Advertisement

Exploiting Data Mining for Fast Inter Prediction Mode Decision in HEVC

  • Tengrui Shi
  • Jian WangEmail author
Article
  • 53 Downloads

Abstract

HEVC has made significant progress in coding efficiency. Compared with the previous generation H.264/AVC video coding standard, HEVC can save 50% of code rate under the same visual quality. However, this drop in bit rate is accompanied by an increase in computational complexity, which poses a great challenge to the application and development of HEVC. After analyzing the great correlation between the partitioning mode of coding unit in the encoder and several parameters, the partitioning problem of the CU is modeled as a classification problem in data mining, and it is decided to use a decision tree to solve this classification problem. We implement the decision tree on the official software HM16.2 and test the algorithm on the test set. Experiments show that fast algorithm based on decision tree can improve the encoding speed effectively with little influence on the encoding performance.

Keywords

HEVC Inter prediction Data mining Decision trees 

References

  1. 1.
    Sullivan GJ, Ohm J, Han WJ, Wiegand T (2013) Overview of the high efficiency video coding (HEVC) standard. IEEE Trans Circ Syst Video Technol 22(12):1649–1668CrossRefGoogle Scholar
  2. 2.
    Ohm J, Sullivan GJ, Schwarz H, Tan TK, Wiegand T (2013) Comparison of the coding efficiency of video coding standards—including high efficiency video coding (HEVC). IEEE Trans Circ Syst Video Technol 22 (12):1669–1684CrossRefGoogle Scholar
  3. 3.
    Bossen F, Bross B, Suhring K, Flynn D (2013) HEVC Complexity and implementation analysis. IEEE Trans Circ Syst Video Technol 22(12):1685–1696CrossRefGoogle Scholar
  4. 4.
    Pourazad MT, Doutre C, Azimi M, Nasiopoulos P (2012) HEVC: the new gold standard for video compression: how does HEVC compare with H.264/AVC consumer. Electron Mag IEEE 1(3):36–46Google Scholar
  5. 5.
    Shen L, Liu Z, Zhang X, Zhao W, Zhang Z (2013) An effective CU size decision method for HEVC encoders. IEEE Trans Multimed 15(2):465–470CrossRefGoogle Scholar
  6. 6.
    Qian LP, Zhang YJ, Huang J, Wu Y (2013) Demand response management via real-time electricity price control in smart grids. IEEE J Selected Areas Commun 31(7):1268–1280CrossRefGoogle Scholar
  7. 7.
    Qian LP, Wu Y, Zhou H, Shen XS (2017) Joint uplink base station association and power control for small-cell networks with nonorthogonal multiple access. IEEE Trans Wirel Commun, 99:1–1Google Scholar
  8. 8.
    Guo L (2015) Adaptive coding-unit size selection based on hierarchical quad-tree correlations for high-efficiency video coding. J Electron Imag 24(2):023036CrossRefGoogle Scholar
  9. 9.
    Xiong J, Li H, Meng F, Wu Q, Ngan KN (2015) Fast HEVC inter CU decision based on latent SAD estimation. IEEE Trans Multimed 17(12):2147–2159CrossRefGoogle Scholar
  10. 10.
    He XH (2013) 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 Imag 22(2):3025CrossRefGoogle Scholar
  11. 11.
    Liu Z, Yu X, Chen S, Wang D (2016) CNN Oriented fast HEVC intra CU mode decision. In: IEEE International Symposium on Circuits and SystemsGoogle Scholar
  12. 12.
    Momcilovic S, Roma N, Sousa L (2016) Milentijevic I run-time machine learning for HEVC/H.265 fast partitioning decision. In: IEEE International Symposium on Multimedia, pp 347– 350Google Scholar
  13. 13.
    Correa G, Assuncao P, Agostini L, Cruz LADS (2014) A method for early-splitting of HEVC inter blocks based on decision trees. In: Signal Processing Conference, pp 276–280Google Scholar
  14. 14.
    Correa G, Assuncao PA, Agostini LV, Cruz LADS (2015) Fast HEVC encoding decisions using data mining. IEEE Trans Circ Syst Video Technol 25(4):660–673CrossRefGoogle Scholar
  15. 15.
    Li K, Wang J (2017) Fast CU-splitting decisions based on data mining. In: IEEE International Conference on Consumer Electronics-China , pp 1–5Google Scholar
  16. 16.
    Andrade MA, Sander C (1996) From data mining to knowledge discovery in databasesGoogle Scholar
  17. 17.
    Alpaydin (2014) Introduction to machine learning / Third edition. MIT Press, CambridgezbMATHGoogle Scholar
  18. 18.
    Mohri M, Rostamizadeh A, Talwalkar A (2012) Foundations of machine learning. MIT Press, CambridgezbMATHGoogle Scholar
  19. 19.
    Suthaharan S (2016) Machine learning models and algorithms for big data classification. Springer, USCrossRefzbMATHGoogle Scholar
  20. 20.
    Huang AH (2009) C4.5 algorithm of decision tree improvement and application. Sci Technol Eng 9(1):34–36Google Scholar
  21. 21.
    Gao Y, Liao JP, Wei WU (2011) Id3 algorithm and c4.5 algorithm based on decision tree. J Hubei University Technol 2, 54–56Google Scholar
  22. 22.
    Quinlan JR (1996) Improved use of continuous attributes in c4.5. J Artif Intell Res 4(1):77–90CrossRefzbMATHGoogle Scholar
  23. 23.
    Orriolspuig A, Bernadómansilla E (2007) The class imbalance problem in UCS classifier system: a preliminary study. In: 2005 International Conference on Learning Classifier Systems, pp 161–180Google Scholar
  24. 24.
    Markov Z, Russell I (2006) An introduction to the WEKA data mining system. ACM SIGCSE Bulletin 38 (3):367–368CrossRefGoogle Scholar
  25. 25.
    Pateux BS, Jung J (2007) An Excel add-in for computing Bjontegaard metric and its evolutionGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Nanjing UniversityNanjingChina

Personalised recommendations