A MOVING-OBJECT EXTRACTION METHOD ROBUST AGAINST ILLUMINATION LEVEL CHANGES FOR PEDESTRIAN COUNTING SYSTEM

This paper describes Ped-Counter, a real-time pedestrian counting system that uses television camera images and image processing. The system employs a moving object extraction method that is robust against illumination level changes. The paper describes two new processes for extracting moving objects from space-time images using background subtraction. Ped-Counter is shown to be robust against illumination level changes, season, weather, and time. It is also accurate and can effectively extract moving objects.

• Supplemental Notes:
  • Publication Date: 1995 Published By: IEEE Computer Society Press, Los Alamitos CA
• Corporate Authors:

  NTT Human Interface Laboratories

  ,    
• Authors:
  • Tsuchikawa, M
• Conference:
  • International Symposium on Computer Vision (1995 : Coral Gables Fla.). Proceedings
• Publication Date: 1995

Language

• English

Media Info

• Pagination: p. 563-568

Subject/Index Terms

• TRT Terms: Computer vision; Image processing; Pedestrian detectors

Filing Info

• Accession Number: 00777270
• Record Type: Publication
• Source Agency: UC Berkeley Transportation Library
• Files: PATH
• Created Date: Nov 17 1999 12:00AM