Abstract
Versatile Video Coding (VVC/H.266) expands the intra-frame prediction modes from 35 of H.265 to 67, which not only improves the prediction accuracy and coding efficiency of the encoder but also increases its encoding complexity. In response to this problem, this paper proposes a support vector machine-based fast planar prediction mode decision algorithm for VVC/H.266, which is used to quickly determine the Planar or non-Planar prediction modes during intra coding, avoiding the rate-distortion optimization calculation of multiple intra prediction modes, and thus reducing the encoding time. The contributions of this paper are: 1) It proposes a novel feature based on Statistical Oriented Gradient (SOG) to extract the feature information of the coding block; 2) Based on the SOG feature, a support vector machine-based method is proposed to make the decision between the Planar and non-Planar modes for intra coding of VVC/H.266. The proposed algorithm has been integrated into the VVC/H.266 standard coder, VTM5.0. The experimental results show that, compared with VTM5.0, the encoding time of the proposed algorithm is reduced by 18.0% on average, while the Bjøntegaard-Delta -Rate (BD-RATE) increased by only 1.3%.
Similar content being viewed by others
References
Bahri N, Randa K (2020) Optimised HEVC encoder intra-only configuration. IET Comput Digit Tech 14(6):256–262. https://doi.org/10.1049/iet-cdt.2019.0197
Bouaafia S, Randa K, Fatma-Ezahra S et al (2020) Fast CU partition-based machine learning approach for reducing HEVC complexity. J Real-Time Image Proc 17(1):185–196. https://doi.org/10.1007/s11554-019-00936-0
Bross B (2018) Versatile Video Coding (Draft 1), JVET-J1001. http://phenix.it-sudparis.eu/jvet/index.php
Bross B, Kenneth A, Max B et al (2020) General video coding Technology in Responses to the joint call for proposals on video compression with capability beyond HEVC. IEEE Trans Circ Syst Video Technol 30(5):1226–1240. https://doi.org/10.1109/TCSVT.2019.2949619
Cao J, Na T, Jun W, et al (2020) Texture-based fast CU size decision and intra mode decision algorithm for VVC. 26th International Conference on MultiMedia Modeling (MMM), 739–751. https://doi.org/10.1007/978-3-030-37731-1_60
Chih-Chung Chang and Chih-Jen Lin (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):1–27 http://www.csie.ntu.edu.tw/~cjlin/libsvm/index.html
Fan Y, Jun'An C, Heming S et al (2020) A fast QTMT partition decision strategy for VVC intra prediction. IEEE Access 8:107900–107911. https://doi.org/10.1109/ACCESS.2020.3000565
Farrugia R-A, Carl-James D (2008) A robust error detection mechanism for H.264/AVC coded video sequences based on support vector machines. IEEE Trans Circ Syst Video Technol 18(12):1766–1770. https://doi.org/10.1109/TCSVT.2008.2004919
Geuder W, Amon P, Steinbach E (2015) Low-complexity block size decision for HEVC intra coding using binary image feature descriptors. Int Conf Image Process(ICIP):242–246. https://doi.org/10.1109/ICIP.2015.7350796
Ghaznavi-Youvalari R, Alireza A (2018) Geometry-based motion vector scaling for omnidirectional video coding. IEEE Int Symp Multimedia (ISM) 2018:127–130. https://doi.org/10.1109/ISM.2018.00030
Grellert M et al (2018) Fast coding unit partition decision for HEVC using support vector machines. IEEE Trans Circ Syst Video Technol 29(6):1741–1753. https://doi.org/10.1109/TCSVT.2018.2849941
Hao Y, Liquan S, An P (2017) An efficient intra coding algorithm based on statistical learning for screen content coding. IEEE Int Conf Image Process (ICIP):2468–2472. https://doi.org/10.1109/ICIP.2017.8296726
Hosseini E, Pakdaman F, Hashemi M et al (2019) A computationally scalable fast intra coding scheme for HEVC video encoder. Multimed Tools Appl 78(9):11607–11630. https://doi.org/10.1007/s11042-018-6713-y
Huang G, Hongming Z, Xiaojian D et al (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern Part b-cybernetics 42(2):513–529. https://doi.org/10.1109/TSMCB.2011.2168604
Huang Y, Dayong W, Sun Y et al (2020) A fast intra coding algorithm for HEVC by jointly utilizing naive Bayesian and SVM. Multimed Tools Appl 79(45–46):33957–33971. https://doi.org/10.1007/s11042-020-08882-x
Kamath S, Aparna P, Abhilash A (2020) Performance enhancement of HEVC lossless mode using context-based angular and planar intra predictions. Multimed Tools Appl 79(17–18):11375–11397. https://doi.org/10.1007/s11042-019-08466-4
Lei M, Falei L, Xiang Z (2019) Look-ahead prediction based coding unit size pruning for VVC intra coding. IEEE Int Conf Image Process (ICIP) 2019:4120–4124. https://doi.org/10.1109/ICIP.2019.8803421
Li C, Congrui L, Junwen L (2018) Fast intra candidate selection and CU Split in intra prediction for future video coding. IEEE Int Conf Safety Produce Inform (IICSPI) 2018:723–727. https://doi.org/10.1109/IICSPI.2018.8690465
Li T, Hongkui W, Yamei C et al (2020) Fast depth intra coding based on spatial correlation and rate-distortion cost in 3D-HEVC. Signal Process Image Commun 80:115668. https://doi.org/10.1016/j.image.2019.115668
Liao W, Daiqin Y, Zhenzhong C (2016) A fast mode decision algorithm for HEVC intra prediction. Visual Comm Image Process (VCIP) 2016:1–4. https://doi.org/10.1109/VCIP.2016.7805540
Liu Y, Fazheng Y (2007) Soft SVM and its application in video-object extraction. IEEE Trans Signal Process 55(7):3272–3282. https://doi.org/10.1109/TSP.2007.894403
Mallikarachchi T, Talagala DS, Arachchi HK, Fernando A (2016) Content-adaptive feature-based CU size prediction for fast low-delay video encoding in HEVC. IEEE Trans Circuits Syst Video Technol 28(3):693–705. https://doi.org/10.1109/TCSVT.2016.2619499
Melgani F, Bruzzone L (2004) Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans Geosci Remote Sens 42(8):1778–1790. https://doi.org/10.1109/TGRS.2004.831865
Pakdaman F, Yu L, Hashemi MR, Ghanbari M, Gabbouj M (2021) SVM based approach for complexity control of HEVC intra coding. Signal Process Image Commun 93:116177. https://doi.org/10.1016/j.image.2021.116177
Polat K, Salih G (2009) A new feature selection method on classification of medical datasets: kernel F-score feature selection. Expert Syst Appl 36(7):10367–10373. https://doi.org/10.1016/j.eswa.2009.01.041
Ruiz D, Damián R, Gerardo F-E et al (2017) Fast CU partitioning algorithm for HEVC intra coding using data mining. Multimed Tools Appl 76(1):861–894. https://doi.org/10.1007/s11042-015-3014-6
Ruiz D, Gerardo F-E, Jose LM et al (2019) A unified architecture for fast HEVC intra-prediction coding. J Real-Time Image Proc 16(5):1825–1844. https://doi.org/10.1007/s11554-017-0685-4
Ryu S, Je-Won K (2018) Machine learning-based fast angular prediction mode decision technique in video coding. IEEE Trans Image Process 27(11):5525–5538. https://doi.org/10.1109/TIP.2018.2857404
Sun X, Xiaodong C, Xu Y et al (2018) An efficient CU partition algorithm for HEVC based on improved Sobel operator. Chengdu: Int Conf Graphic Image Process (ICGIP 2017) 10615:1061544. https://doi.org/10.1117/12.2302920
Wang S, Peidi Y, Hongkui W et al (2020) Densely connected unit based loop filter for short video coding. Data Compression Conf (DCC) 2020:398–398. https://doi.org/10.1109/DCC47342.2020.00076
Wang Z, Fan L (2020) Convolutional neural network-based low complexity HEVC intra encoder. Multimed Tools Appl 80(2):2441–2460. https://doi.org/10.1007/s11042-020-09231-8
Wang Z, Shiqi W, Jian Z et al (2018) Probabilistic decision based block partitioning for future video coding. IEEE Trans Image Process 27(3):1475–1486. https://doi.org/10.1109/TIP.2017.2778564
Yang H, Liquan S, Xinchao D et al (2020) Low complexity CTU partition structure decision and fast intra mode decision for versatile video coding. IEEE Trans Circ Syst Video Technol 30(6):1668–1682. https://doi.org/10.1109/TCSVT.2019.2904198
Yao Y, Tianjie J, Xiaojuan L et al (2018) A fast DEA-based intra-coding algorithm for HEVC. Multimed Tools Appl 77(2):1861–1881. https://doi.org/10.1007/s11042-017-4372-z
Yoon Y-U, Park D-H, Kim J-G et al (2019) Most frequent mode for intra-mode coding in video coding. Electron Lett 55(4):188–189. https://doi.org/10.1049/el.2018.7452
Zhang Q, Yihan W, Lixun H et al (2020) Fast CU partition and intra mode decision method for H.266/VVC. IEEE Access 8:117539–117550. https://doi.org/10.1109/ACCESS.2020.3004580
Zhang Q, Yihan W, Lixun H et al (2021) Fast CU partition decision for H.266/VVC based on the improved DAG-SVM classifier model. Multimedia Systems 27(1):1–14. https://doi.org/10.1007/s00530-020-00688-z
Zhang Y, Sam K, Wang X, Hui Y, Zhaoqing P, Long X (2015) Machine learning-based coding unit depth decisions for flexible complexity allocation in high efficiency video coding. IEEE Trans Image Process 24(7):2225–2238. https://doi.org/10.1109/TIP.2015.2417498
Zhao Z, Shuhua X, Weiheng S et al (2020) An improved R-lambda rate control model based on joint spatial-temporal domain information and HVS characteristics. Multimed Tools Appl 80(1):345–366. https://doi.org/10.1007/s11042-020-09721-9
Zhu W, Yao Y, Hanyu Z et al (2020) Fast mode decision algorithm for HEVC intra coding based on texture partition and direction. J Real-Time Image Proc 17(2):275–292. https://doi.org/10.1007/s11554-018-0766-z
Acknowledgements
This work was supported in part by Public Welfare Technology Research Project Of Zhejiang (LGG19F020014), Scientific research projects of Zhejiang Provincial Department of Education (Y202044430) and General Project of Zhejiang Natural Science Foundation (LY19F010011).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
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
Yao, Y., Wang, J., Du, C. et al. A support vector machine based fast planar prediction mode decision algorithm for versatile video coding. Multimed Tools Appl 81, 17205–17222 (2022). https://doi.org/10.1007/s11042-022-12582-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12582-z