運用輪廓分析對人行為模式辨識之研究｜國立臺灣科技大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	江龍興 Lung-Hsing Chiang
論文名稱：	運用輪廓分析對人行為模式辨識之研究 Silhouette Analysis for Human Behavior Recognition
指導教授：	陳郁堂 Yie-tarng Chen
口試委員:	陳省隆 Hsing-lung Chen 吳乾彌 Chen-mie Wu 林銘波 Ming-bo Lin 方文賢 Wun-hsien Fang
學位類別：	碩士 Master
系所名稱：	電資學院 - 電子工程系 Department of Electronic and Computer Engineering
論文出版年：	2010
畢業學年度：	98
語文別：	中文
論文頁數：	56
中文關鍵詞：	行為辨識、骨架萃取、彈型模型
外文關鍵詞：	human skeleton extraction, Elastic model, human behavior analysis
相關次數：	點閱：238 下載：2
分享至:	分享至facebook 分享至twitter

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

人體骨架的萃取與型態的比對，在監視系統是兩個很重要的議題。在我們的研究中，我們發展了一個新的骨架萃取的方法，並且使用這個方法去做跌倒的偵測。在型態比對的方面，我們利用動態彈性比對(Dynamic elastic matching)，解決這樣的問題。動態彈性比對，是使用遞迴的方式，逐漸將一個型態的序列轉換成另外一個序列。我們利用了在網路上常使用的步伐資料庫(Gait database)，並且進行了一系列的實驗，去驗證我們所使用的方法。實驗結果顯示，在偵測率方面相較於目前普遍使用的方法來的好，但在時間複雜度方面，比其他的方法來的高。

Human skeleton extraction and matching shape sequences from video are important issues in visual surveillance. In this research, we propose a novel human skeleton extraction scheme and apply this scheme to human fall detection scheme. On matching shape sequences, we investigate the dynamic elastic matching to solve this issue. The dynamic elastic matching is an iterative technique for gradually transforming of two shape sequences. We conduct intensive experiments to verify the proposed schemes based on the public domain gait database. The experimental results show that the dynamic elastic matching yield satisfactory performance in the detection rate in comparison with the state of the art approaches at the expense of high computational costs.

摘要	I
Abstract	II
致謝	III
Contents	IV
List of Figures	VI
List of Tables	VII
Chapter 1 Introduction	1
1.1 Objective of this Research:	3
1.2 Summary of the proposed approaches	3
1.3 Contributions	4
Chapter 2 Related Works	6
2.1 Human Skelton Extraction	6
2.1.1 Skeleton extraction based on Delaunay triangulation	6
2.1.2 The Star Skeleton Extraction:	9
2.2 Boundary Matching	10
2.3 Similarity Measure	10
Chapter 3 Human Skeleton Extraction	11
3.1 Feature Point Selection	11
3.2 Feature Point Estimation	12
3.2.1 Head and Limb Estimation	13
3.2.2 Joint Point Estimation	16
3.2.3 Torso Point Estimation	20
3.3 Rules for Human Skeleton Construction	20
3.4. Distance Map of a Human Skeleton	23
3.5 A Novel Hybrid Human Fall Detection Scheme	25
3.5.1 Fall-Down Confirmation	26
Chapter 4 EXPERIMENTAL RESULTS I	27
4.1 Experimental Results of Human Falling Detection	28
4.2 Experimental Results for Human Posture Recognition	31
Chapter 5 Dynamic Elastic Matching	35
5.1 Shape sequence representation	35
5.2 Similarity measure between line segments	36
5.3 Compute the displacement vector	39
5.4 Determine the force field	39
5.5 Iterative Matching and Correspondence	40
5.6 Correspondence and Distance Measure in Gait Recognition	41
Chapter 6 Experimental Results II	42
6.1 Performance Comparison between Different Approaches	42
6.2 Experimental Results for Human Posture Recognition under Different Views	46
Chapter 7 Conclusions	52
REFERENCE	54

                                

[1] A. D. Bimbo and P. Pala, “Visual Image Retrieval by Elastic Matching of User Sketches,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 2, pp. 121-132, February 1997.
[2] Bobick A. and Davis J., 2001, ”The Recognition of Human Movement Using Temporal Template," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 3, pp. 257 - 267.
[3] Borgefors Gunilla, 1986, ”Distance Transformations in Digital Images," Computer Vision, Graphics, and Image Processing, Volume 34, No. 3, Pages 344-371.
[4] Bradski, G. R. and Kaeher, A., 2008, Learning OpenCV: Computer Vision with OpenCV Library, O’Reilly Media, Inc., Sebastopol, CA, USA.
[5] “CASIA Gait Database,” [online] Available: http://www.cbsr.ia.ac.cn/english/Gait Databases.asp

[6] Chew L. P., 1987, ”Constrained Delaunay Triangulations," ACM Proceedings of Third Annual Symposium on Computational Geometry, , pp. 215-222, Waterloo, Ontario, Canada.
[7] D. J. Burr, “A Dynamic Model for Image Registration,” Proceedings IEEE Computer Socity Conference Pattern Recognition and Image Processing, Chicago, pp. 17-24, August 1979.
[8] D. J. Burr, “Elastic Matching of Line Drawings,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-3, no. 6, pp. 708-713, November 1981.
[9] Douglas David and Peucker Thomas, 1973, ”Algorithms for The Reduction of The Number of Points Required to Represent A Digitized Line or Its Caricature," The Canadian Cartographer, Vol.10, No. 2, pp. 112-122.
[10] H. Fujiyoshi and A. J. Lipton, ”Real-time Human Motion Analysis by Image Skeletonization,” Proceedings of the Fourth IEEE Workshop on Applications of Computer Vision, pp. 15-21, 1998.
[11] Hsu Y. T., Liao H. Y. M., and Chen C. C., Hsieh J. W., 2008, ”Video-based Human Movement Analysis and Its Application to Surveillance Systems," IEEE Transactions on Multimedia, Vol. 10, No. 3, pp. 372-392.

[12]

Huang W., Gu I. Y. H., and Li Q. Tian L., 2003, ”Foreground Object Detection from Videos Containing Complex Background," Proceedings of the Eleventh ACM International Conference on Multimedia, pp.2 - 10, Berkeley, CA, USA.
[13] Lin Chia-Wen, Ling Zhi-Hong, Cheng-Yeng, and Kuo Chung J., 2007, “Compressed-domain Fall Incident Detection for Intelligent Homecare," Journal of VLSI Signal Processing System, Vol. 49, No. 3, pp. 393 - 408.
[14] Lindemann U., Hock A., and Stuber, M., 2005, ”Evaluation of A Fall Detector Based on Accelerometers: A Pilot Study," Medical and Biological Engineering and Computing, Vol. 43, No. 5, pp. 548 - 551.
[15] Lena Gorelick, Moshe Blank, Eli Shechtman, and Michal. Weizmann dataset. [Online]. http://www.wisdom.weizmann.ac.il/~vision/SpaceTimeActions.html

[16] Pratt Willam, 2007, Digital Image Processing, 4th ed., John Wiley and Sons, Ltd., New York, USA.
[17] S. Y. Chen, W. C. Lin, C. C. Liang and C. T. Chen, “Improvement on Dynamic Elastic Interpolation Technique for Reconstructing 3-D Objects from Serial Cross Sections,” IEEE Transactions on Medical Image, vol. 9, no. 1, pp. 71-83 , March 1990.
[18] Y. Gdalyahu and D. Weinshall, “Flexible Syntactic Matching of Curves and Its Application to Automatic Hierarchical Classification of Silhouettes,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 12, pp. 1312-1328, December 1999.

簡易檢索 / 詳目顯示

相關論文