跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 王晧群
Hao- Chiun Wang
論文名稱： 深度學習應用於HEVC畫面內編碼單元切割
CNN-based CU Partition for HEVC Intra Prediction
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： 2020
畢業學年度： 108
語文別： 中文
論文頁數： 136
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 、畫面內預測 、快速模式預測 、改善編碼性能 、分散式視訊編碼 、深度學習
外文關鍵詞： High Efficiency Video Coding (HEVC), Support Vector Machine(SVM), Convolutional Neural Network(CNN), Coding Unit(CU), Fast Depth Decision, Intra Prediction, Fast Mode Prediction, Improved Coding Performance, Distributed Video Coding, Deep Learning
相關次數： 點閱：27  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

    • 在這日新月異的時代，隨著網路的進步以及科技的發達，人們對於追求更高品質的事物始終不會停滯，對於高解析度的影像也是如此，為了能夠更有效率的壓縮這些巨大的視訊資料量，HEVC採用了一些更新穎的技術，如編碼樹單元、碼率失真最佳化等等，但於此同時也造成了編碼計算複雜度的提升，本論文結合近幾年來十分熱門的深度學習與機器學習，即卷積神經網路與支持向量機，將其應用於HEVC編碼單元深度決策。不同於原始HEVC遞迴運算編碼單元深度0至3，本論文在編碼一開始時先使用支持向量機將編碼單元分成簡單區塊與複雜區塊，再利用卷積神經網路分層向下細分，分類完成的區塊將只會進行一次深度的編碼，藉此大幅節省編碼所需時間。而後進一步將支持向量機的決策值，透過額外資訊減少進入卷積神經網路的次數便提前完成分區，實驗結果與HEVC相比，整體平均BDBR上升1.5%的情況下，編碼時間大約可以節省64%，後續再導入分散式視訊編碼的概念，結合快速預測模式與解碼端之後處理補償影像品質。

    In this ever-changing era, with the advancement of the Internet and the development of technology, people will never stop pursuing higher-quality things, as well as high-resolution images. In order to be able to compress these huge videos more efficiently The amount of data, HEVC uses some newer technologies, such as coding tree units, rate distortion optimization, etc., but at the same time it also causes the increase in the complexity of coding calculations. This paper combines deep learning and machine learning, which have been very popular in recent years, that is, convolutional neural networks and support vector machines, are applied to HEVC coding unit depth decision. Unlike the original HEVC recursive operation coding unit depth 0 to 3, at the beginning of this paper, the support vector machine is used to divide the coding unit into simple blocks and complex blocks, and then the convolutional neural network is used to layer down , The classified blocks will only be coded once in depth, thereby greatly saving coding time. Then, the decision value of the support vector machine is further used to reduce the number of entering the convolutional neural network through additional information to complete the partition in advance,compared with HEVC, the overall average BDBR is increased by 1.5%, and the encoding time can be saved by about 64%.Finally, introduce the concept of decentralized video coding, combined with fast mode prediction and post-processing to compensate the image quality.

    第一章、緒論.............................................1 1.1研究動機與目的........................................1 1.2論文架構..............................................1 1.3高效率視訊編碼(High Efficiency Video Coding)簡介.......2 1.4 HEVC編碼架構介紹.....................................3 1.4.1碼率失真代價函數.....................................4 1.4.2編碼單元(Coding Unit)...............................6 1.4.3預測單元(Prediction Unit)...........................8 1.4.4轉換單元(Transform Unit)............................9 1.4.5畫面內編碼預測(Intra Predict)介紹....................9 1.4.6量化參數(Quantization Parameter)...................14 1.5支持向量機(Support Vector Machine)介紹...............15 1.6深度學習介紹.........................................18 1.6.1類神經網路.........................................19 1.6.2深度學習...........................................19 第二章、相關文獻回顧.....................................23 2.1減少CU編碼複雜度相關文獻回顧...........................23 2.2利用支持向量機減少編碼單元複雜度相關文獻回顧.............23 2.2.1 Computational Complexity Reduction for HEVC Intra Prediction with SVM....................................24 2.3利用CNN減少CU編碼複雜度相關文獻回顧....................31 2.3.1 A deep convolutional neural network approach for complexity reduction on intra-mode HEVC................31 2.3.2 Asymmetric-Kernel CNN Based Fast CTU Partition for HEVC Intra Coding......................................37 2.3.3 Texture-Classification Accelerated CNN Scheme for Fast Intra CU Partition in HEVC........................43 2.3.4 Computation Reduction of HEVC Intra Prediction using combined SVM and CNN.............................45 第三章、結合SVM與分層式CNN應用於編碼單元(CU)提前終止劃分演算法 .......................................................48 3.1編碼單元提前終止劃分之決策演算法.......................48 3.1.1模型架構與演算法優缺點探討...........................48 3.1.2編碼單元提前終止劃分演算法流程.......................50 3.2卷積神經網路架構訓練..................................53 3.2.1前處理階段.........................................54 3.2.2訓練階段...........................................56 3.2.3測試階段...........................................63 第四章、編碼單元提前終止劃分演算法性能比較與加入決策閾值.....67 4.1 各類編碼單元提前終止劃分演算法性能比較.................67 4.1.1效能分析...........................................67 4.1.2不同模型與演算法性能比較.............................72 4.1.3與HEVC相比編碼單元深度準確率與可視化比較..............79 4.2結合特徵之決策閾值....................................81 4.2.1支持向量機的超平面(hyper plane)與深度之關係..........81 4.2.2加入閾值之編碼單元提前終止劃分演算法流程..............84 4.2.3加入閾值之效能分析..................................86 第五章、以分散式視訊編碼(Distributed Video Coding, DVC)的概念應用於HEVC編解碼器.....................................92 5.1合併畫面內編碼單元提前終止劃分深度及模式預測之快速決策演算法 .......................................................93 5.1.1畫面內預測快速模式決策相關文獻回顧....................93 5.1.2合併畫面內編碼單元提前終止劃分深度及模式預測之快速決策演算法.....................................................96 5.2 於解碼端補償HEVC編碼效能損失.........................101 5.2.1以後處理方式於HEVC解碼端提升影像品質相關文獻回顧......102 5.2.2合併編解碼端之性能分析.............................104 第六章、結論與未來展望..................................111 參考文獻...............................................113

    [1] Y. Lecun, et al., “Gradient-based learning applied to document recognition”, Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
    [2] I. Mrazova, M. Kukacka, “Hybrid convolutional neural networks”, Industrial Informatics INDIN 2008. 6th IEEE International Conference, 2008.
    [3] S. Lawrence, et al., “Face recognition: A convolutional neural-network approach”, IEEE Transactions on Neural Networks, vol.8, no. 1, pp. 98-113, 1997.
    [4] Tao Zhang,Ming-Ting Sun,Debin Zhao,Wen Gao, “Fast Intra-Mode and CU Size Decision for HEVC”, IEEE Transactions on Circuits and Systems for Video Technology ( Volume: 27 , Issue: 8 , Aug. 2017 ).
    [5] Jae Myung Ha,Jong Hyun Bae,Myung Hoon Sunwoo, “Texture-based fast CU size decision algorithm for HEVC intra coding”, 2016 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS).
    [6] Mengmeng Zhang,Yu Liu,Zhi Liu, “A new fast algorithm based on SATD for HEVC intra prediction”, 2016 Visual Communications and Image Processing (VCIP).
    [7] Jiawen Gu,Minhao Tang,Jiangtao Wen,“SATD Based Fast Intra Prediction for HEVC”, 2017 Data Compression Conference (DCC).
    [8] Jiawen Gu,Minhao Tang,Jiangtao Wen,Hao Zhang, “A novel satd based fast intra prediction for HEVC”, 2017 IEEE International Conference on Image Processing (ICIP).
    [9] Dang Le Dinh Trang,Kyung Rae Kim,Ik Joon Chang,Jinsang Kim, “Texture characteristic based fast algorithm for CU size decision in HEVC intra coding”,2017 7th International Conference on Integrated Circuits, Design, and Verification (ICDV).

    [10] Yuting Wang,Jian Cao,Jun Wang,Fan Liang, “Gradient-Based Fast Intra Coding Decision Algorithm for HEVC”, 2019 IEEE 4th International Conference on Signal and Image Processing (ICSIP).
    [11] Jie Jay Wang,Kuo Chun Wu,Yin yi Lin, “RMD-Based Mode Decision for Ordered-Dithering HEVC Intra Prediction”, 2019 IEEE 2nd International Conference on Knowledge Innovation and Invention (ICKII).
    [12] Jinzheng Lu,Yixian Li, “Fast Algorithm for CU Partitioning and Mode Selection in HEVC Intra Prediction”, 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).
    [13]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.
    [14]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.
    [15]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.

    [16] 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).
    [17] 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).
    [18] 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 ).
    [19] 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 ).
    [20] 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).
    [21] 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).

    [22] 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).
    [23] Wenpeng Ren,Jia Su,Chang Sun,Zhiping Shi, “An IBP-CNN Based Fast Block Partition For Intra Prediction”, 2019 Picture Coding Symposium (PCS).
    [24] D. T. Dang-Nguyen, C. Pasquini, V. Conotter, G. Boato, RAISE – A Raw Images Dataset for Digital Image Forensics, ACM Multimedia Systems, Portland, Oregon, March 18-20, 2015.
    [25] G. Schaefer and M. Stich "UCID: an uncompressed color image database", Proc. SPIE 5307, Storage and Retrieval Methods and Applications for Multimedia 2004, (18 December 2003).
    [26] E. Agustsson, R. Timofte, “NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study”, pp.1122-1131, Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA, 24 August 2017.
    [27] Jie-Jay Wang, Yin yi Lin ,“Computation Reduction of HEVC Intra Prediction using combined SVM and CNN”, National Central University, Master Thesis, Jan 2020.
    [28] Han-Yuan Hsu, Yin yi Lin, “Low Computational Complexity, High Coding Efficiency Intra Prediction for HEVC,” Master Thesis, National Central University, Jun. 2016.

    [29] Sheng-Min Fan, Yin yi Lin, “Study of A Deep Learning Architecture For HEVC Decoder”, National Central University, Master Thesis, Jan 2020.
    [30] J. Kim, J.K. Lee, K.M. Lee, “Accurate Image Super-Resolution Using Very Deep Convolutional Networks”, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 1646-1654.
    [31] R. Puri and K. Ramchandran, “PRISM: A new robust video coding architecture based on distributed compression principles,” in Proceedings of the Allerton Conference on Communication, Control an d Computing, Allerton, IL, Oct. 2002.
    [32] A. Aaron, R. Zhang, and B. Girod, “Wyner-Ziv Coding for Motion Video,” Asilomar Conference on Signals, Systems and Computers, Pacific Grove, USA, Nov. 2002.
    [33] D. Slepian and J.K. Wolf, “Noiseless coding of correlated information sources,” IEEE Transactions on Information Theory, Vol. IT-19, July 1973, pp. 471–480.
    [34] Wyner and J. Ziv, “The Rate-Distortion Function for Source Coding with Side Information at the Decoder”. IEEE Transactions on Information Theory, Vol. IT-22, Jan. 1976, pp. 1–10.

    QR CODE
    :::