新一代的視訊編碼標準HEVC(High Efficiency Video Coding)，編碼效率相較先前的視訊編碼標準H.264/AVC 提升許多。HEVC 的編碼單元(Coding Unit, CU)採用了四分樹(Quad-Tree)的編碼架構，提供四種大小的編碼區塊以適應畫面複雜度，在編碼單元中又包含了預測單元(Prediction Unit, PU)與轉換單元(Transform Unit, TU)，在預測單元中，使用了35 個模式來進行預測來達到更精準的預測，但也大幅地增加其計算複雜度。因此在編碼單元中，本論文提出一支持向量機(Support Vector Machine, SVM)應用於編碼單元之快速深度決策演算法， 並利用位元- 失真最佳化(Rate-Distortion Optimization)程序中所得之RDO 失真成本，擷取其中最小值與門檻值比較是否繼續向下切割；而在預測單元的模式決策中，HEVC將進行約略模式決策(Rough Mode Decision, RMD)依據不同預測單元區塊大小選出8、8、3、3、3 個候選模式加上最有可能模式(Most Probable Mode, MPM)進行RDO程序，我們將RDO 程序中各候選模式的SATD 成本參數與該預測單元最小的SATD 成本參數比較，若其比例大於門檻值，即刪去該候選模式，以減少編碼所需時間，而此門檻值與量化參數及區塊大小有關。實驗結果顯示，相較原版，我們所提出的演算法平均可節省大約22%的整體編碼時間，而平均BDBR 上升不到0.1%，幾乎可以忽略。

High efficiency video coding (HEVC) is the latest standard for video compression, which can achieve significant improvements on coding efficiency. HEVC adopted quad-tree based coding unit (CU) which provides four kinds of block size for characteristics of video. CU contains Prediction Unit (PU) and Transform Unit (TU). To improve intra coding efficiency, using 35 prediction modes in PU. However, HEVC encoder complexity is tremendously increased. Hence, in this paper, we proposed a SVM based fast intra CU depth decision algorithm and utilize the minimum Rate-distortion Cost (RD Cost) to develop the criterion of CU early termination under SVM based algorithm. HEVC adopt RMD algorithm which select 8, 8, 3, 3, 3 modes for candidates list in different PU size. In our intra mode decision, the modes with larger SATD Cost are removed from candidate list of RDO process. The threshold is adaptive by block size and QP. The experimental results show that our proposed algorithm
achieves 22% time saving on average, with 0.09% BD-rate increase.

[1] “Generic coding of moving pictures and associated audio information,”
ISO/IEC 13818-2: Video (MPEG-2), May 1996.
[2] “Video coding for low bit rate communication, version 1,” ITU-T
recommendation H.263, 1995.
[3] T. Wiegand, G. J. Sullivan, G. Bjontegaard and A. Luthra, “Overview of
the H.264/AVC video coding standard,” IEEE Transactions on Circuits
and Systems for Video Technology, vol. 13, pp. 560-576, Jul. 2003.
[4] B. Bross, W.-J. Han, G. J. Sullivan, J.-R. Ohm, and T. Wiegand, High
Efficiency Video Coding (HEVC) Text Specification Draft 9, document
JCTVC-K1003, ITU-T/ISO/IEC Joint Collaborative Team on Video
Coding (JCT-VC), Oct. 2012.
[5] A. Saxena and F. C. Fernandes, “DCT/DST-Based Transform Coding or
Intra Prediction in Image/Video Coding”, IEEE Transactions on Image
Processing, vol. 22, No. 10, Oct. 2013.
[6] Shang-En Huang, “Low Computation Complexity for HEVC Intra
Prediction with Support Vector Machine”, Master Thesis, National Central
University, Jun. 2015
[7] B. Bross, W. J. Han, J. R. Ohmn, G. J. Sullivan and T. Wiegand, “WD4:
Working Draft 4 of High-Efficiency Video Coding”, JCTVC-F800, Torino,
Italy, Jul. 2011.
[8] J. Min, S. Lee, I. Kim, W. J. Han, J. Lainema, and K. Ugur, “Unification of
the directional intra prediction methods in TMuC”, JCTVC-B100, Geneva,
CH, 21-28 Jul. 2010
[9] J. Lainema, F. Bossen, W-J Han, J. Min and K. Ugur, “Intra Coding of the
HEVC Standard,” IEEE Transactions on Circuits and Systems for Video
Technology, vol. 22, no. 12, pp. 1792-1801, Dec. 2012.
[10] C. Corinna and V. Vapnik, “Support-vector networks. Mach Learn 20(3),”
pp. 273-297, 1995.
[11]Yang Wang, Xiaopeng Fan, Liang Zhao, Siwei Ma, Debin Zhao, Wen Gao,
“A Fast intra coding algorithm for HEVC”, IEEE International Conference
on Image Processing (ICIP), 10.1109/ICIP.2014.7025836, Oct.2014
[12] Liquan Shen, Zhaoyang Zhang, Ping An, “Fast CU Size Decision and
Mode Decision Algorithm for HEVC Intra Coding”, IEEE Transactions
on Consumer Electronics, vol. 59, no 1, Feb.2013
[13] Chang-Yi Chen, “Low-Complexity Intra Prediction for HEVC”, Master
Thesis, National Central University, Jun. 2014
[14] LIBSVM -- A Library for Support Vector,
Machineshttp://www.csie.ntu.edu.tw/~cjlin/libsvm/index.html
[15]G. Bjontegarrd, “Calculation of average PSNR differences between RD
curves,“ in ITU-T SC16/Q6 13th VCEG meeting, No.VCEG-M33, Austin,
TX, Apr. 2001
[16]Yu-Ru Tsai, “Hadamard Cost based Fast CU Decision Algorithm for
HEVC Intra Coding”, Master Thesis, National Central University, Jun.
2015
[17] C. M. Fang, Y. T. Chang and W. H. Chung, “Fast Intra Mode Decision for
HEVC Based on Direction Energy Distribution,” in proceeding of
IEEE International Symposium on Consumer Electronics, Jun. 2013, pp.
61-62
[18]W. Jiang, H. Ma and Y. Chen, “Gradient Based Fast Mode Decision
Algorithm for Intra Prediction in HEVC,” in proceeding of
IEEE International Consumer Electronics, Communications and
Networks, Apr. 2012, pp. 1836-1840