Research Article Open Access

Human Behavior Classification Using Multi-Class Relevance Vector Machine

B. Yogameena, S. Veera Lakshmi, M. Archana and S. Raju Abhaikumar

Abstract

Problem statement: In computer vision and robotics, one of the typical tasks is to identify specific objects in an image and to determine each object’s position and orientation relative to coordinate system. This study presented a Multi-class Relevance Vector machine (RVM) classification algorithm which classifies different human poses from a single stationary camera for video surveillance applications. Approach: First the foreground blobs and their edges are obtained. Then the relevance vector machine classification scheme classified the normal and abnormal behavior. Results: The performance proposed by our method was compared with Support Vector Machine (SVM) and multi-class support vector machine. Experimental results showed the effectiveness of the method. Conclusion: It is evident that RVM has good accuracy and lesser computational than SVM.

Journal of Computer Science
Volume 6 No. 9, 2010, 1021-1026

DOI: https://doi.org/10.3844/jcssp.2010.1021.1026

Submitted On: 31 December 2009 Published On: 30 September 2010

How to Cite: Yogameena, B., Lakshmi, S. V., Archana, M. & Abhaikumar, S. R. (2010). Human Behavior Classification Using Multi-Class Relevance Vector Machine. Journal of Computer Science, 6(9), 1021-1026. https://doi.org/10.3844/jcssp.2010.1021.1026

  • 3,053 Views
  • 2,846 Downloads
  • 3 Citations

Download

Keywords

  • Video surveillance
  • pose
  • multi class
  • relevance vector machines
  • support vector machine