![]() |
|
以作者查詢圖書館館藏 、以作者查詢臺灣博碩士 、以作者查詢全國書目 、勘誤回報 、線上人數:32 、訪客IP:18.223.107.178
姓名 鄭建宏(CHIEN-HUNG CHENG) 查詢紙本館藏 畢業系所 資訊工程學系 論文名稱 光流特徵應用於走勢辨認
(Human Gait Classification using Optical Flow Features)相關論文 檔案 [Endnote RIS 格式]
[Bibtex 格式]
[相關文章]
[文章引用]
[完整記錄]
[館藏目錄]
[檢視]
[下載]
- 本電子論文使用權限為同意立即開放。
- 已達開放權限電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。
- 請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
摘要(中) 在圖形識別研究領域中,有許多身份認證的應用,諸如臉部辨識、掌紋辨識、虹膜
辨識以及簽名辨識等等,走勢辨識相對於其他辨識系統來說,是比較方便且人性化
的,它不需要額外的特殊儀器,所需要的設備僅需要一台攝影機,同時測試者也不
必停下來做指定的動作,只需要從架設好的環境經過,即可辨識出他的身份。在近
年來監視攝影機普遍的環境下,走勢辨識能夠更有效的去利用監控系統。本篇論文
提出以光流當作特徵資訊的系統架構,實做三種不同的光流演算法,並且透過多樣
化的測試,來分析與討論其優缺點。
我們所提出的系統流程分別如下,首先將輸入的走勢影像轉換成灰階色彩空
間,經過光流演算法的計算,取得光流資訊,先大略捨去掉強度較弱的雜訊,使用
高斯模型(GM)來逼近光流的分佈,推算出移動物的實際位置,以這個範圍為基準,
將光流資訊以強度和角度的表示,建立出二維直方統計圖,並且根據每個人走勢的
運動週期來做特徵資訊的正規劃,最後將特徵資訊經過主成份分析(PCA)和線性辨
別分析(LDA)後,以k-nn分類器來取得辨識結果。
我們利用CASIA走勢資料庫以及自己所錄製的資料庫來驗證我們系統的可行
性,其中包含測試系統對於衣著改變以及攝影機距離的影響,經由實驗結果證實,
即使每個人的走勢不見得會有顯著的差異,以走勢資訊當作特徵確實可以解決身份
認證的問題。此外,即便我們所提出的系統架構僅使用光流資訊作為特徵,其辨識
率也能夠和以輪廓為特徵的方法結果不相上下。最後,針對實驗結果我們加以分析
及討論,歸納並提出可能的改進方向。
摘要(英) Gait classification is an effective and non-intrusive way for human identity identification on the research field of pattern recognition. The required device that we need is a camera, subjects just walk through the hallway naturally and the system can recognize their identity automatically. Recently, surveillance cameras are installed almost
everywhere. Gait classification can be used effectively in detecting illegal intruders without installing extra equipments. In this thesis, we adopt optical flow information as the basic features of gait. Three kinds of optical flow algorithms are manipulated on our proposed system and a variety of testing, analyses and discussions are made to highlight the experiment results. We test and verify that the optical flow information is really working not only on moving object detection and tracking but also on the complex problem of gait classification.
In our work, we first transform the input color image to gray level space. Then, employ optical flow algorithm to get the optical flow field. Some optical flow information on which intensity values are too small are removed and then Gaussian Model (GM) is employed to model the strong intensity information of optical flow. The locations of foreground objects (gait human) are extracted according to the mean and covariance of GM. After that, we adopt flows to construct feature histograms which belong to the bounding box. Since gait cycles are different with each subject, we apply the histogram matching method to normalize each video feature. Next, Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) are performed to reduce the feature dimension and find the best projection axis, respectively. Finally, k-Nearest Neighbor (k-NN) classifier is adopted to get the recognition result.
Through experimental analysis, we find that gait is a very effective feature to classify human’s identity even though the differences of walking postures between different persons are hard to observe. Although the accuracy of optical flow information is doubtful, we proved that optical flow information is useful for gait classification problem. In this thesis, we adopt optical flow information only and do not consider shape features or other information. Moreover, experimental results demonstrate that the
proposed framework contribute as good recognition rates as the contour-based approach in CASIA and our own database.
關鍵字(中) ★ 走勢辨認
★ 光流演算法關鍵字(英) ★ gait classification
★ optical flow論文目次 摘要 I
Abstract II
Content i
List of Figures ii
List of Tables v
Chapter 1. Introduction 1
Chapter 2. Related Work 3
Chapter 3. Gait Classification Proposed Method 6
3.1. System Overview 6
3.2. Optical Flow 7
3.2.1. Horn-Schunck optical flow: 8
3.2.2. Lucas-Kanade optical flow: 10
3.2.3. Multi-Frame optical flow: 11
3.3. Moving Object Detection 15
3.4. Histogram Construction 17
3.5. Gait Cycle Extraction 19
3.6. Principle Component Analysis 20
3.7. Fisher Linear Discriminant 22
Chapter 4. Experiments 26
Chapter 5. Discussions and Conclusions 53
Reference 55
參考文獻 [1] B.K.P Horn and B.G. Schunck, “Determining optical flow”, AI, vol. 71 no. 17, pp. 185-204, 1981
[2] B.D. Lucas, “Generalized Image Matching by the Method of Differences”, PhD Dissertation, Dept. of Computer Science, Carnegie-Mellon University, 1984
[3] B. Lucas and T. Kanade, ”An iterative image registration technique with an application to stereo vision”, Proc. DARPA IU Workshop, pp. 121-130, 1981
[4] Chia-Ming Wang, Kuo-Chin Fan, and Cheng-Tzu Wang, “Estimating Optical Flow by Integrating Multi-Frame Information,” Journal of Information Science and Engineering, Vol. 24, No. 6, pp. 1719-1731, November 2008
[5] Chinese Academy of Sciences, Institute of Automation Gait Database
[6] D.M. Gavrila, “The Visual Analysis of Human Movement: A survey”, Computer Vision Image Understanding, vol. 73, No.1, pp. 82-98, 1999
[7] J.K. Aggarwal and Q. Cai, “Human Motion Analysis: a Review”, Computer Vision and Image Understanding, vol. 73, no.3, pp.428-440, 1999
[8] Shanon X. Ju, Michael J. Black, Yaser Yacoob, “Cardboard People: A parameterized Model of Articulated Image Motion”, Second IEEE International Conference on Face and Gesture Analysis, pp. 38, 1996
[9] Hironobu Fujiyoshi, Alan J. Lipton and Takeo Kanade “Real-Time Human motion Analysis by Image Skeletionization”, IEICE TRANS. INF. & SYST., vol. E87-D, no. 1, 2004
[10] C. Wren, A. Azarbayejani, T. Darrell and A. Pentland, “Pfinder Real-Time Tracking of Human Body”, IEEE Transitions on Pattern Analysis and Machine Intelligence, vol. 19, No. 7, pp. 780-785, 1997
[11] Heba Lakany, “Extracting a diagtnostic gait signature”, Pattern Recognition, vol. 41, no. 5, pp. 1627-1637, 2008
[12] Min-Hsu Cheng, Meng-Fen Hoa, Chung-Lin Huanga, “Gait analysis for human identification through manifold learning and HMM”, Pattern Recognition, vol. 41, no. 8, pp. 2541-2553, 2008.
[13] Simon Denman, Vinod Chandran and Sridha Sridharan, “An adaptive optical flow technique for person tracking systems”, Pattern Recognition Letters, vol. 28, pp. 1232-1239, 2007
[14] Zhen Jia, Arjuna Balasuriya and Subhash Challa, “Vision based data fusion for autonomous vehicles target tracking using interacting multiple dynamic models”, Computer Vision and Image Understanding, vol. 109, pp. 1-21, 2006
[15] Fatemeh Karimi Nejadasl, Ben G.H. Gorte and Serge P. Hoogendoorn, “Optical flow based vehicle tracking strengthened by statistical decisions”, ISPRS Jornal of PHOTOGRAMMETRY & REMOTE SENSING, vol. 61, pp. 159-169, 2006
[16] Suchendra M. Bhandarkar and Xingzhi Luo, “Integrated detection and tracking of multiple faces using particle filtering and optical flow-based elastic matching”, Computer Vision and Image Understanding, vol. 113, pp. 708-725, 2009
[17] Alireza Fathi, Greg Mori, “Action Recognition by Learning Mid-level Motion Features”, IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2008
[18] James J. Little, Jeffrey E. Boyd, “Recognition People by Their Gait: The Shape of Motion”, Videre : Journal of Computer Vision Research, vol. 1, no. 2, 1998
[19] Mohiuddin Ahmad, Seong-Whan Lee, “Human action recognition using shape and CLG-motion flow from multi-view image sequences”, Pattern Recognition, vol. 41, pp. 2237-2252, 2008
[20] Jolliffe, I. T., “Principal Component Analysis.”, Springer-Verlag, pp. 487, 1986
[21] Fisher, R. A., “The use of Multiple Measurements in Taxonomic Problems”, Annals of Eugenics, vol. 7, pp. 179-188, 1936
[22] Erhu Zhang, Yongwei Zhao, Wei Xiong, “Active energy image plus 2DLPP for gait recognition”, Signal Processing, vol. 90, pp. 2295-2302, 2010
[23] http://www.toshibadirect.com/
[24] http://www.willowtechnology.com/
指導教授 范國清、余執彰
(Kuo-Chin Fan、Chih-Chang Yu)審核日期 2010-7-19 推文 plurk
funp
live
udn
HD
myshare
netvibes
friend
youpush
delicious
baidu
網路書籤 Google bookmarks
del.icio.us
hemidemi
myshare