臺灣博碩士論文加值系統

隨著安全需求的提升，智慧型監視系統越來越受到大眾的重視，過去相關的研究中，大部分是針對嚇阻犯罪為主軸的監視系統，主要是辨識具威脅性的事件，一些不具威脅性但需要去協助的事件都會被忽略掉，因此本論文提出了一個新的辨識系統，藉以從公共場所中辨識出需要幫助的事件。
一些事件辨識中，光從單人身上取得的資訊，並不足以當作是辨識的依據，關鍵的資訊，還得由人與人之間的互動關係中取得，因此本研究方法主要分成兩的部份:
(1) 個人行為分析之協助事件辨識
個人行為分析主要是以分析個人身上能取得的特徵作為辨識的依據，系統取出七種特徵: moving trajectory, symmetry shape, principal axis orientation, wave speed, body angle, face orientation and the stooping curve. 經由以上特徵的組合，可以辨識出下以需要協助的事件:走路不穩的人、行動不便的人、盲人。
(2) 人與人關係分析之協助事件辨識
人與人關係分析主要是針對人與周遭人的關係，經由分析一對一的關係(跟從,互動,無互動)和多對一的關係(散開,混合,聚集)來做為協助事件的辨識，經由以上關係，可以辨識出下以需要協助的事件: 無大人陪伴的小孩和身體不適的行人。

As the more security demand increases, the intelligent monitor system has attracted considerable attention in recent years. In the previous related research, much effort is devoted to the detection of threat or dangerous situation. But the security application does not pay attention to the condition when the person is identified as no threat but needs assistance. The thesis proposes a novel intelligent assistance system which can identify if a person needs assistance in public place, for example, disabled, sick people or alone child.
Some kinds of events are solely dependent on the behavior of the target person, however, some other events can not be recognized until the relation between the target person and his neighbors is known. According to requirement of relation of persons, two major approaches are proposed in the research:
(1) Event recognition through analyzing person behavior
The approach detects the behavior of target person by exploiting seven kinds of features: moving trajectory, symmetry shape, principal axis orientation, wave speed, body angle, face orientation and the stooping curve. By computing the different combination of features, the system can identify the assistance events, for example, abnormal gait, the disabled using upholder, and the blind using stick.
(2) Event recognition through analyzing the person relation
The approach analyzes the relation between target person and his neighbors around by evaluating the two modes of relation: one-to-one relation (following, interaction, no_relation) and multiple-to-one relation (scatting, mixing, gathering). The detection results are applicable to recognize if a child has guardian and the sick person.

摘要 4
Abstract 5
List of Figures 6
List of Tables 8
Chapter1 Introduction 9
1.1 Motivation 9
1.2 Related Work 9
1.3 Thesis Overview 10
Chapter2 Feature Extraction 13
2.1 Trajectory Detection 13
2.2 Symmetric Shape Detection 16
2.3 Principal Axis Orientation 17
2.4 Wave Speed Detection 19
2.5 Body Angle Detection 24
2.6 Face Orientation Detection 25
2.6.1 Head detection 25
2.6.2 Face orientation 27
2.7 Stooping Detection 28
Chapter 3 Human Behavior Analysis 31
3.1 Multi-People Tracking 31
3.2 Single Person Behavior Analysis 33
3.2.1 Abnormal Gait Detection 34
3.2.2 Disabled Detection 34
3.2.3 Blind Detection 35
3.2.4 Wheelchair Detection 35
3.3 Multiple persons Behavior Analysis 37
3.3.1 Relation Analysis Between Multiple Persons 38
3.3.2 Alone Child Detection 42
3.3.3 Disturbance Detection 43
Chapter 4 Experimental results 45
4.1 Emergency Score 45
4.2 Experimental Results of Single Behavior Detection 47
4.3 Experimental Results of Multiple Persons Behavior Detection 51
Chapter 5 Conclusions 56
References 58

[1] Chia-Feng Juang and Chia-Ming Chang, ” Human Body Posture Classification by a Neural Fuzzy Network and Home Care System Application”, IEEE Trans. Systems, Man and Cybernetics, Part A, Vol.37, Page(s):984 – 994. Nov. 2007.

[2] R. Cucchiara and C. Grana and A Prati and Vezzani. R, “Probabilistic posture classification for Human-behavior analysis”, IEEE Trans Systems, Man and Cybernetics, Part A, Vol. 35, Page(s):42 – 54. Jan. 2005.

[3] Xinyu Wu and Yongsheng Ou and Huihuan Qian and Yangsheng Xu, “A detection system for human abnormal behavior”, IEEE/RSJ Interational. Conf. Intelligent Robots and Systems, Page(s):1204 – 1208. Aug. 2005.

[4] Chun-Ku Lee and Meng-Fen Ho and Wu-Sheng Wen and Chung-Lin Huang, “Abnormal Event Detection in Video Using N-cut Clustering”, IIH-MSP '06. interational. Conf. Intelligent Information Hiding and Multimedia Signal Processing, Page(s):407 – 410. Dec. 2006.

[5] C. Bauckhage and J.K. Tsotsos and F.E. Bunn, “Detecting abnormal gait”, The 2nd Canadian Conf. Computer and Robot Vision, Proceedings, Page(s):282 – 288. May 2005.

[6] Liang Wang, “Abnormal Walking Gait Analysis Using Silhouette-Masked Flow Histograms”, ICPR. 18th International Conf. Pattern Recognition, Vol. 3, Page(s):473 – 476. 2006.

[7] Duan-Yu Chen and H.-Y.M. Liao and Sheng-Wen Shih, “Continuous Human Action Segmentation and Recognition Using a Spatio-Temporal Probabilistic Framework”, IEEE International Symposium, Multimedia, Page(s):275 – 282. Dec. 2006.

[8] A. Adam and E. Rivlin and I. Shimshoni and D. Reinitz, “Robust Real-Time Unusual Event Detection using Multiple Fixed-Location Monitors”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 30. Page(s):555 – 560. March 2008.

[9] Zhou Hanning and D. Kimber, “Unusual Event Detection via Multi-camera Video Mining”, ICPR. 18th International Conf. Pattern Recognition, Vol. 3. Page(s):1161 – 1166. 2006.

[10] C. Garcia and G. Tziritas. ” Face detection using quantized skin color regions merging and wavelet packet analysis”. IEEE Transactions on Multimedia, Vol. 1, Page(s):264 – 277. Sept. 1999.

[11] P.C. Correa Hernandez and J. Czyz and F. Marques and T. Umeda and X. Marichal and B. Macq, “Bayesian Approach for Morphology-Based 2-D Human Motion Capture”, IEEE Trans. Multimedia, Page(s):754 – 765. June 2007.

[12] O. Boiman and M. Irani “Detecting irregularities in images and in video”. Tenth IEEE International Conf. computer vision, Page(s):462 – 469. Oct. 2005.

[13] Duan-Yu Chen and Sheng-Wen Shih and H.-Y.M. Liao, “Human Action Recognition Using 2-D Spatio-Temporal Templates”. IEEE International Conf. Multimedia and Expo, Page(s):667 – 670. July 2007.

[14] Linda G. Shapiro and George C. Stockman. ”Computer vision”.2001 by Prentice-Hall,Inc.

[15] Jaroslav Borovicka, “Circle Detection Using Hough Transforms Documentation”, COMS30121, Image Process and Computer Vision.

[16] I. Haritaoglu and D. Harwood and L.S. Davis, ” W4: real-time surveillance of people and their activities”. IEEE Tran. Pattern Analysis and Machine Intelligence, Vol. 22. Issue 8. Page(s):809 – 830. Aug. 2000.