second set of lane markers based on the shape of the road in the image;
determining a second confidence value for the second set of lane markers; and
generating a warning signal when a difference between the first confidence value and the second confidence value is greater than a selected criterion.

2. The method of claim 1 , wherein the feature further comprises a road segmentation information.

3. The method of claim 2 , wherein the feature further comprises a trajectory of a road agent on the road.

4. The method of claim 1 , further comprising displaying at a monitor the set of lane markers to a driver of the vehicle.

5. The method of claim 1 further comprising at least one of: (i) sending the image to a lane detection module to determine the first set of lane markers using pixel colors; and (ii) sending the image to both the lane detection module to determine the first set of lane markers using pixel colors and to an information extraction module to determine the second set of lane markers based on the shape of the road.

6. The method of claim 5 , further comprising selecting a final set of marker points from a first set of marker points and a second set of marker points.

7. The method of claim 6 , further comprising selecting the final set of marker points using the first confidence value and the second confidence value.

8. A system for navigating a vehicle, comprising:
a camera for obtaining an image of a road upon which the vehicle is moving;
a processor configured to:
determine a first set of lane markers by segmenting the image using pixel colors;
determine a first confidence value for the first set of lane markers;
determine a feature from the image that includes a shape of the road;
determine a second set of lane markers based on the shape of the road in the image;
determine a second confidence value for the second set of lane markers; and
generate a warning signal when a difference between the first confidence value and the second confidence value is greater than a selected criterion.

9. The system of claim 8 , wherein the feature further comprises a road segmentation information.

10. The system of claim 9 , wherein the feature further comprises a trajectory of a road agent on the road.

11. The system of claim 8 , wherein the processor is further configured to display the set of lane markers to a driver of the vehicle at a monitor.

12. The system of claim 8 , wherein the processor is further configured to perform at least one of: (i) send the image to a lane detection module to determine the first set of lane markers using pixel colors; and (ii) send the image to both the lane detection module to determine the first set of lane markers using pixel colors and to an information extraction module to determine the second set of lane markers based on the shape of the road.

13. The system of claim 12 , wherein the processor is further configured to select a final set of marker points from a first set of marker points and a second set of marker points.

14. The system of claim 13 , wherein the processor is further configured to select the final set of marker points using the first confidence value and the second confidence value.

15. A vehicle, comprising:
a camera for obtaining an image of a road upon which the vehicle is moving;
a processor configured to:
determine a first set of lane markers by segmenting the image using pixel colors;
determine a first confidence value for the first set of lane markers;
determine a feature from the image that includes a shape of the road;
determine a second set of lane markers based on the shape of the road in the image;
determine a second confidence value for the second set of lane markers; and
generate a warning signal when a difference between the first confidence value and the second confidence value is greater than a selected criterion.

16. The vehicle of claim 15 , wherein the feature further comprises at least one of: (i) a road segmentation information; and (ii) a trajectory of a road agent on the road.

17. The vehicle of claim 15 , wherein the processor is further configured to display the set of lane markers to a driver of the vehicle at a monitor.

18. The vehicle of claim 15 , wherein the processor is further configured to perform at least one of: (i) sending the image to a lane detection module to determine the first set of lane markers using pixel colors; and (ii) sending the image to both the lane detection module to determine the first set of lane markers using pixel colors and to and an information extraction module to determine the second set of lane markers based on the shape of the road.

19. The vehicle of claim 18 , wherein the processor is further configured to select a final set of marker points from a first set of marker points and a second set of marker points.

20. The vehicle of claim 19 , wherein the processor is further configured to select the final set of marker points using the first confidence value and the second confidence value.

Assignees

• Gm Global Tech Operations Llc

Inventors

• Lin Wen-Chiao
• Yang Zhongyu
• Du Xinyu
• Hu Yao
• Jiang Shengbing
• Zhang Yilu
• Lu Sidi

Classifications

• B60W2420/403

  Image sensing, e.g. optical camera · CPC title

• B60W40/06

  Road conditions · CPC title

• B60W2552/53

  Road markings, e.g. lane marker or crosswalk · CPC title

• B60W50/14

  Means for informing the driver, warning the driver or prompting a driver intervention · CPC title

• B60W30/12

  Lane keeping · CPC title