Moving cast shadow detection based on color feature and gradient difference estimator
Zhao Rui-xing · Journal of Optoelectronics·laser · 2011
As the texture information applied in current moving cast shadow detection is excessively rough,a novel algorithm based on gradient difference estimator,intensity and normalized color is proposed.In this scheme,the foreground pixels are obtained using Gaussian mixture model,the candidate shadow region is selected through intensity and normalized color feature,and the gradient difference estimator is adopted to get the final shadow region.Experimental results confirm the validity of the algorithm,and indicate that the moving object and the shadow without obvious local texture could be well separated.