Front seat vehicle occupancy detection via seat pattern recognition

• US 8,611,608 B2
• Filed: 08/23/2011
• Issued: 12/17/2013
• 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, Islam, Abu Saeed, Paul, Peter, Xu, Beilei, Mestha, Lalit Keshav
• Primary Examiner(s): GORADIA, SHEFALI DINESH
• Application Number:
  US13/215,401
• Publication Number:
  US 20130051625A1
• Time in Patent Office: 847 Days
• Field of Search: 382/100, 382/104
• 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 front passenger seat is occupied in an image of a motor vehicle traveling in a High Occupancy Vehicle (HOV) lane, 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;

identifying features of a front passenger seat and associated headrest in a front passenger compartment of said motor vehicle where a passenger would be seated, comprising;

performing edge detection on said windshield area of said clipped image to locate vertical, horizontal, and curved lines comprising edge segments of said seat and associated headrest;

determining whether said lines are substantially contiguous; and

determining whether an area bounded by said edge segments is substantially uniform or non-uniform; and

in response to said edge segments being substantially contiguous and said bounded area being substantially uniform, determining from said seat features whether said front passenger seat is occupied.

2. The method of claim 1, wherein said edge detection comprises one of:

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

3. 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 High Occupancy Vehicle (HOV) lane.

4. A system for determining whether a front passenger seat is occupied in an image of a motor vehicle traveling in a High Occupancy Vehicle (HOV) lane, 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;

clipping said image to a windshield area;

identifying features of a front passenger seat and associated headrest in a front passenger compartment of said motor vehicle where a passenger would be seated, comprising;

performing edge detection on said windshield area of said clipped image to locate vertical, horizontal, and curved lines comprising edge segments of said seat and associated headrest;

determining whether said lines are substantially contiguous; and

determining whether an area bounded by said edge segments is substantially uniform or non-uniform; and

in response to said edge segments being substantially contiguous and said bounded area being substantially uniform, determining from said seat features whether said front passenger seat is occupied.

5. The system of claim 4, wherein said edge detection comprises one of:

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

6. The system of claim 4, 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 High Occupancy Vehicle (HOV) lane.