Date of Award

2009

Publication Type

Master Thesis

Degree Name

M.Sc.

Department

Computer Science

First Advisor

Dr. Imran Ahmad

Keywords

Applied sciences

Rights

info:eu-repo/semantics/openAccess

Creative Commons License

Creative Commons Attribution-Noncommercial 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License

Abstract

Intelligent visual surveillance which attempts to detect, recognize and track certain objects from image sequences is becoming an active research topic in computer vision community. Background modeling and foreground segmentation are the first two and the most important steps in any intelligent visual surveillance systems. The accuracy of these two steps highly effects performance of the following steps. In this thesis, we propose a simple and novel method which employs histogram based median method for background modeling and a fuzzy k-Means clustering approach for foreground segmentation. Experiments on a set of videos and benchmark image sequences show the effectiveness of the proposed method. Compared with other two contemporary methods - k -Means clustering and Mixture of Gaussians (MoG) - the proposed method is not only time efficient but also provides better segmentation results.

Share

COinS