臺灣博碩士論文加值系統

隨著網路的興起帶動通訊產業的突飛猛進，行動通訊上帶給人們前所未有的方便性，隨之而來的是人們對多媒體的依賴越來越深，同時3D技術已經深獲使用者喜愛，所以如何利用電腦視覺 (computer vision)技術來帶給使用者自動化的便利性是近年來大家所熱衷研究的議題。
在視訊序列中對人類進行偵測與追蹤，是一個基本且重要的課題。它可以被應用在許多視覺系統上，如視訊的監視、人物的監控以及視訊的編碼等。本篇論文主要探討並實現一個及時的人物追蹤系統。
在我們的系統架構中，我們假設攝影機是固定不動的，人物的運動則呈現線性移動。本研究發展一套追蹤演算法配合機器視覺(computer vision)建立物體追蹤之分析系統。此追蹤演算法係以物體之間的距離量測結合追蹤對應(tracking correspondence) 建立序列影像中物體之追蹤，本方法能改進以Kalman濾波器為主的整合追蹤演算法，此法較以往單純使用Kalman濾波器與近鄰法有較優越的追蹤性能。我們利用一個初始化步驟將獨立的區塊歸屬於個別的人物，之後對人物進行追蹤。對於被追蹤的物體我們定義了一個物體距離量測的方法，並且可以藉此還原部分空間的資訊，進而達到追蹤的目的。
我們的系統在Pentium-III 800 的筆記型電腦，能達到每秒30張的處理速度。實驗結果顯示我們的方法是精確且強健的。

Objects in the world exhibit complex interactions.
When captured in a video sequence, some interactions manifest
themselves as occlusions. A visual tracking system must be
able to track objects which are partially or even fully occluded.
Occlusion is a difficult problem in target tracking, especially
when users need to track multiple targets simultaneously and
maintain the target identities during tracking. With this
complex design issue, in this paper we present a fast occluded
object tracking technique. The purpose of this paper is to
present a novel approach to cope with the occlusion problem
explicitly. Our approach is by use of the occlusion handling
with the measurement on object distance and power. Our
system has the advantages of low cost and low complexity, and
can be realized in real time system.

第1章 介紹 1
1.1 Overview 1
1.2 system diagram 2
1.3 論文大綱 4
第2章 文獻探討 5
2.1 物體擷取 7
2.2 ROI物體鑑別 8
2.3 追蹤分析 8
2.4 Kalman 濾波器在追蹤問題之運用 8
2.5 追蹤對應 10
2.5.1 統計對應法 10
2.6 kalman 濾波器與物體活動性分析 12
第3章 材料、方法與理論分析 14
3.1 實驗設備 14
3.2 物體鑑別 14
3.2.1 影像強化處理 16
3.2.2 影像二值化 16
3.2.3 型態處理 17
3.2.4 標記處理 18
3.2.5 ROI鑑別 19
第4章 kalman-filter base追蹤演算法 20
4.1 系統估測 22
4.2 隨機過程 23
4.3 線性均方估測 25
4.4 離散隨機系統 27
4.5 離散kalman濾波器 29
4.6 Kalman濾波器運於追蹤之實例 36
4.7 利用kalman濾波器處理多人的追蹤情形 41
第5章 具有影像重疊(occlusion)處理能力的監控系統 46
5.1 系統架構 49
5.2 power tactic 52
5.3 力量中心點（POWER CENTER POINT, PCP） 53
5.4 物體的追蹤方法 64
第6章 實驗結果 67
第7章 結論 70
第8章 References 72

第8章References
[1]Ancin, H., T. E. Dufresne, G. M. Ridder, J. N. Turner and B. Roysam. “An improved watershed algorithm for counting objects in noisy, anisotropic 3-D biological images.” In Proceedings of Image Processing, pages 172 –175, 1995.
[2]Bettens, E., J. Scheunders, D. Sijbers, L. M. Van Dyck. “Automatic segmentation and modeling of two-dimensional electrophoresis gels.” In Proceedings of IEEE Image Processing, pages 665-668, 1996.
[3]Zimmer, C., E. Labruyere, V. Meas-Yedid, N. Guillen and J. C. Olivo-Marin. “Segmentation and tracking of migrating cells in videomicroscopy with parametric active contours: a tool for cell-based drug testing.” IEEE Transaction on Medical Image, pages 1212-1221, 2002.
[4]Sumi, Y., M. Ota, N. Yabuki, S. Obote, Y. Matsuda and Y. Fukui. “The automatic counting of Chlorella using image processing and neural network.” IEICE Trans. E84-A(3), pages 794-796, 2001.
[5]Kalman, R. E, “A new approach to linear filtering and prediction problems.” Journal of Basic Engineering 82(D), pages 35-45, 1960.
[6]Bar-Shalom, Y. and E. Tse, “Tracking in a cluttered environment with probability data association.” Automatic 11, pages 451-460, 1975.
[7]Cox, I. J. 1993. “A review of statistical data association techniques for motion correspondence.” International Journal of Computer Vision 10(1):53-66.
[8]Fortmann, T. E. and Y. Bar-Shalom, “Sonar tracking of multiple targets using joint probability data association.” IEEE Journal of Oceanic Engineering, pages 173-184, 1983.
[9]Samuel S., Popoli , Robert, Blackman, “design and analysis of modern tracking system.” Boston : Artech House , 1999
[10]Trucco, Emanuele. Verri , Alessandro, “introductory techniques for 3-D computer vision,” Upper Saddle River, NJ : Prentice Hall , 1998.
[11]Weiming Hu, Tieniu Tan, Fellow, IEEE, Liang Wang, and Steve Maybank, “A survey on visual surveillance of object motion and behaviors,” IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART C: APPLICATIONS AND REVIEWS, VOL. 34, NO. 3, AUGUST 2004.
[12] Morimoto, T.; Kiriyama, O.; Harada, Y.; Adachi, H.; Koide, T.; Mattausch, H.J, “Object tracking in video pictures based on image segmentation and pattern matching,” IEEE International Symposium on Circuits and Systems, ISCAS 2005. Page(s):3215 – 3218, 23-26 May 2005.
[13]Ying Wu; Ting Yu; Gang Hua, “Tracking appearances with occlusions,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003.
[14] Elgammal, A.E.; Davis, L.S “Probabilistic framework for segmenting people under occlusion,” IEEE International Conference on Computer Vision, 2001. ICCV 2001.
[15]Min Hu; Weiming Hu; Tieniu Tan “Tracking people through occlusions,” Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.
[16]Nguyen, H.T.; Smeulders, A.W.M.; “Fast occluded object tracking by a robust appearance filter,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 26, Issue 8 , Page(s):1099 – 1104, Aug. 2004.
[17]Casas, J.R.; Sitjes, A.P.; Folch, P.P “Mutual feedback scheme for face detection and tracking aimed at density estimation in demonstrations,” IEE Proceedings Vision, Image and Signal Processing, Volume 152, Issue 3, Page(s):334 – 346, 3 June 2005.
[18]Toklu, C.; Murat Tekalp, A.; Tanju Erdem, A “Semi-automatic video object segmentation in the presence of occlusion,” IEEE Transactions on Circuits and Systems for Video Technology, Volume 10, Issue 4, Page(s):624 – 629, June 2000
[19]Erdem, C.E.; Murat Tekalp, A.; Sankur, B “Metrics for performance evaluation of video object segmentation and tracking without ground-truth,” Proceedings. 2001 International Conference on Image Processing, Volume 2, Page(s):69 - 72 7-10 Oct. 2001.
[20]Erdem, C.E.; Tekalp, A.M.; Sankur, B “Video object tracking with feedback of performance measures,” IEEE Transactions on Circuits and Systems for Video Technology, Volume 13, Issue 4, Page(s):310 – 324, April 2003.
[21]Erdem, C.E.; Sankur, B.; Tekalp, A.M “Performance measures for video object segmentation and tracking,” IEEE Transactions on Image Processing, Volume 13, Issue 7, Pages: 937–951, July 2004.
[22]Toklu, C.; Tekalp, A.M.; Erdem, A.T.; Sezan, M.I “2-D mesh-based tracking of deformable objects with occlusion,” Proceedings, International Conference on Image Processing, Volume 1, Pages: 933 – 936, 16-19 Sept. 1996.
[23]Haritaoglu, I.; Harwood, D.; Davis, L.S. “W4 real-time surveillance of people and their activities,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 22, Issue 8, Page(s):809 – 830, Aug. 2000.
[24]Dae-Woon Lim; Sung-Hoon Choi; Joon-Suk Jun “Automated detection of all kinds of violations at a street intersection using real time individual vehicle tracking,” Proceedings. Fifth IEEE Southwest Symposium on Image Analysis and Interpretation, Page(s):126 – 129, 7-9 April 2002
[25]Niu, W.; Jiao, L.; Han, D.; Wang, Y.-F “Real-time multiperson tracking in video surveillance,” Proceedings of the 2003 Joint Conference of the Fourth International Conference on Information, Communications and Signal Processing, 2003 and the Fourth Pacific Rim Conference on Multimedia.
[26]Mohan, A. Papageorgiou, C. Poggio, T. “Example-based object detection in images by components,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 23, Issue 4, Page(s):349 – 361, April 2001.
[27]Tao Zhao; Nevatia, R “Tracking multiple humans in complex situations,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 26, Issue 9, Page(s):1208 – 1221, Sept. 2004.
[28]Stauffer, C.; Grimson, W.E.L “Learning patterns of activity using real-time tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 22, Issue 8, Aug. 2000.
[29]Yilmaz A.; Xin Li; Shah M. “Contour-based object tracking with occlusion handling in video acquired using mobile cameras,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 26, Issue 11, Page(s):1531 – 1536, Nov. 2004.
[30]Bremond F.; Thonnat M. “Tracking multiple nonrigid objects in video sequences,” IEEE Transactions on Circuits and Systems for Video Technology, Volume 8, Issue 5, Page(s):585 – 591, Sept. 1998.