A Shadow Removal Approach for a Background Subtraction Algorithm

This paper presents preliminary results of an algorithm for shadow detection and removal in video sequences. The proposal is that from the base of the background subtraction with the Visual Background Extraction (ViBE), which identifies areas of movement, to apply a post processing to separate pixels from the real object and those of the shadow. As the areas of shadows have similar characteristics to those of the objects in movement, the separation becomes a difficult task. Consequently, the algorithms used for this classification may produce several false positives. To solve this problem, we set to use information of the object involved such as the size and movement direction, to estimate the most likely position of the shadow. Furthermore, the analysis of similarity between the present frame and the background model are realized, by means of the traditional indicator of normalized cross correlation to detect shadows. The algorithm may be used to detect both people and vehicles in applications for safety of cities, traffic monitoring, sports analysis, among others. The results obtained in the detection of objects show that it is highly likely to separate the shadow in a high percentage of effectiveness and low computational cost; allowing improving steps of further processing, such as object recognition and tracking.