Fast video encoding based on random forests
- 14 Downloads
Machine learning approaches have been increasingly used to reduce the high computational complexity of high-efficiency video coding (HEVC), as this is a major limiting factor for real-time implementations, due to the decision process required to find optimal coding modes and partition sizes for the quad-tree data structures defined by the standard. This paper proposes a systematic approach to reduce the computational complexity of HEVC based on an ensemble of online and offline Random Forests classifiers. A reduced set of features for training the Random Forests classifier is proposed, based on the rankings obtained from information gain and a wrapper-based approach. The best model parameters are also obtained through a consistent and generalizable method. The proposed Random Forests classifier is used to model the coding unit and transform unit-splitting decision and the SKIP-mode prediction, as binary classification problems, taking advantage from the combination of online and offline approaches, which adapts better to the dynamic characteristics of video content. Experimental results show that, on average, the proposed approach reduces the computational complexity of HEVC by 62.64% for the random access (RA) profile and 54.57% for the low-delay (LD) main profile, with an increase in BD-Rate of 2.58% for RA and 2.97% for LD, respectively. These results outperform the previous works also using ensemble classifiers for the same purpose.
KeywordsFast video coding HEVC Random forests in HEVC Machine learning in HEVC
The authors would like to thank the anonymous reviewers for their comments and suggestions to improve this work. Pedro A. Assuncao would like to acknowledge the support of Fundacao para a Ciencia e Tecnologia (FCT) by Instituto de Telecomunicacoes (IT), grant UID/EEA/50008/2013, and Project ARoundVision SAICT-45-2017-POCI-01-0145-FEDER-030652, PTDC/EEI-COM/30652/2017, Portugal.
- 18.Shen, X., Yu, L., Chen, J.: Fast coding unit size selection for HEVC based on Bayesian decision rule. In: Picture Coding Symposium (PCS), 2012 (IEEE, 2012), pp. 453–456Google Scholar
- 24.Shen, X., Yu, L.: CU splitting early termination based on weighted SVM. EURASIP J. Image Video Process. 2013(4), 1 (2013)Google Scholar
- 26.Du, B., Siu, W.C., Yang, X.: Fast CU partition strategy for HEVC intra-frame coding using learning approach via random forests. In 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015 (0), 1085 (2016)Google Scholar
- 34.Mallikarachchi, T., Talagala, D.S., Arachchi, H.K., Fernando, A.: Content-adaptive feature-based CU size prediction for fast low-delay video encoding in HEVC. IEEE Trans. Circ. Syst. Video Technol. 8215(c), 1 (2016)Google Scholar
- 35.High Efficiency Video Coding (HEVC) | JCT-VC. https://hevc.hhi.fraunhofer.de/. Accessed 2 Feb 2019
- 36.Lee, B.N.: librf: C++ random forests library. http://mtv.ece.ucsb.edu/benlee/librf.html. Accessed 2 Feb 2019
- 37.Bossen, F.: Common test conditions and software reference configurations. in 12th Meeting of JCT-VC of ITU-T SG16 WP3 and ISO/IEC JTC1/SC29/WG11 (Geneva)Google Scholar
- 38.Bjontegaard, G.: Calculation of average PSNR differences between RD-curves. In ITU - T SG16 Q. 6 VCEG-M33 (Austin, Texas)Google Scholar