ROBUST OBJECT TRACKING IN VIDEO AND OCCLUSION HANDLING USING PATTERN CLASSIFICATION

Abstract

The main aspect of ours that we propose a robust object tracking algorithm for occlusion reduction in video object tracking using pattern classification based on pixel-based change detection methods and a sparse collaborative model that exploits both holistic templates and local representations to account for drastic appearance changes. Within the proposed collaborative appearance model, we develop a sparse discriminative classifier (SDC) and sparse generative model (SGM) for object tracking. In the SDC module, we present a classifier that separates the foreground object from the background based on holistic templates. In the SGM module, we propose a histogram-based method that takes the spatial information of each local patch into consideration. The update scheme considers both the most recent observations and original templates, thereby enabling the proposed algorithm to deal with appearance changes effectively and alleviate the tracking drift problem. In this we are using some important features like object tracking, collaborative model, sparse representation, feature selection, occlusion handling. So as to enhance our tracking.