Illumination invariant object tracking based on multiscale phase

Illumination change usually results in challenging problems for many computer vision applications such as recognition, tracking and motion analysis. In this paper, an illumination invariant object tracking approach is proposed. Video feature information is captured using a monogenic scale space representation. From this representation, multiscale phase information, which has the advantage of being invariant to illumination change, can be extracted. By minimizing an energy function, multiscale phase information between frames are matched. Based on the matched phase information, moving objects under high illumination variation can be successfully tracked. Experimental results show that the presented approach is robust to illumination change. As a comparison, we also demonstrate the tracking results from the mean shift tracker, it is proved that our approach outperforms the mean shift tracker under the high lighting change environment.