文摘
Nowadays, people can easily combine several videos into a fake one by means of matte painting to create visually convincing video contents. This raises the need to verify whether a video content is original or not. In this paper we propose a geometric technique to detect this kind of tampering in video sequences. In this technique, the extrinsic camera parameters, which describe positions and orientations of camera, are estimated from different regions in video frames. A statistical distribution model is then developed to characterize these parameters in tampering-free video and provides evidences of video forgery finally. The efficacy of the proposed method has been demonstrated by experiments on both authentic and tampered videos from websites.