Shadow detection approach combining spectral and geometrical properties

In applications requiring objects extraction, cast shadows induce shape distortions and object fusions interfering performance of high level algorithms in video surveillance system. Shadow elimination allows to improve the performances of video object extraction, tracking and description tools. In this work, we propose an approach to automatic shadow detection and extraction, which operates multiple properties derived from spectral, geometric and temporal analysis of shadows. We develop a generic model that chooses the candidate shadow regions based on shadow direction. Then, the validity of detected regions as shadows is verified using the capability of approach that allows associating to each photometric pixel its equivalent part of the shadow, while integrating the various parameters related to illumination and the surface. Simulation results show that the proposed approach is robust and efficient in detecting shadows for different background and changeable illumination conditions.