Accelerating the CU partitioning decision in an HEVC-JEM transcoder

  • D. García-LucasEmail author
  • G. Cebrián-Márquez
  • A. J. Díaz-Honrubia
  • Pedro Cuenca


High Efficiency Video Coding (HEVC) is currently the latest video coding standard available on the market, and it is able to offer up to twice the coding efficiency, in the range of 50% bitrate reduction for the same video quality, of the previous standard, namely H.264/Advanced Video Coding (AVC). HEVC was standardized in 2013 for videos up to a resolution of 2K. However, the popularity of 4K videos is increasing due to the growing use of video-on-demand platforms. Therefore, the ITU-T Video Coding Expert Group (VCEG) and the ISO/IEC Moving Picture Expert Group (MPEG) created the Joint Video Exploration Team (JVET) in 2015 to design the future video coding technology under the Joint Exploration Model (JEM), which its latest version achieves an improvement in coding efficiency of 30%, but at a high cost in terms of computational complexity (10×) with respect to HEVC. The new video standard is expected to be ready in 2020, so it is necessary to find efficient mechanisms to convert current content to the new format adopted in JEM. In this regard, our proposal consists in a probabilistic classifier based on Naïve-Bayes that enables the prediction of the splitting decision at the first quadtree level in JEM, reducing the computational complexity of the transcoding process from HEVC to this new standard. The experimental results show a good trade-off between coding efficiency and complexity compared with the anchor transcoder, obtaining a time reduction up to 12.71% at the expense of low coding efficiency penalties in the configurations evaluated.


HEVC H.265 JEM Transcoding CTU splitting 



  1. 1.
    An J, Chen YW, Zhang K, Huang H, Huang YW, Lei S (2015) Block partitioning structure for next generation video coding. Tech. Rep. COM16-C966, ITU-T SG16 Q6Google Scholar
  2. 2.
    An J, Huang H, Zhang K, Huang YW, Lei S (2016) Quadtree plus binary tree structure integration with JEM tools. Tech. Rep. JVET-B0023, Joint Video Experts Team (JVET)Google Scholar
  3. 3.
    Bjøntegaard G (2008) Improvements of the BD-PSNR model. Tech. Rep. VCEG-AI11, ITU-T SG16 Q6Google Scholar
  4. 4.
    Bross B, Chen J, Liu S (2019) Versatile video coding (Draft 5). Tech. Rep. JVET-N1001, Joint Video Experts Team (JVET)Google Scholar
  5. 5.
    Chen J, Alshina E, Sullivan G, Ohm J, Boyce J (2016) Algorithm description of joint exploration test model 2. Tech. Rep. JVET-B1001, Joint Video Experts Team (JVET)Google Scholar
  6. 6.
    Chen J, Alshina E, Sullivan G, Ohm J, Boyce J (2017) Algorithm description of joint exploration test model 7. Tech. Rep. JVET-G1001, Joint Video Experts Team (JVET)Google Scholar
  7. 7.
    CISCO (2016) Cisco visual networking index - forecast and methodology (2015 to 2020)Google Scholar
  8. 8.
    Díaz-Honrubia AJ, Martínez JL, Cuenca P, Gamez JA, Puerta JM (2016) Adaptive fast quadtree level decision algorithm for H.264 to HEVC video transcoding. IEEE Trans Circuits Syst Video Technol 26(1):154–168. CrossRefGoogle Scholar
  9. 9.
    Fayyad UM, Irani K B (1993) Multi-interval discretization of continuous-valued attributes for classification learning. In: Proceedings of the international joint conference on uncertainty in AIGoogle Scholar
  10. 10.
    Fayyad UM, Piatetsky-Shapiro G, Smyth P (1996) Advances in knowledge discovery and data mining. American association for artificial intelligence, Menlo Park, CA, USA, chap From Data Mining to Knowledge Discovery:, An Overview, pp 1–34Google Scholar
  11. 11.
    Fernandez-Escribano G, Kalva H, Cuenca P, Orozco-Barbosa L, Garrido A (2008) A fast MB mode decision algorithm for MPEG-2 to H.264 P-frame transcoding. IEEE Trans Circuits Syst Video Technol 18(2):172–185. CrossRefGoogle Scholar
  12. 12.
    Franche J, Coulombe S (2018) Efficient h.264-to-hevc transcoding based on motion propagation and post-order traversal of coding tree units. IEEE Trans Circuits Syst Video Technol 28(12):3452–3466. CrossRefGoogle Scholar
  13. 13.
    Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157–1182zbMATHGoogle Scholar
  14. 14.
    Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten I H (2009) The WEKA Data Mining Software: An Update. SIGKDD Explor Newsl 11 (1):10–18. CrossRefGoogle Scholar
  15. 15.
    ISO/IEC ITU-T (2003) Advanced video coding for generic audiovisual services. ITU-T Recommendation H.264 and ISO/IEC 14496–10Google Scholar
  16. 16.
    ISO/IEC ITU-T (2013) High efficiency video coding (HEVC). ITU-T Recommendation H.265 and ISO/IEC 23008–2Google Scholar
  17. 17.
    ITU-T (2008) P.910 - subjective video quality assessment methods for multimedia applicationsGoogle Scholar
  18. 18.
    JCT-VC HEVC Reference Software - Version 16.16.
  19. 19.
    Jiang W, Chen Y, Tian X (2014) Fast transcoding from H.264 to HEVC based on region feature analysis. Multimed Tools Appl 73(3):2179–2200CrossRefGoogle Scholar
  20. 20.
  21. 21.
    Li X, Suehring K (2017) JVET-H1010 - JVET common test conditions and software reference configurationsGoogle Scholar
  22. 22.
    Ohm J R, Sullivan GJ, Schwarz H, K Tan T, Wiegand T (2012) Comparison of the coding efficiency of video coding standards - including high efficiency video coding (HEVC). IEEE Trans Circuits Syst Video Technol 22(12):1669–1684. CrossRefGoogle Scholar
  23. 23.
    Peixoto E, Izquierdo E (2012) A complexity-scalable transcoder from H.264/AVC to the new HEVC codec. In: IEEE international conference on image processing (ICIP 2012), Orlando, FL, USAGoogle Scholar
  24. 24.
    Peixoto E, Macchiavello B, Hung M, Zaghetto A, Shanableh T, Izquierdo E (2013) An H.264/AVC to HEVC video transcoder based on mode mapping. In: IEEE international conference on image processing (ICIP 2013), Melbourne, AustraliaGoogle Scholar
  25. 25.
    Peixoto E, Shanableh T, Izquierdo E (2014) H.264/AVC to HEVC video transcoder based on dynamic thresholding and content modeling. IEEE Trans Circuits Syst Video Technol 24(1):99–112. CrossRefGoogle Scholar
  26. 26.
    Segall A, Baroncini V, Boyce J, Chen J, Suzuk T (2017) JVET-H1002 - joint call for proposals on video compression with capability beyond HEVCGoogle Scholar
  27. 27.
    Vetro A, Christopoulos C, Sun H (2003) Video transcoding architectures and techniques: An overview. IEEE Signal Process Mag 20 (2):18–29. CrossRefGoogle Scholar

Copyright information

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

Authors and Affiliations

  1. 1.High Performance Networks and Architectures LaboratoryUniversity of Castilla-La ManchaAlbaceteSpain
  2. 2.Computer Science DepartmentUniversity of OviedoOviedoSpain
  3. 3.ETS de Ingenieros InformáticosUniversidad Politécnica de MadridMadridSpain

Personalised recommendations