An Efficient Technique for Segmentation of Key Object(s) from Video Shots

  • Authors:
  • JungHwan Oh;JeongKyu Lee;Eswar Vemuri

  • Affiliations:
  • -;-;-

  • Venue:
  • ITCC '03 Proceedings of the International Conference on Information Technology: Computers and Communications
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

The most fundamental task in video processing is to partitionlong video sequences into a number of shots and find a keyframe of each shot for indexing and browsing. In this paper, we want to extract key object(s) instead of key frame. Inorder to do that, we extend our previous technique for shotboundary detection (SBD) to select two candidate frames outof each shot, then propose a new framework to segment object(s) from those selected frames using color quantization andbackground adjustment. We make our scheme cost-effectiveand automatic by avoiding expensive computations, and removing manual processing. Experimental results show that theproposed scheme is promising.