Vehicle image sensor cleaning

Patent metadata

Field	Value
Publication number	US-10518751-B2
Application number	US-201715708015-A
Country	US
Kind code	B2
Filing date	Sep 18, 2017
Priority date	Sep 18, 2017
Publication date	Dec 31, 2019
Grant date	Dec 31, 2019

Abstract

A vehicle computer includes a memory and a processor programmed to execute instructions stored in the memory. The instructions include comparing a captured image of a predetermined object to a target image of the predetermined object to quantify a first noise characteristic of the captured image, comparing the first noise characteristic to a first predetermined threshold, and detecting debris on an image sensor that outputs the captured image as a result of comparing the first noise characteristic to the first predetermined threshold.

First claim

The invention claimed is:

1. A vehicle computer comprising:
a memory; and
a processor programmed to execute instructions stored in the memory, the instructions include comparing a captured image of a predetermined object to a target image of the predetermined object to quantify a first noise characteristic of the captured image, comparing the first noise characteristic to a first predetermined threshold, and detecting debris on an image sensor that outputs the captured image as a result of comparing the first noise characteristic to the first predetermined threshold.

2. The vehicle computer of claim 1 , wherein the first noise characteristic is at least one of a signal-to-noise ratio and a peak signal-to-noise ratio and wherein detecting debris on the image sensor includes detecting debris on the image sensor as a result of determining that the first noise characteristic is below the first predetermined threshold.

3. The vehicle computer of claim 2 , wherein the instructions include comparing the captured image to the target image to quantify a second noise characteristic of the captured image, wherein the second noise characteristic includes at least one of a root mean squared error and a mean absolute error, and wherein detecting debris on the image sensor includes detecting debris on the image sensor as a result of determining that the second noise characteristic exceeds a second predetermined threshold.

4. The vehicle computer of claim 3 , wherein detecting debris on the image sensor includes detecting debris on the image sensor as a result of the determining that the first noise characteristic is below the first predetermined threshold and the second noise characteristic exceeds the second predetermined threshold.

5. The vehicle computer of claim 1 , wherein the instructions include initiating cleaning of the image sensor as a result of detecting debris on the image sensor.

6. The vehicle computer of claim 5 , wherein initiating cleaning of the image sensor includes outputting a control signal to a sensor cleaning system.

7. The vehicle computer of claim 1 , wherein the instructions include identifying the predetermined object in an original image captured by the image sensor.

8. The vehicle computer of claim 1 , wherein the instructions include generating the captured image by manipulating the original image captured by the image sensor.

9. The vehicle computer of claim 8 , wherein manipulating the original image includes at least one of cropping the original image and normalizing the original image.

10. The vehicle computer of claim 9 , wherein normalizing the original image includes adjusting at least one of an exposure, a brightness, and an orientation of the predetermined object in the original image.

11. The vehicle computer of claim 9 , wherein cropping the original image includes removing sections of the original image that do not represent the predetermined object.

12. A method comprising:
comparing a captured image of a predetermined object to a target image of the predetermined object to quantify a first noise characteristic of the captured image;
comparing the first noise characteristic to a first predetermined threshold; and
detecting debris on an image sensor that outputs the captured image as a result of comparing the first noise characteristic to the first predetermined threshold.

13. The method of claim 12 , wherein the first noise characteristic is at least one of a signal-to-noise ratio and a peak signal-to-noise ratio and wherein detecting debris on the image sensor includes detecting debris on the image sensor as a result of determining that the first noise characteristic is below the first predetermined threshold.

14. The method of claim 13 , further comprising comparing the captured image to the target image to quantify a second noise characteristic of the captured image, wherein the second noise characteristic includes at least one of a root mean squared error and a mean absolute error, and wherein detecting debris on the image sensor includes detecting debris on the image sensor as a result of determining that the second noise characteristic exceeds a second predetermined threshold.

15. The method of claim 14 , wherein detecting debris on the image sensor includes detecting debris on the image sensor as a result of the determining that the first noise characteristic is below the first predetermined threshold and the second noise characteristic exceeds the second predetermined threshold.

16. The method of claim 12 , further comprising initiating cleaning of the image sensor as a result of detecting debris on the image sensor.

17. The method of claim 12 , further comprising identifying the predetermined object in an original image captured by the image sensor.

18. The method of claim 12 , further comprising generating the captured image by manipulating the original image captured by the image sensor, wherein manipulating the original image includes at least one of cropping the original image and normalizing the original image.

19. The method of claim 18 , wherein normalizing the original image includes adjusting at least one of an exposure, a brightness, and an orientation of the predetermined object in the original image.

20. The method of claim 18 , wherein cropping the original image includes removing sections of the original image that do not represent the predetermined object.

Assignees

• Ford Global Tech Llc

Inventors

• Seubert Christopher Michael
• Nichols Mark Edward
• Peters Cindy Anne
• Holguin Kerrie Nikaido

Classifications

• G06T2207/20132

  Image cropping · CPC title

• B60S1/56

  specially adapted for cleaning other parts or devices than front windows or windscreens {(rear-view mirror arrangements mounted on vehicle exterior including cleaning devices B60R1/0602)} · CPC title

• G06T2207/30248

  Vehicle exterior or interior · CPC title

• G06T7/74 Primary

  involving reference images or patches · CPC title

• H04N23/811

  by dust removal, e.g. from surfaces of the image sensor or processing of the image signal output by the electronic image sensor · CPC title