A saliency based object tracking method

A novel three-stage framework for object tracking under stationary background conditions is proposed in this paper. The first stage uses an attention based method to extract motion information. The second stage then applies a region growing and matching technique to motion vectors to obtain motion segmentation. Finally the moving objects are tracked based on the displacements of region centroids. The method is tested on various real-world video data and empirical results show that the proposed approach can track moving objects and extract motion information from non-rigid objects such as moving people without prior knowledge of the objectpsilas size or shape.