Moving Cast Shadow Removal Based on Texture Feature and Color Space

Moving cast shadow detection is an essential and pivotal problem in image processing. One problem is that many existed moving cast shadow detection methods are only suitable for some specific situations. In order to solve this problem, a cast shadow detection and elimination algorithm based on the combination of texture feature and YUV color space is proposed in this paper. Firstly, we detect moving object using PBAS algorithm which suppress ghost region. Furthermore, a part of cast shadow candidate region is obtained by texture detection. Then, the other cast shadow candidate region is obtained by shadow detection based on YUV color space. Finally, two parts of the cast shadow candidate regions are screened and merged by the shadow feature. Experimental results show that the proposed method has higher detection rates and discrimination rates compared to some well-known methods.