Moving Cast Shadow Detection Based on PCA

Moving cast shadows are a major concern for foreground detection algorithms. In this paper, a novel method is proposed to detect the moving cast shadows in the scene. This approach uses GMM to generate the background image, and extract the feature using PCA-based transformation to the background image, then, the feature space is utilized to classify moving shadows and foreground objects. Experimental results show that the proposed method succeeds in detecting moving cast shadows within indoor and outdoor environments.