跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 鍾聖政
Sheng-Cheng Chung
論文名稱： 利用支持向量機結合卷積神經網路降低HEVC畫面間預測之計算複雜度研究
Computation Reduction of HEVC Inter Prediction using combined SVM and CNN
指導教授： 林銀議
Yin-Yi Lin
口試委員:
學位類別： 碩士
Master
系所名稱： 資訊電機學院 - 通訊工程學系
Department of Communication Engineering
論文出版年： 2021
畢業學年度： 109
語文別： 中文
論文頁數： 85
中文關鍵詞： 高效率視頻編碼 、支持向量機 、卷積神經網路 、編碼單元 、快速深度決策 、畫面間預測 、改善編碼性能 、深度學習 、移動向量
外文關鍵詞： High Efficiency Video Coding (HEVC), Support Vector Machine(SVM), Convolutional Neural Network(CNN), Coding Unit(CU), Inter Prediction, Improved Coding Performance, Deep Learning, Motion Vector, Fast Depth Decision
相關次數： 點閱：17  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

    • 在這網路快速進步的時代，對於高解析度影像的需求不斷提升，高解析度代表著資料量相對龐大，HEVC/H.265採用編碼單元(Coding Unit,CU)、預測單元(Prediction Unit,PU)、碼率失真最佳化(Rate-Distortion Optimization)等等，這些先進的編碼技術提高了壓縮率，但運算複雜度卻也大幅的增加，本論文結合卷積神經網路與支持向量機應用於編碼單元深度決策。首先在編碼一開始使用支持向量機將編碼單元分類為只做深度0、深度0~1、深度0~2、深度0~3四種類別，再各別使用卷積神經網路依據在支持向量機已取得的畫面間預測移動向量值做為特徵(Feature)，判斷是否需要提前終止，提前終止的區塊只會進行一次深度的編碼，且因為移動向量值為特徵複用，進而節省編碼所需花費的運算時間。在只進行64x64編碼決策的情況下，實驗結果與HEVC進行比較，平均BDBR上升1.32%的情況下，編碼時間節省46.84%。

    In the era of rapid Internet advancement, the demand for high-resolution images continues to increase. The use of high-resolution images implies that a large amount of data is resulted. HEVC/H.265 adopts advanced encoding techniques such as Coding Unit (CU), Prediction Unit (PU), and Rate-Distortion Optimization to improve the compression ratio of data; however, such approach also increases the computational complexity significantly. In this thesis, Convolutional Neural Network (CNN) was combined with Support Vector Machine (SVM) and applied to the depth decision of coding unit. At the beginning of the coding process, Support Vector Machine was used to sort the coding units into four categories of depth 0, depth 0~1, depth 0~2 and depth 0~3. Convolutional Neural Network was then used to determine whether early termination is needed based on the inter prediction motion vector value obtained by the Support Vector Machine as a feature. The block that terminates early will only be deep-coded once. Since the motion vector value is feature multiplex, it reduces the computation time required for coding. For 64x64 coding decision, the experimental results were compared with HEVC, showing that the coding time was reduced by 46.84% when the average BDBR was increased by 1.32%.

    第一章、緒論 1 1.1研究動機與目的 1 1.2論文架構 2 第二章、H.265/HEVC視訊編碼標準介紹 3 2.1 H.265/HEVC視訊編碼介紹 3 2.2 H.265/HEVC視訊編碼架構介紹 4 2.2.1 編碼單元(Coding Unit, CU) 5 2.2.2 預測單元(Prediction Unit, PU) 7 2.2.3 轉換單元(Transform Unit, TU) 8 2.2.4 畫面間預測(Inter Prediction) 8 第三章、支持向量機及深度學習介紹 17 3.1支持向量機(Support Vector Machine, SVM) 17 3.2深度學習介紹 19 3.2.1 類神經網路 20 3.2.2 深度神經網路(Deep Neural Networks, DNN) 20 3.2.3 卷積神經網路(Convolutional Neural Networks, CNN) 21 第四章、相關文獻回顧 25 4.1 利用支持向量機減少編碼單元複雜度相關文獻回顧 25 4.1.1 Reduction of Computational Complexity HEVC Inter Prediction With Support Vector Machine 25 4.2利用CNN減少CU編碼複雜度相關文獻回顧 31 4.2.1 Fast CU Depth Decision for HEVC Using Neural Networks 32 4.2.2 SVM/CNN-based CTU partition for HEVC inter prediction 34 第五章、結合SVM與CNN應用於編碼單元快速決策演算法 37 5.1 編碼單元快速決策演算法 37 5.1.1 演算法優缺點探討 37 5.1.2 編碼單元快速決策演算法流程 38 5.2 整體系統架構 40 5.2.1 前處理階段(Pre-processing stage) 41 5.2.2 訓練階段(Training stage) 41 5.2.3 測試階段(Testing stage) 46 第六章、編碼單元快速決策演算法性能比較 48 6.1 環境設置 48 6.2 效能分析 52 6.3 不同模型與演算法性能比較 57 6.4移動向量值的可視化比較 61 第七章、結論與未來展望 63 參考文獻 64

    [1] JCT-VC, “High efficiency video coding (HEVC) test model 15(HM15) encoder description,” JCTVC-Q1002, JCT-VC Meeting, Valencia, ES, Apr. 2014.
    [2] “Generic coding of moving pictures and associated audio information,” ISO/IEC 13818-2: Video (MPEG-2), May 1996.
    [3] I. E. G. Richardson, H.264 and MPEG-4 Video Compression: Video Coding for Next-generation Multimedia. Aberdeen, U.K.: John Wiley & Sons, 2003.
    [4] P. Helle, S. Oudin, B. Bross, D. Marpe, M. O. Bici, K. Ugur, J. Jung, G. Clare, and T. Wiegand, “Block merging for quadtree-based partitioning in HEVC,” in Proc. IEEE Transactions on circuits and systems for video technology, vol. 22, no. 12, pp. 1720-1731, Dec. 2012.
    [5] L. Zhao, X. Guo, S. Lei, S. Ma and D. Zhao, “Simplified AMVP for high efficiency video coding,” in Proc. IEEE ICIP, pp. 1-4, 27-30 Nov. 2012.
    [6] J. L. Lin, Y. W. Chen, Y. W. Huang, and S. M. Lei, “Motion vector coding in the HEVC standard,” in Proc. IEEE Journal of Selected Topics in Signal Processing, vol. 7, no. 6, pp. 957-968, 3 July 2013.
    [7] Y. Ismail and S. El-etriby, “Fast diamond search algorithm for real time video
    coding,” in Proc. IEEE ICNC, pp. 729-733, Feb. 2012.
    [8] K. Alex, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep
    Convolutional Neural Networks,” in Advances in Neural Information Processing
    Systems, pp.1097-1105, 2012.
    [9]X. Liu, Y. Li, D. Liu, P. Wang, L. T. Yang, “An Adaptive CU Size Decision Algorithm for HEVC Intra Prediction Based on Complexity Classification Using Machine Learning”, IEEE Transactions on Circuits and Systems for Video Technology, Vol 29, pp.144-155, 27 November 2017.
    [10]T. Zhang, M. T. Sun, D. Zhao, W. Gao, “Fast Intra-Mode and CU Size Decision for HEVC”, IEEE Transactions on Circuits and Systems for Video Technology, Vol 27, pp.1714-1726, 20 April 2016.
    [11]S. J. Cai, Yin yi Lin, “ Reduction of Computation Complexity for HEVC Intra Prediction with Support Vector Machine”, National Central University, Master Thesis, Jun 2017.
    [12] J.K. Liu, “Reduction of Computational Complexity for HEVC Inter Prediction with Support Vector Machine,” Department of Communication Engineering National Central University, Taiwan 32054, R.O.C.,Jan 2019.
    [13] K. Kim and W. W. Ro, "Fast CU depth decision for HEVC using neural networks", IEEE Trans. Circuits Syst. Video Technol., vol. 29, no. 5, pp. 1462-1473, May 2019.
    [14]DH
    [15] Tianyi Li,Mai Xu,Xin Deng, “ A deep convolutional neural network approach for complexity reduction on intra-mode HEVC”, 2017 IEEE International Conference on Multimedia and Expo (ICME).
    [16] Takafumi Katayama,Kazuki Kuroda,Wen Shi,Tian Song,Takashi Shimamoto,“Low-complexity intra coding algorithm based on convolutional neural network for HEVC”, 2018 International Conference on Information and Computer Technologies (ICICT).
    [17] Kyungah Kim,Won Woo Ro,“Fast CU Depth Decision for HEVC Using Neural Networks”, IEEE Transactions on Circuits and Systems for Video Technology ( Volume: 29 , Issue: 5 , May 2019 ).
    [18] Mai Xu,Tianyi Li,Zulin Wang,Xin Deng,Ren Yang,Zhenyu Guan, “Reducing Complexity of HEVC: A Deep Learning Approach”, IEEE Transactions on Image Processing ( Volume: 27 , Issue: 10 , Oct. 2018 ).
    [19] Shiba Kuanar,K.R. Rao,Christopher Conly, “Fast Mode Decision In Hevc Intra Prediction, Using Region Wise CNN Feature Classification”, 2018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW).
    [20] Jun Shi,Changsheng Gao,Zhibo Chen, “Asymmetric-Kernel CNN Based Fast CTU Partition for HEVC Intra Coding”, 2019 IEEE International Symposium on Circuits and Systems (ISCAS).
    [21] Yongfei Zhang,Gang Wang,Rui Tian,Mai Xu,C. C. Jay Kuo, “Texture-Classification Accelerated CNN Scheme for Fast Intra CU Partition in HEVC”, 2019 Data Compression Conference (DCC).
    [22] Wenpeng Ren,Jia Su,Chang Sun,Zhiping Shi, “An IBP-CNN Based Fast Block Partition For Intra Prediction”, 2019 Picture Coding Symposium (PCS).
    [23] Tianyi Li,Mai Xu,Xin Deng, “ A deep convolutional neural network approach for complexity reduction on intra-mode HEVC”, 2017 IEEE International Conference on Multimedia and Expo (ICME).
    [24] Jun Shi,Changsheng Gao,Zhibo Chen, “Asymmetric-Kernel CNN Based Fast CTU Partition for HEVC Intra Coding”, 2019 IEEE International Symposium on Circuits and Systems (ISCAS).
    [25] A. Mercat, M. Viitanen, and J. Vanne, “UVG dataset: 50/120fps 4K sequences for video codec analysis and development,” in Proc. ACM Multimedia Syst. Conf., Istanbul, Turkey, June 2020.
    [26] Gitl HEVC/H. 265 Analyzer, [online] Available: https://github.com/lheric/GitlHEVCAnalyzer.

    QR CODE
    :::