臺灣博碩士論文加值系統

近年來視頻監控是十分活躍的研究題目，因為隨著需求有許多的應用日漸開發，例如物件識別、物件追蹤和人物動作識別。這些應用需要具有穩健性和安全性的背景建模來作為系統的基礎。本篇論文的目的在於提升背景建模的效率，以及普遍建模方法衍生的應用與發展。
首先，介紹一種新穎的基於階層式粗糙到細緻描述的背景建模方法，第二部分我們提出一個為了偵測遺留物體與遺失物體的架構，此架構結合了基於偵測和基於能量的模型。第三部分我們介紹一種明確且新穎的方法，為利用低成本的Microsoft Kinect感測器來設計出遺留物體偵測系統(AOD)。在本論文中，我們提供了廣泛的定量和定性量測實驗，設計出更完善且更準確的演算法，使監控系統的應用效能得以更為提升。

Video Surveillance has been a very active research topic in recent years. This is because the growing needs in many applications, such as object recognition, object tracking and human activity monitoring. Such applications require robust and secure background modeling as base systems. This dissertation aims at enhancing the efficiency of background modeling as well as developing advance application as a derivation of general background modeling method. First, a novel background modeling method based on a hierarchical coarse-to-fine texture description is introduced. Second, we propose a framework for detecting abandoned and removed object that incorporate detection-based approach and energy-based model. Third, we present a specific-purposed and novel approach for designing abandoned object detection (AOD) system using the low-cost Microsoft Kinect sensor. In this dissertation, we try to devise more robust and accurate methods so a better video surveillance applications can be achieved. In addition, extensive experiments that mainly focus on quantitative and qualitative measurements are provided.

中文摘要 ii
Abstract iii
Contents v
List of Figures viii
List of Tables xi
Chapter 1 Introduction 1
1.1 Introduction to Video Surveillance Systems 1
1.2 Contributions 2
1.3 Organization 3
Chapter 2 Background Review 5
2.1 Mixture of Gaussians model 5
2.2 Heikkilä and Pietikäinen’s method 8
2.3 GrabCut Segmentation 9
2.4 Kinect Camera 12

Chapter 3 Real-Time Background Modeling Based on a Multi-level Texture Description 13
3.1 Overview 13
3.2 Multi-level Texture Description 14
3.2.1 Observation 14
3.2.2 Texture descriptor 15
3.2.3 Texture-based Background Modeling 17
3.2.4 Multi-level Background Modeling 21
3.2.4.1Hierarchical texture description 21
3.2.4.2Background modeling with extension 27
3.3 Experimental Results 30
3.3.1 Data and qualitative Results 30
3.3.2 Quantitative Results 41
3.4 Summary 54
Chapter 4 Robust Techniques for Abandoned and Removed Object Detection Based on Markov Random Field 56
4.1 Overview 56
4.2 GrabCut-based Abandoned Object (AO) 57
4.2.1 Observation 57
4.2.2 Proposed Algorithm 59
4.3 Experimental Results 67
4.4 Summary 84
Chapter 5 RGB-D Abandoned Object Detection based on GrabCut using Kinect 86
5.1 Introduction 86
5.2 3D-AOGrabCut 89
5.3 Experimental Results 96
5.4 Summary 101
Chapter 6 Conclusions and Future Work 102
5.1 Conclusions 102
5.2 Future Work 103
Bibliography 104
Publication List 115
Curriculum Vitae 118

[1]EC Funded CAVIAR project/IST 2001 37540, 2003.
[2]C. Beleznai, P. Gemeiner, and C. Zinner, “Reliable Left Luggage Detection Using Stereo Depth and Intensity Cues,” in Computer Vision Workshops (ICCVW), 2013 IEEE International Conference on. Sydney, Australia, 2013.
[3]W. Bender, D. Gruhl, N. Morimoto, and A. Lu, “Techniques for data hiding,” IBM Systems Journal, vol. 35, no. 3-4, pp. 313 - 336, 1996
[4]T. Bouwmans, “Recent advanced statistical background modeling for foreground detection-a systematic survey,” Recent Patents on Computer Science, vol. 4, no. 3, pp. 147-176, Sep. 2011.
[5]Y. Boykov and G. Funka-Lea, “Graph cuts and efficient ND image segmentation,” International journal of computer vision, vol. 70, no. 2, pp. 109-131, 2006.
[6]Y. Boykov and V. Kolmogorov, “An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 26, no. 9, pp. 1124-1137, 2004.
[7]Y. Y. Boykov and M.-P. Jolly, “Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images,” in Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on, vol. 1. Vancouver, BC, 2001, pp. 105-112.
[8]L. C. Campos, J. C. SanMiguel, and J. M. Martínez, “Discrimination of abandoned and stolen object based on active contours,” in Advanced Video and Signal-Based Surveillance (AVSS), 2011 8th IEEE International Conference on. Klagenfurt, 2011, pp. 101 - 106.
[9]F. Chang, C. J. Chen, and C. J. Lu, “A Linear-Time Component-Labeling Algorithm Using Contour Tracing Technique,” Computer Vision and Image. Understanding, vol. 93, no. 2, pp. 206-220, 2004.
[10]A. Collazos, D. Fernández-López, A. S. Montemayor, J. J. Pantrigo, and M. L. Delgado, Abandoned Object Detection on Controlled Scenes Using Kinect,” in Natural and Artificial Computation in Engineering and Medical Applications: Springer Berlin Heidelberg, 2013, pp. 169-178.
[11]J.-F. Connolly, E. Granger, and R. Sabourin, “An adaptive classification system for video-based face recognition,” Information Sciences, vol. 192, no., pp. 50–70, 2012.
[12]Y. Dedeoglu, B. U. Töreyin, U. Güdükbay, and A. E. Çetin, “Silhouette-Based Method for Object Classification and Human Action Recognition in Video,” Proceedings of ECCV Workshop on Computer Vision in Human-Computer Interaction, Graz, Austria, pp. 64-77, 2006.
[13]E. J. Delp and O. R. Mitchell, “Image Compression Using Block Truncation Coding,” IEEE Transactions on Communications, vol. 27, no. 9, pp. 1335-1341, 1979.
[14]T. Fawcett, “An introduction to ROC analysis,” Pattern recognition letters vol. 27, no. 8, pp. 861-874, Jun. 2006.
[15]J. Ferryman, D. Hogg, J. Sochman, A. Behera, J. A. Rodriguez-Serrano, S. Worgan, L. Li, V. Leung, M. Evans, P. Cornic, S. Herbin, S. Schlenger, and M. Dose, “Robust abandoned object detection integrating wide area visual surveillance and social context,” Pattern Recognition Letters, vol. 34, no. 7, pp. 789-798, May. 2013.
[16]N. Friedman and S. Russell, “Image Segmentation in Video Sequences: A Probabilistic Approach,” Proceedings of the 13th Conference on Uncertainty in Artificial Intelligence, San Francisco, pp. 175-181, 1997.
[17]L. Gallo, A. P. Placitelli, and M. Ciampi, “Controller-free exploration of medical image data: experiencing the Kinect,” in Computer-Based Medical Systems (CBMS), 2011 24th International Symposium on. Bristol, United Kingdom: IEEE, 2011.
[18]S. Geman and D. Geman, “Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 6, no. 6, pp. 721-741, Nov. 1984.
[19]N. Goyette, P.-M. Jodoin, F. Porikli, J. Konrad, and P. Ishwar, “A novel video dataset for change detection benchmarking,” IEEE Transactions on Image Processing, vol. 23, no. 11, pp. 4663 - 4679, 2014.
[20]M. D. Gregorio and M. Giordano, “Change detection with weightless neural networks,” in Computer Vision and Pattern Recognition Workshops (CVPRW), 2014 IEEE Conference on. Columbus, OH, 2014, pp. 409 - 413.
[21]M. Heikkilä and M. Pietikäinen, “A Texture-Based Method for Modeling the Background and Detecting Moving Objects,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 4, pp. 657-662, 2006.
[22]M. Heikkilä, M. Pietikäinen, and J. Heikkilä, “A Texture-Based Method for Detecting Moving Objects,” Proceedings of British Machine Vision Conference, British, pp. 187-196, 2004.
[23]T. Horprasert, D. Harwood, and L. S. Davis, “A statistical approach for real-time robust background subtraction and shadow detection,” in IEEE ICCV, vol. 99. Corfu, Greece, Sep. 1999, pp. 1-19.
[24]I.-S. Lee and W.-H. Tsai, “Data hiding in grayscale images by dynamic programming based on a human visual model,” Pattern Recognition, vol. 42, no. 7, pp. 1604–1611, 2009.
[25]R. Lienhart and J. Maydt, “An extended set of haar-like features for rapid object detection,” in Image Processing. 2002. Proceedings. 2002 International Conference on, vol. 1, 2002, pp. I-900 - I-903.
[26]C.-Y. Lin, C.-S. Chan, L.-W. Kang, and K. Muchtar, “Left-object detection through background modeling,” International Journal of Innovative Computing, Information and Control, vol. 9, no. 4, pp. 1373-1388, Apr. 2013.
[27]C.-Y. Lin, K. Muchtar, and C.-H. Yeh, “Robust techniques for abandoned and removed object detection based on Markov random field,” Journal of Visual Communication and Image Representation, vol. 39, no., pp. 181–195, 2016.
[28]H. Liu and F. Sun, “Efficient visual tracking using particle filter with incremental likelihood calculation,” Information Sciences, vol. 195, no., pp. 141–153, 2012.
[29]R. Lumia, L. Shapiro, and O. Zuniga, “A New Connected Components Algorithm for Virtual Memory Computers,” Computer Vision, Graphics, and Image Pmcessing, vol. 22, no. 2, pp. 287-300, 1983.
[30]E. Machida, M. Cao, T. Murao, and H. Hashimoto, “Human motion tracking of mobile robot with Kinect 3D sensor,” SICE Annual Conference (SICE), 2012 Proceedings of, Akita, Japan, pp., 2012.
[31]L. Maddalena and A. Petrosino, “A self-organizing approach to background subtraction for visual surveillance applications,” IEEE Transactions on Image Processing, vol. 17, no. 7, pp. 1168-1177, 2008.
[32]L. Maddalena and A. Petrosino, “The SOBS algorithm: what are the limits?,” in Computer Vision and Pattern Recognition Workshops (CVPRW), 2012 IEEE Computer Society Conference on. Providence, RI, 2012, pp. 21 - 26.
[33]M. Mason and Z. Duric, “Using Histograms to Detect and Track Objects in Color Video,” Proceedings of the 30th on Applied Imagery Pattern Recognition Workshop, Washington, DC, USA, pp. 154-159, 2001.
[34]J. M. McHugh, J. Konrad, V. Saligrama, and P.-M. Jodoin, “Foreground-Adaptive Background Subtraction,” IEEE Signal Processing Letters, vol. 16, no. 5, pp. 390-393, 2009.
[35]G. P. Meyer and M. N. Do, “3D GrabCut: interactive foreground extraction for reconstructed 3D scenes,” Proceedings of the 2015 Eurographics Workshop on 3D Object Retrieval, pp. 1-6 2015.
[36]K. Muchtar, C.-Y. Lin, L.-W. Kang, and C.-H. Yeh, “Rubust Background Modeling Based on Multiscale Color Description,” in Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. Xi''an,China, 2011.
[37]M. Munaro, F. Basso, and E. Menegatti, “Tracking people within groups with RGB-D data,” in Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on. Vilamoura-Algarve, Portugal: IEEE, 2012.
[38]D. Park and H. Byun, “A unified approach to background adaptation and initialization in public scenes,” Pattern Recognition, vol. 46, no. 7, pp. 1985–1997, 2013.
[39]F. Porikli, Y. Ivanov, and T. Haga, “Robust abandoned object detection using dual foregrounds,” EURASIP Journal on Advances in Signal Processing, vol. 2008, no., Jan. 2008.
[40]O. W. Power, “Understanding Background Mixture Models for Foreground Segmentation,” Proceedings of Image and Vision Computing, Auckland,New Zealand, pp. 267-271, 2002.
[41]Z. Ren, J. Yuan, J. Meng, and Z. Zhang, “Robust Part-Based Hand Gesture Recognition Using Kinect Sensor,” IEEE Transactions on Multimedia, vol. 15, no. 5, pp. 1110 - 1120, 2013.
[42]C. Rother, V. Kolmogorov, and A. Blake, “"GrabCut": interactive foreground extraction using iterated graph cuts,” ACM Transactions on Graphics (TOG), vol. 23, no. 3, pp. 309-314, Aug. 2004.
[43]H. Sajid and S.-C. S. Cheung, “Background Subtraction For Static & Moving Camera,” in The International Conference on Image Processing (ICIP). Québec, 2015.
[44]N. K. Sallem and M. Devy, Extended GrabCut for 3D and RGB-D Point Clouds,” in Advanced Concepts for Intelligent Vision Systems. Poznań, Poland: Springer International Publishing, 2013, pp. 354-365.
[45]P.-L. St-Charles, G.-A. Bilodeau, and R. Bergevin, “SuBSENSE: A Universal Change Detection Method With Local Adaptive Sensitivity,” Image Processing, IEEE Transactions on, vol. 24, no. 1, pp. 359 - 373, 2015.
[46]C. Stauffer and W. E. L. Grimson, “Adaptive Background Mixture Models for Real-Time Tracking,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Fort Collins, Colorado, USA, pp. 246-252, 1999.
[47]C. Stauffer and W. E. L. Grimson, “Learning Patterns of Activity Using Real-Time Tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 747-757, 2000.
[48]Y. Tian, R. S. Feris, H. Liu, A. Hampapur, and M.-T. Sun, “Robust detection of abandoned and removed objects in complex surveillance videos,” Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, vol. 41, no. 5, pp. 565-576, Sep. 2011.
[49]K. Vaiapury, A. Aksay, and E. Izquierdo, “GrabcutD: improved grabcut using depth information,” Proceedings of the 2010 ACM workshop on Surreal media and virtual cloning, Firenze, Italy, pp. 57-62, 2010.
[50]S. Varadarajan, P. Miller, and H. Zhou, “Spatial Mixture of Gaussians for dynamic background modelling,” in Advanced Video and Signal Based Surveillance (AVSS), 2013 10th IEEE International Conference on. Krakow, 2013, pp. 63 - 68
[51]P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” Proc. IEEE Conf. Computer Vision Pattern Recognit., Kauai, Hawaii, pp. I-511-518, 2001.
[52]B. Wang and P. Dudek, “A fast self-tuning background subtraction algorithm,” in Computer Vision and Pattern Recognition Workshops (CVPRW), 2014 IEEE Conference on. Columbus, OH, 2014, pp. 401 - 404.
[53]R. Wang, F. Bunyak, G. Seetharaman, and K. Palaniappan, “Static and moving object detection using flux tensor with split gaussian models,” in Computer Vision and Pattern Recognition Workshops (CVPRW), 2014 IEEE Conference on. Columbus, OH, 2014, pp. 420 - 424.
[54]T. Whelan, S. Leutenegger, R. F. Salas-Moreno, B. Glocker, and A. Davison, “ElasticFusion: Dense SLAM without a pose graph,” Proc. Robotics: Science and Systems, Rome, Italy, pp., 2015.
[55]L. Wixson, “Detecting Salient Motion by Accumulating Directionally-Consistent Flow,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 774-780, 2000.
[56]C. R. Wren, A. Azarbayejani, T. Darrell, and A. P. Pentland, “Pfinder: Real-Time Tracking of the Human Body,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 780-785, 1997.
[57]M. Wu and B. Liu, “Data Hiding in Image and Video:Part I Fundamental Issues and Solutions,” IEEE Transaction on Image Processing, vol. 12, no. 6, pp. 685-695, 2003.
[58]C.-H. Yeh, C.-Y. Lin, K. Muchtar, and L.-W. Kang, “Real-Time Background Modeling Based on a Multi-level Texture Description,” Information Sciences, vol. 269, no., pp. 106–127, 2014.
[59]Z. Zivkovic, “Improved Adaptive Gaussian Mixture Model for Background Subtraction,” Proceedings of the 17th International Conference on Pattern Recognition, Cambridge, UK., pp. 28-31, 2004.