臺灣博碩士論文加值系統

隨著多媒體資訊科技的進步，數位相機、數位攝影機、照相手機等科技產品的普及，數位影片隨手可得，人們生活中的影像資料日益豐富。在影片資料庫檢索、分析的處理過程中，很重要的一點，就是建立索引。特徵比對是影片分析的基礎，而一個好的影像索引結構能大幅的提昇特徵比對的性能，所以在這篇論文中，我們希望能利用影像索引技巧組織不同的視覺特徵，並嘗試引入機器學習的概念來改善索引效能，加速特徵的比對、減少I/O運作量，來嘗試解決眾多的影片分析應用問題，如：影片壓縮(Video Coding)、物件追蹤(Object Tracking)、關鍵畫面萃取(Key-Frame Extraction)、影片場景切割與檢索(Video Shot Segmentation and Retrieval)及人類行為偵測(Human Action Detection)等。
本論文的主要內容包括：（1）提出「區域式霍福轉換」應用於快速影像檢索系統(Image Retrieval)；（2）提出一個基於影像索引的全新區塊比對(Block-Matching)方法，用以過濾H.264視訊壓縮的搜尋點(Search Points)；（3）提出「三維矩量保存法」應用於快速的影片場景檢索；（4）擴充區域式霍福轉換應用於影片檢索、人類行為偵測及辨識。實驗結果顯示我們提出的方法在不同的影片分析應用上都有優異的表現。

Following advances in multimedia technology and the popularization of technological products, the image data in people’s lives become increasingly abundant each day. In the processing of searching and analyzing video databases, building indices is of the utmost importance. Feature matching is the foundation of video analysis; and good image indexing architecture can greatly increase the performance of feature matching. Therefore, in this dissertation, we hope to use image indexing techniques to organize different visual features, and introduce the concepts of machine learning to improve index performance; thereby accelerating characteristic matching and decreasing I/O operations to resolve the numerous application problems in video analysis, including: video coding, object segmentation and tracking, key-frame extraction, object-based video shot segmentation and retrieval, and human action detection.
The main contributions of this dissertation include: (1) A fast image retrieval system based the proposed region-based Hough transform (GBHT) is proposed; (2) A novel block-matching scheme with image indexing, which sets a proper priority list of search points, to encode a H.264 video sequence; (3) Based on the 3D moment-preserving principle, a fast video shot retrieval scheme is proposed; (4) The GBHT framework is also extended to perform video retrieval, human action detection and recognition. Experimental results demonstrate that the proposed methods outperform the compared methods for video based applications.

Chapter 1 Introduction 1
1.1 Background 2
1.2 Motivations 4
1.3 Organization 6
Chapter 2 Related Works 7
2.1 Visual Object Retrieval 7
2.2 Video Coding 10
2.3 Video Retrieval 14
2.4 Human Action Detection and Recognition 18
Chapter 3 Region-Based Visual Object Retrieval Using GHT 24
3.1 Object Search Using Region-Based GHT 26
3.2 Segmentation Strategy for Region-Based GHT 29
3.3 The Object Search Method 40
3.4 Experimental Results 45
Chapter 4 Motion Estimation for H.264/AVC Using Image Indexing 53
4.1 The Structure of Block Indexing 53
4.2 Optimal Block Matching Using Image Indexing 58
4.3 Extension to H.264/AVC 62
4.4 Experimental Results 72
Chapter 5 Space-Time Volume Analysis for Fast Video Retrieval 82
5.1 Space-Time Volume Analysis Using 3D Moment- Preserving 82
5.2 Fast Volume-Based Video Retrieval 91
5.3 Experimental Results 101
Chapter 6 Learning Discriminative Models for Event Recognition and Retrieval in Video Archives Using Hough Voting 111
6.1 The GHT-based Action Detection and Recognition 112
6.2 Detecting and Classifying Actions by Dynamic Programming 127
6.3 Experimental Results 133
Chapter 7 Conclusions and Future Work 139
References 142

[1] P. John. Eakins, Toward intelligent image retrieval, Pattern Recognition, 1 (2002) 3-14.
[2] Smeulders, A. W. M., M. Worring, A. Gupta, and R. Jain, “Content-based image retrieval at the end of the early years,” IEEE Trans. Pattern Anal. Machine Intell., 22 (2000) 1349-1380.
[3] Yong Rui, T. S. Huang, and Shih-Fu Chang, “Image retrieval: current techniques, promising directions, and open Issues,” Journal of Visual Communication and Image Representation, 10 (1999) 39-62.
[4] Y. Liu, D. Zhang, G Lu, and W.-Y. Ma, “A Survey of Content-Based Image Retrieval with High-Level Semantics,” Pattern Recognition, vol. 40, pp. 262-28.20072.
[5] J. Z. Wang, J. Li, and G. Wiederhold, “SIMPLIcity: Semantic-Sensitive Integrated Matching for Picture Libraries,” IEEE Trans. on Pattern Analysis and Machine Intelligence, 23 (2001) 947-963.
[6] I. Pratikakis, I. Vanhamel, H. Sahli, B. Gatos, and S. J. Perantonis, “Unsupervised Watershed-Driven Region-Based Image Retrieval,” IEE Proc. Vision, Images, and Signal Processing, 153 (2006) 313-322.
[7] C. Carson, S. Belongie, H. Greenspan, and J. Malik, “Blobword: Image Segmentation Using E-M and Its Application to Image Querying,” IEEE Trans. Pattern Anal. Mach. Intell., 24 (2002) 1026-1038.
[8] J.-W. Hsieh and W. Eric L. Grimson, “Spatial Template Extraction for Image Retrieval by Region Matching,” IEEE Trans. Image Processing, 12 (2003) 1404-1415.
[9] J. Fan, Y. Gao, H. Luo, and G. Xu, “Statistical Modeling and Conceptualization of Natural Images,” Pattern Recognition, 38 (2005) 865-885.
[10] J. Luo and C.-E. Guo, “Perceptual Grouping of Segmented Regions in Color Images,” Pattern Recognition, 36 (2003) 2781-2792.
[11] S.-C. Zhu, “Statistical Modeling and Conceptualization of Visual Patterns,” IEEE Trans. On Pattern Analysis and Machine Intelligence, 25 (2003) 691-712.
[12] W. Jiang, G. Er, Q. Dai, and J. Gu, “Similarity-Based Online Feature Selection in Content-Based Image Retrieval,” IEEE Trans. Image Processing, 15 (2006) 702-712.
[13] F. Jing, M. Li, H.-J. Zhang, and B. Zhang, “Relevance Feedback in Region-Based Image Retrieval,” IEEE Trans. Circuits and Systems for Video Technology, 14 (2004) 672-681.
[14] D. Ballard, “Generalizing the Hough transform to detect arbitrary shapes,” Pattern Recognition, 13 (1981) 111-122.
[15] S.-C. Cheng, C.-T. Kuo, and H.-J. Chen, “Visual Object Retrieval via Block-Based Visual Pattern Matching,” Pattern Recognition, 40 (2007) 1695-1710.
[16] Draft ITU-T Recommendation and Final Draft International Standard of Joint Video Specification. ITU-T Rec. H.264 and ISO/IEC 14 496-10 AVC, Joint Video Team, 2003.
[17] Information Technology—Coding of Audio-Visual Objects—Part 2: Visual, ISO/IEC 14 496-2, 1999.
[18] Video Coding for Low Bit Rate Communication, ITU-T Rec. H.263, 1998.
[19] Information Technology—Generic Coding of Moving Pictures and Associated Audio Information: Video, ISO/IEC 13 818-2 and ITU-T Rec.H.262, 1996.
[20] A. Joch, F. Kossentini, H. Schwarz, T. Wiegand, and G. J. Sullivan, “Performance Comparison of Video Coding Standards Using Lagragian Coder Control,” in Proc. IEEE Int. Conf. Image Process., 2002, pp.501–504.
[21] T. Wiegand, G. J. Sullivan, G. Bjntegaard, and A. Luthra, “Overview of the H.264/AVC video coding standard,” IEEE Trans. Circuits Syst. Video Technol., 13 (2003) 560-576.
[22] Joint Video Team Reference Software JM 17.0 May 2004 [Online].
[23] T.-H. Tsai and Y. N. Pan, “A Novel 3-D Hexagon Search Algorithm for Fast Block Motion Estimation on H.264 Video Coding,” IEEE Trans. Circuits Syst. Video Technol., 16 (2006) 1542-1549.
[24] D. Wu, F. Pan, K. P. Lim, S. Wu, Z. G. Li, X. Lin, S. Rahardja, and C. C. Ko, “Fast Intermode Decision in H.264/AVC Video Coding,” IEEE Trans. Circuits Syst. Video Technol., 15 (2005) 953-958.
[25] Y. H. Huang, B. Y. Hsieh, T. C. Wang, S. Y. Chen, S. Y. Ma, C. F. Shen, and L. G. Chen, “Analysis and Complexity Reduction of Multiple Reference Frames Motion Estimation in H.264/AVC,” IEEE Trans. Circuits Syst. Video Technol., 16 (2006) 507-522.
[26] T. Koga, K. Iinuma, A. Hirano, Y. Iijima, and T. Ishiguro, “Motion Compensated Interframe Coding for Video Conferencing,” in Proc. Nat. Telecommunications Conf., 1981, pp. C9.6.1-C9.6.5.
[27] S. Zhu and K. K. Ma, “A New Diamond Search Algorithm for Fast Block-Matching Motion Estimation,” IEEE Trans. Image Process., 9 (2000) 287-290.
[28] C. Zhu, X. Lin, and L. P. Chau, “Hexagon-Based Search Pattern for Fast Block Motion Estimation,” IEEE Trans. Circuits Syst. Video Technol., 12 (2002) 349-355.
[29] T. Y. Kuo and C. H Chan, “Fast Variable Block Size Motion Estimation for H.264 Using Likelihood and Correlation of Motion Field,” IEEE Trans. on Circuits and Systems for Video Technology, 16 (2006) 1185-1195.
[30] Xu, X. and He, Y., “Improvements on fast motion estimation strategy for H.264/AVC,” IEEE Trans. Circuits Syst. Video Technol., 18 (2008) 285-293.
[31] Gonzalez-Diaz, I. and Diaz-de-Maria, F., “Adaptive multi-pattern fast block-matching algorithm based on motion classification techniques,” IEEE Trans. Circuits Syst. Video Technol., 18 (2008) 1369-1382.
[32] C. M. Mak, C. K. Fong, and W. K. Cham, “Fast Motion Estimation for H.264/AVC in Walsh-Hadamard Domain,” IEEE Trans. on Circuits and Systems for Video Technology, 18 (2008) 735-745.
[33] P.-L. Tai, S.-Y. Huang, C.-T. Liu, and J.-S. Wang, “Computation-Aware Scheme for Software-Based Block Motion Estimation,” IEEE Trans. Circuits Syst. Video Technol., 13 (2003) 901-913.
[34] S.-Y. Huang, “Adaptive Computation-Aware Scheme for Software-Based Predictive Block Motion Estimation,” Journal of Visual Communication and Image Representation, 17 (2006) 767-782.
[35] C.-Y. Chen, Y.-W. Huang, C.-L. Lee, and L.-G. Chen, “One-Pass Computation-Aware Motion Estimation with Adaptive Search Strategy,” IEEE Trans. Multimedia, 8 (2006) 698-706.
[36] C.-Y. Cho, S.-Y. Huang, and J.-S. Wang, “Design of computation-aware mode decision scheme for H.264/AVC,” in Proc. Of 31st IEEE International Conference on Acoustics, Speech and Signal Processing, Vol. II, pp. 565-568, May 14-19, 2006 Toulouse, France.
[37] M. Jakubowski and G. Pastuszak, “A new multi-path scheme for adaptive computation-aware motion estimation,” Opto-electronics Review, 15 (2007) 118-124.
[38] S. Theodridis and K. Koutroumbas, Pattern Recognition, second. Ed., Academic Press, 2003.
[39] H. Murase and S. K. Nayar, “Visual Learning and Recognition of 3D Objects from Appearance,” International J. of Computer Vision, 14 (1995) 5-24.
[40] A. K. Jain and R. C. Dubes, Algorithms for Clustering Data, Prentice Hall, 1988.
[41] Jim Z. C. Lai and Y.-C. Liaw, “Fast Searching Algorithm for Vector Quantization Using Projection and Triangular Inequality,” IEEE Trans. Image Processing, 13 (2004) 1554-1558.
[42] S.-C. Cheng and T.-L. Wu, ”Fast Indexing Method for Image Retrieval Using k Nearest Neighbors Searches by Principal Axis Analysis,” Journal of Visual Communication and Image Representation, 17 (2006) 42-56.
[43] T. Kim, “Side Match and Overlap Match Vector Quantizers for Images,” IEEE Trans. Image Processing, 1 (1992) 170-185.
[44] J. McNames, “A Fast Nearest-Neighbor Algorithm Based on a Principal Axis Search Tree,” IEEE Trans. PAMI, 23 (2002) 964-976.
[45] Jim Z. C. Lai, Y.-C. Liaw, and J. Liu, “Fast k-Nearest-Neighbor Search Based on Projection and Triangular Inequality,” Pattern Recognition, 40 (2007) 351-359.
[46] S.-C. Cheng, “Content-based Image Retrieval Using Moment-preserving Edge Detection,” Image and Vision Computing, 21 (2003) 809-826.
[47] X. Q. Gao, C. J. Duanmu, and C. R. Zou, “A Multilevel Successive Elimination Algorithm for Block Matching Motion Estimation,” IEEE Trans. On Image Processing, 9 (2000) 501-504.
[48] Shou-Der Wei, Shao-Wei Liu, and Shang-Hong Lai, “Fast and Optimal Block Motion Estimation Via Adaptive Successive Elimination,” in Proc. of IEEE International Conf. on Image Process, pp. 2361-2364, 2006.
[49] W. Li and E. Salari, “Successive Elimination Algorithm for Motion Estimation,” IEEE Trans. On Image Processing, 4 (1995) 105-107.
[50] M. Roach, J. Mason, N. Evans, L. Q. Xu, and F. Stentiford, “Recent trends in video analysis: a taxonomy of video classification problems,” in: M. A. Hamza (Ed.), Proceedings of Internet and Multimedia Systems Conference, Kauai, USA, Acta Press (2003).
[51] C.-L. Huang and B.-Y. Liao, “A Robust Scene-Change Detection Method for Video Segmentation,” IEEE Trans. Circuits Syst. Video Technol., 11 (2) (2001) 1281–1288.
[52] C.-W. Su, H.-Y. Mark Liao, H.-R. Tyan, C.-W. Lin, D.-Y. Chen, and K.-C. Fan, “Motion Flow-Based Video Retrieval,” IEEE Trans. Multimedia, 9 (2007) 1193–1201.
[53] A. J. T. Lee, R.-W. Hong, and M.-F. Chang, “An Approach to Content-Based Video Retrieval,” in Porc. IEEE International Conference on Multimedia and Expo (ICME), 1 (2004) 273–276.
[54] Z. Min, “Key Frame Extraction From Scenery Video,” in Proc. IEEE International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR), 2 (2007) 540–543.
[55] K.-W. Sze, K.-M. Lam, and G. Qiu, “A New Key Frame Representation for Video Segment Retrieval,” IEEE Trans. Circuits and Systems for Video Technology, 15 (2005) 1148-1155.
[56] Y. Ricquebourg and P. Bouthemy, “Real-time Tracking of Moving Persons by Exploiting Spatial-Temporal Image Slice,” IEEE Trans. Pattern Analysis and Machine Intelligence, 22 (8) (2000) 797-808.
[57] W.-S. Li, K.-S. Candan, “SEMCOG: A Hybrid Object-Based Image and Video Database System and Its Modeling,” Theory Prac. Object System (TAPOS), 5 (3) (1999) 163-180.
[58] W. Ren, S. Singh, M. Singh, Y. S. Zhu, “State-of-the-art on Spatial-Temporal Information-Based Video Retrieval,” Pattern Recognition, 42 (2) (2009) 267-282.
[59] J. K. Aggarwai and Q. Cai, “Human Motion Analysis: A Review,” Comput. Vision Image Understanding, 73 (3) (1999) 428-440.
[60] Y. Ke, R. Sukthankar, and M. Hebert, “Efficient Visual Event Detection Using Volumetric Features,” in Proc. ICCV (2005).
[61] T. Pavlidis, “Polygonal Approximation by Newton’s Method,” IEEE Trans. Comput. 26 (1977) 800-807.
[62] F. S. Cohen, Z. Huang, and Z. Yang, “Invariant Matching and Identification of Curves Using B-Splines Curve Representation,” IEEE Trans. Image Processing, 4 (1995) 1-10.
[63] T. Xiang and S. Gong, “Activity Based Surveillance Video Content Modeling,” Pattern Recognition, 41 (7) (2008) 2309-2326.
[64] A. Briassouli and N. Ahujia, “Extraction and Analysis of Multiple Periodic Motions in Video Sequences,” IEEE Trans. Pattern Anal. Mach. Intell. 29 (7) (2007) 1244-1251.
[65] T. Goodhart, P. Yan, and M. Shah, “Action Recognition Using Spatial-Temporal Requlaity Based Features,” in Proc. IEEE International Conference on Accoustics, Speech and Signal Processing (ISASSP 2008) (2008) 745-748.
[66] J.-W. Hsieh, Y.-T. Hsu, H.Y.M. Liao, and C.C. Chen, “Video-Based Human Movement Analysis and Its Application to Surveillance Systems,” IEEE Trnas. Multimedia, 10 (3) (2008) 372-384.
[67] X. Ma, F. Bashir, A.A. Khokhar, and D. Schonfeld, “Event Analysis Based on Multiple Interactive Motion Trajectories,” IEEE Trans. Circuits and Systems for Video technology, 19 (3) (2009) 397-406.
[68] T. Liu and J. R. Kender, “Computational Approaches to Temporal Sampling of Video Sequences,” ACM Trans. Multimedia Computing, Communications and Applications, 3 (2007) 1-17.
[69] A. Anjulan and N. Canagaraiah, “A Unified Framework for Object Retrieval and Mining,” IEEE Trans. Circuits and Systems for Video technology, 19 (1) (2009) 63-76.
[70] K.-H. Liu, M.-F. Weng, C.-Y. Tseng, Y.-Y. Chuang, and M.-S. Chen, “Association and Temporal Rule Mining for Post-filtering of Semantic Concept Detection in Video,” IEEE Trnas. Multimedia, 10 (2) (2008) 240-251.
[71] W.-K. Huang, C.-H. Chuang, S.-C. Cheng, and J.-W. Hsieh, “A Fast Cube-based Video Shot Retrieval Using 3D Moment-Preserving Technique,” in Proc. IEEE International Conference on Image Processing (ICIP), (2009).
[72] E. Shechtman and M. Irani, “Space-Time Behavior-Based Correlation -or- How to Tell If Two Underlying Motion Fields Are Similar without Computing Them?” IEEE Trans. Pattern Analysis and Machine Intelligence, 29 (11) (2007) 2045-2056.
[73] K. Yan, “Volumetric Features for Video Event Detection,” Ph. D. Thesis, CMU-CS-08-113, Carnegie Mellon University, USA, March 2008.
[74] R. Poppe, “A survey on vision-based human action recognition,” Image and Vision Computing, 28 (6) (2010), 976-990.
[75] P. Turaga, R. Chellappa, V. S. Subrahmanian, O. Udrea, “Machine recognition of human activities: a survey,” IEEE Trans. Circuits and Systems for Video Technology, 18 (11) (2008), 1473-1488.
[76] I. Laptev, M. Lindeberg, “Space time interest points,” Proc. IEEE Int’l Conf. Computer Vision, 2003, 432-439.
[77] A. A. Efros, A. C. Berg, G. Mori, J. Malik, “Recognizing action at a distance,” Proc. IEEE Int’l Conf. Computer Vision, 2003, 726-733.
[78] C. Schuldt, I. Laptev, B. Caputo, “Recognizing human actions: A local SVM approach,” Proc. IEEE Int’l Conf. Pattern Recognition, 2004, 32-36.
[79] M. Blank, L. Gorelick, E. Schechtman, M. Irani, and R. Basri, “Actions as space-time shapes,” in IEEE Conf. Computer Vision, 2005, 1395-1402.
[80] S. Ali, M. Shah, “Human action recognition in videos using kinematic features and multiple instance learning,” IEEE Trans. Pattern Analysis and Machine Intelligence, 32 (2) (2010), 288-302.
[81] I. Laptev, B. Caputo, C. Schuldt, T. Lindeberg, “Local velocity-adapted motion events for spatio-temporal recognition,” Computer Vision and Image Understanding, 108 (2007) 207-229.
[82] S. Nowozin, G. Bakur, K. Tsuda, “Discriminative subsequence mining for action classification,” Proc. Int’l Conf. Computer Vision, 2007, 1-8.
[83] J. Neibles, H. Wang, F. Li, “Unsupervised learning of human action categories using spatial temporal words,” Proc. British Machine Vision Conf., 2005.
[84] B. Yao, S.-C. Zhu, “Learning deformable action templates from cluttered videos,” Proc. Int’l Conf. Computer Vision, 2009, 1507-1514.
[85] A. Yao, J. Gall, L. V. Gool, “A Hough transform-based voting framework for action recognition,” in IEEE Conf. Computer Vision and Pattern Recognition, 2010, 2061-2068.
[86] K. Mikolajczyk, H. Uemura, “Action recognition with motion-appearance vocabulary forest,” in IEEE Conf. Computer Vision and Pattern Recognition, 2008, 1-8.
[87] A. Oikonomopoulos, I. Patras, M. Pantic, “An implicit spatiotemporal shape model for human activity localization and recognition,” in IEEE Conf. Computer Vision and Pattern Recognition, 2009, 20-25.
[88] Y.-C. Lo, P.-Y. Lee, S.-C. Cheng , “Space-time template matching for human action detection using volume-based generalized Hough Transform,” in Proc. IEEE Intl. Conf. Image Processing (ICIP), 2011, 2097-2100.
[89] V. Ferrari, F. Jurie, C. Schmid, “Accurate object detection with deformable shape models learnt from images,” in IEEE Conf. Computer Vision and Pattern Recognition, 2007, 1-8.
[90] P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan, “Object detection with discriminatively trained part based models,” IEEE Trans. Pattern Analysis and Machine Intelligence, 32 (2010), 1627-1645.
[91] J. Gall, V. Lempitsky, “Class-specific Hough forests for object detection,” in Int’l Conf. Computer Vision and Pattern Recognition, 2009, 1022-1029.
[92] P. Felzenszwalb, R. Girshick, D. McAllester, “Cascade object detection with deformable part models,” in IEEE Conf. Computer Vision and Pattern Recognition, 2010, 2241-2248.
[93] B. Leibe, A. Lenardis, B. Schiele, “Robust object detection with interleaved categorization and segmentation,” International Journal of Computer Vision, 77 (1-3) (2008), 259-289.
[94] C. Lampert, M. Blaschko, T. Hofmann, “Efficient subwindow search: A branch and bound framework for object localization,” IEEE Trans. Pattern Analysis and Machine Intelligence, 31 (2009) 2129-2142.
[95] P. Scovanner, A. Ali, M. Shah, “A 3-dimensional SIFT descriptor and its application to action recognition,” Proc. ACM Int’l Conf. Multimedia, 2007, 357-360.
[96] I. Laptev, M. Marszalek, C. Schmid, B. Rozenfeld, “Learning realistic human actions from movies,” in IEEE Computer Vision and Pattern Recognition, 2008, 1-8.
[97] J. Liu, J. Luo, M. Shah, “Recognizing realistic actions from videos 'in the wild',” in IEEE Computer Vision and Pattern Recognition, 2009, 1996-2003.
[98] J. Gall, A. Yao, N. Razavi, L. V. Gool, V. Lempitsky, “Hough forests for object detection, tracking, and action recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, 33 (2011) 2188-2202.
[99] J. Niebles, H. Wang, L. Fei-Fei, “Unsupervised learning of human action categories using spatial-temporal words,” Int’l Computer Vision, 79 (3) (2008), 299-318.
[100] D. Weinland, E. Boyer, R. Ronfard, “Action recognition from arbitrary views using 3D examples,” Proc. International Conf. Computer Vision (ICCV’07), 2007, 1-8.
[101] M. Brand, N. Oliver, A. Pentland, “Coupled hidden Markov models for complex action recognition,” Proc. IEEE Int’l Conf. Computer Vision and Pattern Recognition, 1997, 994-999.
[102] F. Lv, R. Nevatia, “Single view human action recognition using key pose matching and Viterbi path searching,” Proc. IEEE Int’l Conf. Computer Vision and Pattern Recognition, 2007, 1-8.
[103] N. Oliver, B. Rosario, “A. Petland, A Bayesian computer vision system for modeling human interactions,” IEEE Trans. Pattern Analysis and Machine Intelligence, 22 (8) (2000) 831-843.
[104] D. Xu, S.-F. Chang, “Video event recognition using kernel methods with multilevel temporal alignment,” IEEE Trans. Pattern Analysis and Machine Intelligence, 30 (1) (2008) 1985-1967.
[105] L. Gorelick, M. Blank, E. Shechtman, M. Irani, R. Basri, “Actions as space-time shapes,” IEEE Trans. Pattern Analysis and Machine Intelligence, 29 (12) (2007) 2247-2253.
[106] P. Scovanner, A. Ali, M. Shah, “A 3-dimensional SIFT descriptor and its application to action recognition,” Proc. ACM Int’l Conf. Multimedia, 2007, 357-360.
[107] B. Yao, S.-C. Zhu, “Learning deformable action templates from cluttered videos,” Proc. Int’l Conf. Computer Vision, 2009, 1507-1514.
[108] J. Zhang, S. Gong, “Action categorization with modified hidden conditional random field,” Pattern Recognition, 43 (1) (2010) 197-203.
[109] T. Zhao, R. Nevatia, B. Wu, “Segmentation and tracking of multiple humans in crowded environments,” IEEE Trans. Pattern Analysis and Machine Intelligence, 30 (7) (2008) 1198-1121.
[110] L. S. Silva, J. Scharcanski, “Video segmentation based on motion coherence of particles in a video sequence,” IEEE Trans. Image Processing, 19 (4) (2010), 1036-1049.
[111] C.-H. Chuang, S.-C. Cheng, C.-C. Chang, “Adaptive image segmentation for region-based object retrieval using generalized Hough transform,” Pattern Recognition, 43 (2010) 3219-3232.
[112] D. H. Ballard and C. M. Brown, Computer Vision, Prentice-Hall, Englewood Cliffs, NJ, 1982.
[113] C. P Chau and W. C. Siu, “Generalized Hough Transform Using Regions with Homogeneous Color,” Int. J. Computer Vision, 59 (2004) 183-199.
[114] S. Beucher and F. Meyer, “The Morphological Approach to Segmentation: The Watershed Transformation, in Mathematical Morphology in Image Processing,” E. R. Doughertty, Ed. New York: Marcel Dekker, 1993.
[115] J. F. Canny, “A Computational Approach to Edge Detection,” IEEE Trans. Patt. Anal. Mach. Intell., PAMI-8 (1986) 679-698.
[116] H.-C. Lee and David R. Cok, “Detecting Boundaries in a Vector Field,” IEEE Trans. On Signal Processing, 39 (1991) 1181-1194.
[117] J. Matas, O. Chum, M. Urban, and T. Pajdla, “Robust Wide-Baseline Stereo from Maximally Stable Extremal Regions,” Image and Vision Computing, 20 (2004) 761–767.
[118] S. P. Shan, X. Xuan, R. J. DeLeeuw, M. Khojasten, W. L. Lam, R. Ng, and K. P. Murphy, “Integrating Copy Number Polymorphisms into Array CGH Analysis Using a Robust HMM,” J. Bioinformatics, 22 (2006) e431-e439.
[119] J. M. Morel and G. Yu, “ASIFT: A New Framework for Fully Affine Invariant Image Comparison,” SIAM Journal on Imaging Sciences, 2 (2009) 438-469
[120] M. R. Spiegel, Mathematical Handbook of Formulas and Tables, McGraw-Hill Book Company, 1981.
[121] Y. P. Sun and M. T. Sun, “Fast Multiple Reference Frame Motion Estimation for H.264/AVC,” IEEE Trans. Circuit and Systems Video Technol., 16 (2006) 447-452.
[122] M. J. Chen, G. L. Li, Y. Y. Chiang, and C. T. Hsu, “Fast Multiframe Motion Estimation Algorithm by Motion Vector Composition for the MPEG-4/AVC/H.264 standard,” IEEE Trans. Multimedia, 8 (2006) 478-487.
[123] Z. Liu, S. Goto, and T. Ikenaga, “Content-Aware Fast Motion Estimation for H.264/AVC,” IEICE Trans. Fundamentals, E91-A (2008) 1944-1952.
[124] C.-Y. Cho, N. S.-Y. Huang, and J.-S. Wang, “Design of Computation-Aware Mode Decision Scheme for H.264/AVC,” in Proc. IEEE Intl. Conf. Acoustics, Speech, and Signal Processing (ICASSP), 2006, 565-568.
[125] Paul Viola and Michael J. Jones, “Rapid Object Detection using a Boosted Cascade of Simple Features,” in Proc. IEEE Intl. Conf. on Computer Vision and Pattern Recognition (VCPR), 2001, 511-518.
[126] S. Winkler, “Issues in vision modeling for perceptual video quality assessment,” Signal Processing, 78 (1999) 231-252.
[127] S.-C. Cheng and T.-L.Wu, “Subpixel edge detection of color images using moment-preserving technique and principal axis analysis,” Pattern Recognition, 38 (4) (2006) 527-537.
[128] W.-H. Tsai, “Moment preserving thresholding: A new approach,” Comput. Vis., Graph., Image Process., (1984) 377-393.
[129] S. C. Pei and C. M. Cheng, “Color image processing by using binary quaternion moment preserving thresholding technique,” IEEE Trans. Image Process., 8 (1999) 614-628.
[130] C.-H. Chuang, B.-N. Chen, S.-C. Cheng, “An optimal Computation aware block matching for motion estimation using image indexing,” Journal of Visual Communication and Image Representation, 22 (2011) 451-464.
[131] D. Comaniciu, P. Meer, “Mean-shift: A robust approach toward feature space analysis,” IEEE Trans. PAMI, 24(5) (2002) 603-619.
[132] D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, 60(2) (2004) 91-110.
[133] T. Kanungo, D. M. Mount, N. S. Netanyahu, C. D. Piatko, R. Silverman, A. Y. Wu, “An efficient k-means clustering algorithm: Analysis and implementation,” IEEE Trans. Pattern Analysis and Machine Intelligence 24 (2002) 881–892.
[134] P. Beyerlein, “Discriminative model combination,” in Proc. IEEE Workshop on Automatic Speech Recognition and Understanding, 1997, 238-245.
[135] H. Ruppertshofen, C. Lorenz, S. Schmidt, P. Beyerlein, Z. Salah, G. Rose, H. Schramm, “Iterative training of discriminative models for the generalized Hough transform,” in Proc. International MICCAI Conference on Medical Computer Vision, 2010, 21-30.
[136] J. Matas, O. Chum, M. Urba, T. Pajdla, “Robust wide baseline stereo from maximally stable extremal regions,” in Proc. British Machine Vision Conference, 2002, 384-396.
[137] M. Rodriguez, J. Ahmed, and M. Shah, “Action mach a spatio-temporal maximum average correlation height filter for action recognition,” in IEEE Conf. Computer Vision and Pattern Recognition, 2008, 1-8.
[138] K. Schindler and L. Van Gool, “Action snippets: How many frames does human action recognition require?” in IEEE Conf. Computer Vision and Pattern Recognition, 2008, 1-8.
[139] B. Ommer, T. Mader, and J. M. Buhmann, “Seeing the objects behind the dots: Recognition in videos from a moving camera,” Int’l J. Computer Vision, 83 (2009) 57–71.