MULTIMODAL TRACKING SYSTEM FOR BOARDER SURVEILLANCE

Abstract

Video surveillance activity is the activity of observing the behavior of object under motion, that object can be a human being or vehicle. The surveillance at boarders is a very sensitive issue of security of nation. But unfortunately till date no effective automated real time boarder surveillance system has been developed which can handle the real problems of the boarders and provide solutions to them. With the proposed method for tracking object on boarders, with the help of two features (visual and audio/ seismic signal information) a real time multimodal system has been developed which caters the solution to the problems at boarder i.e. large distance between the camera and the object. It is the major problem, due to the scenario of the boarder. This problem is overcome by adding seismic signal information, with the help of which we are able to identify without viewing the scene that how many and which object (tank/normal training vehicle) is there in the field. It is done by extracting the unique pattern available in the mixed seismic signal, if there is more than two vehicle/objects in the field. And the normal tracking is performed on the basis of visual information. For this specific task in this work we have used the simple and efficient tracking algorithm of optimization (PSO) Particle Swarm Optimization.