A hybrid background subtraction approach for moving object detection

Background subtraction is widely used technique for moving object detection from videos. This paper presents a hybrid approach for moving objects detection and shadow removal from color videos obtained using stationary camera. A background subtraction technique based on frame differencing and ViBe algorithm for detecting moving objects has been proposed. Then, a robust algorithm for shadow removal is employed to remove cast shadows. Foreground is reconstructed using graph cut based cleaning and non-recursive blob finding. Comparative experimental results demonstrate that proposed approach performs better in comparison to other state-of-the-art algorithms.