Advertisement

Fast Inter Prediction Mode Decision Algorithm Based on Data Mining

  • Tengrui Shi
  • Xiaobo Guo
  • Daihui Mo
  • Jian Wang
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 251)

Abstract

The HEVC greatly improves coding efficiency. However, this is accompanied by an increase in the complexity of the coding calculation, which is higher than H.264. We find that there are several features that are highly correlated with the CU’s best split decision in inter prediction. As a result, we choose decision trees to solve the splitting decision problem. We implement the decision trees on official software HM16.2 and test the algorithm on the testing set. Experiments indicate that the fast decision algorithm improve the coding performance more efficiently than some existing algorithms.

Keywords

HEVC Inter prediction Data mining Decision trees 

References

  1. 1.
    Ohm, J., Sullivan, G.J., Schwarz, H., Tan, T.K., Wiegand, T.: Comparison of the coding efficiency of video coding standards including high efficiency video coding (HEVC). IEEE Trans. Circ. Syst. Video Technol. 22, 1669–1684 (2012)CrossRefGoogle Scholar
  2. 2.
    Bossen, F., Bross, B., Suhring, K., Flynn, D.: HEVC complexity and implementation analysis. IEEE Trans. Circ. Syst. Video Technol. 22, 1685–1696 (2012)CrossRefGoogle Scholar
  3. 3.
    Guo, L., Zhou, L., Tian, X., Chen, Y.: Adaptive coding-unit size selection based on hierarchical quad-tree correlations for high-efficiency video coding. J. Electron. Imaging 24, 023036–023036 (2015)CrossRefGoogle Scholar
  4. 4.
    Xiong, J., Li, H., Meng, F., Wu, Q., Ngan, K.N.: Fast HEVC inter CU decision based on latent SAD estimation. IEEE Trans. Multimed. 17, 2147–2159 (2015)CrossRefGoogle Scholar
  5. 5.
    Zhong, G.Y., He, X.H., Qing, L.B., Li, Y.: Fast inter-mode decision algorithm for high-efficiency video coding based on similarity of coding unit segmentation and partition mode between two temporally adjacent frames. J. Electron. Imaging 22, 381–388 (2013)CrossRefGoogle Scholar
  6. 6.
    Fernández, G., Cuenca, P., Barbosa, L.O., Kalva, H.: Very low complexity MPEG-2 to H.264 transcoding using machine learning. In: Proceedings of the 14th Annual ACM International Conference on Multimedia, pp. 931–940 (2006)Google Scholar
  7. 7.
    Van, L.P., et al.: Fast transrating for high efficiency video coding based on machine learning. In: 2013 20th IEEE International Conference on Image Processing (ICIP), pp. 1573–1577 (2013)Google Scholar
  8. 8.
    Correa, G., Assuncao, P., Agostini, L., da Silva Cruz, L.A.: A method for early-splitting of HEVC inter blocks based on decision trees. 2014 Proceedings of the 22nd European Signal Processing Conference (EUSIPCO), pp. 276–280 (2014)Google Scholar
  9. 9.
    Correa, G., Assuncao, P.A., Agostini, L.V., da Silva Cruz, L.A.: Fast HEVC encoding decisions using data mining. IEEE Trans. Circuits Syst. Video Technol. 25, 660–673 (2015)CrossRefGoogle Scholar
  10. 10.
    Li, K., Wang, J.: Fast CU-splitting decisions based on data mining. In: IEEE International Conference on Consumer Electronics-China, pp. 1–5 (2017)Google Scholar
  11. 11.
    Fayyad, U., Piatetsky-Shapiro, G., Smyth, P.: From data mining to knowledge discovery in databases. AI Mag. 17, 37 (1996)Google Scholar
  12. 12.
    Shan, S.: Decision tree learning. In: Shan, S. (ed.) Machine Learning Models and Algorithms for Big Data Classification, vol. 36, pp. 237–269. Springer, Boston (2016).  https://doi.org/10.1007/978-1-4899-7641-3_10CrossRefGoogle Scholar
  13. 13.
    Quinlan, J.R.: C4. 5: Programs for Machine Learning. Morgan Kaufmann, Los Altos (1993)Google Scholar
  14. 14.
    Orriols-Puig, A., Bernadó-Mansilla, E.: The Class imbalance problem in UCS classifier system: a preliminary study. In: Kovacs, T., Llorà, X., Takadama, K., Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 2003–2005. LNCS (LNAI), vol. 4399, pp. 161–180. Springer, Heidelberg (2007).  https://doi.org/10.1007/978-3-540-71231-2_12CrossRefzbMATHGoogle Scholar
  15. 15.
    Russell, I., Markov, Z.: An introduction to the WEKA data mining system. In: ACM SIGCSE Technical Symposium on Computer Science Education, pp. 742–742 (2017)Google Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018

Authors and Affiliations

  • Tengrui Shi
    • 1
    • 2
  • Xiaobo Guo
    • 2
  • Daihui Mo
    • 3
    • 4
  • Jian Wang
    • 1
  1. 1.Nanjing University, NJUNanjingPeople’s Republic of China
  2. 2.Science and Technology on Information Transmission and Dissemination in Communication Networks LaboratoryThe 54th Institute of CETCShijiazhuangPeople’s Republic of China
  3. 3.Department of Electronic EngineeringTsinghua UniversityBeijingPeople’s Republic of China
  4. 4.Academy of Military Sciences PLA ChinaBeijingPeople’s Republic of China

Personalised recommendations