In this thesis, we have proposed three mechanisms to enhance OBT in drifting resistance.
First, we exploit depth information to lower background interference. Second, we introduce scalability for EOBT to solve drifting caused by distance variation. Third, we design a lifetimer so as to get through temporary occlusion. Also, we have proposed a new evaluation method to avoid wrong target problem in original evaluation method. New evaluation method is composed of two factors, RIO and RIT. RIO is a ratio to reveal the percentage of object that tracker has caught. RIT is used to reflect the area that tracker spends on tracking. Especially, RIT is used when tracker size is changeable.
All three of proposed mechanisms have been examined. Experimental results show that, EOBT does help to eliminate drifting probability. We also conduct research on stability, which is seldom addressed in related literature. Discussions on object tracking and tracking methods are described in previous chapter. Our future work will focus on solving manifold problem. Also, introducing parallel computing into tracking methods seems appropriate and may substantially accelerate performance. Improvements could be made in search sampling, and so on and so forth. Tracking using online boosting is still a developing research!
References
[1] A. Yilmaz, O. Javed, and M. Shah, ''Object tracking: A survey,'' Acm Computing Surveys (CSUR), vol. 38, no. 4, p. 13, 2006.
[2] D. Hoiem, A. Efros, and M. Hebert, ''Putting objects in perspective,'' International Journal of Computer Vision, vol. 80, no. 1, pp. 3--15, 2008.
[3] S. Nejhum, J. Ho, and M. Yang, ''Visual tracking with histograms and articulating blocks,'' in Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on.
IEEE, 2008, pp. 1 -- 8.
[4] C. Tomasi and T. Kanade, Detection and tracking of point features. Citeseer, 1991.
[5] K. Cannons, ''A review of visual tracking,'' Technical Report CSE-2008-07, York Univer-sity, Department of Computer Science and Engineering, Tech. Rep., 2008.
[6] C. Harris and M. Stephens, ''A combined corner and edge detector,'' in Alvey vision con-ference, vol. 15. Manchester, UK, 1988, p. 50.
[7] D. Lowe, ''Distinctive image features from scale-invariant keypoints,'' International jour-nal of computer vision, vol. 60, no. 2, pp. 91--110, 2004.
[8] H. Bay, T. Tuytelaars, and L. Van Gool, ''Surf: Speeded up robust features,'' in Computer Vision – ECCV 2006, ser. Lecture Notes in Computer Science, A. Leonardis, H. Bischof, and A. Pinz, Eds. Springer Berlin / Heidelberg, 2006, vol. 3951, pp. 404 -- 417, 10.1007/11744023-32. [Online]. Available: http://dx.doi.org/10.1007/11744023_32
[9] M. Kass, A. Witkin, and D. Terzopoulos, ''Snakes: Active contour models,'' International Journal of Computer Vision, vol. 1, pp. 321--331, 1988, 10.1007/BF00133570. [Online].
Available: http://dx.doi.org/10.1007/BF00133570
[10] V. Caselles, R. Kimmel, and G. Sapiro, ''Geodesic active contours,'' International Journal of Computer Vision, vol. 22, pp. 61--79, 1997, 10.1023/A:1007979827043. [Online].
Available: http://dx.doi.org/10.1023/A:1007979827043
[11] Y. Ming-Hsuan, ''Advances in visual tracking,'' Asian Conference on Computer Vision (ACCV), 2010.
[12] G. Welch and G. Bishop, ''An introduction to the kalman filter,'' Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC, Tech. Rep., 2006.
[13] H. Grabner and H. Bischof, ''On-line boosting and vision,'' in Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, vol. 1. IEEE, 2006, pp. 260 -- 267.
[14] H. Grabner, M. Grabner, and H. Bischof, ''Real-time tracking via on-line boosting,'' in Proc. BMVC, vol. 1. Citeseer, 2006, pp. 47 -- 56.
[15] S. Grossberg, ''Competitive learning: From interactive activation to adaptive resonance**,'' Cognitive science, vol. 11, no. 1, pp. 23--63, 1987.
[16] H. Grabner, C. Leistner, and H. Bischof, ''Semi-supervised on-line boosting for robust tracking,'' in Computer Vision – ECCV 2008, ser. Lecture Notes in Computer Science, D. Forsyth, P. Torr, and A. Zisserman, Eds. Springer Berlin / Heidelberg, 2008, vol. 5302, pp. 234 -- 247, 10.1007/978-3-540-88682-2-19. [Online]. Available:
http://dx.doi.org/10.1007/978-3-540-88682-2_19
[17] S. Stalder, H. Grabner, and L. Van Gool, ''Beyond semi-supervised tracking: Tracking should be as simple as detection, but not simpler than recognition,'' in Computer Vision Workshops (ICCV Workshops), 2009 IEEE 12th International Conference on. IEEE, 2009, pp. 1409 -- 1416.
[18] B. Babenko, M.-H. Yang, and S. Belongie, ''Visual tracking with online multiple instance learning,'' in Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Confer-ence on, june 2009, pp. 983 --990.
[19] F. Yoav and E. Robert, ''A decision-theoretic generalization of on-line learning and an application to boosting,'' Journal of Computer and System Sciences, vol. 55, no. 1, pp.
119--139, 1997.
[20] J. Friedman, T. Hastie, and R. Tibshirani, ''Additive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors),'' The annals of statistics, vol. 28, no. 2, pp. 337--407, 2000.
[21] P. Viola and M. Jones, ''Robust real-time face detection,'' International Journal of Com-puter Vision, vol. 57, no. 2, pp. 137--154, 2004.
[22] N. Oza, ''Online Ensemble Learning,'' Ph.D. dissertation, UNIVERSITY of CALIFOR-NIA, 2001.
[23] S. Nejhum, J. Ho, and M. Yang, ''Online visual tracking with histograms and articulating blocks,'' Computer Vision and Image Understanding, vol. 114, no. 8, pp. 901--914, 2010.
[24] D. Comaniciu, V. Ramesh, and P. Meer, ''Real-time tracking of non-rigid objects using mean shift,'' in cvpr. Published by the IEEE Computer Society, 2000, p. 2142.
[25] X. Zhu, ''Semi-supervised learning literature survey,'' Computer Science, University of Wisconsin-Madison, Tech. Rep. 1530, 2008.
[26] P. Mallapragada, R. Jin, A. Jain, and Y. Liu, ''Semiboost: Boosting for semi-supervised learning,'' Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 31, no. 11, pp. 2000--2014, 2009.
[27] C. Leistner, H. Grabner, and H. Bischof, ''Semi-supervised boosting using visual similarity learning,'' in Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Confer-ence on. IEEE, 2008, pp. 1 -- 8.
[28] O. Maron and T. Lozano-P´erez, ''A framework for multiple-instance learning,'' in Advances in neural information processing systems. Citeseer, 1998, pp. 570 -- 576.
[29] P. Viola, J. Platt, and C. Zhang, ''Multiple instance boosting for object detection,'' Advances in neural information processing systems, vol. 18, p. 1417, 2006.
[30] R. Collins, ''Mean-shift blob tracking through scale space,'' in Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on, vol. 2, june 2003, pp. II -- 234--40 vol.2.
[31] M.-H. Yang and J. Ho, ''Toward robust online visual tracking,'' in Distributed Video Sensor Networks, B. Bhanu, C. V. Ravishankar, A. K. Roy-Chowdhury, H. Aghajan, and D. Terzopoulos, Eds. Springer London, 2011, pp. 119 -- 136, 10.1007/978-0-85729-127-1--8. [Online]. Available: http://dx.doi.org/10.1007/978-0-85729-127-1--8
[32] P. Belhumeur and D. Kriegman, ''What is the set of images of an object under all possible lighting conditions?'' in Computer Vision and Pattern Recognition, 1996. Proceedings CVPR '96, 1996 IEEE Computer Society Conference on, jun 1996, pp. 270 --277.
[33] F. Porikli, ''Integral histogram: a fast way to extract histograms in cartesian spaces,'' in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, vol. 1, june 2005, pp. 829 -- 836 vol. 1.
[34] M. Godec, H. Grabner, C. Leistner, and H. Bischof, ''Speeding up semi-supervised on-line boosting for tracking,'' 2010.
[35] A. Singh, R. Nowak, and X. Zhu, ''Unlabeled data: Now it helps, now it doesn’t,'' Advances in Neural Information Processing Systems, vol. 21, no. 2008, pp. 1513--1520, 2008.