A MULTIMEDIA DATA MINING FRAMEWORK : MINING INFORMATION FROM TRAFFIC VIDEO SEQUENCES

This paper presents a multimedia data mining framework for analyzing and mining traffic video sequences. It analyzes the traffic video sequences at intersections by using background subtraction image/video segmentation, vehicle tracking and modeling with the multimedia augmented transition network model and multimedia input strings. The spatio-temporal relationships of the vehicle objects in each frame are then captured and modeled. Three real-life traffic video sequences are used to illustrate the effectiveness and robustness of the proposed framework.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/09259902
• Supplemental Notes:
  • Publication Date: July 2002
• Corporate Authors:

  Florida International University, Miami

  School of Computer Engineering
  Miami, FL  United States  33199
• Authors:
  • Chen, Shu-Ching
  • Shyu, Mei-Ling
  • Zhang, Chengcui
  • Strickrott, J
• Publication Date: 2002

Language

• English

Media Info

• Pagination: p. 61-77
• Serial:
  • Journal of intelligent information systems. Vol. 19, no. 1
  • Publisher: Florida International University, Miami
  • ISSN: 0925-9902

Subject/Index Terms

• TRT Terms: Databases; Image processing; Traffic flow; Traffic surveillance
• Subject Areas: Operations and Traffic Management;

Filing Info

• Accession Number: 00944253
• Record Type: Publication
• Source Agency: UC Berkeley Transportation Library
• Files: PATH
• Created Date: Jul 3 2003 12:00AM