Improved Path Detection in Tracking of Moving and Stationary objects in Moving Cameras

Detection and tracking of moving objects is an important topic of research in the field of video surveillance. Most of the existing video surveillance cameras are stationary and the tracking algorithms are developed for the same. In recent times, the applications are not confined to stationary cameras. There is a lot of technological improvement in surveillance videos and there is a high requirement of tracking a moving object in non stationary cameras. A new calibration procedure for effectively tracking moving objects in non stationary cameras is presented in this paper. The procedure is adapted to Gaussian Mixture Model and Mean Shift Algorithms. Results show that the calibration procedure presented in this paper is best suited for all tracking algorithms.