Methods and systems for vehicle tire analysis using vehicle mounted cameras

Patent metadata

Field	Value
Publication number	US-10078892-B1
Application number	US-201715461269-A
Country	US
Kind code	B1
Filing date	Mar 16, 2017
Priority date	Mar 16, 2017
Publication date	Sep 18, 2018
Grant date	Sep 18, 2018

Abstract

Methods and systems are provided for analyzing tires of a vehicle utilizing camera images from one or more cameras mounted on the vehicle (or infrastructure). In one example, the method includes obtaining camera images of one or more tires of a vehicle, utilizing one or more cameras that are mounted on the vehicle, during operation of the vehicle; and processing the camera images, via a processor, in order to generate an analysis of one or more of the tires based on the images that were obtained via the one or more cameras that are mounted on the vehicle.

First claim

What is claimed is:

1. A method comprising:
obtaining camera images of one or more tires of a vehicle, utilizing one or more cameras, during operation of the vehicle;
processing the camera images, via a processor, in order to generate an analysis of one or more of the tires based on the images that were obtained via the one or more cameras that are mounted on the vehicle;
determining, using data provided by one or more sensors, a speed of the vehicle; and
determining, using data provided by the one or more sensors, a turn angle of a turn of the vehicle;
wherein the obtaining of the camera images comprises obtaining the camera images when the turn angle is greater than a first predetermined threshold and the speed is less than a second predetermined threshold.

2. The method of claim 1 , wherein the obtaining of the camera images comprises obtaining camera images of the one or more tires from one or more side cameras that are mounted on one or more sides of the vehicle, when the vehicle is making a turn.

3. The method of claim 2 , wherein the obtaining of the camera images comprises:
obtaining first images of a tread of a respective tire from a first respective camera that is on a first side of the vehicle, during the turn; and
obtaining second images of a sidewall of the respective tire from a second respective camera that is on a second side of the vehicle, opposite the first side, during the turn.

4. The method of claim 1 , wherein the processing of the camera images comprises:
determining a first tread pattern of a respective tire based on the camera images; and
comparing the first tread pattern with one or more known second tread patterns from a historical database of a different tire, or the vehicles tires when rather new, having a known amount of wear.

5. The method of claim 4 , wherein the determining of the first tread pattern comprises determining the first tread pattern using a histogram of oriented gradient (HoG) values.

6. The method of claim 4 , wherein the determining of the first tread pattern comprises determining the first tread pattern using a machine learning method or a deep learning neural network model.

7. The method of claim 4 , further comprising:
updating the historical database using the first tread pattern.

8. The method of claim 1 , wherein the processing of the camera images comprises:
determining a first sidewall pattern of a respective tire based on the camera images; and
comparing the first sidewall pattern with one or more known sidewall patterns of a different tire having a known amount of wear.

9. The method of claim 1 , further comprising:
determining whether a warning is appropriate based on the analysis of the tire; and
providing the warning, via instructions provided by the processor, when it is determined that the warning is appropriate.

10. The method of claim 1 , further comprising:
obtaining additional sensor data pertaining to a wheel of the vehicle;
wherein the processing of processing of the camera images further comprises processing the camera images using the additional sensor data pertaining to the wheel of the vehicle, via the processor, in order to facilitate the analysis of the one or more of the tires based on the images that were obtained via the one or more cameras that are mounted on the vehicle.

11. A method comprising:
obtaining camera images of tracks made by one or more tires of a vehicle, utilizing one or more cameras that are mounted on the vehicle, during operation of the vehicle; and
processing the camera images of the tracks, via a processor, in order to generate an analysis of one or more of the tires based on the images that were obtained via the one or more cameras that are mounted on the vehicle;
wherein the processing of the camera images of the tracks comprises, via a processor:
determining a first tread pattern of a respective tire based on the tracks made by the one or more tires, using the camera images of the tracks; and
comparing the first tread pattern with one or more known second tread patterns of a different tire having a known amount of wear.

12. The method of claim 11 , wherein the obtaining of the camera images comprises obtaining camera images of the tracks from a rear camera when the vehicle is driving forward.

13. The method of claim 11 , wherein the obtaining of the camera images comprises obtaining camera images of the tracks from a front camera when the vehicle is driving in reverse.

14. The method of claim 11 , further comprising:
determining, using data provided by one or more sensors or map data, a condition of a road or type of the road on which the vehicle is travelling;
wherein the camera images are obtained and processed when the condition represents not a dry road, but when the condition represents a wet, snowy, sandy, or muddy road.

15. The method of claim 11 , wherein the determining of the first tread pattern comprises determining the first tread pattern using a histogram of oriented gradient (HoG) values.

16. The method of claim 11 , wherein the determining of the first tread pattern comprises determining the first tread pattern using a neural network model machine learning method or a deep learning neural network model.

17. The method of claim 11 , further comprising:
obtaining additional sensor data pertaining to a wheel of the vehicle;
wherein the processing of processing of the camera images further comprises processing the camera images using the additional sensor data pertaining to the wheel of the vehicle, via the processor, in order to facilitate the analysis of the one or more of the tires based on the images that were obtained via the one or more cameras that are mounted on the vehicle.

18. A vehicle comprising:
one or more tires;
one or more cameras onboard the vehicle, the one or cameras mounted on the vehicle as part of the vehicle, or low on an infrastructure, as part of the vehicle, the one or more cameras configured to generate camera images of tracks made by one or more of the tires; and
a processor onboard the vehicle and configured to process the camera images in order to generate an analysis of one or more of the tires based on the images that were obtained via the one or more cameras that are mounted on the vehicle, wherein the processor is configured to generate the analysis by:
determining a first tread pattern of a respective tire based on the tracks made by the one or more tires, using the camera images of the tracks; and
comparing the first tread pattern with one or more known second tread patterns of a different tire having a known amount of wear.

Assignees

• Gm Global Tech Operations Llc

Inventors

• Wang Jinsong
• Litkouhi Bakhtiar B

Classifications

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• H04N23/80

  Camera processing pipelines; Components thereof · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G01M17/027

  using light, e.g. infrared, ultraviolet or holographic techniques · CPC title