A Shadow Removal Algorithm for ViBe in HSV Color Space

Shadow removal has always been one of the research hot topics in the field of computer vision. Recently, more and more attention was paid on the ViBe (Visual background extraction) foreground extraction algorithm for its simplicity and high speed. However, for the videos with moving cast shadows, the detection performance is not satisfactory. In this paper, a new shadow removal algorithm for ViBe in HSV (Hue, Saturation, Value) color space is proposed. The ratio of H, S and V components between foreground and background is used to determine whether the interest pixels detected by ViBe are shadows or not. For indoor and outdoor videos with moving cast shadows, ROC (Receiver Operating Characteristic) curve is used to evaluate the proposed approach. Experimental results show that the performance has been improved greatly with the proposed shadow removal approach: for the given TPR (True Positive Rate), FPR (False Positive Rate) is improved even by 11 percentages (for video cubicle).