基於支持向量機之HEVC畫面內編碼單位快速決策演算法

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：79

、訪客IP：13.59.188.225

姓名

劉宴均(Yen-chun Liu) 查詢紙本館藏

畢業系所

通訊工程學系

論文名稱

基於支持向量機之HEVC畫面內編碼單位快速決策演算法
(SVM based fast intra CU depth decision for HEVC)

相關論文

★ 基於區域權重之衛星影像超解析技術	★ 延伸曝光曲線線性特性之調適性高動態範圍影像融合演算法
★ 實現於RISC架構之H.264視訊編碼複雜度控制	★ 基於卷積遞迴神經網路之構音異常評估技術
★ 具有元學習分類權重轉移網路生成遮罩於少樣本圖像分割技術	★ 具有注意力機制之隱式表示於影像重建三維人體模型
★ 使用對抗式圖形神經網路之物件偵測張榮	★ 基於弱監督式學習可變形模型之三維人臉重建
★ 以非監督式表徵分離學習之邊緣運算裝置低延遲樂曲中人聲轉換架構	★ 基於序列至序列模型之 FMCW雷達估計人體姿勢
★ 基於多層次注意力機制之單目相機語意場景補全技術	★ 基於時序卷積網路之單FMCW雷達應用於非接觸式即時生命特徵監控
★ 視訊隨選網路上的視訊訊務描述與管理	★ 基於線性預測編碼及音框基頻週期同步之高品質語音變換技術
★ 基於藉語音再取樣萃取共振峰變化之聲調調整技術	★ 即時細緻可調性視訊在無線區域網路下之傳輸效率最佳化研究

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

[檢視]

[下載]

本電子論文使用權限為同意立即開放。
已達開放權限電子全文僅授權使用者為學術研究之目的，進行個人非營利性質之檢索、閱讀、列印。
請遵守中華民國著作權法之相關規定，切勿任意重製、散佈、改作、轉貼、播送，以免觸法。

摘要(中)

由JCT-VC (ISO/IEC MPEG和 ITU-TVCEG)所制定的最新一代視訊壓縮標準High Efficiency Video Coding (HEVC)，其編碼效率相較於目前主流H.264視訊壓縮標準有顯著提升。延續H.264的巨區塊架構(Macroblock)，HEVC將基本編碼區塊改為編碼單元(Coding unit, CU)，並採用四分樹編碼結構(Quad-tree)提供更多編碼區塊大小以適應畫面特性，但此種樹狀架構也大幅增加了計算複雜度；而從視訊解析度不斷提升的演進來看，相較於畫面間編碼(Inter coding)，畫面內編碼(Intra coding)更能針對畫面中高移動量的部份以較精準的方向模式(Intra mode)去預測，因此發展畫面內CU深度決策快速演算法有其必要性。
本論文提出一個應用於畫面內編碼的CU深度快速決策演算法，擷取四種空間上的相關性以及原始畫面的資訊為特徵(Feature)，包含鄰近CU深度、邊界像素差值、像素變異數以及邊緣點數量，利用類神經網路分析這些特徵對CU切割與否的影響程度，依照輸入特徵給予支持向量機(Support vector machine, SVM)所預測出的結果不同的權重，加權後判斷目前CU是否往下切割，以減少位元-失真最佳化程序(Rate-Distortion Optimization)所帶來的龐大運算量。實驗結果顯示，在些微增加位元率的情況下，利用本演算法平均可以減少46.5%，最高至58.9%的總編碼時間。

摘要(英)

Intra coding of the latest video coding standard, High Efficiency Video Coding (HEVC) is an extension of that in H.264/AVC, which is more efficient than inter coding when video resolution becomes higher since it is hard to perform motion estimation well in a limited area when strong motion exists. In addition, HEVC adopted quad-tree based coding unit (CU) which is similar to the role of macroblock (MB) in H.264, had achieved much higher coding efficiency. However, the significant increase of complexity due to the advanced encoding structure cannot be neglected.
In this paper, an SVM based fast intra CU depth decision algorithm is proposed to reduce the computational complexity. It is convenient to develop the criterion of early CU splitting and termination by applying SVM with features extracted from spatial domain and pixel domain, including neighboring CU depth, boundary pixel difference, pixel variance and number of edge points. Furthermore, proper weightings are given to each SVM prediction result according to the impact of input features analyzed by artificial neural network for making CU depth decision.
The experiment results show that this fast algorithm provides 58.9% encoding time saving at most, and 46.5% encoding time saving on average compared to HM 12.1.

關鍵字(中)

★ 高效能視訊編碼
★ 畫面內編碼
★ 編碼單位
★ 快速演算法
★ 支持向量機

關鍵字(英)

★ HEVC
★ all intra
★ CU
★ fast algorithm
★ SVM

論文目次

摘要 I
Abstract II
致謝 III
目錄 V
附圖目錄 VII
附表目錄 VIII
第一章、緒論 1
1.1 研究背景 1
1.2 研究動機與目的 1
1.3 論文架構 2
第二章、HEVC編碼標準介紹 3
2.1編碼單位 4
2.2預測單位 4
2.2.1畫面間預測 5
2.2.2畫面內預測 6
2.3轉換單位 7
2.4編碼環境介紹 8
第三章、應用於HEVC編碼單位之快速演算法 10
3.1相關文獻探討 10
3.2基於支持向量機之畫面內編碼單位快速決策演算法 15
3.2.1支持向量機 15
3.2.2特徵選取 16
3.2.3特徵分析 19
3.3所提之演算法流程 24
第四章、實驗結果與討論 27
4.1實驗環境與SVM模組設置 27
4.2實驗結果 28
第五章、結論與未來展望 33
第六章、參考文獻 34

參考文獻

[1]Advanced Video Coding, ISO/IEC 14496-10, ITU-T Rec. H.264, Version 13, Mar. 2011.
[2]J. Ohm, W. J. Han, and T. Wiegand, “Overview of the high efficiency video coding (HEVC) standard,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 22, no. 12, pp. 1649–1668, Dec. 2012.
[3]J. Lainema, F. Bossen, W. J. Han, and J. H. Min, “Intra Coding of the HEVC Standard,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 22, no. 12, pp. 1792-1801, Dec. 2012.
[4]C. X. and C. Yuan, “Fast coding tree unit decision for HEVC intra coding,” IEEE ICCE-China Workshop, Shenzhen, China, Apr. 2013, pp. 28-31.
[5]J. W. Qiu, F. Liang, and Y. L. Luo, “A fast coding unit selection algorithm for HEVC,” IEEE International Conference on Multimedia and Expo Workshops (ICMEW), California, USA, July 2013, pp. 1-5.
[6]T. Nishikori, T. Nakamura, T. Yoshitome, and K. Mishiba, “A fast CU decision using image variance in HEVC intra coding,” IEEE Symposium on Industrial Electronics and Applications (ISIEA), Kuching, Malaysia, Sep. 2013, pp.52-56.
[7]L. Shen, Z. Zhang, and P. An, “Fast CU Size Decision and Mode Decision Algorithm for HEVC Intra Coding,” IEEE Transactions on Consumer Electronics, vol. 59, no. 1, pp. 207-213, Feb. 2013.
[8]H. Kalva, P. Kunzelmann, R. Jillani, A. Pandya, “Low Complexity H.264 Intra MB Coding,” International Conference on Consumer Electronics (ICCE), pp. 1-2, Las Vegas, USA, Jan. 2008.
[9]J. Kim, M. C. Kim, S. J. Hahm, I. J. Cho, and C. S. Park, “Block-Mode Classification Using SVMs for Early Termination of Block Mode Decision in H.264|MPEG-4 Part 10 AVC,” International Conference on Advances in Pattern Recognition (ICAPR), Kolkata, India, Feb. 2009, pp. 83-86.
[10]C. Corinna and V. Vapnik, “Support-vector networks. Mach Learn 20(3),” pp. 273-297, 1995.
[11] J. Xiong, H. L. Li, “Fast and Efficient Prediction Unit Size Selection for HEVC Intra Prediction,” IEEE International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS 2012), pp.366-369, New Taipei, Nov. 2012.
[12]X. Shen and L. Yu, “CU splitting early termination based on weighted SVM,” EURASIP Journal on Image and Video Processing, vol. 2013:4, Jan. 2013.
[13]LIBSVM -- A Library for Support Vector,
Machineshttp://www.csie.ntu.edu.tw/~cjlin/libsvm/index.html
[14]G. E. Hinton and R. R. Salakhutdinov, “Reducing the dimensionality of data with neural networks,” Science, vol. 313. no. 5786, pp. 504-507, July 2006.
[15]Matlab Central, Deep Learning Toolbox, http://www.mathworks.com/matlabcentral/fileexchange/38310-deep-learning-toolbox
[16]G. Bjontegaard, “Calculation of Average PSNR Difference Between RD-curves,” ITU-T Q.6/SG16 VCEG 13th Meeting, Document VCEG-M33, 2001.

指導教授

張寶基(Pao-chi Chang)

審核日期

2014-7-31

推文