Abstract： In this paper, a novel technique to detect moving targets copy-move forgery in video sequences based on LK optical flow and the pre-screening mechanism of moving targets was proposed. The proposed scheme is a coarse-to-fine approach and composed of moving targets detection and tracking, candidate motion sequences selection, and spatial matching. In the pre-processing round, the visual background extractor (ViBe) mechanism and Kalman filter were used to detect and tracking moving objects. To screen duplicated candidates in the temporal domain, the optical flow features in each motion sequences were obtained using the Lucas_Kanade algorithm and calculate their correlation. To evaluate the similarity of image content, the scale invariant feature transform (SIFT) algorithm was used to measure spatial correlation of each corresponding frame between the motion sequences. The experimental results show that the proposed scheme can detect moving targets copy-move forgery well in homologous video.
Key words：