FRONT SEAT VEHICLE OCCUPANCY DETECTION VIA SEAT PATTERN RECOGNITION

• US 20130051625A1
• Filed: 08/23/2011
• Published: 02/28/2013
• Est. Priority Date: 08/23/2011
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: FAN, Zhigang, PAUL, Peter, XU, Beilei, MESTHA, Lalit Keshav, ISLAM, Abu Saeed
• Granted Patent: US 8,611,608 B2
• Time in Patent Office: Days
• US Class Current: 382/104
• CPC Class Codes: G06V 10/143 Sensing or illuminating at different wavelengths
• CPC Class Codes: G06V 20/593 Recognising seat occupancy
• CPC Class Codes: G06V 40/162 using pixel segmentation or colour matching

Abstract

What is disclosed is a system and method for determining whether a front seat in a motor vehicle is occupied based on seat pattern recognition. The present invention takes advantage of the observation that an unoccupied seat of a motor vehicle exhibits features which are distinguishable from an occupied seat. An unoccupied motor vehicle seat typically features long contiguous horizontal line segments and curve segments, and substantially uniform areas encompassed by these segments which are not present in an occupied seat. The present method provides a long horizontal edge test which uses location information within a defined window of the image, edge linking, softness of the edge, number of lines, line/curve fitting, and other techniques to locate horizontal edges in the image which define a seat, and a uniformity step which determines whether the area bounded by the horizontal edges is relatively uniform indicating an unoccupied seat.

Claims

1. A method for determining whether a seat in an image of a motor vehicle is occupied, the method comprising:

receiving an image of a motor vehicle which is intended to be analyzed for seat occupancy;

analyzing said image to determine features of a seat in said vehicle; and

determining from said seat features whether said seat is occupied.

2. The method of claim 1, further comprising:

clipping said image to a windshield area; and

analyzing said windshield area of said image to determine said seat features.

3. The method of claim 1, wherein determining whether said seat is occupied comprises determining whether said seat and headrest boundaries are contiguous.

4. The method of claim 1, wherein determining whether said seat is occupied comprises:

analyzing an area of said seat for reflectance; and

determining whether said reflectance is uniform.

5. The method of claim 1, wherein determining said seat features comprises:

performing edge detection to determine line and curve segments; and

analyzing said line segments to determine a boundary of a seat and headrest.

6. The method of claim 5, wherein said edge detection comprises one of:

a horizontal edge detection followed by edge linking, and a Hough Transform.

7. The method of claim 1, further comprising using a face detection algorithm to determine whether said seat is occupied.

8. The method of claim 1, further comprising alerting an authority in the instance wherein a front passenger seat of said motor vehicle is not occupied and said motor vehicle is traveling in a HOV lane.

9. A system for determining whether a seat in an image of a motor vehicle is occupied, the system comprising:

a memory and a storage medium; and

a processor in communication with and said storage medium and said memory, said processor executing machine readable instructions for performing the method of;

receiving an image of a motor vehicle which is intended to be analyzed for seat occupancy;

analyzing said image to determine features of a seat in said vehicle; and

determining from said seat features whether said seat is occupied.

10. The system of claim 9, further comprising:

clipping said image to a windshield area; and

analyzing said windshield area of said image to determine said seat features.

11. The system of claim 9, wherein determining whether said seat is occupied comprises determining whether said seat and headrest boundaries are contiguous.

12. The system of claim 9, wherein determining whether said seat is occupied comprises:

analyzing an area of said seat for reflectance; and

determining whether said reflectance is uniform.

13. The system of claim 9, wherein determining said seat features comprises:

performing edge detection to determine line and curve segments; and

analyzing said line segments to determine a boundary of a seat and headrest.

14. The system of claim 13, wherein said edge detection comprises one of:

a horizontal edge detection followed by edge linking, and a Hough Transform.

15. The system of claim 9, further comprising using a face detection algorithm to determine whether said seat is occupied.

16. The system of claim 9, further comprising alerting an authority in the instance wherein a front passenger seat of said motor vehicle is not occupied and said motor vehicle is traveling in a HOV lane.

17. A computer implemented method for determining whether a seat in an image of a motor vehicle is occupied, the method comprising:

receiving an image of a motor vehicle which is intended to be analyzed for seat occupancy;

clipping said image to a windshield area of said motor vehicle;

performing edge detection to determine line and curve segments;

determining whether said line segments form seat features comprising at least one of;

a seat and a headrest; and

determining from said seat features whether said seat is occupied.

18. The computer implemented method of claim 17, wherein determining whether said seat is occupied comprises determining whether said seat and headrest boundaries are contiguous.

19. The computer implemented method of claim 17, wherein determining whether said seat is occupied comprises:

analyzing an area of said seat for reflectance; and

determining whether said reflectance is uniform.

20. The computer implemented method of claim 17, wherein said edge detection comprises one of:

a horizontal edge detection followed by edge linking, and a Hough Transform.

21. The computer implemented method of claim 17, further comprising using a face detection algorithm to determine whether said seat is occupied.

22. The computer implemented method of claim 17, further comprising alerting an authority in the instance wherein a front passenger seat of said motor vehicle is not occupied and said motor vehicle is traveling in a HOV lane.