Vision-based wet road surface detection

• US 9,090,264 B1
• Filed: 06/12/2014
• Issued: 07/28/2015
• Est. Priority Date: 06/12/2014
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Zhang, Wende, Wang, Jinsong, Litkouhi, Bakhtiar Brian, Zhao, Qingrong
• Primary Examiner(s): Cheung, Mary
• Assistant Examiner(s): Mazzara, Anne
• Application Number:
  US14/302,632
• Time in Patent Office: 411 Days
• Field of Search: 701/36
• US Class Current: 1/1
• CPC Class Codes: B60T 2210/12 Friction
• CPC Class Codes: B60T 2210/32 Vehicle surroundings
• CPC Class Codes: B60T 8/172 Determining control parameters used in the regulation, e.g. by calculations involving measured or detected parameters B60T8/17551 takes precedence
• CPC Class Codes: B60T 8/1764 Regulation during travel on surface with different coefficients of friction, e.g. between left and right sides, mu-split or between front and rear
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 40/06 Road conditions

Abstract

A method for determining a wet road surface condition for a vehicle driving on a road. An image exterior of the vehicle is captured by an image capture device at a first and second instance of time. Potential objects and feature objects are detected on a ground surface of the road of travel at the first instance of time and the second instance of time. A determination is made whether the ground surface includes a mirror effect reflective surface based on a triangulation technique utilizing the feature points in the captured images at the first instance of time and the second instance of time. A wet driving surface indicating signal is generated in response to the determination that the ground surface includes a mirror effect reflective surface.

Claims

1. A method for determining a wet road surface condition for a vehicle driving on a road, the method comprising the steps of:

capturing an image exterior of the vehicle by an image capture device at a first instance of time;

detecting, by a processor, a potential object on a ground surface of the road of travel in the image captured at the first instance of time;

identifying, by the processor, a feature point on the potential object on the ground surface of the road of travel of the image captured at the first instance of time;

capturing an image exterior of the vehicle by the image capture device at a second instance of time;

detecting, by the processor, the potential object on the ground surface of the road of travel captured at the second instance of time;

identifying, by the processor, the feature point on the potential object of the image captured at the second instance of time;

determining whether the ground surface includes a mirror effect reflective surface based on a triangulation technique utilizing the feature points in the captured images at the first instance of time and the second instance of time; and

generating a wet driving surface indicating signal in response to the determination that the ground surface includes a mirror effect reflective surface.

2. The method of claim 1 wherein triangulation technique utilizing the feature points in the captured images at the first instance of time and the second instance of time utilizes a line-of-sight light rays extending between the image capture device and first and second feature points.

3. The method of claim 2 wherein the triangulation technique comprises the following steps:

identifying a first location where a light ray associated with the first feature point intersects the ground surface;

identifying a second location where a light ray associated with the second feature point intersects the ground surface when the second image is captured by the image capture device;

determining whether the first location and the second location are at a same location;

wherein the ground surface is determined as including still water in response to the first location and the second location being different locations;

otherwise, determining that the ground surface includes a non-still water surface.

4. The method of claim 3 wherein the determination that the first location and the second location are different locations is determined in response to the following inequality:

d₁−

d_travel<

d₂

where d_travel is a distance traveled by the vehicle between a time the first image is captured and a time the second image is captured, d₁ represents a distance from a vehicle position when the first image is captured and a location where the light ray associated with the first detected feature point intersects the ground surface, and d₂ represents a distance from a vehicle position when the second image is captured and a location where the light ray associated with the second feature point intersects the ground surface.

5. The method of claim 3 wherein the determination that the first location and the second location are the same location is determined in response to the following equality:

d₁−

d_travel=d₂

where d_travel is a distance traveled by the vehicle between a time the first image is captured and a time the second image is captured, d₁ represents a distance from a vehicle position when the first image is captured and a location where the light ray associated with the first feature point intersects the ground surface, and d₂ represents a distance from a vehicle position when the second image is captured and a location where the light ray associated with the second feature point intersects the ground surface.

6. The method of claim 1 wherein the image capture device is positioned on the vehicle at a same height above them the ground surface when the first image and the second image is captured.

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

analyzing the feature point identified in the first image with the feature point identified in the second image for determining similar properties; and

performing the triangulation technique in response to the determination that the first and second feature points include similar properties and are determined to be a same point on the object.

8. The method of claim 7 wherein analyzing the feature point identified in the first image with the feature point identified in the second image for determining similar properties is performed by a scale-invariant feature transform technique.

9. The method of claim 7 wherein analyzing the feature point identified in the first image with the feature point identified in the second image for determining similar properties is performed by a speed up robust features technique.

10. The method of claim 1 wherein the wet driving surface indicating signal is used to warn a driver of water on the road surface.

11. The method of claim 1 wherein the wet driving surface indicating signal alerts a driver of a potential reduced traction between vehicle tires and the road surface.

12. The method of claim 1 wherein the wet driving surface indicating signal alerts a driver of the vehicle against a use of cruise control.

13. The method of claim 1 wherein the wet driving surface indicating signal alerts a driver to reduce a vehicle speed.

14. The method of claim 1 wherein the wet driving surface indicating signal is provided to a vehicle controller for shutting baffles on an air intake scoop of a vehicle for preventing water ingestion.

15. The method of claim 1 wherein the wet driving surface indicating signal is provided to a vehicle controller, the controller autonomously actuating vehicle braking for mitigating condensation build-up on vehicle brakes.

16. The method of claim 1 wherein the wet driving surface indicating signal is provided to a wireless communication system for alerting other vehicles of the wet road surface condition.

17. The method of claim 1 wherein multiple temporal images are analyzed for detecting whether the ground surface includes the mirror effect reflective surface for each temporal image captured, and wherein each detection result for each captured image is utilized cooperatively to generate a confidence level of whether the ground surface includes a mirror effect reflective surface.

18. The method of claim 17 wherein cooperatively utilizing each detection result to generate the confidence level is performed by averaging the detection results from the multiple temporal images.

19. The method of claim 17 wherein cooperatively utilizing each detection result to generate a confidence level is performed by a multi-voting technique of the detection results from the multiple temporal images.