(3.238.173.209) 您好!臺灣時間:2021/05/16 21:37
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:黃琮閔
研究生(外文):Cong-Ming Huang
論文名稱:以深度學習改善HEVC插值器品質
論文名稱(外文):CNN-based HEVC interpolation filters
指導教授:林銀議
指導教授(外文):Yin-Yi Lin
學位類別:碩士
校院名稱:國立中央大學
系所名稱:通訊工程學系
學門:工程學門
學類:電資工程學類
論文出版年:2020
畢業學年度:108
語文別:中文
論文頁數:111
中文關鍵詞:高效率視訊編碼支持向量機深度學習畫面間預測運動估計
外文關鍵詞:HEVCSupport Vector MachineDeep LearningInter PredictionMotion Estimation
相關次數:
  • 被引用被引用:0
  • 點閱點閱:35
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
隨著人們要求視覺上的享受,網路和多媒體技術不斷進步,2013國際標準組織制訂了新的視訊壓縮標準,HEVC/H.265(High Efficient Video Coding),HEVC視訊壓縮率可以提高到H.264兩倍以上,且畫質更優於H.264,相對的HEVC計算複雜度也提高了很多,原本H.264的插值濾波器,在亮度部分二分之一使用6-tap的濾波器、四分之一使用雙線性插值濾波器,而HEVC的插值濾波器,在亮度部分二分之一使用8-tap的濾波器、四分之一使用7-tap的濾波器,在插值濾波器的運算時間HEVC就比H.264多了兩倍的時間,而HEVC採用固定插值濾波器是根據信號處理理論設計的,前提假設視頻信號是理想的低通信號。但是視頻信號不一定是低通的並且不是固定的,近年來,基於深度學習的方法已被廣泛使用,並在圖像和視頻處理中獲得了顯著的效果,而本篇論文一開始先使用支持向量機,先將訓練資料分為四個次群,分別為四個次群訓練模型,並且根據消息理論,越多的側面消息,是能有效幫助到訓練的,本篇論文使用了SVM Features Mask與殘差做為我們的側面消息,並形成我們的雙輸入模型與三輸入模型,以三輸入模型來說,與HEVC相比BDBR可以下降1.33%,編碼時間節省了13.39%,但是編碼能節省時間是因為Liu[18]的支持向量機編碼單元快速決策演算法,實際上卷積神經網路是增加編碼時間的,所以我們提出了一個想法,使用最簡單的的雙線性插值濾波器,並且最後使用我們提出的架構做一個改善,以三通架構來說,BDBR可以下降約1.09%,編碼時間能節省20.64%。
As people demand visual enjoyment, network and multimedia technologies continue to progress, 2013 International Standards Organization has formulated a new video compression standard, HEVC/H.265 (High Efficient Video Coding), HEVC video compression rate can be increased to H. 264 is more than twice, and the image quality is better than H.264. The relative HEVC calculation complexity is also greatly improved. The original H.264 interpolation filter uses a 6-tap filter in the half of the brightness part. Quarter uses a bilinear interpolation filter, while the HEVC interpolation filter uses an 8-tap filter for half of the luminance part, a 7-tap filter for quarter, and an interpolation filter The operation time of HEVC is twice as long as that of H.264, and HEVC uses a fixed interpolation filter designed according to the signal processing theory, assuming that the video signal is an ideal low-pass signal. However, the video signal is not necessarily low-pass and not fixed. In recent years, deep learning-based methods have been widely used, and have achieved significant results in image and video processing, and this paper used support vector machine first divides the training data into four subgroups, and trains the model for four subgroups respectively. According to the message theory, the more side messages can effectively help the training, this paper uses SVM Features Mask and residuals as our side messages, and form our two-input model and three-input model. For the three-input model, BDBR can be reduced by 1.33% compared with HEVC, and the encoding time is saved by 13.39%, but the encoding can be saved The time is because Liu[18] support vector machine coding unit fast decision algorithm, in fact, the convolutional neural network increases the coding time, so we proposed an idea to use the simplest bilinear interpolation filter, and Finally, we use the proposed architecture to make an improvement. In terms of the three-pass architecture, BDBR can be reduced by about 1.09%, and encoding time can be saved by 20.64%.
第一章、緒論 1
1.1高效率視訊編碼(High Efficiency Video Coding) 1
1.2HEVC編碼架構介紹 2
1.1.1編碼單元(Coding Unit) 3
1.1.2預測單元(Prediction Unit) 4
1.1.3轉換單元(Transform Unit) 5
1.1.4碼率失真代價函數 6
1.1.5量化(Quantization) 7
1.1.6 HEVC編碼架構 8
1.3研究動機與目的 9
1.4論文架構 10
第二章、相關背景知識與文獻探討 11
2.1畫面間預測(Inter Prediction) 11
2.1.1運動估計(Motion Estimation) 11
2.1.2運動補償(Motion Compensation) 12
2.1.3畫面間模式決策介紹(Inter Mode Decision) 13
2.2 支持向量機介紹(Support Vector Machine) 20
2.3 深度學習介紹(Deep Learining) 22
2.4 SVM應用於HEVC畫面間編碼單元快速決策演算法 25
2.4.1 支持向量機編碼單元特徵選取 27
2.4.2 系統流程圖 34
2.4.3實驗數據 34
2.5相關文獻 35
2.5.1 Learning a convolutional neural network for fractional interpolation in HEVC inter coding 36
2.5.2 Enhancing Hevc Compressed Videos With A Partition-Masked Convolutional Neural Network 38
2.5.3 An In-loop Filter Based on Low-Complexity CNN Using Residuals in Intra Video Coding 40
第三章、混合卷積神經網路與支持向量機次像素點插值預測 42
3.1 HEVC插值濾波器介紹 42
3.2 演算法架構 44
3.2.1 編碼端SVM演算法應用於解碼端之準確率 48
3.3 卷積神經網路訓練與測試 49
3.3.1 訓練環境 49
3.3.2 前處理階段 50
3.3.3網路架構與訓練階段 55
3.3.4測試階段 62
3.4架構性能探討與分析 63
3.4.1 SVM與CNN架構改善半像素性能探討 64
3.4.2 架構性能探討 65
3.4.3碼率失真曲線與時間曲線 70
第四章、應用雙線性濾波器及深度學習於HEVC插值器設計 74
4.1 使用雙線性插值來簡化HEVC插值濾波器 75
4.2 演算法架構 76
4.2.1 前處理階段 78
4.2.2 測試階段 79
4.3 性能探討與分析 81
4.3.1 性能探討 81
4.3.2 碼率失真曲線與時間曲線 85
第五章、結論與未來展望 89
參考文獻 90
[1] Han Zhang, Li Song, Zhengyi Luo, and Xiaokang Yang,“Learning a convolutional neural
network for fractional interpolation in hevc inter coding,’’ in Proc. IEEE Vis. Commun. Image Process. (VCIP), Dec. 2017, pp. 1–4.
[2] Ning Yan, Dong Liu, Houqiang Li, and Feng Wu, “A convolutional neural network
approach for half-pel interpolation in video coding,’’ in Proc. IEEE Int.Symp. Circuits Syst. (ISCAS), May 2017, pp. 1–4.
[3] T. Wedi, “Adaptive interpolation filters and high-resolution displacements for video coding,” IEEE Trans. Circuits Syst. Video Technol.,vol. 16, no. 4, pp. 484–491, Apr. 2006.
[4] T. Wedi and H. G. Musmann, “Motion- and aliasing-compensated prediction for hybrid video coding,” IEEE Trans. Circuits Syst. Video Technol., vol. 13, no. 7, pp. 577–586, Jul. 2003.
[5] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in Proc. Adv. Neural Inf. Process. Syst., 2012, pp. 1097–1105.
[6] Zhenghui Zhao, Shiqi Wang, Shanshe Wang, Xinfeng Zhang, Siwei Ma, and Jiansheng Yang, “Cnn-based bi-directional motion compensation for high efficiency
video coding,” in Circuits and Systems (ISCAS), 2018IEEE International Symposium on. IEEE, 2018, pp. 1–4.
[7] C. Dong, C. C. Loy, K. He, and X. Tang, “Learning a deep convolutional network for image super-resolution,” in Proc. Eur. Conf. Comput. Vis., 2014, pp. 184–199.
[8] J. Kim, J. K. Lee, and K. M. Lee, “Accurate image super-resolution using very deep convolutional networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2016, pp. 1646–1654.
[9] Y. Dai, D. Liu, and F. Wu, “A convolutional neural network approach for post-processing in High Efficiency Video Coding intra coding,” in Proc. Int. Conf. Multimedia Modeling, 2017, pp. 28–39.
[10] F. May, “Model based movement compensation and interpolation for ISDN videotelephony,” in Proc. Int. Symp. Circuits Syst., 1998,pp. 463–466.
[11] M. Gilge, “A high quality videophone coder using hierarchical motion estimation and structure coding of the prediction error,” Proc. SPIE,vol. 1001, pp. 864–874, Oct. 1988.
[12] B. Girod, “Motion-compensating prediction with fractional-pel accuracy,” IEEE Trans. Commun., vol. 41, no. 4, pp. 604–612, Apr. 1993.
[13] Gary J Sullivan, Jens-Rainer Ohm, Woo-Jin Han,Thomas Wiegand, et al.,“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, 2012.
[14] Thomas Wiegand, Gary J Sullivan, Gisle Bjontegaard,and Ajay Luthra, “Overview of the h. 264/avc video coding standard,” IEEE Transactions on circuits and systems for video technology, vol. 13, no. 7, pp. 560–576, 2003.
[15] X. He, Q. Hu, X. Han, X. Zhang, C. Zhang, W. Lin, "Enhancing Hevc Compressed Videos With A Partition-Masked Convolutional Neural Network", International Conference on Image Processing(ICIP) 2018, pp.216-220
[16] Daowen Li, “An In-Loop Filter Based on Low-Complexity CNN using Residuals in Intra Video Coding”: 2019 IEEE International Symposium on Circuits and Systems (ISCAS).
[17] Jiwon Kim, “Accurate Image Super-Resolution Using Very Deep Convolutional Networks”: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[18] J.K. Liu, “Efficient HEVC inter prediction using SVM,” Department of Communication Engineering National Central University, Taiwan 32054, R.O.C.,
Jan 2019.
[19] S.J Cai, “ Reduction of computation complexity for HEVC intra prediction with support vector machine,” National Central University, Master Thesis, Jun 2017.
[20] H. Lv, R. Wang, X. Xie, H. Jia, and W. Gao, “A comparison of fractional-pel interpolation filters in High Efficiency Video Coding and H.264/AVC,” in Proc. IEEE Conf. Vis. Commun. Image Process.,Nov. 2012, pp. 1–6.
[ 21] Kemal Ugur, “Motion Compensated Prediction and Interpolation Filter Design in H.265/HEVC”:2013 IEEE Journal of Selected Topics in Signal Processing.
[22] S. Wittmann and T. Wedi, “Separable adaptive interpolation filter for video coding,” in Proc. Int. Conf. Image Process., 2008, pp. 2500–2503.
[23] H. Lakshman, H. Schwarz, and T. Wiegand, “Generalized interpolation-based fractional sample motion compensation,” IEEE Trans. Circuits Syst. Video Technol., vol. 23, no. 3, pp. 455–466, Mar. 2013.
[24] J. Yang, J. Wright, T. S. Huang, and Y. Ma, “Image super-resolution via sparse representation,” IEEE Trans. Image Process., vol. 19, no. 11,pp. 2861–2873, Nov. 2010.
[25] V. Nair and G. E. Hinton, “Rectified linear units improve restricted Boltzmann machines,” in Proc. Int. Conf. Mach. Learn., 2010,pp. 807–814.
[26] J.-L. Lin, Y.-W. Chen, Y.-W. Huang, and S.-M. Lei, “Motion vector coding in the HEVC standard,” IEEE J. Sel. Topics Signal Process.,vol. 7, no. 6, pp. 957–968, Dec. 2013.
[27] Y.Dai, D. Liu, F.Wu, "A Convolutional Neural Network Approach for Post- Processing in HEVC Intra Coding", MultiMedia Modeling(MMM) 2017, pp.28-39
電子全文 電子全文(網際網路公開日期:20230728)
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top