Support vector regression for surveillance purposes


Özer S., CIRPAN H. A. , Kabaoglu N.

MULTIMEDIA CONTENT REPRESENTATION, CLASSIFICATION AND SECURITY, vol.4105, pp.442-449, 2006 (Journal Indexed in SCI) identifier

  • Publication Type: Article / Article
  • Volume: 4105
  • Publication Date: 2006
  • Title of Journal : MULTIMEDIA CONTENT REPRESENTATION, CLASSIFICATION AND SECURITY
  • Page Numbers: pp.442-449

Abstract

This paper addresses the problem of applying powerful statistical pattern classification algorithm based on kernel functions to target tracking on surveillance systems. Rather than directly adapting a recognizer, we develop a localizer directly using the regression form of the Support Vector Machines (SVM). The proposed approach considers to use dynamic model together as feature vectors and makes the byperplane and the support vectors follow the changes in these features. The performance of the tracker is demonstrated in a sensor network scenario with a constant velocity moving target on a plane for surveillance purpose.