Abstract
The High Efficiency Video Coding (HEVC) standard provides improved compression rates in comparison to its predecessors at the cost of large increases in computational complexity. An important share of such increases is due to the introduction of flexible Coding Tree structures, which best configuration is decided through exhaustive tests in a rate-distortion optimization (RDO) scheme. In this work, an early termination method for the decision of such structures was designed using classification trees obtained through Data Mining techniques. The classification trees were trained using intermediate encoding results from a set of video sequences and implemented in the encoder to avoid the full RDO-based decision. An average reduction of 37 % in the HEVC encoder computational complexity was achieved when using the designed classification trees, with a negligible cost of only 0.28 % in terms of Bjontegaard Delta-rate increase.
Similar content being viewed by others
References
Vanne, J., Viitanen, M., Hamalainen, T., & Hallapuro, A. (2012). Comparative rate-distortion-complexity analysis of HEVC and AVC video codecs. IEEE Transactions on Circuits and Systems for Video Technology, 22, 1885–1898.
Correa, G., Assuncao, P., Agostini, L., & da Silva Cruz, L. A. (2012). Performance and computational complexity assessment of high efficiency video encoders. IEEE Transactions on Circuits and Systems for Video Technology, 22, 1899–1909.
Sanchez, G., Corrêa, M., Noble, D., Porto, M., Bampi, S., & Agostini, L. (2012). Hardware design focusing in the tradeoff cost versus quality for the H.264/AVC fractional motion estimation targeting high definition videos. Analog Integrated Circuits and Signal Processing, 73, 931–944.
Sanchez, G., Zatt, B., Porto, M., & Agostini, L. (2015). Hardware-friendly HEVC motion estimation: new algorithms and efficient VLSI designs targeting high definition videos. Analog Integrated Circuits and Signal Processing, 82, 135–146.
Kuhn, P. M., & Kuhn Peter, M. (1999). Algorithms, complexity analysis and VLSI architectures for MPEG-4 motion estimation. Dordrecht: Kluwer Academic Publishers.
Tourapis, A. M. (2002). Enhanced predictive zonal search for single and multiple frame motion estimation. Electronic Imaging, 2002, 1069–1079.
Bossen, F., Bross, B., Suhring, K., & Flynn, D. (2012). HEVC complexity and implementation analysis. IEEE Transactions on Circuits and Systems for Video Technology, 22, 1685–1696.
ISO/IEC-JCT1/SC29/WG11 (2013). High efficiency video coding (HEVC) test model 12 (HM 12) encoder description. Vienna, Austria.
Seunghyun, C., & Munchurl, K. (2013). Fast CU splitting and pruning for suboptimal CU partitioning in HEVC Intra coding. IEEE Transactions on Circuits and Systems for Video Technology, 23, 1555–1564.
Correa, G., Assuncao, P., Agostini, L., & Silva Cruz, L. (2014). Complexity scalability for real-time HEVC encoders. Journal of Real-Time Image Processing, 1–16.
Jong-Hyeok, L., Chan-Seob, P.,& Byung-Gyu, K. (2012). Fast coding algorithm based on adaptive coding depth range selection for HEVC. In IEEE international conference on consumer electronics-Berlin (ICCE-Berlin) (pp. 31–33).
Goswami, K., Kim, B.-G., Jun, D.-S., Jung, S.-H., & Choi, J. S. (2014).Early coding unit (cu) splitting termination algorithm for high efficiency video coding (HEVC). ETRI Journal.
Jian, X., Hongliang, L., Qingbo, W., & Fanman, M. (2014). A fast HEVC inter CU selection method based on pyramid motion divergence. IEEE Transactions on Multimedia, 16, 559–564.
Lampert, C. H. (2006). Machine learning for video compression: Macroblock mode decision. In 18th international conference on pattern recognition, ICPR (pp. 936–940).
Garcia, R., Ruiz Coll, D., Kalva, H., & Fernandez-Escribano, G. (2013). HEVC decision optimization for low bandwidth in video conferencing applications in mobile environments. In IEEE international conference on multimedia and expo (ICME 2013), San Jose.
Shen, X., & Yu, L. (2013). CU splitting early termination based on weighted SVM. EURASIP Journal on Image and Video Processing, 2013, 4.
ISO/IEC-JCT1/SC29/WG11 (2013). High Efficiency Video Coding (HEVC) text specification draft (vol. 10). Geneva, Switzerland.
Correa, G., Assuncao, P., Agostini, L., & da Silva Cruz, L. A. (2011). Complexity control of high efficiency video encoders for power-constrained devices. IEEE Transactions on Consumer Electronics, 57, 1866–1874.
ISO/IEC-JCT1/SC29/WG11 (2012). Common test conditions and software reference configurations. Geneva, Switzerland.
Bjontegaard, G. (2001). Calculation of average PSNR differences between RD-curves. Austin, Texas.
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, 10–18.
Quinlan, J. R. (1983). C4.5: Programs for machine learning. Burlington: Morgan Kaufmann Publishers.
Kullback S. & Leibler R. A. (1951) On information and sufficiency (pp. 79–86).
Japkowicz, N. (2000). The class imbalance problem: Significance and strategies. In Proceedings of the 2000 international conference on artificial intelligence (IC-{AI}’2000) (pp. 111–117).
Correa, G., Assuncao, P., Agostini, L., & da Silva Cruz, L. (2015). Fast HEVC encoding decisions using data mining. IEEE Transactions on Circuits and Systems for Video Technology, 25(4), 660–673.
Acknowledgments
The authors would like to acknowledge the valuable help of Giovanni Ávila, Eliézer Ribeiro, Douglas Corrêa and Iago Storch, who conducted the method robustness analysis presented in Sect. 5.2. The authors also acknowledge financial aid from FAPERGS-Brazil, CAPES-Brazil, CNPq-Brazil, and FCT-Portugal. This work was supported by FAPERGS-Brazil, CAPES-Brazil, CNPq-Brazil, the project FCT-CAPES (4.4.1.00 CAPES) (FCT/1909/27/2/2014/S), the R&D Unit UID/EEA/50008/2013 and the FCT grant SFRH/BSAB/113682/2015.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Correa, G., Assuncao, P., Agostini, L. et al. Fast coding tree structure decision for HEVC based on classification trees. Analog Integr Circ Sig Process 87, 129–139 (2016). https://doi.org/10.1007/s10470-016-0719-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10470-016-0719-z