MULTIPLE VEHICLE DETECTION AND TRACKING

This article describes a real time vision system that recognizes and tracks multiple cars from video sequences taken from a car driving on the road. Recognition is accomplished by combining the analysis of single image frames with the analysis of the motion information provided by multiple consecutive image frames. The dynamic creation and termination of tracking processes optimizes the amount of computational resources spent and allows fast detection and tracking of multiple cars. Experimental results demonstrate robust, real-time recognition and tracking over thousands of image frames.

• Supplemental Notes:
  • Publication Date: 1997 Published By: SPIE, Bellingham WA
• Corporate Authors:

  National Institute of Standards and Technology

  Intelligent Systems Division
  Gaithersburg, MD  United States  20899
• Authors:
  • Betke, M
  • Haritaoglu, E
  • Davis, L S
• Conference:
  • AIPR Workshop (25th : 1996 : Washington, D.C.). Emerging applications of computer vision : proceedings of SPIE, vol. 2962
• Publication Date: 1997

Language

• English

Media Info

• Pagination: p. 104-110

Subject/Index Terms

• TRT Terms: Computer vision; In vehicle sensors; Pattern recognition systems

Filing Info

• Accession Number: 00775369
• Record Type: Publication
• Source Agency: UC Berkeley Transportation Library
• Files: PATH
• Created Date: Nov 17 1999 12:00AM