Background modelling, detection and tracking of human in video surveillance system

Abstract

Video Surveillance System is a powerful tool used for monitoring people and their activities for public security. The motive of having surveillance system is not only to put cameras in place of human eyes, but also making it capable for recognizing activities automatically. In this paper, human detection and tracking is performed on Weizmann dataset having various activities like run, bend, hand wave, skip, etc. First background modelling is done by taking mean of first n frames. After this, human detection is done using background subtraction algorithm and then tracking is done using Kalman filter. Result of each stage has been discussed. The proposed methodology shows promising results which can further be used for activity recognition.