An efficient shadow removing algorithm based on projection features

In order to remove the problem of the shadow of moving vehicles in video surveillance, this paper presents an algorithm based on projection features of the connected regions to eliminate the dynamic shadow. Firstly, the Frame Difference method is applied to image blocks to extract the background. Then, the moving vehicles are detected as the foreground in the current frame by background subtraction and binarization. Secondly, the connected regions in the binary image are labeled, and the horizontal and vertical projection sequences are obtained by projecting each connected region in the binary image to the two coordinate directions. Finally, use the sequences obtained by the projection to detect the objects and remove the moving shadow. Experimental results show that the proposed method not only can effectively detect and then remove the moving shadows from the video, but it also improve the reliability of vehicle extraction in the traffic video surveillance.