Vision-based on-board real-time estimation of water film thickness

Patent metadata

Field	Value
Publication number	US-10082795-B2
Application number	US-201615245522-A
Country	US
Kind code	B2
Filing date	Aug 24, 2016
Priority date	Aug 24, 2016
Publication date	Sep 25, 2018
Grant date	Sep 25, 2018

Abstract

A method for determining a thickness of water on a path of travel. A plurality of images of a surface of the path of travel is captured by an image capture device over a predetermined sampling period. A plurality of wet surface detection techniques are applied to each of the images. A detection rate is determined in real-time for each wet surface detection technique. A detection rate trigger condition is determined as a function of a velocity of the vehicle for each detection rate. The real-time determined detection rate trigger conditions are compared to predetermined detection rate trigger conditions in a classification module to identify matching results pattern. A water film thickness associated with the matching results pattern is identified in the classification module. A water film thickness signal is provided to a control device. The control device applies the water film thickness signal to mitigate the wet surface condition.

First claim

What is claimed is:

1. A method for determining a thickness of water on a path of travel of a vehicle having a subsystem, the subsystem including air baffles on an air intake scoop of the vehicle, a traction control system, a cruise or adaptive cruise control system, a steering assist system, and/or a brake system, the method comprising:
capturing a plurality of images of a surface of the path of travel by an image capture device over a predetermined sampling period, the image capture device being focused at the surface where water splash is expected as the vehicle travels along the path of travel;
applying a plurality of wet surface detection techniques, by a processor of a controller of the vehicle, to each of the images;
determining in real-time, by the processor, a respective detection rate for each of the wet surface detection techniques;
determining, by the processor, a respective detection rate trigger condition as a function of a velocity of the vehicle for each of the respective detection rates;
comparing each of the respective detection rate trigger conditions to predetermined detection rate trigger conditions in a classification module of the controller to identify a matching results pattern, the predetermined detection rate trigger conditions representing various water film thickness levels;
identifying a water film thickness associated with the matching results pattern in the classification module;
providing a water film thickness signal to the controller indicative of the identified water film thickness associated with the matching results pattern; and
in response to receipt of the water film thickness signal, executing a control action of the subsystem aboard the vehicle, via the controller, to thereby mitigate an effect of the wet surface condition on operation of the vehicle;
wherein executing a control action includes shutting the air baffles, actuating the traction control system, disabling the cruise or adaptive cruise control system, disabling the steering assist system, and/or applying brakes of the brake system.

2. The method of claim 1 wherein the plurality of wet surface detection techniques includes at least a rearward tire splash analysis technique.

3. The method of claim 1 wherein the plurality of wet surface techniques includes at least a side tire splash analysis technique.

4. The method of claim 1 wherein the plurality of wet surface techniques includes at least a tire track analysis technique.

5. The method of claim 1 wherein the plurality of wet surface techniques includes at least a mirrored light image analysis technique.

6. The method of claim 1 wherein the detection rate for each applied wet surface detection technique is determined using the following formula:

PTi
=

sample
⁢

⁢
numbers
⁢

⁢
of
⁢

⁢
wet
⁢

⁢
road
⁢

⁢
decision

N

where the sample numbers of wet road decision represents a number of samples that positively identifies water on the surface by a respective technique during a window period, N represents the total number of images sampled for that respective technique during the window period, and Ti represents the respective technique used to identify the surface condition.

7. The method of claim 1 wherein each detection rate trigger condition is determined as function of comparing each detection rate to a respective predetermined velocity-based threshold value.

8. The method of claim 7 wherein each detection rate trigger condition is normalized.

9. The method of claim 8 wherein each normalized detection rate trigger condition represents a degree of certainty of water present on the surface.

10. The method of claim 7 wherein utilizing the classification module includes utilizing a Dempster-Shafer Evidential theory.

11. The method of claim 7 wherein utilizing the classification module includes utilizing a Bayesian Network theory.

12. The method of claim 7 wherein utilizing the classification module includes utilizing a lookup table.

13. The method of claim 12 wherein the normalized detection rate trigger condition includes one of a positive determination of water present on the surface, a positive indication of water present on the surface, an uncertainty of whether water is present on the surface, and no detection of water on the surface, wherein the positive determination of water present on the surface is representative of the detection rate substantially equal to a value of 1, wherein the positive indication of water present on the road surface is representative of the detection rate being greater than the velocity-based threshold but less than 1, the uncertainty of water present on the surface is representative of the detection rate being less than the velocity-based threshold but greater than 0, and no detection of water on the surface is represented by the detection rate substantially equal to 0.

14. The method of claim 13 wherein the lookup table is generated in an offline process and is stored in a vehicle memory.

15. The method of claim 14 wherein the lookup table includes groups of detection rate trigger conditions, wherein each group includes a respective detection rate trigger condition from each wet surface technique.

16. The method of claim 15 wherein each group in the lookup table is associated with a respective water film thickness range.

17. The method of claim 1 wherein the control action includes using the identified water film thickness to determine and execute an autonomous actuating vehicle braking strategy aboard the vehicle by applying the brakes of the brake system at a braking force sufficient for removing water from the brakes.

18. The method of claim 1 wherein the subsystem is the traction control system of the vehicle, and the control action includes autonomously actuating the traction control system.

19. The method of claim 1 wherein the subsystem is a wireless communication system of the vehicle, the method further comprising providing the identified water film thickness signal to the wireless communication system to thereby alert other vehicles of the identified water film thickness on the surface.

20. The method of claim 1 further comprising using the identified water film thickness signal alerts to alert a driver of the vehicle of a potential reduced traction between vehicle tires and the surface as a result of the identified water film thickness or against a use of a driver assistance system.

21. The method of claim 1 further comprising using the identified water film thickness signal to alert a driver of the vehicle against a use of a driver assistance system.

22. The method of claim 1 wherein the subsystem includes the cruise control system, and th

Assignees

• Gm Global Tech Operations Llc

Inventors

• Zhao Qingrong
• Zhang Qi
• Litkouhi Bakhtiar B
• Wang Jinsong

Classifications

• G01F23/292 Primary

  Light {, e.g. infrared or ultraviolet} · CPC title

• B60T2210/13

  Aquaplaning, hydroplaning · CPC title

• B60T8/172

  Determining control parameters used in the regulation, e.g. by calculations involving measured or detected parameters {(B60T8/17551 takes precedence)} · CPC title

• B60R16/023

  for transmission of signals between vehicle parts or subsystems · CPC title

• G01B11/0616 Primary

  of coating · CPC title