簡易檢索 / 詳目顯示

回結果列表
研究生： 鄭明旭
Ming-Hsu Cheng
論文名稱： 利用流形學習與隱藏式馬可夫模型做步態分析用以鑑別身分
Gait Analysis for Human Identification through Manifold Learning and HMM
指導教授： 黃仲陵
Chung-Lin Huang
口試委員:
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 電機工程學系
Department of Electrical Engineering
論文出版年： 2006
畢業學年度： 94
語文別： 英文
論文頁數： 64
中文關鍵詞： 身分鑑別 、非線性 、馬可夫模型 、流形學習
外文關鍵詞： MANIFOLD, ISOMAP, HMM, GP-LVM
相關次數： 點閱：1  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

    • 視覺監控系統可以被應用在許多場合，如機場、銀行、學校等，運用電腦視覺的技術，可以幫助使用者分析一些行為。視覺監控系統的目的是希望能夠分析，分類且進一步達到辨識觀測物體功能，尤其是在911攻擊後，有許多研究是有關於視覺監控系統。遠距離的身分鑑別系統在近年來也吸引人們許多注意。步態辨識是利用每個人的獨特走路方式來進行身鑑別。與其它人體生物特徵相比，萃取人的步伐不需要太精密的攝影設備，而且人的步伐提供我們可以在較遠的距離下進行身份辨識，這點是其他生物特徵無法提供的，而且也不需要使用者的互動，讓辨識的過程更簡單與方便。本篇論文提出了一個利用步伐剪影來實現路徑及身份的多重辨識用系統，首先目標物的路徑方向會先被偵測出，之後再對目標物進行身份辨識。我們會利用機率模型將前景與背景做分割，產生出乾淨的剪影。由於步伐動作是一種非線性的行為，所以我們也會利用一些例子說明非線性降維方法處理後的效果比線性佳。步伐剪影被非線性的轉換到維度較低空間並利用高斯機率對低維度空間分類，而在時間上步伐剪影的變化也會對印在低維度空間上高斯機率的轉移，因此我們可以利用隱藏式馬可夫模型來幫助我們進行訓練與身份辨識，實驗結果顯示所提出的系統架構可以有效率的鑑別身份。

    With the increasing demands of visual surveillance systems, human identification at a distance has recently gained more interest. Gait recognition is a process of identifying individuals by the way they walk, which is often used as a unobstrusive biometric offering the possibility to identify people at a distance without any interaction or co-operation with the subject. This thesis has presents a novel effectively method for both automatic viewpoint and person identification using only the silhouette sequence of gait. The gait silhouettes are nonlinearly transformed into low dimensional embedding and the dynamics in time-series images are modeled by HMM in the corresponding embedding space. The experimental results will demonstrate that the proposed algorithm is an encouraging progress for the research of human identification.

    Chapter 1. Introduction 1 1.1 Motivation of gait recognition 1 1.2 Related work 2 1.3 System overview 4 Chapter 2. Human Object Segmentation 7 2.1 Background modeling 7 2.2 Shadows removal 8 2.3 Silhouette segmentation 9 2.4 The results of human segmentation 10 2.5 Silhouette representation 11 Chapter 3. Nonlinear Dimension Reduction Methods 14 3.1 Dimension reductions 14 3.2 Nonlinearity of human activities 15 3.3 Nonlinear dimension reduction methods 16 3.4 The ISOMAP algorithm 17 3.5 Experiment Results using ISOMAP, PCA and MDS 21 3.5.1 Experiment 1: Swiss roll data 21 3.5.2 Experiment 2: human gait silhouette in path 1 22 3.5.3 Experiment 3: human gait silhouette in path 2 24 3.5.4 Experiment 4: human gait silhouette in path 3 27 3.6 Problems of nonlinear dimension methods 29 3.7 Gaussian Process Latent Variable Model 29 3.7.1 Kernel matrix of GP-LVM 29 3.7.2 GP-LVM learning 30 3.7.3 The sparsification of GP-LVM 31 3.7.4 The latent variable optimization of GP-LVM 31 Chapter 4. Identification of Human ID in Multiple Paths through GP-LVM and HMMs 35 4.1 Employment of GP-LVM for new input gait shapes 36 4.1.1 GP-LVM training for gait classification 36 4.1.2 GP-LVM testing for gait classification 37 4.1.3 Using the characteristic of GP-LVM for new input silhouette 39 4.2 The Hidden Markov Model 40 4.2.1 Basic concept of Hidden Markov Models 41 4.2.2 Elements of HMMs 41 4.2.3 HMM learning 42 4.2.4 HMM identifying 43 4.3 Implementation of GP-LVM and HMM as the learning procedure 43 4.3.1 The training data set for leaning 43 4.3.2 The learning procedure using GP-LVM for identifying 45 4.3.3 The learning procedure using HMM for identifying 46 Chapter 5. Experiment Results of Gait recognition 49 5.1 Experiment 1: Walking Path Recognition 51 5.2 Experiment 2: Human ID Recognition 52 5.3 Experiment 3: Human ID recognition using NLPR gait database 54 5.4 Experiment 4: Human ID recognition using SOTON gait database 57 Chapter 6. Conclusion and Future Work 60 References 61

    1) T. Horprasert, D. Harwood, and L. S. Davis, “A robust background subtraction and shadow detection”, 4th Asian Conf. on Computer Vision, Taipei, Taiwan, pp. 983-988, 2000.
    2) Elgammal, A., Duraiswami, R., Harwood, D., and Davis, L.S. “Background and Foreground Modeling Using Nonparametric Kernel Density Estimation for Visual Surveillance”, Proc. of the IEEE, vol. 90, 2002.
    3) Liang Wang, Huazhong Ning, Tieniu Tan and Weiming Hu, “Fusion of static and dynamic body biometrics for gait recognition”, Proc. of the NinthIEEE Int. Conf. On Computer Vision, pp.1449-1454, 2003.
    4) L. Lee and W. E. L. Grimson, “Gait analysis for recognition and classification,” in Proc. IEEE Conf. Face and Gesture Recognition, 2002, pp.155–161
    5) D. Cunado, M. S. Nixon, and J. N. Carter, “Using gait as a biometric, via phase-weighted magnitude spectra,” in Proc. 1st Int. Conf. Audio- and Video-Based Biometric Person Authentication, 1997, pp. 95–102.
    6) P. J. Phillips, S. Sarkar, I. Robledo, P. Grother, and K. W. Bowyer, . “The gait identification challenge problem: Data sets and baseline algorithm”,. in International Conference on Pattern Recognition, August 2002.
    7) Y. Liu, R. Collins, and Y. Tsin, . “Gait Sequence Analysis using Frieze Patterns”,. in European Conference on Computer Vision, Copenhagen, May 2002.
    8) C. BenAbdelkader, R. Culter, H. Nanda, and L. Davis, “EigenGait: Motion-Based Recognition of People Using Image Self-Similarity,” Proc. Int’l Conf. Audio- and Video-Based Biometric Person Authentication, pp. 284-294, 2001.
    9) L. Wang, T. Tan, H. Ning, and W. Hu, . “Silhouette Analysis-based Gait Recognition for Human Identification”,. IEEE Trans. Pattern Anal. and Mach. Intell., vol. 25, no. 12, pp. 1505.1518, Dec. 2003
    10) R. Collins, R. Gross, and J. Shi, “Silhouette-based human identification from body shape and gait”, in Proc. Int. Conf. Automatic Face and Gesture Recognition, 2002, pp. 366–371.
    11) N.V. Boulgouris, K.N. Plataniotis, and D. Hatzinakos, “An angular transform of gait sequences for gait assisted recognition,” in Proc. IEEE Int. Conf. Image Processing, Singapore, Oct. 2004, pp. 857–860.
    12) L.Wang, T. Tan,W. Hu, and H. Ning, “Automatic gait recognition based on statistical shape analysis,” IEEE Trans. Image Processing, vol. 12, pp. 1120–1131, Sept. 2003.
    13) I. T. Jolliffe, “Principal Component Analysis”. Springer-Verlag, 1986.
    14) A. Elgammal “Nonlinear Generative Models for Dynamic Shape and Dynamic Appearance”, 2nd International Workshop on Generative-Model based vision. GMBV 2004, Washington DC, USA, June 2004 in association with CVPR04
    15) T. Cox and M. Cox, “Multidimentional scaling”. Chapman & Hall, 1994.
    16) C. Bregler and S. M. Omohundro. “Nonlinear manifold learning for visual speech recognition”. In ICCV, 1995.
    17) K. Toyama and A. Blake. “Probabilistic tracking in a metric space”. In ICCV, pages 50–59, 2001.
    18) J. B. Tenenbaum, de Silva, V.& Langford, J.C, “A global geometric framework for nonlinear dimensionality reduction”, Science, 2000, 290, pp. 2319-2323
    19) S. T. Roweis, and K. S. Lawrance, “Nonlinear Dimensionality reduction by locally linear embedding”, Science, 2000, 290, pp. 2323-2326
    20) Douglas Fidaleo and M. Trivedi, “Manifold analysis of facial gestures for face recognition”. In ACM SIGMM Multimedia Biometrics Methods and Application Workshop, Nov. 8, 2003.
    21) Tian, T., Li, R., Sclaroff, S. “Articulated pose estimation in a learned smooth space of feasible solutions”. CVPR Learning Workshop, San Diego, 2005
    22) Thomas H. Cormen, Charles E. Leirserson, Ronald R. Livest, Introduction to Algorithms, Floyd-Warshall Algorithm, The MIT Press, Cambridge, Massachusetts, pages 558-565, 1997
    23) Thomas H. Cormen, Charles E. Leirserson, Ronald R. Livest, Introduction to Algorithms, Dijkstra’s Algorithm, The MIT Press, Cambridge, Massachusetts, pages 527-532, 1997
    24) N. Lawrence. “Probabilistic non-linear principal component analysis with Gaussian Process Latent Variable Models”. Technical Report CS-04-8, Dept. of Computer Science, Univ. of Sheffield, 2004.
    25) Neil D. Lawrence, Matthias Seeger, and Ralf Herbrich. Fast sparse Gaussian process methods: The informative vector machine. In Sue Becker, Sebastian Thrun, and Klaus Obermayer, editors, Advances in Neural Information Processing Systems, volume 15, pages 625–632, Cambridge, MA, 2003. MIT Press.
    26) C. Williams. Prediction with Gaussian processes: From linear regression to linear prediction and beyond. In M. Jordan, editor, Learning Graphical Models, volume 89 of Series D: Behavioural and Social Sciences. Kluwer, 1998.
    27) K. Grochow, S., L. Martin, A. Hertzmann, and Z. Popovic. Style-Based Inverse Kinematics. In ACM Computer Graphics (SIGGRAPH), 2004.
    28) Rabiner, L. R., A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition, Proceedings of the IEEE, vol. 77, no. 2, Feb. 1989, pgs 257 - 285. There is a lot of notation but verbose explanations accompany.
    29) J. Shutler,M. Nixon, and C. Harris, “Statistical gait recognition via temporal moments,” in Proc. 4th IEEE Southwest Symp. Image Analysis and Interpretation, 2000, pp. 291–295.
    30) J. B. Hayfron-Acquah, M. S. Nixon, and J. N. Carter, “Automatic gait recognition by symmetry analysis,” in Proc. 3rd Int. Conf. Audio- and Video-Based Biometric Person Authentication, 2001, pp. 272–277.
    31) J. Foster, M. Nixon, and A. Prugel-Bennett, “New area based metrics for gait recognition,” in Proc. 3rd Int. Conf. Audio- and Video-Based Biometric Person Authentication, 2001, pp. 312–317.

    無法下載圖示 全文公開日期 本全文未授權公開 (校內網路)
    全文公開日期 本全文未授權公開 (校外網路)

    QR CODE