Abstract
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.
Similar content being viewed by others
References
Sullivan, G.J., Ohm, J.R., Han, W.J., Wiegand, T.: Overview of the high efficiency video coding (HEVC) standard. IEEE Trans. Circ. Syst. Video Technol. 22(12), 1649 (2012)
Correa, G., Assuncao, P., Agostini, L., Da Silva Cruz, L.A.: Performance and computational complexity assessment of high-efficiency video encoders. IEEE Trans. Circ. Syst. Video Technol. 22(12), 1899 (2012)
Shen, L., Liu, Z., Zhang, X., Zhao, W., Zhang, Z.: An effective CU size decision method for HEVC encoders. IEEE Trans. Multimedia 15(2), 465 (2013)
Lee, Hoyoung, Shim, Huik Jae, Park, Younghyeon, Jeon, B.: Early skip mode decision for HEVC encoder with emphasis on coding quality. IEEE Trans. Broadcast. 61(3), 388 (2015)
Zhang, Y., Kwong, S., Wang, X., Yuan, H., Pan, Z., Xu, L.: Machine learning based coding unit depth decisions for flexible complexity allocation in high efficiency video coding. IEEE Trans. Image Process. 24(7), 2225 (2015)
Correa, G., Assuncao, P., Agostini, L., Da Silva Cruz, L.A.: Fast HEVC encoding decisions using data mining. IEEE Trans. Circ. Syst. Video Technol. 25(4), 660 (2015)
Breiman, L.: Random forests. J. Mach. Learn. 45(1), 5 (2001)
Rhee, C.E., Lee, K., Kim, T., Lee, H.J.: A survey of fast mode decision algorithms for inter-prediction and their applications to high efficiency video coding. IEEE Trans. Consum. Electron. 58(4), 1375 (2012)
Sun, X., Chen, X., Xu, Y., Xiao, Y., Wang, Y., Yu, D.: Fast CU size and prediction mode decision algorithm for HEVC based on direction variance. J. Real-Time Image Proc. (2017). https://doi.org/10.1007/s11554-017-0682-7
Shen, L., Zhang, Z., Liu, Z.: Adaptive inter-mode decision for HEVC jointly utilizing inter-level and spatiotemporal correlations. IEEE Trans. Circuits Syst. Video Technol. 24(10), 1709 (2014)
Lin, T.L., Chou, C.C., Liu, Z., Tung, K.H.: HEVC early termination methods for optimal CU decision utilizing encoding residual information. J. Real-Time Image Proc. (2016). https://doi.org/10.1007/s11554-016-0608-9
Tai, Kh, Hsieh, My, Chen, Mj, Chen, Cy, Yeh, C.H.: A fast HEVC encoding method using depth information of collocated CUs and RD cost characteristics of PU modes. IEEE Trans. Broadcast. 63(4), 680 (2017)
Chen, F., Li, P., Peng, Z., Jiang, G., Yu, M., Shao, F.: A fast inter coding algorithm for hevc based on texture and motion quad-tree models. Signal Process. Image Commun. 47, 271 (2016)
Huang, X., Zhang, Q., Zhao, X., Zhang, W., Zhang, Y., Gan, Y.: Fast inter-prediction mode decision algorithm for HEVC. Signal Image Video Process. 11(1), 33 (2017)
Jaja, E.T., Omar, Z., Ab Rahman, A.AH., et al.: Enhanced inter-mode decision algorithm for HEVC/H. 265 video coding. J. Real-Time Image Proc. (2015). https://doi.org/10.1007/s11554-015-0542-2
Ahn, S., Lee, B., Kim, M.: A novel fast CU encoding scheme based on spatiotemporal encoding parameters for HEVC inter coding. IEEE Trans. Circ. Syst. Video Technol. 25(3), 422 (2015)
Lee, J.H., Goswami, K., Kim, B.G., Jeong, S., Choi, J.S.: Fast encoding algorithm for high-efficiency video coding (HEVC) system based on spatio-temporal correlation. J. Real-Time Image Process. 12(2), 407 (2016)
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. 453–456
Shen, L., Zhang, Z., Zhang, X., An, P., Liu, Z.: Fast TU size decision algorithm for HEVC encoders using Bayesian theorem detection. Signal Process. Image Commun. 32, 1–8 (2015)
Xiong, J., Li, H., Wu, Q., Meng, F.: A fast HEVC inter CU selection method based on pyramid motion divergence. IEEE Trans. Multimedia 16(2), 559 (2014)
Grellert, M., Zatt, B., Bampi, S., da Silva Cruz, L.A.: Fast coding unit partition decision for HEVC using support vector machines. IEEE Trans. Circ. Syst. Video Technol. (2018). https://doi.org/10.1109/TCSVT.2018.2849941
Kim, H.S., Park, R.H.: Fast CU partitioning algorithm for HEVC using an online-learning-based bayesian decision rule. IEEE Trans. Circ. Syst. Video Technol. 26(1), 130 (2016)
Zhu, L., Zhang, Y., Pan, Z., Wang, R., Kwong, S., Peng, Z.: Binary and multi-class learning based low complexity optimization for HEVC encoding. IEEE Trans. Broadcast. 63(3), 547 (2017)
Shen, X., Yu, L.: CU splitting early termination based on weighted SVM. EURASIP J. Image Video Process. 2013(4), 1 (2013)
Ruiz, D., Fernández-Escribano, G., Martínez, J.L., Cuenca, P.: A unified architecture for fast HEVC intra-prediction coding. J. Real-Time Image Proc. (2017). https://doi.org/10.1007/s11554-017-0685-4
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)
Woźniak, M., Graña, M., Corchado, E.: A survey of multiple classifier systems as hybrid systems. Inf. Fusion 16, 3 (2014)
Fern, M., Cernadas, E.: Do we need hundreds of classifiers to solve real world classification problems ? J. Mach. Learn. Res. 15(1), 3133 (2014)
Duda, R.O., Hart, P.E.P.E., Stork, D.G.: Pattern Classification. Wiley, Oxford (2001)
Yu, L., Liu, H.: Efficient feature selection via analysis of relevance and redundancy. J. Mach. Learn. Res. 5, 1205 (2004)
Hall, M.A., Holmes, G.: Benchmarking attribute selection techniques for discrete class data mining. IEEE Trans. Knowl. Data Eng. 15(6), 1437 (2003)
Zhu, L., Zhang, Y., Li, N., Jiang, G., Kwong, S.: Machine learning based fast h.264/avc to hevc transcoding exploiting block partition similarity. J. Vis. Commun. Image Rep. 38, 824 (2016)
Fawcett, T.: Tom: an introduction to ROC analysis. Pattern Recogn. Lett. 27(8), 861 (2006)
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)
High Efficiency Video Coding (HEVC) | JCT-VC. https://hevc.hhi.fraunhofer.de/. Accessed 2 Feb 2019
Lee, B.N.: librf: C++ random forests library. http://mtv.ece.ucsb.edu/benlee/librf.html. Accessed 2 Feb 2019
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)
Bjontegaard, G.: Calculation of average PSNR differences between RD-curves. In ITU - T SG16 Q. 6 VCEG-M33 (Austin, Texas)
Acknowledgements
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.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Tahir, M., Taj, I.A., Assuncao, P.A. et al. Fast video encoding based on random forests. J Real-Time Image Proc 17, 1029–1049 (2020). https://doi.org/10.1007/s11554-019-00854-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-019-00854-1