簡易檢索 / 詳目顯示

研究生: 薛伊倩
Hsueh, I-Chien
論文名稱: HEVC編碼器平行化之負載平衡研究
Load Balanced Slice-level Parallelism of the HEVC Encoder
指導教授: 王家祥
口試委員: 賴尚宏
蕭旭峰
學位類別: 碩士
Master
系所名稱: 電機資訊學院 - 資訊工程學系
Computer Science
論文出版年: 2012
畢業學年度: 100
語文別: 英文
論文頁數: 46
中文關鍵詞: 平行編碼器負載平衡
相關次數: 點閱:2下載:0
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • HEVC (H.265)是一個新的視訊壓縮技術標準,目標是和H.264/AVC比較可以節省50%的位元率,提升高畫質影片壓縮效率以及品質,HEVC提出了由 Coding Unit、Prediction Unit及Transform Unit組成的coding tree結構。和之前的H.264/AVC最大為16x16的 macro block相比,HEVC的 Coding Unit最小為8x8,最大則可以到16x16。藉由較大的Coding Unit,HEVC可以有效的降低位元率。另外,HEVC還用了許多新的機制來提升壓縮效率及品質。然而,伴隨而來的則是大量的運算複雜度使得編碼時間過長。本篇論文主要是利用多核心系統平行運算的方式將HEVC編碼器平行化以達到編碼速度的提升。
    在HEVC編碼過程中,一張影像可以被切成多個獨立編碼的slice,因此本篇論文提出了一個以slice為資料平行處理單位的平行演算法(slice-level parallelism)。由於編碼過程中各個slice所消耗的運算量不盡相同,以往的slice-level parallelism在做平行運算時會使得各處理器的工作量分布不均而導致系統效能降低。然而,本篇論文的方法能夠針對此問題改進而達到更高的平行化效果。我們所提出的演算法中,首先會針對每個LCU做運算時間的預估,依照預估的結果來配置每個slice的LCU個數試圖使每個Slice的運算平衡。另外利用提早結束編碼的機制來縮短不同Slice間編碼時間的差距。


    致謝 I 中文摘要 II Abstract III Table of Contents V List of Figures VII List of Tables IX Chapter 1. Introduction 1 Chapter 2. Related Work 4 2-1. Introduction to HEVC Encoder 4 2-1-1. Coding Structure 5 2-1-2. Intra prediction in HEVC 8 2-2. Early CU termination 9 2-3. Parallelism 11 Chapter 3. Load Balanced Slice-level parallelism 14 3-1 Workload Estimation 18 3-2 Slice Partition 20 3-1 Work Load Reduction 22 Chapter 4. Simulation Results 28 4-1 Evaluation of Encoding Speed 29 4-2 Evaluation of Quality and Coding Efficiency 36 Chapter 5. Conclusions and Future Works 43 References 45

    [1] ISO/IEC JVC 1 SC29 WG11, “Joint Call for Proposals on Video Compression Technology,” Doc. N11113, Jan. 2010.
    [2] Liang Zhao, Li Zhang, Siwei Ma and Dedin Zhao, “Fast Mode Decision Algorithm for Intra Prediction in HEVC,” IEEE Visual Communications and Image Processing (VCIP), pp. 1-4, November. 2011.
    [3] Jongho Kim, Seyoon Jeong, Sukhee Cho and Jin Soo Choi, “Adaptive Coding Unit Early Termination Algorithm for HEVC,” IEEE International Conference on Consumer Electronics (ICCE), pp. 261-262, January 2012.
    [4] Gary .J Sullivan and Jens-Rainer Ohm, “Recent developments in standardization of high efficiency video coding (HEVC),” Applications of digital Image Processing XXXIII. Proceeding of SPIE Volume: 7798, 2010.
    [5] Kiho Choi, Sang-Hyo Park, and Euee S. Jang, ”Coding tree pruning based CU early termination,” JCT-VC document, JCTVC-F092, July, 2011.
    [6] Thomas Davies, “BBC’s Response to the Call for Proposals on Video Compression Technology,” JCT-VC document, JCTVC-A125, April, 2010.
    [7] Ken McCann, Benjamin Bross, I1-Koo Kim, Shun-ichi Sekiguchi and Woo-Jin Han, “HM5: High Efficiency Video Coding (HEVC) Test Model 5 Encoder Description,” JCT-VC document, JCTVC-G1102, November, 2011.
    [8] Guilherme Correa, Pedro Assuncao, Luciano Agostini and Luis A. da Silva Cruz, “Complexity Control of High Efficiency Video Encoders for Power-Constrained Devices,” IEEE Transactions on Consumer Electronics, Vol.57, No.4, pp.1866-1974, November 2011.

    [9] Félix Henry, and Stéphane Pateux, ”Wavefront Parallel Processing,” JCT-VC document, JCTVC-E196, March, 2011.
    [10] Arild Fuldseth, Michael Horowitz, Shilin Xu and Minhua Zhou, “Tiles,” JCT-VC document, JCTVC-E408, March, 2011.
    [11] https://hevc.hhi.fraunhofer.de/svn/svn_HEVCSoftware/branches/HM-5.2-dev/ HEVC test model HM-5.2, 2012.
    [12] Mauricio Alvarez-Mesa, Chi Ching Chi, Ben Juurlink, Valeri George and Thomas Schierl, “Parallel Video Decoding in the Emerging HEVC Standard,” in Proc. 37th Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2012, accepted for publication.
    [13] Bin Li, Gary J. Sullivan and Jizheng Xu, ” Comparison of Compression Performance of HEVC Working Draft 5 with AVC High Profile, ” JCT-VC document, JCTVC-H0360, February, 2012.

    無法下載圖示 全文公開日期 本全文未授權公開 (校內網路)
    全文公開日期 本全文未授權公開 (校外網路)

    QR CODE