Windshield localization for occupancy detection

• US 8,971,579 B2
• Filed: 04/09/2013
• Issued: 03/03/2015
• Est. Priority Date: 04/09/2013
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Xu, Beilei, Paul, Peter
• Primary Examiner(s): Newman, Michael A
• Assistant Examiner(s): SHIN, SOO JUNG
• Application Number:
  US13/859,047
• Publication Number:
  US 20140301597A1
• Time in Patent Office: 693 Days
• Field of Search: None
• US Class Current: 382/103
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G06V 20/59 inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions

Abstract

A system and method to capture an image of an oncoming target vehicle and localize the windshield of the target vehicle. Upon capturing an image, it is then analyzed to detect certain features of the target vehicle. Based on geometrical relationships of the detected features, the area of the image containing the windshield of the vehicle can then be identified and localized for downstream processing.

Claims

1. A system configured to perform feature-based image analysis for localization of a windshield within an image comprising:

an image capture device operably connected to a data processing device and a target trigger device, wherein said image capture device captures an image upon receiving notification from said target trigger device; and

a processor-usable medium embodying computer code, said processor-usable medium being coupled to said data processing device, said computer program code comprising instructions executable by said processor and configured for;

identifying at least one object of interest on a target vehicle within said image that is not a windshield;

locating said at least one object of interest within said image; and

identifying a windshield of said target vehicle within said image based on a location of said at least one object of interest and a relative geometric relationship between said identified at least one object of interest and said windshield by conversion of physical dimensions to pixel dimensions within said image utilizing one of;

2. The system of claim 1 wherein said computer program code comprising instructions executable by said processor is further configured for:

identifying a region containing said target vehicle within said image.

3. The system of claim 1 wherein identifying objects of interest on said target vehicle comprises analyzing said image for saturated pixels utilizing one of:

a predetermined threshold value of saturation and a predetermined top percentage level of pixel values.

4. The system of claim 1 wherein said computer program code comprising instructions executable by said processor is further configured for:

detecting violations of lane requirements in managed lanes.

5. A computer implemented method of feature-based image analysis for localization of a windshield within an image comprising:

upon receipt of a notification from a target trigger device operably connected to an image capture device, capturing an image utilizing said image capture device;

identifying a target vehicle within said image;

identifying at least one object of interest on said target vehicle that is not a windshield;

locating said at least one object of interest within said image; and

identifying a windshield of said target vehicle within said image based on a location of said at least one object of interest, a relative physical geometric relationship between said identified at least one object of interest and said windshield, and a conversion of physical dimensions to pixel dimensions within said image utilizing one of;

6. The method of claim 5 further comprising localizing said target vehicle upon identification of said target vehicle.

7. The system of claim 5 wherein identifying objects of interest on said target vehicle comprises analyzing said image for saturated pixels utilizing one of:

a predetermined threshold value of saturation, and

a predetermined top percentage level of pixel values.

8. The method of claim 5 further comprising utilizing connected component analysis to identify objects of interest on said target vehicle.

9. The method of claim 5 wherein said objects of interest comprise headlights of said target vehicle.

10. The method of claim 5 further comprising detecting violations of lane requirements in managed lanes.

11. A non-transitory computer-usable medium for identifying a windshield within an image, said computer-usable medium embodying computer program code, said computer program code comprising computer executable instructions configured for:

upon receipt of a notification from a target trigger device operablv connected to an image capture device, capturing an image utilizing said image capture device;

identifying a target vehicle within said image;

identifying at least one object of interest on said target vehicle that is not the windshield; and

identifying a windshield of said target vehicle based on a location of said at least one object of interest and a relative physical geometric relationship between said identified at least one object of interest and said windshield, and a conversion of physical dimensions to pixel dimensions within said image utilizing one of;

12. The non-transitory computer-usable medium of claim 11 further comprising localizing an area of said image containing said windshield.

13. The non-transitory computer-usable medium of claim 11 wherein identifying objects of interest on said target vehicle comprises analyzing said image for saturated pixels utilizing one of:

a predetermined threshold value of saturation, and

a predetermined top percentage level of pixel values.

14. The non-transitory computer-usable medium of claim 11 further comprising utilizing connected component analysis to identify objects of interest on said target vehicle.

15. The non-transitory computer-usable medium of claim 11 wherein said objects of interest comprise headlights of said target vehicle.

16. The non-transitory computer-usable medium of claim 11 further comprising detecting violations of lane requirements in managed lanes.