Moving Cast Shadows Detection Using Ratio Edge.pdf

1202 IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 9, NO. 6, OCTOBER 2007 Moving Cast Shadows Detection Using Ratio Edge Wei Zhang, Xiang Zhong Fang, Xiaokang K. Yang, Senior Member, IEEE, and Q. M. Jonathan Wu, Member, IEEE Abstract—Moving objects segmentation plays a very important role in real-time image analysis. However, as one of the common parts in the natural scenes, shadows severely interfere with the accuracy of moving objects detection in video surveillance. In this paper, we present a novel method for moving cast shadows detection. Based on the analysis of the physical model of moving shadows, we prove that the ratio edge is illumination invariant. The distribution of the ratio edge is discussed and a significance test is performed to classify each moving pixel into foreground object or moving shadow. Intensity constraint and geometric heuristics are imposed to further improve the performance. Experiments on various typical scenes exhibit the robustness of the proposed method. Extensively quantitative evaluation and comparison demonstrate that the proposed method significantly outperforms state-of-the-art methods. Index Terms—Chi-square distribution, moving objects detec- tion, ratio edge, shadow detection. I. INTRODUCTION MOVING objects segmentation is an important topic incomputer vision applications, including video confer- ences, vehicle tracking, and three-dimensional (3-D) object identification, and has been actively investigated in recent years. However, in real world scenes, the performance of the state-of-the-art methods may be plagued by the moving cast shadows. For example, in a traffic surveillance situation, shadows cast by moving vehicles may be segmented as part of vehicles, which not only interfere with the size and shape in- formation but also generate occlusions. Therefore, an effective shadow detection algorithm can greatly benefit the practical image analysis system. Essentially, shadow is formed by the change of illumination conditions and s