Fast Shadow Detection According to the Moving Region

Shadow detection is a very important step in the recognition and tracking of the moving vehicles. Based on the color-based and model-based shadow detection methods, this paper presents a fast coarse model shadow detection method according to the moving region. Firstly, it quickly detects the moving region of the image using improved background subtraction method. A quick self-adaptive background updating algorithm based on moving region (Bo Qin et al., 2006). Then it establishes a coarse model of the shadow detection by model-based method. Only the coarse region is applied to the shadow detection method based on the HSV color space. Experiment results show that this method can improve the efficiency of shadow detection greatly.