( 您好!臺灣時間:2021/05/16 21:31
字體大小: 字級放大   字級縮小   預設字形  


研究生(外文):Chien-Tsung Lee
論文名稱(外文):The Study on Tracking and Identification of Moving People for Entering & Leaving a Surveillance Area
指導教授(外文):Chao-Ho (Thou-Ho ) ChenTsong-Yi Chen
外文關鍵詞:Computer VisionVideo SegmentationColor VectorPeople TrackingPeople Recognition
  • 被引用被引用:1
  • 點閱點閱:198
  • 評分評分:
  • 下載下載:13
  • 收藏至我的研究室書目清單書目收藏:4
因此本文基於電腦視覺 (computer vision) 技術開發一種可適用於自動監控保全系統中之行人追蹤暨識別方法,針對在監視區域進出、徘徊之行人進行追蹤,並自動辨別是否為可疑者。本方法主要可分為三大部份:(1)偵測模組:採用快速且有效的背景相減法(background subtraction)來偵測行人;(2)追蹤模組:對被偵測出的行人,利用其人身影像的幾何位置、面積及行人之色彩向量(color vector)等特徵,以追蹤監視區域中的行人;(3)識別模組:將單一人身影像分割成數個不重疊的區域,再各別擷取色彩向量(color-vector)作特徵描述,最後將色彩向量與空間資訊結合做行人的識別。在本實驗中,不僅對行人進行追蹤處理,也可對同一行人進出同一監視區域時,仍能夠識別行人的關係並給予對應的追蹤標籤(tag)及統計其出現次數與計算相似度。
Intelligent surveillance of security system is essential for safe monitoring in the modern. In the digital video surveillance system that replace traditional analog closed-circuit system. But surveillance of security system is still need controlled by guards. The guards need spend a lot of time to look at screen. That situation usually makes guards to feel tired for their body and mind to reduce efficiency of maintaining safety.
This article based on computer vision technology that is suitable for tracking and identifying pedestrian of automatic surveillance system. This technology aim at surveillance area entering/leaving, pedestrian tracking and automatic identify dubious person.
There are three parts in this method as below explanations.
1. Detection model: To adopt quickly and efficiently background subtraction to detect pedestrian.
2. Tracking model: To use pedestrian’s geometric position, measure of area and color-vector to track them.
3. Identification model: To divide the pedestrian’s image to several non-overlapping area then adopt each color vector to describe its characteristics. Finally, to combine color vector and space information with pedestrian’s discriminate.
In this experiment, it is not only to process pedestrian’s tracking but also identify pedestrian’s relation, provide corresponding tracking tags, count appearance times and count similarity for the same pedestrian entering and leaving the same surveillance area.
摘 要 i
誌 謝 iv
目 錄 v
表 目 錄 viii
圖 目 錄 ix
第一章、緒論 1
1.1 研究動機 1
1.2 研究背景 2
1.3 系統架設與流程 4
1.4 論文架構 6
第二章、相關研究 7
2.1 移動物偵測 7
2.2 常見影像分析方法 10
2.2.1 色彩分析方法 10
2.2.2 紋理分析方法 13
2.3 人體追蹤 14
第三章、移動物體偵測 17
3.1 適應性背景相減 18
3.1.1 前景區域偵測 18
3.1.2 背景模型更新 22
3.2 陰影區域移除 23
3.3 物體破碎補償與雜訊濾除 32
3.4 物體區域標記 37
第四章、特徵擷取 41
4.1 色彩特徵 42
4.2 空間特徵 49
第五章、人員追蹤與識別 53
5.1 人員追蹤模組 53
5.1.1 追蹤處理 55
5.1.2 分合情況之處理 57
5.2 人員識別模組 61
5.3 特徵比對 65
第六章、實驗結果 68
6.1 測試環境 68
6.2 實驗結果 71
6.3 識別錯誤之分析 79
第七章、結論 80
7.1 本研究方法之評析 80
7.2 未來展望 81
參考文獻 82
[1] C. Rider, O. Munkelt and H. Kirchner, 1995, ”Adaptive Background Estimation and Foreground Detection using Kalman-filter”, International Conference on Recent Advances in Mechatronics, pp.193-199.

[2] K. Karmann and A. Von Brandt, 1990, “Moving Object Recognition using an Adaptive Background Memory”, Time-varing Image Process. Moving Object Recognition, no. 2, pp. 289-296.

[3] D. Koller, J. Weber, T. Huang, J. Malik, G. Ogasawara, B. Rao and S. Russel, 1994, “Towards robust automatic traffic scene analysis in real-time”, in Proc. Int. Conf. Pattern Recognition, vol. 1, pp. 126-131, October.

[4] C. R. Wren, A. Azarbayejani, T. Darrell and A. P. Pentland, 1997, ”Pfinder: Real-Time Tracking of Human Body”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, No. 7, July.

[5] C. Eveland, K. Konolige and R. C. Bolles, 1998, “Background Modeling for segmentation of video-rate stereo sequences”, in Proc. IDDD Conf. Computer Vision and Pattern Recognition,pp. 266-271, June.

[6] C. Stauffer and W. Grimson, 1999, “Adaptive background mixture models for real-time tracking”, in Proc. IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 246-252, June.

[7] B. Gloyer, H. K. Aghajan, K. Y. Siu and T. Kailath, 1995, “Video-Based freeway monitoring system using recursive vehicle tracking”, in Proc. Of the IS& T-SPIE Symp. on Electronic Imaging: Image and Video Processing, vol. 2421, pp. 173-180. March.

[8] I. Haritaoglu, D. Harwood, L. Davis, 2000, “W4: Real-Time Surveillance of People and Their Activities”, IEEE Trans. Pattern Anal. Mach. Intell., vol. 22, no. 8, pp. 809-830.

[9] M.-P. D. Jolly, S. Lakshmanan and A. K. Jain, 1996, “Vehicle segmentation and classification using deformable templates”, IEEE Trans on PAMI, vol. 18, pp. 293-308.

[10] A. J. Lipton, H, Fujiyoshi and R. Patil, 1998, “Moving target classication and tracking from real-time video”, in Proce. IEEE Workshop on Applications of Computer Vision, pp. 8-14, October.

[11] R. Collins, A. Lipton, T. Kanade, H. Fujiyoshi, D. Duggins, Y. Tsin, D. Tolliver, N. Enomoto, and O. Hasegawa, 2000, A system for video surveillance and monitoring: VSAM final report, Technical CMU-RI-TR-00-12.

[12] D. Meyer, J. Denzler and H. Niemann, 1997, “Model based extraction of articulated objects in image sequences for gait analysis”, IEEE International Conference on Image Processing, vol. 3, pp. 78-81.

[13] D. Gutchess, M. Trajkonic, E. Cohen-Solal, D. Lyons and A. K. Jain, 2001, ”A background model initialization algorithm for video surveillance”, the 8th IEEE Int. Conf. on Computer Vision, pp. 733-740.

[14] I. Karaulova, P. Hall, A. Marshall, ,“A hierarchical model of dynamics for tracking people with a single video camera”, In Proc British Machine Vision Conference, pp. 352-361.

[15] K. Rohr, 1994,“Towards model-based recognition of human movements in image sequences”,CVGIP: Image Understanding, vol. 59, no. 1, pp. 94-115.

[16] C. R. Wren, A. Azarbayejani, T. Darrell and A. P. Pentland, 1997, ”Pfinder: Real-Time Tracking of Human Body”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, No. 7, July

[17] S. McKenna, S. Jabri, Z. Duric, A. Rosenfeld, and H. Wechsler, 2000,“Tracking groups of people”, Computer Vision and Image Understanding, vol. 80, pp. 42-56.

[18] N. Peterfreund, 2000,“Robust tracking of position and velocity with Kalman snakes”, IEEE Trans. On Pattern Analysis and Machine Intelligence, vol. 22, no. 6, pp. 564-569.

[19] R. Polana, R. Nelson, 1994,“Low level recognition of human motion”, In Proc IEEE Workshop on Motion of Non-Rigid and Articulated Objects, pp. 77-82.

[20] S. McKenna, S. Jabri, Z. Duric, A. Rosenfeld, and H. Wechsler, 2000,“Tracking groups of people”, Computer Vision and Image Understanding, vol. 80, pp. 42-56.

[21] M. Dahmane and J. Meunier, 2005, “Real-Time Video Surveillance with Self-Organizing Maps”, IEEE Conference. On Computer and Robot Vision, vol. 00, pp. 136-143.

[22] R.C. Gonzalez and R.E. Woods, 1996, “Digital Image Processing”, Second Editiion, Addison-Wesley, New York..

[23] S.D. Jean, C.M. Liu, C.C. Chang, and Z. Chen, 1994, “A New Algorithm and its VLSI Architecture Design for Connected Component Labeling”, IEEE International Symposium on Circuits and Systems, London, UK, Jun. Vol. 2, pp. 565-568.


[25] Tsong-Yi Chen, Thou-Ho (Chao-Ho) Chen and Da-Jinn Wang, 2009, “A Cost-Effective People-Counter for Passing Through a Gate Based On Image Processing,” International Journal of Innovative Computing, Information and Control (IJICIC). Vol. 5, no. 3, pp.785-800, March.

[26] R.M. Haralick, K. Shanmugam and I. Dinstein, 1973, “Textural features for Image classification”, IEEE Transactions on System, Man, and Cybernetics, vol. 3, , pp. 610-621, Nov.
第一頁 上一頁 下一頁 最後一頁 top