Moving Shadow Detection Based on Multi-feature Fusion

A moving shadow detection algorithm based on Multi-feature fusion is proposed. At first, the moving object region is acquired by Visual Background extractor model. Then, the shadow pixels are detected by the intensity and chromaticity in HSI color space. Meanwhile, the gradient histogram back-projection method is used to distinguish the moving object and shadow. Finally, the detection results based on the above two methods are reasonably fused to get the final shadow area. Compared with the typical algorithms, the experimental results show that the accuracy and robustness of shadow detection are effectively improved.