An adaptive shadow elimination algorithm using shadow position and edges attributes

An adaptive shadow removal algorithm with background subtraction method based on shadow position and edges attributes is presented. Accumulative frames differences of symmetrical frames are adopted to detect the moving regions approximately, and the moving regions templates are constructed through static index, then the background model is built by the statistics of brightness information. On the base of above, background subtraction method and Sobel edge detector are combined to extract moving object and its edges which include shadow. The direction of shadow is determined by the edge and position of the shadow combining with the horizontal and vertical projections of the edge image respectively, the position of the shadow is located accurately through proportion method, the shadow can be removed finally. Experimental results indicate that the proposed method is easy to be realized and can determine the direction of the shadow adaptively, then eliminate the shadow and extract the whole moving object accurately, especially when the chrominance invariant principle is ineffective.