Real-time object tracking is a challenging task due to the frequent occlusion encountered among moving objects. By applying adaptive background subtraction, foreground regions are first segmented and extracted as video objects. This thesis presents a novel algorithm in
tracking objects at multiple distances. By combing two different models of matching method, our system deals with occlusion and is able to correctly label objects during occlusion. The distance transform based off-line human database has been constructed and the multiple search tree is adopted to identify humans. The motion vector analysis is used to count the number of objects with the same walking direction as user predefined one. Experimental results reveal that our method improves the tracking performance.

1 Introduction
1.1 Motivation
1.2 Objectives
1.3 Thesis Overview
2 Literature Survey
2.1 Survey of Background Modeling
2.2 Survey of Object Tracking
3 Background Modeling and Segmentation
3.1 Background Construction
3.2 Foreground Segmentation
3.3 Shadow Detection
3.4 Moving Objects Labeling
3.5 Background Update
4 Video Object Tracking
4.1 Video Object Correspondence and Tracking
4.1.1 Video Object Correspondence
4.1.2 Estimation with Kalman Filter
4.1.3 Object Tracking Algorithm
4.2 Handling Occlusion at Multiple Distances
4.2.1 Occlusion Detection
4.2.2 Matching with Mean Shift at Multiple Distances
5 Human Identification and Flow Counting
5.1 Human Silhouette Database Construction
5.1.1 Training Image and Distance Transform
5.1.2 Image Matching Algorithm
5.1.3 Multiple Search Tree
5.2 Human Identification and Flow Counting
5.2.1 Human Identification
5.2.2 Flow Counting
6 Experimental Results
6.1 Simulation Results of Background Modeling and Segmentation
6.2 Simulation Results of Video Object Tracking
6.3 Simulation Results of Human Identification and Flow Counting
7 Conclusion and Future Work

[1] G. Jing, C. E. Siong, and D. Rajan. Foreground motion detection by difference-based spatial temporal entropy image. IEEE Region 10 Conference Proceedings: Analog and Digital Techniques in Electrical Engineering, pages 379–382, 2004.
[2] A. J. Lipton, H. Fujiyoshi, and R. S. Patil. Moving target classification and tracking from real-time video. Applications of Computer Vision, 1998. WACV’98. Proceedings., Fourth IEEE Workshop on, pages 8–14, 1998.
[3] O. Masoud and N. P. Papanikolopoulos. A novel method for tracking and counting pedestrians in real-timeusing a single camera. IEEE Transactions on Vehicular Technology, 50(5):1267–1278, 2001.
[4] W. E. L. Grimson, C. Stauffer, R. Romano, and L. Lee. Using adaptive tracking to classify and monitor activities in asite. Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on, pages 22–29, 1998.
[5] I. Haritaoglu, D. Harwood, and L. S. Davis. W4: Real-Time Surveillance of People and Their Activities. 2000.
[6] C. Kim and J.-N. Hwang. Fast and automatic video object segmentation and tracking forcontent-based applications. IEEE Transactions on Circuits and Systems for Video Technology, 12(2):122–129, 2002.
[7] E. Stringa and C. S. Regazzoni. Real-time video-shot detection for scene surveillance applications. IEEE Transactions on Image Processing, 9(1):69–79, 2000.
[8] C. R. Wren, A. Azarbayejani, T. Darrell, and A. P. Pentland. Pfinder: Real-Time Tracking of the Human Body. 1997.
[9] C. Stauffer and W.E.L. Grimson. Adaptive background mixture models for real-time tracking. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2:246–252, 1999.
[10] A. Elgammal, R. Duraiswami, D. Harwood, and L. S. Davis. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proceedings of the IEEE, 90(7):1151–1163, 2002.
[11] K. Toyama, J. Krumm, B. Brumitt, and B. Meyers. Wallflower: principles and practice of background maintenance. Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on, 1, 1999.
[12] A. Monnet, A. Mittal, N. Paragios, R. T. Vision, S. C. R. Modeling, and N. J. Princeton. Background modeling and subtraction of dynamic scenes. Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on, pages 1305–1312, 2003.
[13] J. Zhong and S. Sclaroff. Segmenting foreground objects from a dynamic textured background via a robust Kalman filter. Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on, pages 44–50, 2003.
[14] T. J. Broida and R. Chellappa. Estimation of object motion parameters from noisy images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(1):90–99, 1986.
[15] R. Rosales and S. Sclaroff. 3 D trajectory recovery for tracking multiple objects and trajectory guided recognition of actions. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2:117–123, 1999.
[16] D. Comaniciu, V. Ramesh, and P. Meer. Kernel-Based Object Tracking. 2003.
[17] A. D. Jepson, D. J. Fleet, and T. F. El-Maraghi. Robust Online Appearance Models for Visual Tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 1296–1311, 2003.
[18] H. Tao, H. S. Sawhney, and R. Kumar. Object Tracking with Bayesian Estimation of Dynamic Layer Representations. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 75–89, 2002.
[19] J. Kang, I. Cohen, and G. Medioni. Object reacquisition using geometric invariant appearance model. International Conference on Pattern Recongnition (ICPR), pages 759–762, 2004.
[20] V. Salari and I. K. Sethi. Feature point correspondence in the presence of occlusion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(1):87–91, 1990.
[21] C. J. Veenman, M. J. T. Reinders, and E. Backer. Resolving Motion Correspondence for Densely Moving Points. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 54–72, 2001.
[22] T. H. Chang, S. Gong, and E. J. Ong. Tracking multiple people under occlusion using multiple cameras. Proc. 11th British Machine Vision Conference, 2000.
[23] S. L. Dockstader and A. M. Tekalp. Multiple camera fusion for multi-object tracking. Proc. IEEE Workshop on Multi-Object Tracking, pages 95–102, 2001.
[24] S. Khan and M. Shah. Tracking people in presence of occlusion. Asian Conference on Computer Vision, 5, 2000.
[25] H. Roh, S. Kang, and S. W. Lee. Multiple people tracking using an appearance model based on temporal color. Proc. International Conference on Pattern Recognition, 4:643–646, 2000.
[26] D. Beymer and K. Konolige. Real-time tracking of multiple people using continuous detection. IEEE Frame Rate Workshop, 1999.
[27] M. Isard and J. MacCormick. BraMBLe: A Bayesian multiple-blob tracker. International Conference on Computer Vision, 2(5), 2001.
[28] P. KaewTraKulPong and R. Bowden. An improved adaptive background mixture model for real-time tracking with shadow detection. Proc. 2nd European Workshop on Advanced Video Based Surveillance Systems (AVBS01), 2001.
[29] R. C. Gonzalez and R. E. Woods. Digital Image Processing 2/e. Prentice Hall, 2002.
[30] C. E. Erdem, A. M. Tekalp, and B. Sankur. Video object tracking with feedback of performance measures. IEEE Transactions on Circuits and Systems for Video Technology, 13(4):310–324, 2003.
[31] H. Luo and A. Eleftheriadis. Model-based segmentation and tracking of head-andshoulder video objects for real time multimedia services. IEEE Transactions on Multimedia, 5(3):379–389, 2003.
[32] R. E. Kalman. A new approach to linear filtering and prediction problems. Journal of Basic Engineering, 82(1):35–45, 1960.
[33] D.-T. Lin and H.-C. Lee. Intelligent surveillance system for halt detection and people counting. Journal of Information Technology and Applications, 2(3):133–142, 2008.
[34] G. Borgefors. Hierarchical chamfer matching: a parametric edge matching algorithm. IEEE Transactions on Pattern Analysis and Machine Intelligence, 10(6):849–865, 1988.
[35] T. Koga, K. Linuma, A. Hirano, Y. Lijima, and T. Ishiguro. Motion compensated interframe coding for video conferencing. In Nat. Telecommun. Conf., pages G5.3.1–G5.3.5, New Orleans, La, USA, Dec. 1981.
[36] http://archer.ee.nctu.edu.tw/contest/index.htm.
[37] L.R. Dice. Measures of the Amount of Ecologic Association Between Species. Ecology, 26(3):297–302, 1945.
[38] http://www.cvg.cs.rdg.ac.uk/PETS2001/pets2001~dataset.html.
[39] A. Senior, A. Hampapur, Y. L. Tian, L. Brown, S. Pankanti, and R. Bolle. Appearance models for occlusion handling. Image and Vision Computing, 24(11):1233–1243, 2006.