Responsive image
博碩士論文 etd-0115113-120355 詳細資訊
Title page for etd-0115113-120355
論文名稱
Title
使用分散式智慧攝影機偵測人群異常事件
Using Distributed Smart Cameras to Detect Abnormal Events among a Crowd of People
系所名稱
Department
畢業學年期
Year, semester
語文別
Language
學位類別
Degree
頁數
Number of pages
91
研究生
Author
指導教授
Advisor
召集委員
Convenor
口試委員
Advisory Committee
口試日期
Date of Exam
2011-07-29
繳交日期
Date of Submission
2013-01-15
關鍵字
Keywords
人類行為辨識、透視投影法、支撐向量機、影像監控系統、分散式智慧攝影機、行人辨識
Human behaviors recognition, Perspective projection, Video surveillance systems, Distributed smart cameras, Pedestrian detection, Support vector machines
統計
Statistics
本論文已被瀏覽 5877 次,被下載 1300
The thesis/dissertation has been browsed 5877 times, has been downloaded 1300 times.
中文摘要
現在的社會越來越依賴影像監控系統,街道上或者建築物內,都會佈置許多的攝影機,有了這些攝影機可以幫助人們達成人員出入的管理,貴重財物的監控,犯罪行為的搜證,交通流量的管制,管理人員只需要坐在監控中心就可以同時控管許多地方。但是攝影機的佈置並不是沒有上限的,往往受限於系統的影像傳輸頻寬,監控人員的負荷範圍。因此最新的影像監控系統開始引進影像辨識的技術,來輔助監控人員快速地注意追蹤目標。最新影像辨識研究之一是行人影像辨識,系統有了行人辨識的能力,就可以進一步去分析人類的行為,讓電腦可以了解監控區域內的人們正在做什麼,如此電腦可以即時地提供資訊和支援。過去文獻研究往往透過分析人類的所在位置,使用什麼設備的背景資料來辨識人類行為,但是這只限於家庭和辦公室等室內空間,開放的公共空間缺乏以上環境資訊內容,這樣的行為辨識方法便無法作用。此外相同的事件每個人的反應動作並不會一致,要從單一個人的動作行為來了解發生什麼異常事件,勢必會發生許多問題,如果能從一群人的行為特徵中,發現可供分析的一致性行為模式,便可以解決以上的問題。本研究設計一個分散式智慧攝影機系統,可以避免監控系統在擴充上所會遭遇的瓶頸,可以有效地利用人群行為來辨識出所發生的異常事件,幫助監控人員做出即時的處理反應,透過分散式智慧攝影機的互相合作,克服影像監控的常發生的偵測阻擋和死角問題,提升系統在事件辨識上的可靠性和穩定度。
Abstract
Modern society relies on surveillance system more and more. On the streets or in the buildings, there are many cameras which are installed to help people accomplish access management, valuables monitor, and traffic flow control. The monitoring staff can just stay in the monitoring center, but able to see to multiple places simultaneously. However, the number of deployed cameras is not unlimited. It depends on bandwidth and users' loading. The latest video surveillance systems tend to apply image recognition technology to assist the monitoring staff. One of the latest image recognitions is pedestrian detection that detects people in the pictures or videos. If the system is able to figure out the image of humans, it may analyze human's behaviors in advance. The computers, therefore, can provide relevant information to the monitoring staff immediately. The previous surveys tended to analyze the user context, such as human’s location and action. But it can only be used in indoor space, rather than the public space that needs more environmental context to identify human behaviors. The identification of human behavior is useful for event detection, especially when the patterns of behaviors in a crowd of people can be classified. This can help the monitoring staff to take action to abnormal events in time. This study designs a distributed smart cameras system coupled with a machine learning technique to detect abnormal events by analyzing behaviors among a crowd of people. Moreover, this system includes a camera collaboration strategy to overcome the recurrent problems in video surveillances, such as the occlusion and blind visions. It confirms the reliability and stability of the proposed system in event recognition.
目次 Table of Contents
誌 謝 ii
摘 要 iii
Abstract iv
第 一 章 緒論 1
1.1 研究背景 1
1.2 研究動機 5
1.3 研究問題與目的 6
1.4 研究流程 7
第 二 章 文獻探討 8
2.1 行人辨識(Pedestrian Detection) 8
2.1.1 方向梯度直方圖辨識方法(Histogram of Oriented Gradients based Detector) 8
2.2 分散式智慧攝影機(Distributed Smart Cameras) 10
2.3 事件樣式辨識方法(Event Pattern Recognition Methods) 15
2.4 支撐向量機(Support Vector Machine) 18
第 三 章 研究架構 23
第 四 章 研究方法 26
4.1 研究問題定義 26
4.2 環境假設 28
4.3 系統設計 29
4.3.1 影像監控系統架構 29
4.3.2 智慧攝影機運作架構 30
4.4 系統問題與解決方法 32
4.4.1 行人特徵萃取 32
4.4.2 資料處理 34
4.4.3 時序特徵資料建立 37
4.4.4 特徵編碼 39
4.4.5 智慧攝影機協同合作機制 41
4.4.6 事件行為辨識 46
4.4.7 攝影機故障後覆蓋缺口修正 48
第 五 章 實驗與結果 52
5.1 實驗環境 52
5.2 事件行為模擬 52
5.3 實驗 57
5.3.1 不同混合比率實驗 58
5.3.2 不同人數編碼實驗 62
5.3.3 不同比例缺失值實驗 63
5.3.4 不足人數補值型態實驗 65
5.3.5 多事件行為辨識實驗 68
5.3.6 分散式合作與決策實驗 71
第 六 章 結論與未來研究 75
6.1 結論 75
6.2 未來研究 75
第 七 章 參考文獻 77
參考文獻 References
[1] S. Fleck, et al., "Smart Camera Based Monitoring System and Its Application to Assisted Living," Proceedings of the IEEE, vol. 96, pp. 1698-1714, 2008.
[2] Gero, et al., "Survey of Pedestrian Detection for Advanced Driver Assistance Systems," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 32, pp. 1239-1258, 2010.
[3] T. Heinrich, "Bewertung Von Technischen Masnahmen zum Fusga‥ngerschutz am Kraftfahrzeug," Technische Univ, Berlin, technical report2003.
[4] N. Dalal, et al., "Human Detection Using Oriented Histograms of Flow and Appearance," Computer Vision – ECCV 2006. vol. 3952, A. Leonardis, et al., Eds., ed: Springer Berlin / Heidelberg, 2006, pp. 428-441.
[5] Z. Qiang, et al., "Fast Human Detection Using a Cascade of Histograms of Oriented Gradients," Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, 2006, pp. 1491-1498.
[6] P. Viola, et al., "Detecting Pedestrians Using Patterns of Motion and Appearance," International Journal of Computer Vision, vol. 63, pp. 153-161, 2005.
[7] D. Lymberopoulos, et al., "Macroscopic Human Behavior Interpretation Using Distributed Imager and Other Sensors," Proceedings of the IEEE, vol. 96, pp. 1657-1677, 2008.
[8] O. Brdiczka, et al., "Detecting Human Behavior Models From Multimodal Observation in a Smart Home," Automation Science and Engineering, IEEE Transactions on, vol. 6, pp. 588-597, 2009.
[9] C. Wongun, et al., "What are they doing? : Collective activity classification using spatio-temporal relationship among people," Computer Vision Workshops (ICCV Workshops), 2009 IEEE 12th International Conference on, 2009, pp. 1282-1289.
[10] C. Papageorgiou, et al., "A Trainable System for Object Detection," International Journal of Computer Vision, vol. 38, pp. 15-33, 2000.
[11] D. M. Gavrila, et al., "Real-time object detection for smart vehicles," Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on, 1999, pp. 87-93 vol.1.
[12] M. Bramberger, et al., "Distributed embedded smart cameras for surveillance applications," Computer, vol. 39, pp. 68-75, 2006.
[13] W. Wolf, et al., "Smart cameras as embedded systems," Computer, vol. 35, pp. 48-53, 2002.
[14] I. F. Akyildiz, et al., "A survey on wireless multimedia sensor networks," Computer Networks, vol. 51, pp. 921-960, 2007.
[15] B. Rinner, et al., "An Introduction to Distributed Smart Cameras," Proceedings of the IEEE, vol. 96, pp. 1565-1575, 2008.
[16] M. Valera, et al.. Velastin, "Intelligent distributed surveillance systems: a review," Vision, Image and Signal Processing, IEE Proceedings -, vol. 152, pp. 192-204, 2005.
[17] S. Thrun, et al., "Stanley: The Robot That Won the DARPA Grand Challenge," in The 2005 DARPA Grand Challenge. vol. 36, M. Buehler, et al., Eds., ed: Springer Berlin / Heidelberg, 2007, pp. 1-43.
[18] M. Leeser, et al., "Smart camera based on reconfigurable hardware enables diverse real-time applications," in Field-Programmable Custom Computing Machines, 2004. FCCM 2004. 12th Annual IEEE Symposium on, 2004, pp. 147-155.
[19] L. Chang Hong, et al., "A peer-to-peer architecture for distributed real-time gesture recognition," Multimedia and Expo, 2004. ICME '04. 2004 IEEE International Conference on, 2004, pp. 57-60 Vol.1.
[20] W. Chen, et al., "Model-based human posture estimation for gesture analysis in an opportunistic fusion smart camera network," Advanced Video and Signal Based Surveillance, 2007. AVSS 2007. IEEE Conference on, 2007, pp. 453-458.
[21] A. Rowe, et al., "A Second Generation Low Cost Embedded Color Vision System," Computer Vision and Pattern Recognition - Workshops, 2005. CVPR Workshops. IEEE Computer Society Conference on, 2005, pp. 136-136.
[22] C. M. Bishop, Pattern recognition and machine learning vol. 4: Springer New York, 2006.
[23] M. Blank, et al., "Actions as space-time shapes," in Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on, 2005, pp. 1395-1402.
[24] O. Masoud, et al., "A method for human action recognition," Image and Vision Computing, vol. 21, pp. 729-743, 2003.
[25] L. Zelnik-Manor, et al., "Statistical analysis of dynamic actions," IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1530-1535, 2006.
[26] H. Jiang, et al., "Successive convex matching for action detection," in Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, 2006, pp. 1646-1653.
[27] K. Yan, et al., "Event Detection in Crowded Videos," Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on, 2007, pp. 1-8.
[28] E. Shechtman and M. Irani, "Space-time behavior based correlation," in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, 2005, pp. 405-412.
[29] A. F. Bobick , et al., "The recognition of human movement using temporal templates," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 23, pp. 257-267, 2001.
[30] M. Pittore, et al., "Representing and recognizing visual dynamic events with support vector machines," in Image Analysis and Processing, 1999. Proceedings. International Conference on, 1999, pp. 18-23.
[31] M. Fleischman, et al., "Mining temporal patterns of movement for video content classification," in Proceedings of the 8th ACM international workshop on Multimedia information retrieval, 2006, pp. 183-192.
[32] D. Cao, et al., "Online motion classification using support vector machines," in Robotics and Automation, 2004. Proceedings. ICRA'04. 2004 IEEE International Conference on, 2004, pp. 2291-2296.
[33] D. Xu and S. F. Chang, "Visual event recognition in news video using kernel methods with multi-level temporal alignment," in Computer Vision and Pattern Recognition, 2007. CVPR'07. IEEE Conference on, 2007, pp. 1-8.
[34] C. Piciarelli, et al., "Trajectory clustering and its applications for video surveillance," in Advanced Video and Signal Based Surveillance, 2005. AVSS 2005. IEEE Conference on, 2005, pp. 40-45.
[35] Y. Freund, et al., "A short introduction to boosting," JOURNAL-JAPANESE SOCIETY FOR ARTIFICIAL INTELLIGENCE, vol. 14, pp. 771-780, 1999.
[36] D. Minnen, et al., "Recognizing soldier activities in the field," in 4th International Workshop on Wearable and Implantable Body Sensor Networks (BSN 2007), 2007, pp. 236-241.
[37] I. Laptev and P. Perez, "Retrieving actions in movies," in Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on, 2007, pp. 1-8.
[38] S. Nowozin, et al., "Discriminative subsequence mining for action classification," in Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on, 2007, pp. 1-8.
[39] F. Lv, et al., "Automatic tracking and labeling of human activities in a video sequence," in Proceedings of the 6th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS04), 2004.
[40] P. Ribeiro, et al., "Boosting with temporal consistent learners: An application to human activity recognition," Advances in Visual Computing, pp. 464-475, 2007.
[41] P. C. Ribeiro, et al., "Detecting luggage related behaviors using a new temporal boost algorithm," in Proc. of PETS, 2007.
[42] P. Smith, et al., "Temporalboost for event recognition," in Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on, 2005, pp. 733-740.
[43] H. Vassilakis, et al., "Comparison of feedforward (tdrbf) and generative (tdrgbn) network for gesture based control," Gesture and Sign Language in Human-Computer Interaction, pp. 87-104, 2002.
[44] C. Cortes, et al., "Support-vector networks," Machine Learning, vol. 20, pp. 273-297, 1995/09/01 1995.
[45] L. Liang, et al., "Collaborative Target Localization in Camera Sensor Networks," in Wireless Communications and Networking Conference, 2008. WCNC 2008. IEEE, 2008, pp. 2403-2407.
[46] G. Lavee, et al., "Understanding Video Events: A Survey of Methods for Automatic Interpretation of Semantic Occurrences in Video," Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, vol. 39, pp. 489-504, 2009.
[47] T. Yu-Chee, et al., "iMouse: An Integrated Mobile Surveillance and Wireless Sensor System," Computer, vol. 40, pp. 60-66, 2007.
[48] L. Chiu-Kuo, et al., "Movement Assisted Sensor Deployment in Directional Sensor Networks," in Mobile Ad-hoc and Sensor Networks (MSN), 2010 Sixth International Conference on, 2010, pp. 226-230.
[49] J. Ai, et al., "Coverage by directional sensors in randomly deployed wireless sensor networks," Journal of Combinatorial Optimization, vol. 11, pp. 21-41, 2006/02/01 2006.
[50] L. Chiu-Kuo, et al., "Coverage Enhancing Algorithms in Directional Sensor Networks with Rotatable Sensors," Services Computing Conference (APSCC), 2011 IEEE Asia-Pacific, 2011, pp. 377-383.
[51] D. Tao, et al., "Coverage-Enhancing Algorithm for Directional Sensor Networks," Mobile Ad-hoc and Sensor Networks. vol. 4325, J. Cao, et al., Eds., ed: Springer Berlin Heidelberg, 2006, pp. 256-267.
[52] D. Tao, et al., "Virtual potential field based coverage-enhancing algorithm for directional sensor networks," Ruan Jian Xue Bao(Journal of Software), vol. 18, pp. 1152-1163, 2007.
[53] C. Yanli, et al., "Energy Efficient Target-Oriented Scheduling in Directional Sensor Networks," Computers, IEEE Transactions on, vol. 58, pp. 1259-1274, 2009.
[54] A. Newell, et al., "Distributed collaborative camera actuation for redundant data elimination in wireless multimedia sensor networks," Ad Hoc Networks, vol. 9, pp. 514-527, 2011.
[55] T. K. Truong, et al., "Segmentation of specific speech signals from multi-dialog environment using SVM and wavelet," Pattern Recognition Letters, vol. 28, pp. 1307-1313, 2007.
電子全文 Fulltext
本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。
論文使用權限 Thesis access permission:自定論文開放時間 user define
開放時間 Available:
校內 Campus: 已公開 available
校外 Off-campus: 已公開 available


紙本論文 Printed copies
紙本論文的公開資訊在102學年度以後相對較為完整。如果需要查詢101學年度以前的紙本論文公開資訊,請聯繫圖資處紙本論文服務櫃台。如有不便之處敬請見諒。
開放時間 available 已公開 available

QR Code