臺灣博碩士論文加值系統

目前社會的治安每況愈下，世界各地犯罪與暴力事件層出不窮，慶幸的是犯罪場景被監視錄影系統拍攝下來，最後得以破案的案例時有所聞，這也讓如何利用監視錄影系統，來防止犯罪的發生之重要性與需求性日愈提高。目前現有監視系統的功能略顯不足，大部份的監視系統，都僅能對場景作單純的錄影，無法有效地對人多的室內封閉或開放性場景並做自動分析。
有鑑於此，專家學者提出結合了全景相機和PTZ相機的新式智慧型監控系統，不但能藉助全景相機的廣角視野優點掌握監視場所內的各個角落，以改善定點攝影機的觀察死角；更能透過 PTZ 相機的放大追蹤功能提供較多重要的資訊。
而本文中將針對此類型的系統進行探討，包括全景影像的形成、全景影像中物體的定位方式，及如何以全景相機控制PTZ相機進行放大追蹤等技術。
此外，為了能適應全景影像解析度較低的缺點，文中將以多層次成長法進行物體偵測以取得較完整的物體區塊。而在物體追蹤的部份，我們則提出一藉由樣版比對搭配移動軌跡協助的物體辨識演算法，並結合移動預測技術，以加強PTZ相機在實際應用時的追蹤效能，而在以 Borland C++ 實現此監控系統後，也證實了演算法的可行性。

The deterioration of social order, which causes vandalism and terrorism around the world, has increased the importance of security and raised the demand on surveillance system. Therefore, the improvement on the capability of surveillance system is currently attracting a great deal of attention.
Although intelligent multi-camera surveillance systems have been developed for some time, most of the systems can not effectively achieve the goal of tracking and positioning in an indoor environment. A functional analysis found that the reason is due to mutual occlusion under multiple people condition. Moreover, given wide surveillance area, the limitation on the image resolution can not offer the effective recognition and understanding.
In order to overcome difficulties mentioned above, recent researches proposed intelligent surveillance systems composed of multiple cameras. Among them, some systems use the Pan-Tilt-Zoom camera to trace moving objects and try to zoom in the scene to acquire a higher resolution image. In addition, some systems even combined with omni-directional camera hanged on the ceiling, instead of ordinary flat camera, to obtain an overview of the surveillance region.
In this thesis, we will investigate functionalities of one intelligent surveillance system composed of single omni-directional camera and two Pan-Tilt-Zoom cameras. Three key issues will be discussed in respective chapters, they are: (1) the imaging technique of the omni-directional image, (2) the localization of moving objects in the omni-directional image, and (3) the method of using the omni-directional camera to guide the PTZ camera for zooming and tracing the moving objects.
Since the resolution of omni-directional images is much lower than that of the regular camera, we adopt a multi-resolution technique which uses thresholding-with-hysteresis to obtain a more complete object in omni-directional images. Furthermore, we not only develop an algorithm which combines template matching and motion history for object recognition, but also employ the motion estimation to improve the object tracking using PTZ camera.
This surveillance system has been implemented by Borland C++ in PC, and experimental results show its feasibility of working in the real-time environment.

中文摘要 i
英文摘要 ii
誌謝 iv
目錄 v
圖目錄 vii
表目錄 ix
第一章 序論 1
1.1 相關文獻與研究動機 1
1.2 研究目的與方法概述 2
1.3 論文架構 3
第二章 基礎原理介紹 4
2.1全景相機的來由及類型比較 4
2.2 全景相機的成像及定位原理 7
2.3 PTZ 相機功能介紹 15
2.4監控系統架構及相關研究 22
2.5結論 25
第三章 全景影像中的移動物體偵測 26
3.1多層解析度成長法 26
3.2 柱狀投影及局部視角轉換 32
3.3多物體追蹤法則 40
3.3.1預測已知物體移動後的位置 43
3.3.2移動後物體與移動前的物體比對 44
3.3.3搜尋其他新物體並更新背景 47
3.4 結論 48
第四章 結合全景相機與PTZ 相機之監控系統 49
4.1 緒論 49
4.2 物體追蹤策略 51
4.3 全景相機和 PTZ 相機的定位 56
4.4 結論 62
第五章 系統實現及測試 63
5.1 實驗結果 63
5.1.1 材料與設備 63
5.1.2 全景相機的定位測試 63
5.1.3 全景相機搭配 PTZ 相機的定位與放大測試 65
5.1.4全景引導式 PTZ 追蹤系統 68
5.2 結論 80
5.3 未來展望 80
參考文獻 81

[1] Elena Stringa, and Carlo S. Regazzoni, “Real-Time Video-Shot Detection for Scene
Surveillance Applications,” IEEE Trans. on Image Processing, Vol. 9, pp. 69-79, Jan.
2000.

[2] Ismail Haritaoglu, David Harwood, and Larry S. Davis, “Active Outdoor Surveillance,” IEEE Conf. on Image Analysis and Processing, pp. 27-29, Sept. 1999.

[3] Vincent Girondel, Laurent Bonnaud, and Alice Caplier, “Hands Detection and Tracking for Interactive Multimedia Applications,” Archives of Theoretical and Applied Informatics, 2003.

[4] Gabriel L. Miller and Eric R. Wagner, “An Optical Rangefinder for Autonomous Robot Cart Navigation,” Proc. SPIE Mobile vision, Machine Vision & Application, Robots 1 , pp.223-240 (1988) pp.1136-1142 (1989) Robots 11, ~01.852, pp.132-144 (1987).

[5] Nayar, S.K,“Catadioptric Omnidirectional Camera,” IEEE Computer Society
Conference on Computer Vision and Pattern Recognition, pp. 482 – 488, 17-19 June
1997.

[6] Venkata N. Peri and Shree K. Nayer, “Generation of Perspective and Panoramic
Video from Omnidirectional Video,”Proc. Of DARPA Image Understanding
WorkShop, May 1997.

[7] Kazumasa YAMAZAWA, Yasushi YAGI ,and Masahiko YACHIDA,
“Omnidirectional Imaging with Hyperboloidal Prjoection,”
IEEE International Conference on Intelligent Robots and Systems, July 1993.

[8] Yong Rui, Anoop Gupta and JJ Cadiz, “Viewing Meetings Captured by an Omni-Directional Camera,” Proc. Of SIGCHI’01, March 31-April 4, 2001.

[9] Niall Winters, Jose Santos-Victor, “Mobile Robot Navigation using Omni-directional Vision,”Irish Machine Vision and Image Processing Conference, Dublin, Ireland, Sep. 1999.

[10] Yagi, Y., Yachida, M., “Omnidirectional Sensing for Human Interaction,”
Proc. of IEEE Workshop on Omnidirectional Vision, pp. 121 – 127, June, 2, 2002,.

[11] Xilin Chen, Jie Yang, “Towards Monitoring Human Activities Using an Omnidirectional Camera,”IEEE International Conference on Multimodal Interfaces, pp. 423 – 428, 14-16 Oct. 2002.

[12] Terry Boult, R. Micheals, A. Erkan, P. Lewis, C. Powers, C. Qian, and W. Yin,
“Frame-rate Multi-body Tracking for Surveillance,”Proc. of DARPA Image Understanding, 1998.

[13] Zhong Zhang, Blum, R.S.,“Extraction of 3-D Coordinates from Fusion of Omnicamera Images,”IEEE Conference on Signals, Systems, and Computers,
vol.1, pp. 397 - 401, 24-27, Oct. 1999.

[14] Gandhi T., Trivedi M.M., “Motion Based Vehicle Surround Analysis Using an Omni-Directional Camera,”IEEE Conf. on Intelligent Vehicles Symposium,
pp. 560 – 565, 14-17, June, 2004.

[15] Boult T.E., Micheals R.J., Xiang Gao, and Eckmann M.,“Into the Woods: Visual Surveillance of Nocooperative and Camouflaged Targets in Complex Outdoor Settings,”IEEE Journal , Volume 89, pp. 1382 – 1402, Oct. 2001,

[16] Xilin Chen, Jie Yang, and Waibel A.,“Calibration of a Hybrid Camera Network,”
IEEE International Conference on Computer Vision, vol.1, pp.150 – 155, 13-16 Oct. 2003.

[17] Boult T.E.,“Geo-spatial Active Visual Surveillance on Wireless Networks,”
Proc. of IEEE Applied Imagery Pattern Recognition Workshop, pp. 244 – 249, 15-17, Oct. 2003.

[18] David Gries, Fred B. Schneider, “Book_Monographs in Computer Science.”

[19] Shinji Morita, Kazumasa Yamazawa , and Naokazu Yokoya, “Internet Telepresence
by Real-Time View-Dependent Image Generation with Omnidirectional Video
Camera,”Computer Vision and Image Understanding, pp. 154-165, 1998.

[20] Terry Boult, Chen Qian, Weigong Yin, Peter Lewis, Chris Power, and Ross Micheals,
“Applications of Omnidirectional Imaging: Multi-body tracking and remote
reality,” IEEE Workshop on Applications of Computer Vision, 1998.

[21] CZECH Technical University, Tomas Svoboda, “Central Panoramic Cameras
Design Geometry Egomotion.”

[22] 余福平, 傅偢善, “以環場攝影機引導近照攝影機追蹤人物,” 國立台灣大學資訊工程學研究所, 2000.

[23] Yoshio Onoe, Naokazu Yokoya, Kazumasa Yamazawa, and Haruo Takemura, “Visual Surveillance and Monitoring System Using an Omnidirectional Video
Camera,” ICPR98, Vol. 1, pp. 588-592.

[24] Yi-Tsung Chen, Hung-Xin Zhao, and Yea-Shuan Huang, “A Robust Sensor Connection for Intrusion Detection,”Conference of Computer Vision, Graphics, and Image Processing, 2004.

[25] Yachi K., Wada T., Matsuyama T.,“Human Head Tracking Using Adaptive Appearance Models with A Fixed-Viewpoint Pan-Tilt-Zoom Camera,”IEEE International Conference on Automatic Face and Gesture Recognition, pp. 28 - 30, March 2000.

[26] Yu-Wen Huan, Bing-Yu Hsieh, Shao-Yi Chien, and Liang-Gee Chen,“Simple And Effective Algorithm for Automatic Tracking of A Single Object Using A Pan-Tilt-Zoom Camera,”IEEE International Conference on Multimedia and Expo,
Vol.1, pp. 789 - 792, Aug. 2002.

[27] Kawanishi T., Murase H., Takagi S., and Werner M.,“Dynamic Active Search for Quick Object Detection with Pan-Tilt-Zoom Camera,”IEEE International Conference on Image Processing, Vol.3, pp. 716 – 719, Oct. 2001.

[28] Ismail Haritaoglu, David Harwood ,and Larry S. Davis,“W4: Who? When? Where? What? A Real Time System for Detecting and Tracking People,”IEEE Conf. on Computer Vision and Pattern Recognition, pp. 23-25, June 1998.

[29] Cindy X., Collange F., Jurie F., Martinet P.,“Object Tracking with A Pan-Tilt-Zoom Camera: Application to Car Driving Assistance,”IEEE International Conference on Robotics and Automation, Vol.2, pp. 1653 - 1658, 2001.

[30] Ying- Shing Shiao and Yi–Feng Su,“Design and Implementation of A Tracking
Controller with Image Vision Servo forActive Camera,” Conference of Computer
Vision, Graphics, and Image Processing, 2004.


[31] Kim Y.-O., Paik J., Jingu Heo, Koschan A., Abidi B., and Abidi M.,“Automatic Face Region Tracking for Highly Accurate Face Recognition in Unconstrained Environments,”IEEE Conference on Advanced Video and Signal Based Surveillance, pp.29 – 36, July 2003.

[32] Funahasahi T., Tominaga M., Fujiwara T., and Koshimizu H.,“Hierarchical Face Tracking by Using PTZ Camera,”IEEE International Conference on Automatic Face and Gesture Recognition, pp. 427 – 432, May 2004.

[33] Hong Liu, Wenkai Pi, Hongbin Zha, and Robotics,“Motion Detection for Multiple Moving Targets by Using An Omnidirectional Camera,”IEEE International Conference on Intelligent Systems and Signal Processing, vol.1, pp. 422 – 426, 8-13, Oct. 2003.

[34] Rosales R., Sclaroff S.,“3D Trajectory Recovery for Tracking Multiple Objects and Trajectory Guided Recognition of Actions,”IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 23-25, June 1999.

[35] Hsu D., Leu J., Chen S., Chang W., Fang W.,“Using Shape Feature Matching to Track Moving Objects in Image Sequences,”IEEE International Conference on Multimedia and Expo, Vol. 2, pp.785 – 788, Aug. 2000.

[36] Davis J.W., Bobick A.F.,“The Representation and Recognition of Human Movement Using Temporal Templates,”IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 928 – 934, June 1997.

[37] 張仁鴻, 吳先晃, “智慧型監視系統之物體偵測與交通影片之車輛偵測與索
引,” 國立雲林科技大學電機研究所, 2004.

[38] 梁永福, 楊茂村, “3D Scene Reconstruction Using Panorama Arrays,” 國立東華大學資訊工程學系, 2003.

[39] Romer Rosales and Stan Sclaroff, “Improved Tracking of Multiple Humans with
Trajectory Prediction and Occlusion Modeling,”Proc. IEEE Workshop on
Interpretation of Visual Motion, 1998.

[40] Regazzoni C.S.; Tesei A.,“Density evaluation and tracking of multiple objects from image sequences,” IEEE International Conference on Image Processing, Vol.1, pp. 545 – 549 , 13-16 Nov. 1994.

[41] Stephen J. McKenna, Sumer Jabri ,Zoran Duric, and Azriel Rosenfeld,“Tracking Groups of People,” Computer Vision and Image Understanding, 80, 42-56, 2000.

[42] Lyons D.M.,“Discrete event modeling of misrecognition in PTZ tracking,” IEEE Conference on Advanced Video and Signal Based Surveillance, pp. 61 – 66, 21-22 July 2003.

[43] Chung-Lin Huang, and Wen-Chieh Liao,“A vision-based vehicle identification system,” IEEE International Conference on Pattern Recognition, Volume 4, pp. 364 – 367, 23-26 Aug. 2004.

[44] W. Grimson, C. Stauffer, R. Romano, and L. Lee, “Usingadaptive Tracking to
Classify and Monitor Activities in A Site,” in Proceedings of IEEE Conference on
Computer Vision and Pattern Recognition, pp. 22–29, 1998.

[45] B. Flinchbaugh and T. Olson, “Autonomous Video Surveillance,”in 25th AIPR
Workshop: Emerging Applications of Computer Vision, May 1996.

[46] Lipton, H. Fuijiyoshi, and R. Patil, “Moving Target Detection and Classification
from Real-time Video,” in Proc. of the IEEE Workshop on Applications of
Computer Vision, 1998.

[47] Haritaoglu, D. Harwood, and L. Davis, “Real-time Surveillance of People and Their Activities,” IEEE Tran. On Pattern Analysis and Machine Intelligence, pp. 809–830, August 2000.

[48] 李子洋, 王嘉銘, 洪一平, 范國清, “A Visual Monitoring System Using
Wide-Angle Cameras and Pan-Tilt Cameras,” Conference of Computer
Vision, Graphics, and Image Processing, 2004.

[49] 簡逸聰, 趙鴻欣, 黃雅軒, “A Robust Sensor Connection for Intrusion
Detection,” Conference of Computer Vision, Graphics, and Image Processing, 2004.