A comparison on textured motion classification

Oztekin K., Akar G. B.

MULTIMEDIA CONTENT REPRESENTATION, CLASSIFICATION AND SECURITY, vol.4105, pp.722-729, 2006 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 4105
  • Publication Date: 2006
  • Journal Name: MULTIMEDIA CONTENT REPRESENTATION, CLASSIFICATION AND SECURITY
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, EMBASE, MathSciNet, Philosopher's Index, zbMATH
  • Page Numbers: pp.722-729
  • Middle East Technical University Affiliated: Yes

Abstract

Textured motion - generally known as dynamic or temporal texture analysis, classification, synthesis, segmentation and recognition is popular research areas in several fields such as computer vision, robotics, animation, multimedia databases etc. In the literature, several algorithms are proposed to characterize these textured motions such as stochastic and deterministic algorithms. However, there is no study which compares the performances of these algorithms. In this paper, we carry out a complete comparison study. Also, improvements to deterministic methods are given.