Multiple moving objects tracking for video surveillance systems

This paper is devoted to present an algorithm that is able to perform simultaneous moving objects tracking for video surveillance systems. The algorithm starts with the distinction between the moving objects versus background scene. The distinction is achieved based on background subtraction method. To be immune to anomalous components, background subtraction is integrated with two additional mechanisms: shadow detection and background frame adaptation. When the moving objects are identified and characterized by their features, the algorithm switches to tracking mode. The goals of tracking are to determine when a new object enters the filed of view, compute the correspondence matching between objects in previous frame and objects currently to be tracked, and estimate the spatial position of each object. The algorithm uses two similarity functions and dynamic template matching to achieve the aforementioned goals. The results are shown the flexibility of the proposed algorithm to cope with multiple simultaneously objects and occlusions.