HEVC Double Compression Detection Based on SN-PUPM Feature

  • Qianyi Xu
  • Tanfeng SunEmail author
  • Xinghao Jiang
  • Yi Dong
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10431)


During the process of video forgery detection, double compression is a significant evidence. A novel scheme based on the Sequence of Number of Prediction Unit of its Prediction Mode (SN-PUPM) is proposed to conduct double compression detection on videos under HEVC standard, together with estimation on GOP structures. Number of PU with three kinds of prediction mode (INTRA, INTER and SKIP) is firstly extracted from each frame inside a given video sequence. Then the SN-PUPM is calculated by Absolute Difference Values from adjacent three frames in original extracted features and filtered with Twice Averaging Filter to reduce noises induced by the process. Then, an initiative Abnormal Value Classifier is trained with SVM to label I-P frames and have a final sequence for double compression detection and GOP analysis. Nineteen original YUV sequences are adopted for dataset in experiments. Results have demonstrated better performance in HEVC double compression than previous method adapted to HEVC.


HEVC Double compression First GOP detection Sequence of number of PU of PM Prediction mode 



This work was supported by the National Natural Science Foundation of China (No. 61572320, 61572321).


  1. 1.
    Al-Sanjary, O., Sulong, G.: Detection of video forgery: a review of literature. J. Theor. Appl. Inf. Techn. 74(2), 207–220 (2015)Google Scholar
  2. 2.
    Milani, S., Fontani, M., et al.: An overview on video forensics. In: Asian-Pacific Signal and Information Processing Association, APSIPA 2012, Hollywood, CA, USA, vol. 1(1), pp. 1229–1233, 3–6 December 2012Google Scholar
  3. 3.
    Chen, W., Shi, Y.Q.: Detection of double MPEG compression based on first digit statistics. In: International Workshop on Digital Watermarking, IWDW 2008, Busan, Korea, Selected Papers. DBLP, pp. 16–30, 10–12 November 2008Google Scholar
  4. 4.
    Sun, T.F., Wang, W., Jiang, X.H.: Exposing video forgeries by detecting MPEG double compression. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2012, Kyoto, Japan, pp. 1389–1392. IEEE, 25–30 March 2012Google Scholar
  5. 5.
    Jiang, X.H., Wang, W., Sun, T.F., Shi, Y.Q., Wang, S.: Detection of double compression in MPEG-4 videos based on Markov statistics. IEEE Signal Process. Lett. 20(5), 447–450 (2013)CrossRefGoogle Scholar
  6. 6.
    Ravi, H., Subramanyam, A., Gupta G., Kumar, B.A.: Compression noise based video forgery 
detection. In: 2014 IEEE International Conference on Image Processing, ICIP 2014, Paris, France, pp. 5352–5356. IEEE, 27–30 October 2014Google Scholar
  7. 7.
    He, P., Sun, T., Jiang, X., Wang, S.: Double compression detection in mpeg-4 videos based on block artifact measurement with variation of prediction footprint. In: Huang, D.-S., Han, K. (eds.) ICIC 2015, Part III. LNCS, vol. 9227, pp. 787–793. Springer, Cham (2015). doi: 10.1007/978-3-319-22053-6_84 CrossRefGoogle Scholar
  8. 8.
    He, P.S., Jiang, X.H., Sun, T.F., Wang, S.: Double compression detection based on local motion vector field in staticbackground videos. J. Vis. Commun. Image Represent. 35, 55–66 (2016)CrossRefGoogle Scholar
  9. 9.
    Sullivan, G., Ohm, J., Han, W., et al.: Overview of the high efficiency video coding (HEVC) standard. IEEE Trans. Circ. Syst. Video Technol. 22(12), 1649–1668 (2012)CrossRefGoogle Scholar
  10. 10.
    Jia, R.S., Li, Z.H., Zhang, Z.Z., Li, D.D.: Double HEVC compression detection with the same QPs based on the PU numbers. In: ITM Web of Conferences, ITA 2016, vol. 7, p. 02010 (2016)Google Scholar
  11. 11.
    Huang, M.L., Wang, R.D., Xu, J., et al.: Detection of double compression in HEVC videos based on the statistical characteristic of DCT coefficient. Guangdianzi Jiguang/J. Optoelectron. Laser 26(4), 733–739 (2015)Google Scholar
  12. 12.
    Huang, M., Wang, R., Xu, J., Xu, D., Li, Q.: Detection of double compression for hevc videos based on the co-occurrence matrix of DCT coefficients. In: Shi, Y.-Q., Kim, H.J., Pérez-González, F., Echizen, I. (eds.) IWDW 2015. LNCS, vol. 9569, pp. 61–71. Springer, Cham (2016). doi: 10.1007/978-3-319-31960-5_6 CrossRefGoogle Scholar
  13. 13.
    Huang, M.L., Wang, R.D., Xu, J., Xu, D.W., Li, Q.: Detection of double compression based on optimization of Markov features for HEVC videos. In: Proceeding of 12th China Information Hiding Workshop, CIHW 2015, Wuhan, China, pp. 475–481, 28–29 March 2015Google Scholar
  14. 14.
    Vazquez-Padin, D., Fontani, M., Bianchi, T., Comesana, P., Piva, A., Barni, M.: Detection of video double encoding with GOP size estimation. In: IEEE International Workshop on Information Forensics and Security, WIFS 2013, Guangzhou, China, vol. 2, pp. 151–156. IEEE, 18–21 November 2013Google Scholar
  15. 15.
    Chen, S., Sun, T.F., Jiang, X.H., He, P.S., Wang, S.L., Shi, Y.Q.: Detecting double H.264 compression based on analyzing prediction residual distribution. In: Shi, Y.Q., Kim, H.J., Perez-Gonzalez, F., Liu, F. (eds.) IWDW 2016. LNCS, vol. 10082, pp. 61–74. Springer, Cham (2017). doi: 10.1007/978-3-319-53465-7_5 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Qianyi Xu
    • 1
  • Tanfeng Sun
    • 1
    • 2
    Email author
  • Xinghao Jiang
    • 1
    • 2
  • Yi Dong
    • 1
  1. 1.School of Electronic Information and Electronic EngineeringShanghai Jiao Tong UniversityShanghaiChina
  2. 2.National Engineering Lab on Information Content Analysis Techniques, GT036001ShanghaiPeople’s Republic of China

Personalised recommendations