Method of misalignment correction and diagnostic function for lane sensing sensor

• US 9,930,323 B2
• Filed: 04/23/2014
• Issued: 03/27/2018
• Est. Priority Date: 04/23/2014
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Zeng, Shuqing, Song, Xiaofeng F.
• Primary Examiner(s): Harold, Jefferey F
• Assistant Examiner(s): Khalid, Omer
• Application Number:
  US14/259,470
• Publication Number:
  US 20150312564A1
• Time in Patent Office: 1,434 Days
• Field of Search: 348175, 348149, 348 E7085, 701 29, 701 41
• CPC Class Codes: G06T 2207/20076 Probabilistic image processing
• CPC Class Codes: G06T 2207/30168 Image quality inspection
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/80 Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
• CPC Class Codes: G06V 10/24 Aligning, centring, orientation detection or correction of the image
• 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 17/002 for television cameras

Abstract

A method of diagnosing a state of health of a vision-based lane sensing system. A first misalignment factor is calculated as a function of a vehicle lateral offset and a vehicle heading. A second misalignment factor is calculated as a function of a vehicle speed, an estimated curvature of an expected path of travel, a lane curvature, and the vehicle heading. Histograms are generated for the first and second misalignment factors. A probability of a state of health is determined. A determination is made whether the probability of the state of health is within a predetermined threshold. An angle misalignment of the vision system is estimated. The angle misalignment of the vision system is corrected in response to the determination that the probability of the state of health is within the predetermined threshold; otherwise a warning of a faulty lane sensing system is actuated.

Claims

1. A method of diagnosing a state of health of a vision-based lane sensing system for a vehicle, the method comprising the steps of:

calculating a first misalignment factor as a function of a vehicle lateral offset and a vehicle heading;

calculating a second misalignment factor as a function of a vehicle speed, an estimated curvature of an expected path of travel of the vehicle, a lane curvature of a traveled road, and the vehicle heading;

generating a histogram for the first misalignment factor and a histogram for the second misalignment factor;

determining a probability of a state of health based on the histogram of first misalignment factor and the histogram of the second misalignment factor;

determining whether the probability of the state of health is within a predetermined threshold; and

estimating an angle misalignment of the vision system;

correcting the angle misalignment of the vision system in response to the determination that the probability of the state of health is within the predetermined threshold;

otherwise actuating a warning of a faulty lane sensing system.

2. The method of claim 1 wherein determining the probability of a state of health comprises the following steps:

determining a probability of the first misalignment factor;

determining whether the probability of the first misalignment factor is less than a first distribution threshold;

determining a probability of the second misalignment factor;

determining whether the probability of the second misalignment factor is less than a second distribution threshold;

determining the probability of the state of health as a function of the probability of the first misalignment factor being less than the first distribution threshold and the probability of the second misalignment factor being less than the second distribution threshold.

3. The method of claim 1 wherein the first misalignment factor is determining by the following formula:

4. The method of claim 3 wherein the first misalignment factor substantially equal to zero indicates no angle misalignment of the vision system.

5. The method of claim 3 wherein the second misalignment factor is determined by the following formula:

β

={dot over (θ

)}−

(C_Y−

C_L)v_H

where {dot over (θ

)} is a derivative of the vehicle heading with respect to a lane of travel, C_Y is the estimated curvature of an expected path of travel of the vehicle, C_L is the lane curvature of a traveled road, and v_H is the vehicle speed.

6. The method of claim 5 wherein the first misalignment factor and the second misalignment factor are stored in a buffer.

7. The method of claim 5 wherein the second misalignment factor substantially equal to zero indicates no angle misalignment of the vision system.

8. The method of claim 5 further comprising the steps of recursively estimating respective histograms for the first misalignment factor and the second misalignment factor.

9. The method of claim 1 wherein determining whether the probability of the state of health is within a predetermined threshold includes determining whether the probability state of the state of health is within 0.8.

10. The method of claim 1 further comprising the steps of:

obtaining new sensor data in response to correcting the angle misalignment of the vision system.

11. The method of claim 1 wherein the first misalignment factor and the second misalignment factor is determined only in response to a determination of an unintended lane change movement.

12. The method of claim 11 wherein the unintended lane change movement is determined by a factor of at least the vehicle speed being greater than a predetermined speed.

13. The method of claim 11 wherein the unintended lane change movement is determined by a factor of at least a turn signal not being actuated.

14. The method of claim 9 wherein the unintended lane change movement is determined by a factor of at least detecting no lane crossing within a predetermined amount of time.