Moving object removal in video sequence and background restoration using kalman filter

Object removal in image and video sequences has attracted many researchers in video processing. In this paper, a novel method is proposed to separate moving objects from background based on combination of Kalman filtering and background subtraction. Also, a video completion algorithm is proposed to remove the extracted objects. This algorithm uses the temporal information of frames to complete the holes appeared after object removal. The holes associated to the fixed objects in background model are removed and filled by image completion algorithm based on exemplar texture synthesis. Experimental results demonstrate the privilege performance of the proposed method in object removing and background restoration of real captured video sequences.