Detection of motion compensated frame interpolation via motion-aligned temporal difference
- 135 Downloads
Motion compensated frame interpolation (MCFI) is a special frame based video manipulation, which increases the temporal continuity of low frame rate videos by synthesizing new frames between successive frames. MCFI might also be used to counterfeit high frame-rate videos, which mislead users’ attraction and waste storage spaces in video-sharing websites. Existing MCFI detectors are designed to judge the absence or presence of MCFI forgery in a controllable environment of known MCFI techniques. Practical detector should consider the possibility of unknown MCFI techniques. We are motivated to propose a robust MCFI detector for more practical scenarios. Considering the effects of non-motion regions in candidate frame, the statistical moments are firstly extracted from motion-aligned frame differences (MAFD). Then, the one-class support vector machine (SVM), following a training stage capturing the properties of original frames, is exploited to judge whether the candidate frame is interpolated by MCFI or not. Finally, a special interpolated frame detection (SIFD) is designed to pick out interpolated frames, which are synthesized from two consecutive reference frames with no motion vectors (MVs) or less MVs. A series of experiments evaluated on four representative MCFI techniques have shown promising results.
KeywordsVideo forensics Motion compensated frame interpolation Motion-aligned One-class SVM
The authors appreciate Dr. Ran Li in Xinyang Normal University, China for permission to use their codes in theirs experiments. They appreciate Dr. Won Hee Lee in Korea Advanced Institute of Science and Technology, Korea for providing up-converted videos in the experiments. They also appreciate Dr Ningbo Zhu in Hunan University, China for providing technical editing of the revised manuscript. This work is supported in part by the National Natural Science Foundation of China (61572183, 61379143).
- 1.Available on the online video Databases. http://media.xiph.org/video/derf/#
- 2.Available on the online video Databases. http://www.nada.kth.se/cvap/actions/
- 3.Bestagini P, Battaglia S, Milani S, Tagliasacchi M, Tubaro S (2013) Detection of temporal interpolation in video sequences. In: Proceedings of the International Conference Acoustic, Speech Signal Process, pp 3033–3037Google Scholar
- 5.Black MJ, Anandan P (1993) A framework for the robust estimation of optical flow. In: Proceedings of the 4th International Conference on Computing Vision, pp 231–236Google Scholar
- 6.Boser BE, Guyon IM, Vapnik VN (1992) A training algorithm for optimal margin classifiers. In: Proceedings of the ACM 5th Annual Workshop COLT, Pittsburgh, PA USA, pp 144–152Google Scholar
- 33.Vapnik VN, Lerner A (1963) Pattern recognition using generalized portrait method. Autom Remote Control 24(6):774–780Google Scholar
- 36.Wu Y, Jiang X, Sun T, Wang W (2014) Exposing video inter-frame forgery based on velocity field consistency. In: Proceedings of the International Conference Acoustic, Speech Signal Process, pp 2674–2678Google Scholar
- 37.Xia M, Yang G, Li L, Li R, Sun X (2016) Detecting video frame rate up-conversion based on frame-level analysis of average texture variation. Multimed Tools Appl:1–23Google Scholar
- 40.Zhang J, Su Y, Zhang M (2009) Exposing digital video forgery by ghost shadow artifact. In: Proceedings of the 1st ACM workshop on multimedia in forensics,(mifor09), pp 49–54Google Scholar