Shadow Suppression Based on Adaptive Gaussian Mixture Model

According to the HSV color space characteristics , changes the modeling space in the process of Gaussian mixture model, based on the setting of each component, deals with shadow casted by using the Gaussian mixture model algorithm detecting the moving objects. Morphological operators are used to compensate edge detail information and to remove the noise. Finally, using the similarity of gray density, texture value and the gradient value, a good result can be obtained. The experimental result showed that this method can effectively solve the shadow and have good real-time performance and robustness. Keywords-HSV color space; Gaussian mixture model; morphological; shadow; image gradient