A Language for Content-Based Video Retrieval

  • Authors:

  • Forouzan Golshani;Nevenka Dimitrova

  • Affiliations:

  • Department of Computer Science, Arizona State University, Tempe, Arizona 85287-5406. E-mail: golshani@asu.edu;Philips Research, 345 Scarborough Rd., Briarcliff Manor, NY 10510. E-mail: nvd@philabs.research.philips.com

  • Venue:
  • Multimedia Tools and Applications
  • Year:
  • 1998

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present an effective technique for automatic extraction,representation, and classification of digital video, and a visuallanguage for formulation of queries to access the semantic informationcontained in digital video. We have devised an algorithm thatextracts motion information from a video sequence. This algorithmprovides a low-cost extension to the motion compensation component ofthe MPEG compression algorithm. In this paper, we present a visuallanguage called VEVA for querying multimedia information in general,and video semantic information in particular. Unlike many otherproposals that concentrate on browsing the data, VEVA offers acomplete set of capabilities for specifying relationships between theimage components and formulating queries that search for objects,their motions and their other associated characteristics. VEVA hasbeen shown to be very expressive in this context mainly due to thefact that many types of multimedia information are inherently visualin nature.