An Efficient Method of Shadow Elimination Based on Image Region Information in HSV Color Space

In recent years, people have paid more attention to the shadow detection of moving target in video surveillance system. The shadow will directly affect the accuracy of moving target recognition, and do adverse effects on the subsequent processing such as target segmentation, target extraction and target tracking. So shadow elimination is an important part of intelligent video surveillance system. The paper proposes an efficient method of shadow elimination based on HSV color space and image region information. The proposed method uses the shadow elimination algorithm based on HSV color space to obtain the shadow regions to be dealt with. Then combining with the image region information, it judges whether the four boundary points of the moving target are shadow points. Eliminate the connected regions which shadow points exist from outer to inner along the shadow direction. It can avoid the regions whose color features are close to shadow inside the target object to be mistakenly eliminated. The experimental results show that the proposed method significantly improves the quality of shadow elimination.