Detection of moving cast shadows using edge information

Abstract

Tracking moving objects in video sequence is an important problem in computer vision, with applications in several fields, such as video surveillance and target tracking. As the shadows attached along with the moving object also have the same motion that of objects, the detection of shadows as foreground objects is very common and produce large errors in object localization and recognition. This paper introduces an effective method which uses the edge information to detect moving cast shadows for traffic sequences. The proposed method initially removes the boundary of the cast shadow, preserving object's interior edges. The coarse object shapes are then reconstructed using the object interior edges. Finally, the cast shadow is detected by subtracting the reconstructed moving object from the change detection mask. The method is implemented and tested using three benchmark videos. The efficiency of the proposed method is compared with five other popular shadow detection methods and the results proved its superiority over others.