Shadow Detection in Complex Environments via An Innovative Information Fusion Approach

In this paper a novel moving shadows detecting algorithm is proposed. The algorithm can be used in indoor and outdoor environments. The algorithm we propose fuses together color and stereo disparity information using the Dempster-Shafer combination rule. Some considerations on the nature of the shadow improves the algorithm's ability to candidate the pixels as shadow or foreground. The candidate of both color and disparity information are then weighted by analyzing the effectiveness in the scene.