Discriminatively trained patch-based model for occupant classification

This study presents a vision-based occupant classification method, essential for developing a system which can intelligently decide when to turn on airbags based on vehicle occupancy. To circumvent intra-class variance, the study considers the empty class as a reference and describes the occupant class by using appearance difference rather than the traditional methods of using appearance itself. Each class is modelled using a set of representative parts called patches. Each patch is represented by a Gaussian distribution. The approach successfully alleviates the mis-classification problem which results from severe lighting change, making the image locally overexposed or underexposed. Instead of using maximum likelihood for patch selection and estimating the parameters of the proposed generative models, the proposed method discriminatively learns models through a boosting algorithm by minimising training error. Experimental results from many videos from a camera deployed on a moving platform demonstrate the effectiveness of the proposed approach.

• Record URL:
  • https://doi.org/10.1049/iet-its.2011.0048
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/1751956X
• Authors:
  • Huang, S S
• Publication Date: 2012-6

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: pp 132-138
• Serial:
  • IET Intelligent Transport Systems
  • Volume: 6
  • Issue Number: 2
  • Publisher: Institution of Engineering and Technology (IET)
  • ISSN: 1751-956X
  • EISSN: 1751-9578
  • Serial URL: https://ietresearch.onlinelibrary.wiley.com/journal/17519578
• Publication flags:

  Open Access (libre)

Subject/Index Terms

• TRT Terms: Air bags; Computer vision; Discriminant analysis; Image analysis; Occupant protection devices; Vehicle occupants
• Uncontrolled Terms: Gaussian distribution
• Subject Areas: Highways; Passenger Transportation; Safety and Human Factors; Vehicles and Equipment; I91: Vehicle Design and Safety;

Filing Info

• Accession Number: 01375664
• Record Type: Publication
• Files: TRIS
• Created Date: Jul 18 2012 4:11PM