Publication 2001 Issue No. 6 - June Abstract - Probabilistic Data Association Methods for Tracking Complex Visual Objects
Probabilistic Data Association Methods for Tracking Complex Visual Objects
June 2001 (vol. 23 no. 6)
pp. 560-576
 ASCII Text x Christopher Rasmussen, Gregory D. Hager, "Probabilistic Data Association Methods for Tracking Complex Visual Objects," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 6, pp. 560-576, June, 2001.
 BibTex x @article{ 10.1109/34.927458,author = {Christopher Rasmussen and Gregory D. Hager},title = {Probabilistic Data Association Methods for Tracking Complex Visual Objects},journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence},volume = {23},number = {6},issn = {0162-8828},year = {2001},pages = {560-576},doi = {http://doi.ieeecomputersociety.org/10.1109/34.927458},publisher = {IEEE Computer Society},address = {Los Alamitos, CA, USA},}
 RefWorks Procite/RefMan/Endnote x TY - JOURJO - IEEE Transactions on Pattern Analysis and Machine IntelligenceTI - Probabilistic Data Association Methods for Tracking Complex Visual ObjectsIS - 6SN - 0162-8828SP560EP576EPD - 560-576A1 - Christopher Rasmussen, A1 - Gregory D. Hager, PY - 2001KW - Visual trackingKW - data associationKW - color regionsKW - textured regionsKW - snakes.VL - 23JA - IEEE Transactions on Pattern Analysis and Machine IntelligenceER -

Abstract—We describe a framework that explicitly reasons about data association to improve tracking performance in many difficult visual environments. A hierarchy of tracking strategies results from ascribing ambiguous or missing data to: 1) noise-like visual occurrences, 2) persistent, known scene elements (i.e., other tracked objects), or 3) persistent, unknown scene elements. First, we introduce a randomized tracking algorithm adapted from an existing probabilistic data association filter (PDAF) that is resistant to clutter and follows agile motion. The algorithm is applied to three different tracking modalities—homogeneous regions, textured regions, and snakes—and extensibly defined for straightforward inclusion of other methods. Second, we add the capacity to track multiple objects by adapting to vision a joint PDAF which oversees correspondence choices between same-modality trackers and image features. We then derive a related technique that allows mixed tracker modalities and handles object overlaps robustly. Finally, we represent complex objects as conjunctions of cues that are diverse both geometrically (e.g., parts) and qualitatively (e.g., attributes). Rigid and hinge constraints between part trackers and multiple descriptive attributes for individual parts render the whole object more distinctive, reducing susceptibility to mistracking. Results are given for diverse objects such as people, microscopic cells, and chess pieces.

[1] J. Mendel, Lessons in Digital Estimation Theory. Prentice-Hall, 1987.
[2] W.H. Press, S.A. Teukolsky, W.T. Vetterling, and B.P. Flannery, Numerical Recipes in C. Cambridge Univ. Press, 1992.
[3] Y. Bar-Shalom and T. Fortmann, Tracking and Data Association. Academic Press, 1988.
[4] R. Kalman, “A New Approach to Linear Filtering and Prediction Problems,” J. Basic Eng., vol. 82, pp. 35-45, 1960.
[5] D. Mumford, “Pattern Theory: A Unifying Perspective,” Perception as Bayesian Inference, D. Knill and W. Richards, eds., pp. 25-62, Cambridge Univ. Press, 1996.
[6] B. Ripley, Pattern Recognition and Neural Networks. Cambridge Univ. Press, 1996.
[7] M. Isard and A. Blake, “Condensation-Conditional Density Propagation for Visual Tracking,” Int'l J. Computer Vision, vol. 29, pp. 5-28, 1998.
[8] D. Knill, D. Kersten, and A. Yuille, “Introduction: A Bayesian Formulation of Visual Perception,” Perception as Bayesian Inference, D. Knill and W. Richards, eds., pp. 1-21, Cambridge Univ. Press, 1996.
[9] J.D. Foley,A. van Dam,S.K. Feiner,, and J.F. Hughes,Computer Graphics: Principles and Practice,Menlo Park, Calif.: Addison-Wesley, 1990.
[10] C. Rasmussen and G. Hager, “Tracking Objects by Color Alone,” Technical Report DCS-RR-1114, Yale Univ., 1996.
[11] C. Rasmussen, “Integrating Multiple Visual Cues for Robust Tracking,” PhD thesis, Yale Univ., New Haven, Conn., 2000.
[12] G. Klinker, S. Shafer, and T. Kanade, “A Physical Approach to Color Image Understanding,” Int'l J. Computer Vision, vol. 4, pp. 7-38, 1990.
[13] R. Duda and P. Hart, Pattern Classification and Scene Analysis. John Wiley and Sons, 1973.
[14] B. Lucas and T. Kanade, “An Iterative Image Registration Technique with an Application to Stereo Vision,” Proc. Int'l Joint Conf. Artificial Intelligence, pp. 674-679, 1981.
[15] J. Shi and C. Tomasi, Good Features to Track Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 593-600, 1994.
[16] G. Hager and P. Belhumeur, “Efficient Region Tracking with Parametric Models of Geometry and Illumination,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 10, pp. 1025-1039, Oct. 1998.
[17] A. Blake, M. Isard, and D. Reynard, “Learning to Track the Visual Motion of Contours,” Artificial Intelligence, no. 78, pp. 101-133, 1995.
[18] D. Terzopoulos and R. Szeliski, “Tracking with Kalman Snakes,” Active Vision, A. Blake and A. Yuille, eds., pp. 3-20, MIT Press, 1992.
[19] J. Canny, “A Computational Approach to Edge Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, no. 6, pp. 679-698, June 1986.
[20] I. Sobel, “An Isotropic$3 \times 3$Image Gradient Operator,” Machine Vision for Three-Dimensional Scenes, H. Freeman, ed., pp. 376-379, Academic Press, 1990.
[21] J. Hoschek and D. Lasser, Fundamentals of Computer-Aided Geometric Design. A.K. Peters, 1993.
[22] A. Watt and M. Watt, Advanced Animation and Rendering Techniques. Reading, Mass.: ACM Press and Addison-Wesley, pp. 119-124, 1992.
[23] M. Isard and A. Blake, “Contour Tracking by Stochastic Propagation of Conditional Density,” Proc. European Conf. Computer Vision, pp. 343-356, 1996.
[24] B.K. Horn, Robot Vision. Cambridge, Mass.: MIT Press, 1986.
[25] J.R. Bergen, P. Anandan, K.J. Hanna, and R. Hingorani, “Hiercharchical Model-Based Motion Estimation,” Proc. European Conf. Computer Vision, pp. 237-252, 1992.
[26] I. Cox, “A Review of Statistical Data Association Techniques for Motion Correspondence,” Int'l J. Computer Vision, vol. 10, no. 1, pp. 53-65, 1993.
[27] D. Koller, J. Weber, and J. Malik, “Robust Multiple Car Tracking with Occlusion Reasoning,” Computer Vision-ECCV '94, J.-O. Eklundh, ed., vol. 1, pp. 189-196, 1994.
[28] J.M. Rehg and T. Kanade, “Model-Based Tracking of Self-Occluding Articulated Objects,” Proc. Fifth Int'l Conf. Computer Vision, pp. 612–617, June 1995.
[29] C. Bregler and J. Malik, “Tracking People with Twists and Exponential Maps,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 8–15, June 1998.
[30] M. Yamamoto and K. Koshikawa, “Human Motion Analysis Based on a Robot Arm Model,” Proc. Conf. Computer Vision and Pattern Recognition, 1991.
[31] S. Basu, I. Essa, and A. Pentland, “Motion Regularization for Model-Based Head Tracking,” Proc. Int'l Conf. Pattern Recognition, 1996.
[32] D.D. Morris, J.M. Rehg, “Singularity Analysis for Articulated Object Tracking,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 289–296, June 1998.
[33] A. Pentland and B. Horowitz, “Recovery of Non-Rigid Motion and Structure,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 7, pp. 730-742, July 1991.
[34] J. MacCormick and A. Blake, “A Probabilistic Exclusion Principle for Tracking Multiple Objects,” Proc. Int'l Conf. Computer Vision, 1999.
[35] T.J. Cham and J. Rehg, “A Multiple Hypothesis Approach to Figure Tracking,” Proc. Conf. Computer Vision and Pattern Recognition, vol. II, pp. 239–245, June 1999.

Index Terms:
Visual tracking, data association, color regions, textured regions, snakes.
Citation:
Christopher Rasmussen, Gregory D. Hager, "Probabilistic Data Association Methods for Tracking Complex Visual Objects," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 6, pp. 560-576, June 2001, doi:10.1109/34.927458