跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 潘東名
Tung-Ming Pan
論文名稱： 在受限的無線網路頻寬下以物件為主的監視影像自適應編碼方法
Object-based Approach for Adaptive Source Coding of Surveillance Video under Restricted Wireless Bandwidth
指導教授： 范國清
Kuo-Chin Fan
王元凱
Yuan-Kai Wang
口試委員:
學位類別： 博士
Doctor
系所名稱： 資訊電機學院 - 資訊工程學系
Department of Computer Science & Information Engineering
論文出版年： 2021
畢業學年度： 109
語文別： 英文
論文頁數： 100
中文關鍵詞： 動態物件偵測 、自適應編碼 、影像品質 、回歸算法 、線性模型 、非線性模型
外文關鍵詞： moving object detection, adaptive source coding, video quality, regression algorithm, linear model, nonlinear model
相關次數： 點閱：19  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

    • 在網路上的監控影像智慧分析需要較高識別度品質的影片，但是會顯著的增加網路頻寬要求。由於高動態物體影像在無線網路傳輸下造成影像品質下降問題，成為了智慧影像監控分析是否成功的關鍵。在本篇論文中，提出了一種基於物件特性的編碼方法，用以保持無線網路上影像資料流的穩定品質。影像品質與物件動態之間的反比關係（即，由於出現大而快速移動的物件而導致影像品質下降）在統計上可被表示為線性或非線性模型。本文針對線性模型提出了一種使用健全的M-estimator統計量的回歸演算法來建構針對不同bitrate的線性模型，應用線性模型來預測增強影像品質所需的bitrate增量。在非線性模型中採用二次多項式回歸演算法來建構針對不同bitrate的模型，利用迭代方法預測最適合的編碼bitrate。實驗中建立了一個模擬的無線網路環境，以驗證在不同無線網路情況下提出的方法，進行了具有各種物件動態的真實監控影像的實驗，以評估該方法的性能。實驗結果表明，相對於視覺和定量方面而言，以較低的無線網路頻寛即可達到所需的串流影像品質。

    An intelligent analysis of surveillance videos over networks requires high recognition accuracy by analyzing good-quality videos, which requires a significant amount of bandwidth. Degraded video quality due to high object dynamics during wireless video transmission causes more critical issues for smart video surveillance success. In this thesis, an object-based source coding method is proposed to maintain steady video streaming quality over wireless networks. The inverse relationship between video quality and object dynamics (i.e., decreasing video quality due to the presence of large and fast-moving objects) is statistically defined as a linear or nonlinear model. A regression algorithm based on robust M-estimator statistics is proposed to construct the linear model considering different bitrates. The linear model is used to predict bitrate increments required to improve video quality. A quadratic polynomial regression algorithm and an iterative method for predicting the most suitable encoding bitrates are used to develop the nonlinear model considering different bitrates. A simulated wireless environment is set up to verify the proposed method in various wireless scenarios. Experiments with real surveillance videos of a variety of object dynamics are conducted to evaluate the method’s performance. Experimental results show that the proposed method significantly improves video streaming in both visual and quantitative aspects when using lower wireless bandwidth.

    摘要 i Abstract ii Table of Contents iii List of Figures v List of Tables vii 1 Introduction 1 1.1 Background and motivation 1 1.2 Approach of the research 2 1.3 Organization of dissertation 7 2 Overview Of Adaptive Video Quality Scheme 8 2.1 Introduction 8 2.2 Network transmission method 8 2.3 Device-dependent method 9 2.4 Source coding method 10 2.4.1 Rate control scheme 10 2.4.2 Region of interest approach 14 2.4.3 Frame layer control approach 15 3 Proposed Adaptive Coding Method Using Object Dynamics 17 3.1 Introduction 17 3.2 Modeling the statistical relationship 17 3.2.1 Linear regression 17 3.2.2 Robust prediction approach 18 3.2.3 Nonlinear regression 22 3.2.4 Evaluate regression fit 26 3.3 Minimum distance from a point on a surface to a plane 29 3.4 Normalization and translation 32 3.5 Adaptive bitrate by prediction 35 4 Experimental Results 38 4.1 Experiment environment and parameters 38 4.2 Dataset 41 4.2.1 Training data 41 4.2.2 Testing data 42 4.3 Analysis of experimental results 43 4.3.1 Comparison of linear regression and quadratic polynomial regression models 44 4.3.2 Experimental case analysis 61 4.3.3 Adaptive bitrate prediction experimental analysis 66 5 Concluding Remarks 72 5.1 Summary 72 5.2 Conclusions 72 5.3 Future research 73 References 75 Appendix A 80 Appendix B 84

    [1] Wang, Y.K.; Chen, H.Y. Intelligent Mobile Video Surveillance System with Multilevel Distillation. J. Electron. Sci. Technol. 2017, 15, pp. 133–140.
    [2] Fan, C.T.; Wang, Y.K.; Huang, C.R. Heterogeneous information fusion and visualization for a large-scale intelligent video surveillance system. IEEE Trans. Syst. Man Cybern. Syst. 2017, 47, pp. 593–604.
    [3] Pan, Z.; Jin, P.; Lei, J.; Zhang, Y.; Sun, X.; Kwong, S. Fast reference frame selection based on content similarity for low complexity HEVC encoder. J. Vis. Commun. Image Represent. 2016, 40, pp. 516–524.
    [4] Dey, B.; Kundu, M.K. Enhanced Macroblock Features for Dynamic Background Modeling in H. 264/AVC Video Encoded at Low Bitrate. IEEE Trans. Circuits Syst. Video Technol. 2018, 28, pp. 616–625.
    [5] Lee, C.; Jung, Y.; Lee, S.; Oh, Y.; Kim, J. Real-Time Frame-Layer H.264 Rate Control for Scene-Transition Video at Low Bit Rate. IEEE Trans. Consum. Electron. 2007, 53, pp. 1084–1092.
    [6] Chen, X.; Lu, F. A reformative frame layer rate control algorithm for H.264. IEEE Trans. Consum. Electron. 2010, 56, pp. 2806–2811.
    [7] Network Simulator-2. Available online: http://www.isi.edu/nsnam/ns/ (accessed on 11 January 2019).
    [8] Chen, J.Y.; Chiu, C.W.; Li, G.L.; Chen, M.J. Burst-aware dynamic rate control for H. 264/AVC video streaming. IEEE Trans. Broadcast. 2011, 57, pp. 89–93.
    [9] Choi, H.; Yoo, J.; Nam, J.; Sim, D.; Bajic, I.V. Pixel-wise unified rate-quantization model for multi-level rate control. IEEE J. Sel. Top. Signal Process. 2013, 7, pp. 1112–1123.
    [10] Khan, M.U.K.; Shafique, M.; Henkel, J. An adaptive complexity reduction scheme with fast prediction unit decision for HEVC intra encoding. 2013 IEEE International Conference on Image Processing, Melbourne, Australia, 15–18 September 2013; pp. 1578–1582.
    [11] Lam, K.Y.; Chiu, C.K. The design of a wireless real-time visual surveillance system. Multimedia Tools and Applications. 2007, 33(2), pp. 175–199.
    [12] Fiandrotti, A.; Gallucci, D.; Masala, E.; De Martin, J.C. Content-adaptive traffic prioritization of spatio-temporal scalable video for robust communications over QoS-provisioned 802.11e networks. Signal Process Image Commun. 2010, 25, pp. 438–449.
    [13] IEEE Draft Standard 802.11e/D13.0, “Telecommunications and Information Exchange Between Systems--LAN/MAN Specific Requirements-- Part 11 Wireless Medium Access Control (MAC) and Physical Layer (PHY) specifications: Medium Access Control (MAC) Quality of Service (QoS) Enhancements”. January 2005.
    [14] Stefan Mangold, Sunghyun Choi, Peter May, Ole Klein, Guido Hiertz, Lothar Stibor, “IEEE 802.11e Wireless LAN for Quality of Service”, European Wireless '2002, Florence, Italy, February 2002.
    [15] Yan Li, Athina Markopoulou, John Apostolopoulos, Nicholas Bambos, “Content-Aware Playout and Packet Scheduling for Video Streaming Over Wireless Links” , Multimedia, IEEE Transactions on Volume 10, Issue 5, Aug. 2008, pp.885 – 895.
    [16] Gabriel-Miro Muntean, Nikki Cranley, “Resource Efficient Quality-Oriented Wireless Broadcasting of Adaptive Multimedia Content”, IEEE TRANSACTIONS ON BROADCASTING, VOL. 53, NO. 1, MARCH 2007, pp. 362 – 368.
    [17] Hulya Seferoglu, Athina Markopoulou, “Video-Aware Opportunistic Network Coding over Wireless Networks”, IEEE Journal on Volume 27, Issue 5, June 2009, pp. 713 – 728.
    [18] Advanced Video Coding for Generic Audiovisual Services, ITU-T Rec. H.264 & ISO/IEC 14496-10 AVC, v3: 2005, Amendment 3: Scalable Video Coding.
    [19] H. Schwarz, D. Marpe, and T. Wiegand, “Overview of the scalable video coding extension of H.264/AVC,” IEEE Trans. Circuits Syst. Video Technol., vol. 17, no. 9, pp. 1103–1120, Sep. 2007
    [20] Thomas Schierl, Thomas Stockhammer, Thomas Wiegand, “Mobile Video Transmission Using Scalable Video Coding”, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. 17, NO. 9, SEPTEMBER 2007.
    [21] Gualdi G., Prati A., Cucchiara R., “Video Streaming for Mobile Video Surveillance”, Multimedia, IEEE Transactions on Volume 10, Issue 6, Oct. 2008, pp. 1142 – 1154.
    [22] Han, B.; Zhou, B. VBR rate control for perceptually consistent video quality. IEEE Trans Consum. Electron. 2008, 54, pp. 1912–1919.
    [23] Sun, Y.; Zhou, Y.; Feng, Z; He, Z.; Sun, S. Incremental rate control for H.264/AVC video compression. IET Image Process. 2009, 3, pp. 286–298.
    [24] Wang, S.; Rehman, A.; Zeng, K.; Wang, J.; Wang, Z. SSIM-motivated two-pass VBR coding for HEVC. IEEE Trans. Circuits Syst. Video Technol. 2017, 27, pp. 2189–2203.
    [25] Bajic, I.V.; Ma, X. A testbed and methodology for comparing live video frame rate control methods. IEEE Signal Process. Lett. 2011, 18, pp. 31–34.
    [26] Ma, S.; Gao, W.; Lu, Y. Rate-distortion analysis for H.264/AVC video coding and its application to rate control. IEEE Trans. Circuits Syst. Video Technol. 2005, 15, pp. 1533–1544.
    [27] Lee, B.; Choi, J.Y. A rate perceptual-distortion optimized video coding HEVC. IEICE Trans. Inf. Syst. 2018, 101, pp. 3158–3169.
    [28] Zhong, H.; Shen, S.; Fan, Y.; Zeng, X. A Low Complexity Macroblock Layer Rate Control Scheme Base on Weighted-Window for H.264 Encoder. International Conference on Multimedia Modeling, Klagenfurt, Austria, 4-6 January 2012; pp. 563–573.
    [29] Dong, J.; Ling, N. A Context-Adaptive Prediction Scheme for Parameter Estimation in H.264/AVC Macroblock Layer Rate Control. IEEE Trans. Circuits Syst. Video Technol. 2009, 19, pp. 1108–1117.
    [30] Li, B.; Li, H.; Li, L.; Zhang, J. λ Domain Rate Control Algorithm for High Efficiency Video Coding. IEEE Trans. Image Process. 2014, 23, pp. 3841–3854.
    [31] Atta, R.; Ghanbari, M. Low-Complexity Joint Temporal-Quality Scalability Rate Control for H. 264/SVC. IEEE Trans. Circuits Syst. Video Technol. 2018, 28, pp. 2331–2344.
    [32] Geng, M.; Zhang, X.; Tian, Y.; Liang, L.; Huang, T. A fast and performance-maintained transcoding method based on background modeling for surveillance video. IEEE International Conference on Multimedia and Expo, Melbourne, Australia, 9–13 July 2012; pp. 61–66.
    [33] Meuel, H.; Reso, M.; Jachalsky, J.; Ostermann, J. Superpixel-based segmentation of moving objects for low bitrate ROI coding systems. 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, Krakow, Poland, 27–30 August 2013; pp. 395–400.
    [34] Kim, N.V.; Chervonenkis, M.A. Situation control of unmanned aerial vehicles for road traffic monitoring. Mod. Appl. Sci. 2015, 9, pp. 1–13.
    [35] Meddeb, M.; Cagnazzo, M.; Pesquet-Popescu, B. Region-of-interest-based rate control scheme for high-efficiency video coding. APSIPA Trans. Signal Inf. Process. 2014, 3, e16. doi:10.1017/ATSIP.2014.15.
    [36] Chen, X.; Wu, Z.; Zhang, X.; Xiang, Y.; Xie, S. One Novel Rate Control Scheme for Region of Interest Coding. International Conference on Intelligent Computing Methodologies, Lanzhou, China, 2–5 August 2016; pp. 139–148.
    [37] Wu, C.Y.; Su, P.C. A Region of Interest Rate-Control Scheme for Encoding Traffic Surveillance Videos. 2009 Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Kyoto, Japan, 12–14 September 2009; pp. 194–197.
    [38] A. Zainaldin, I. Lambadaris, B. Nandy, Adaptive Rate Control Low bit-rate Video Transmission over Wireless Zigbee Networks, IEEE International Conference on Communications, May. 2008, pp. 52 – 58
    [39] V. Baroncini , R. Felice , G. Iacovoni, “Variable frame rate control jerkiness-driven”, J Real-Time Image Proc (2009) 4: pp. 167–179.
    [40] Muthukrishnan, R.; Radha, M. M-Estimators in Regression Models. J. Math. Res. 2010, 2, pp. 23–27.
    [41] Huber, P.J. Robust Estimation of Location Parameter. Ann. Math. Statistics 1964, 35, pp. 73–101.
    [42] Tukey, J.W. Exploratory Data Analysis; Addison-Wesley Publishers: Boston, MA, USA, 1977.
    [43] Ostertagová, Eva. Modelling using polynomial regression. Procedia Engineering, 2012, 48, pp. 500-506.
    [44] Theil, Henri. A rank-invariant method of linear and polynomial regression analysis. Indagationes Mathematicae 12(85), 1950, p173.
    [45] Chen, X. D., Xu, G., Yong, J. H., Wang, G., Paul, J. C. Computing the minimum distance between a point and a clamped B-spline surface. Graphical Models, 2009, 71(3), pp. 107-112.
    [46] Boyan, D. M., Zheng, K. X., Shijun, S. O. N. G., An algorithm for quickly calculating the minimum distance between a space point and a surface [J]. Modular Machine Tool & Automatic Manufacturing Technique, 2004, 9.
    [47] Xu, R. F., Chen, Z. T., Chen, W. Y. Grid algorithm for calculating the shortest distance from spatial point to free-form surface. Computer Integrated Manufacturing Systems, 2011, 17(1), pp. 95-100.
    [48] Godbehere, A.B.; Matsukawa, A.; Goldberg, K. Visual tracking of human visitors under variable-lighting conditions for a responsive audio art installation. 2012 American Control Conference (ACC), Montreal, QC, Canada, 27–29 June 2012; pp. 4305–4312.
    [49] Ke, C.H.; Shieh, C.K.; Hwang, W.S.; Ziviani, A. An Evaluation Framework for More Realistic Simulations of MPEG Video Transmission. J. Inf. Sci. Eng. 2008, 24, pp. 425–440.
    [50] Klaue, J.; Rathke, B.; Wolisz, A. EvalVid—A Framework for Video Transmission and Quality Evaluation. In Proceedings of the 13th International Conference on Modelling Techniques and Tools for Computer Performance Evaluation, Urbana, IL, USA, 2–5 September 2003; pp. 255–272.
    [51] Kahaki, S.M.M.; Nordin, M.J.; Ashtari, A.H.; Zahra, S.J. Invariant feature matching for image registration application based on new dissimilarity of spatial features. PLoS ONE. 2016, 11, e0149710.
    [52] Kahaki, S.M.; Arshad, H.; Nordin, M.J.; Ismail, W. Geometric feature descriptor and dissimilarity-based registration of remotely sensed imagery. PLoS ONE. 2018, 13, e0200676.
    [53] Bondzulic, B.P.; Pavlovic, B.Z.; Petrovic, V.S.; Andric, M.S. Performance of peak signal-to-noise ratio quality assessment in video streaming with packet losses. Electron. Lett. 2016, 52, pp. 454–456.
    [54] Kwon, S.K.; Tamhankar, A.; Rao, K.R. Overview of H. 264/MPEG-4 part 10. J. Vis. Commun. Image Represent. 2006, 17, pp. 186–216
    [55] OH, Sangmin, et al. A large-scale benchmark dataset for event recognition in surveillance video. In: CVPR 2011. IEEE, 2011, pp. 3153-3160.

    QR CODE
    :::