VEHICLE VISION SYSTEM WITH LENS POLLUTION DETECTION

• US 20180316828A1
• Filed: 07/09/2018
• Published: 11/01/2018
• Est. Priority Date: 03/27/2012
• Status: Active Grant

• Current Assignee: Magna Electronics Incorporated (Magna International Incorporated)
• Original Assignee: Magna Electronics Incorporated (Magna International Incorporated)
• Inventors: Lu, Yuesheng, Hunt, Shawn T.
• Granted Patent: US 10,397,451 B2
• Time in Patent Office: Days
• CPC Class Codes: B60R 1/00 Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
• CPC Class Codes: B60R 2300/30 characterised by the type of image processing
• CPC Class Codes: H04N 23/811 by dust removal, e.g. from surfaces of the image sensor or processing of the image signal output by the electronic image sensor
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

A vehicular vision system includes a camera and a processor operable to process captured image data. With the vehicle moving, the processor models outputs of photosensing elements of the camera as Gaussian distributions. With the vehicle moving, the processor determines an output of respective photosensing elements over multiple frames of captured image data, and determines whether the output of a photosensing element fits the Gaussian distribution for that element. Responsive to determination that the output of the element fits within the respective Gaussian distribution for that element, the system classifies that element as a blocked element. Responsive to determination that the output of the element does not fit within the respective Gaussian distribution for that element, the system classifies that element as a not blocked element. Responsive to determination that the ratio of blocked elements to not blocked elements is greater than a threshold ratio, a blockage condition is determined.

Claims

1. A vision system for a vehicle, said vision system comprising:

a camera disposed at a vehicle and having a field of view exterior of the vehicle, said camera operable to capture frames of image data;

wherein said camera comprises a lens and an imager comprising an array of photosensing elements having multiple columns of photosensing elements and multiple rows of photosensing elements;

a processor operable to process image data captured by said camera;

wherein, with the vehicle moving, and with said camera capturing image data, said processor models outputs of photosensing elements as Gaussian distributions;

wherein, with the vehicle moving, and with said camera capturing frames of image data, said processor determines an output of respective ones of said modeled photosensing elements over multiple frames of captured image data;

wherein, with the vehicle moving, and with said camera capturing frames of image data, said processor determines whether the output of a modeled photosensing element fits the respective Gaussian distribution for that photosensing element;

wherein, responsive to determination that the output of the modeled photosensing element fits within the respective Gaussian distribution for that photosensing element, said vision system classifies that photosensing element as a blocked element;

wherein, responsive to determination that the output of the modeled photosensing element does not fit within the respective Gaussian distribution for that photosensing element, said vision system classifies that photosensing element as a not blocked element; and

wherein, responsive to determination over multiple frames of captured image data that the ratio of the number of photosensing elements classified as a blocked element to the number of photosensing elements classified as a not blocked element is greater than a threshold ratio, a blockage condition is determined.

2. The vision system of claim 1, wherein the threshold ratio comprises at least a thirty percent ratio of blocked elements to not blocked elements.

3. The vision system of claim 1, wherein said processor models outputs of photosensing elements as respective Gaussian distributions during an initialization period.

4. The vision system of claim 1, wherein, when the vehicle is not moving, said vision system does not determine, for each frame of captured image data, whether outputs of modeled photosensing elements fit within respective Gaussian distributions for those photosensing elements.

5. The vision system of claim 1, wherein, responsive to a blockage condition being determined, said system at least one of (i) generates an alert, (ii) adapts processing of captured image data to at least partially accommodate for the blockage condition and (iii) cleans said lens.

6. The vision system of claim 1, wherein said processor is incorporated in circuitry of said camera.

7. The vision system of claim 1, wherein said processor is incorporated in circuitry of an electronic control unit of the vehicle.

8. The vision system of claim 1, wherein the vehicle moving comprises the vehicle being driven forward on a road.

9. The vision system of claim 1, wherein said camera comprises a CMOS camera.

10. The vision system of claim 9, wherein said imager comprises at least 640 columns of photosensing elements and at least 480 rows of photosensing elements.

11. The vision system of claim 1, wherein said camera is part of a multi-camera birds-eye surround view system of the equipped vehicle.

12. A vision system for a vehicle, said vision system comprising:

a camera disposed at a vehicle and having a field of view exterior of the vehicle, said camera operable to capture frames of image data;

wherein said camera comprises a lens and an imager comprising an array of photosensing elements having multiple columns of photosensing elements and multiple rows of photosensing elements;

a processor operable to process image data captured by said camera;

wherein, with the vehicle moving, and with said camera capturing image data, said processor models outputs of photosensing elements as Gaussian distributions;

wherein said processor models outputs of photosensing elements as respective Gaussian distributions during an initialization period;

wherein, with the vehicle moving after the initialization period, and with said camera capturing frames of image data, said processor determines an output of respective ones of said modeled photosensing elements over multiple frames of captured image data;

wherein, with the vehicle moving, and with said camera capturing frames of image data, said processor determines whether the output of a modeled photosensing element fits within the respective Gaussian distribution for that photosensing element;

wherein, responsive to determination that the output of the modeled photosensing element fits within the respective Gaussian distribution for that photosensing element, said vision system classifies that photosensing element as a blocked element;

wherein, responsive to determination that the output of the modeled photosensing element does not fit within the respective Gaussian distribution for that photosensing element, said vision system classifies that photosensing element as a not blocked element;

wherein, responsive to determination over multiple frames of captured image data that the ratio of the number of photosensing elements classified as a blocked element to the number of photosensing elements classified as a not blocked element is greater than a threshold ratio, a blockage condition is determined; and

wherein, when the vehicle is not moving, said vision system does not determine, for each frame of captured image data, whether outputs of modeled photosensing elements fit within respective Gaussian distributions for those photosensing elements.

13. The vision system of claim 12, wherein the threshold ratio comprises at least a thirty percent ratio of blocked elements to not blocked elements.

14. The vision system of claim 12, wherein, responsive to a blockage condition being determined, said system at least one of (i) generates an alert, (ii) adapts processing of captured image data to at least partially accommodate for the blockage condition and (iii) cleans said lens.

15. The vision system of claim 12, wherein said processor is incorporated in circuitry of said camera.

16. The vision system of claim 12, wherein said processor is incorporated in circuitry of an electronic control unit of the vehicle.

17. The vision system of claim 12, wherein the vehicle moving comprises the vehicle being driven forward on a road.

18. A vision system for a vehicle, said vision system comprising:

a camera disposed at a vehicle and having a field of view exterior of the vehicle, said camera operable to capture frames of image data;

wherein said camera comprises a lens and an imager comprising an array of photosensing elements having multiple columns of photosensing elements and multiple rows of photosensing elements;

a processor operable to process image data captured by said camera;

wherein, with the vehicle driven forward along a road, and with said camera capturing image data, said processor models outputs of photosensing elements as Gaussian distributions;

wherein said processor models outputs of photosensing elements as respective Gaussian distributions during an initialization period;

wherein, with the vehicle driven forward along the road after the initialization period, and with said camera capturing frames of image data, said processor determines an output of respective ones of said modeled photosensing elements for each frame of captured image data;

wherein, with the vehicle driven forward along the road, and with said camera capturing frames of image data, said processor determines whether the output of a modeled photosensing element fits within the respective Gaussian distribution for that photosensing element;

wherein, responsive to determination that the output of the modeled photosensing element fits within the respective Gaussian distribution for that photosensing element, said vision system classifies that photosensing element as a blocked element;

wherein, responsive to determination that the output of the modeled photosensing element does not fit within the respective Gaussian distribution for that photosensing element, said vision system classifies that photosensing element as a not blocked element;

wherein, responsive to determination over multiple frames of captured image data that the ratio of the number of photosensing elements classified as a blocked element to the number of photosensing elements classified as a not blocked element is greater than a threshold ratio, a blockage condition is determined; and

wherein, responsive to a blockage condition being determined, said system at least one of (i) generates an alert, (ii) adapts processing of captured image data to at least partially accommodate for the blockage condition and (iii) cleans said lens.

19. The vision system of claim 18, wherein said processor is incorporated in circuitry of said camera.

20. The vision system of claim 18, wherein said processor is incorporated in circuitry of an electronic control unit of the vehicle.