Multi variant feature similarity based behavior tracking in video surveillance using ann

Abstract

The problem of video surveillance has been well studied which has been adapted for several issues. The behavior of any human can be monitored through video surveillance. There are number of approaches available for the video surveillance and behavior analysis. The previous methods uses background models, object tracking for the problem of behavior analysis. The methods suffer with poor accuracy in behavior analysis. To improve the performance, a multi variant feature similarity model based behavior tracking in video surveillance is presented. The method involves in identifying interest points throughout the images of video. Second, the changing feature has been identified to measure the multi variant feature similarity by using multi variant feature model. Based on the MVFS, the object tracking is performed. The human tracking is performed in the same way and the multi variant features are trained with artificial neural network which has number of behavior classes. At the testing phase, the video has been removed with background features according to the multi feature model adapted. Once the object has been identified, then tracking and behavior analysis is performed by measuring MVFS with the features at different behavior classes. The artificial neural network has been used for the classification of behavior identified through video surveillance. The method would produce higher accuracy and improves the performance.