請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/47641完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 洪一平(Yi-Ping Hung) | |
| dc.contributor.author | Zong-Hua You | en |
| dc.contributor.author | 游宗樺 | zh_TW |
| dc.date.accessioned | 2021-06-15T06:10:11Z | - |
| dc.date.available | 2014-08-22 | |
| dc.date.copyright | 2011-08-22 | |
| dc.date.issued | 2011 | |
| dc.date.submitted | 2011-08-19 | |
| dc.identifier.citation | [1] V. M. Zatsiorsky, Kinematics of Human Motion. Champaign, IL: Human Kinetics Publishers, 1997.
[2] A. Galata, N. Johnson, and D. Hogg, “Learning variable-length Markov models of behavior,” Comput. Vis. Image Understand., vol. 81, pp.398–413, 2001. [3] A. Bobick and J. Davis. The recognition of human movement using temporal templates. IEEE Trans. PAMI, 23(3):257– 267, 2001. [4] P. Dollar, V. Rabaud, G. Cottrell, and S. Belongie. Behavior recognition via sparse spatio-temporal features. VS-PETS, pp. 65-72, 2005 [5] I. Laptev, M. Marszalek, C. Schmid, and B. Rozenfeld. Learning realistic human actions from movies. CVPR, pp. 1-8, 2008. [6] J. C. Niebles, H.Wang, and L. Fei-Fei. Unsupervised learning of human action categories using spatial-temporal words. Int’l J. Computer Vision, 79(3):299– 318, 2008. [7] S. Nowozin, G. Bakir, and K. Tsuda. Discriminative subsequence mining for action classification. ICCV, pp. 1-8, 2007. [8] N. Nguyen, D. Phung, S. Venkatesh, and H. Bui, “Learning and detecting activities from movement trajectories using the hierarchical hidden Markov models,” in Proc. Comput. Vis. Pattern Recognit., 2005, vol. 2, pp. 955–960. [9] S. Ali, A. Basharat, and M. Shah, “Chaotic invariants for human action recognition,” in Proc. Int. Conf. Comput. Vis., 2007, pp. 1–8. [10] W. Lin, M.-T. Sun, P. Poovandran, and Z. Zhang, “Human activity recognition for video surveillance,” IEEE Trans. Circuits Syst. Video Technol., vol. 18, no. 8, pp. 1128–1139, Aug. 2008. [11] A. Yilmaz and M. Shah, “Actions sketch: a novel action representation,” in Proc. Comput. Vis. Pattern Recognit., 2005, vol. 1, pp. 984–989. [12] Y. Ke, R. Sukthankar, and M. Hebert, “Event detection in crowded videos,” in Proc. Int. Conf. Comput. Vis., 2007, pp. 1–8. [13] L. Gorelick, M. Blank, E. Shechtman, M. Irani, and R. Basri, “Actions as space-time shapes,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 29, no. 12, pp. 2247–2253, Dec. 2007. [14] I. Laptev and P. Perez. Retrieving actions in movies. ICCV, pp. 1-8, 2007. [15] H.-Bo Zhang, S.-Z. Li, F. Guo, S. Liu, B.-X. Liu.“Real-time human action recognition based on shape combined with motion feature,” IEEE International Conference on ICIS, pp. 633 – 637, Oct. 2010 [16] H. Jhuang, T. Serre, L.Wolf, and T. Poggio. A biologically inspired system for action recognition. ICCV, pp. 1-8, 2007. [17] J. Liu and M. Shah. Learning human actions via information maximization. CVPR, pp. 1-8, 2008. [18] K. Schindler and L. V. Gool. Action snippets: How many frames does human action recognition require? CVPR, pp. 1-8, 2008. [19] C. Schuldt, I. Laptev, and B. Caputo. Recognizing human actions: A local svm approach. ICPR, pp. 32-36, 2004. [20] Y. Wang, P. Sabzmeydani, and G. Mori. Semi-latent dirichlet allocation: A hierarchical model for human action recognition. ICCV Workshop on Human Motion, pp. 240-254, 2007. [21] D. Weinland and E. Boyer. Action recognition using exemplar-based embedding. CVPR, pp. 1-7, 2008. [22] A. A. Efros, A. C. Berg, G.Mori, and J.Malik. Recognizing action at a distance. ICCV, pp. 726-733, 2003. [23] A. Fathi and G.Mori. Action recognition by learning mid-level motion features. CVPR, pp. 1-8, 2008. [24] I. Laptev and P. Perez. Retrieving actions in movies. ICCV, pp. 1-8, 2007. [25] A. Elgammal, V. Shet, Y. Yacoob, and L. S. Davis. Learning dynamics for exemplar-based gesture recognition. CVPR, pp. 571-578, 2003. [26] F. Lv, R. Nevatia, Single view human action recognition using key pose matching and viterbi path searching. CVPR, pp. 1-8, 2007. [27] D. Weinland, E. Boyer, R. Ronfard, Action recognition from arbitrary views using 3d exemplars. ICCV, 2007. [28] W. Li, Z. Zhang, and Z. Liu. Expandable data-driven graphical modeling of human actions based on salient postures. IEEE Transactions on Circuits and Systems for Video Technology, 18(11):1499–1510, 2008 [29] C. Cedras and M. Shah, “Motion Based Recognition: A Survey,” Image and Vision Computing, vol. 13, no. 2, pp. 129-155, 1995. [30] J.K. Aggarwal, Q. Cai, W. Liao, and B. Sabata, “Articulated and Elastic Non-Rigid Motion: A Review,” Proc. Workshop Motion of Non-Rigid and Articulated Objects, 1994. [31] D. Weinlanda, R. Ronfardb, and E. Boyer, “A Survey of Vision-Based Methods for Action Representation, Segmentation and Recognition,” Technical Report 7212, INRIA - February 2010 [32] J. Yamato, J. Ohya, and K. Ishii, “Recognizing Human Action in Time Sequential Images Using Hidden Markov Model,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 1992. [33] H. Jiang, M.S. Drew, and Z.N. Li, “Successive Convex Matching for Action Detection,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2006. [34] I. Laptev and T. Lindeberg, “Space-Time Interest Points,” Proc. IEEE Int’l Conf. Computer Vision, 2003. [35] J. Yuan, Z. Liu, and Y. Wu, “Discriminative Subvolume Search for Efficient Action Detection,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2009. [36] J. Niebles, H. Wang, and L. Fei-Fei, “Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words,” Int’l J. Computer Vision, vol. 79, no. 3, pp. 299-318, Mar. 2008. [37] J. Niebles and L. Fei-Fei, “A Hierarchical Models of Shape and Appearance for Human Action Classification,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2007. [38] C. Schuldt, I. Laptev, and B. Caputo, “Recognizing Human Actions: A Local SVM Approach,” Proc. IEEE Int’l Conf. Pattern Recognition, 2004. [39] R. Polana, R. Nelson, Low level recognition of human motion (or how to get your man without finding his body parts), in: NAM, 1994. [40] S. Ali and M. Shah, “Human Action Recognition in Videos Using Kinematic Features and Multiple Instance Learning,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 32, no. 2, pp. 288-303, Feb. 2010. [41] 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, vol. 29, no. 11, pp. 2045-2056, Nov. 2007. [42] Y. Ke, R. Sukthankar, and M. Hebert, “Efficient Visual Event Detection Using Volumetric Features,” Proc. IEEE Int’l Conf. Computer Vision, 2005. [43] P. Viola and M. Jones, “Robust Real-Time Object Detection,” Int’l J. Computer Vision, vol. 57, no. 2, pp. 137-154, 2004. [44] P. Scovanner, S. Ali, and M. Shah, “A 3-Dimensional SIFT Descriptor and Its Application to Action Recognition,” Proc. ACM Int’l Conf. Multimedia, 2007. [45] H. Ning, T. Han, D. Walther, M. Liu, and T. Huang, “Hierarchical Space-Time Model Enabling Efficient Search for Human Actions,” IEEE Trans. Circuits and Systems for Video Technology, vol. 19, no. 6, pp. 808-820, June 2009. [46] V. Kellokumpu, M. Pietikainen, and J. Heikkila. Human activity recognition using sequences of postures. In Proc IAPR Conf. Machine Vision Applications, pages 570–573, 2005. 2 [47] J. W. Davis and A. Tyagi. Minimal-latency human action recognition using reliable-inference. Image and Vision Computing, 24(5):455–472, 2006. [48] C. Sminchisescu, A. Kanaujia, Z. Li, and D. Metaxas. Conditional models for contextual human motion recognition. In Proc ICCV, volume 2, pages 808–815, 2005. [49] J. Zhang and S. Gong. Action categoration with modified hidden conditional random field. Pattern Recognition, 43:197–203, 2010. [50] E. Yu and J. K. Aggarwal. Human action recognition with extremities as semantic posture representation. In Proc CVPR, 2009. [51] W. Li, Z. Zhang, and Z. Liu. Action Recognition Based on A Bag of 3D Points. Computer Vision and Pattern Recognition Workshops (CVPRW), 2010. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/47641 | - |
| dc.description.abstract | 本論文提出一個使用已追踨到之人體關節三維位置的行為辨識的新演算法。本研究使用行為機率圖來模擬動作的動態，利用人體各關節位置的分布當作行為機率圖之訓練特徵藉以描述一個行為內所含有的姿勢。也就是在動作機率圖中的節點。更進一步的，我們也提出了一個階層式行為辨識架構，用來加速辨識的速度以及增進動作的辨識準確率。在我們的階層式架構中，人體可被分成四個部位(也就是左上肢、右上肢、左下肢和右下肢)。我們的想法是提出一個動態指標，用來評估每一個部位移動程度。因此所有的動作可以透過部位移動程度粗略的分成若干類。由實驗結果可得知，動作辨識正確率在未使用階層式架構時約為80%，而使用階層式系統可以超過90%，而在速度方面使用階層式系統可以增進20%的效能。
此外，本研究應用於人偶以及舞者互動之表演，透過深度攝影機以及現有追踨系統取得人體關節的資訊，並且將這些資訊透過我們所提出的系統對動作分析，達到互動的效果。 | zh_TW |
| dc.description.abstract | This study presents an innovative action recognition approach using tracked human body joint locations from a depth sensor with full-body tracking capability. The proposed method encodes actions in a weighted directed action graph to model the kinematics of actions and models distribution of joints to be a set of salient postures that correspond to the nodes in the action graph. In addition, we propose a hierarchical action seeking framework for increasing recognition performance and raising the accuracy rate. In our hierarchical framework, the human body is divided into four parts ( left upper limb, right upper limb, left lower limb, and right lower limb). We propose a motion indicator to evaluate the degree of movement in each human limb, referred to as motion descriptor. Then, the system classifies observed motion into several a specific action clusters using motion descriptor content. Second, we employ a smaller action data set, which is relative to specific motion, to seek the most appropriate action. Experimental results show that about 80% recognition accuracy were gained in non-hierarchical system, and over 90% recognition accuracy were achieved in hierarchical system.
Moreover, we employ the proposed action recognition framework to an interactive performance between an intelligent puppet and actors. In this performance, the puppet is able to realize the meaning of actor’s behavior by our action recognition framework. Thus, the puppet is able to make related action to the actors. Experimental results demonstrate the proposed hierarchical-based action recognition approach reduces the computational cost and increases the accuracy rate. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-15T06:10:11Z (GMT). No. of bitstreams: 1 ntu-100-R98944036-1.pdf: 3815527 bytes, checksum: a9f15c43a8ab7b4c4a2fd2cd98e395d1 (MD5) Previous issue date: 2011 | en |
| dc.description.tableofcontents | 誌謝 i
摘要 ii Abstract iii Contents v List of Figures vii List of Tables ix Chapter 1 Introduction 1 Chapter 2 Related Work 4 2.1 Appearance-Based Representations 4 2.2 Interest-Point-Based Representations 5 2.3 Optical-Flow-Based Representations 5 2.4 Volume-Based Representations 6 2.5 Shape-Based Representations 7 Chapter 3 Action Modeling and Recognition 8 3.1 Graphical Modeling 8 3.2 Pose Extraction and Action Modeling 10 3.2.1 Salient Posture Generation 11 3.2.2 Posture Modeling 13 3.2.3 Action Graph Construction 14 3.3 Action Recognition 15 Chapter 4 Hierarchical Recognition Framework 17 4.1 Hierarchical 17 4.2 Action Encoding 19 4.2.1 Motion Descriptor Evaluation 21 4.2.2 Hierarchical Salient Posture Generation 21 4.2.3 Hierarchical Posture Modeling 22 4.2.4 Hierarchical Action Graph Construction 23 4.3 Hierarchical Action Decoding 25 Chapter 5 Interactive Performance between an Intelligent Puppet and Actors 28 Chapter 6 Experiments 33 Chapter 7 Conclusion 39 Appendix A 40 Bibliography 42 | |
| dc.language.iso | en | |
| dc.subject | 動作機率圖 | zh_TW |
| dc.subject | 動作辨識 | zh_TW |
| dc.subject | 形狀特徵 | zh_TW |
| dc.subject | 顯著姿勢 | zh_TW |
| dc.subject | 動態指標 | zh_TW |
| dc.subject | Action graph | en |
| dc.subject | Shape descriptor | en |
| dc.subject | Motion descriptor | en |
| dc.subject | Salient posture | en |
| dc.subject | Action recognition | en |
| dc.title | 基於追踨三維人體關節結構之動作辨識方法及其應用 | zh_TW |
| dc.title | A Novel Human Action Recognition Approach based on 3D Tracked Body Joints and its Application | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 99-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 石勝文,陳祝嵩 | |
| dc.subject.keyword | 動作辨識,動作機率圖,形狀特徵,顯著姿勢,動態指標, | zh_TW |
| dc.subject.keyword | Action recognition,Action graph,Shape descriptor,Salient posture,Motion descriptor, | en |
| dc.relation.page | 46 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2011-08-19 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
| 顯示於系所單位： | 資訊網路與多媒體研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-100-1.pdf 未授權公開取用 | 3.73 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。