Vision-Based Multiple Interacting Targets Tracking via On-Line Supervised Learning
Abstract
Successful multi-target tracking requires locating the targets and labeling their identities. This mission becomes significantly more challenging when many targets frequently interact with each other (present partial or complete occlusions). This paper presents an on-line supervised learning based method for tracking multiple interacting targets. When the targets do not interact with each other, multiple independent trackers are employed for training a classifier for each target. When the targets are in close proximity or present occlusions, the learned classifiers are used to assist in tracking. The tracking and learning supplement each other in the proposed method, which not only deals with tough problems encountered in multi-target tracking, but also ensures the entire process to be completely on-line. Various evaluations have demonstrated that this method performs better than previous methods when the interactions occur, and can maintain the correct tracking under various complex tracking situations, including crossovers, collisions and occlusions.
Keywords
Target Tracking Image Patch Data Association Tracking Result Continuous FrameSupplementary material
References
- 1.Avidan, S.: Ensemble tracking. IEEE Trans. PAMI 29, 261–271 (2007)CrossRefGoogle Scholar
- 2.Le, L., Gregory, D.: A nonparametric treatment for location/segmentation based visual tracking. In: Proc. IEEE CVPR, pp. 261–268 (2007)Google Scholar
- 3.Bar-Shalom, Y., Fortmann, T.E.: Tracking and data association. Academic Press, New York (1998)zbMATHGoogle Scholar
- 4.Okuma, K., Taleghani, A., Freitas, N.D., Little, J.J., Lowe, D.G.: A boosted particle filter: Multitarget detection and tracking. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 28–39. Springer, Heidelberg (2004)CrossRefGoogle Scholar
- 5.Vermaak, J., Doucet, A., Perez, P.: Maintaining multi-modality through mixture tracking. In: Proc. IEEE ICCV, pp. 1110–1116 (2003)Google Scholar
- 6.Zhao, T., Nevatia, R.: Tracking multiple humans in complex situations. IEEE Trans. PAMI 7, 1208–1221 (2004)CrossRefGoogle Scholar
- 7.Rasmussen, C., Hager, G.: Probabilistic data association methods for tracking complex visual objects. IEEE Trans. PAMI 23, 560–576 (2001)CrossRefGoogle Scholar
- 8.Gennari, G., Hager, G.: Probabilistic data association methods in visual tracking of groups. In: Proc. IEEE CVPR, pp. 876–881 (2004)Google Scholar
- 9.Vermaak, J., Godsill, S.J., Perez, P.: Monte carlo filtering for multi target tracking and data association. IEEE Trans. Aerospace and Electronic Systems 41, 309–332 (2005)CrossRefGoogle Scholar
- 10.Schulz, D., Burgard, W., Fox, D., Cremers, A.: People tracking with a mobile robot using sample-based joint probabilistic data association filters. International Journal of Robotics Research 22, 99–116 (2003)CrossRefGoogle Scholar
- 11.Oh, S., Russell, S., Sastry, S.: Markov chain monte carlo data association for general multiple target tracking problems. In: Proc. IEEE Conf. Decision and Control, pp. 735–742 (2004)Google Scholar
- 12.Khan, Z., Balch, T., Dellaert, F.: Mcmc data association and sparse factorization updating for real time multitarget tracking with merged and multiple measurements. IEEE Trans. PAMI 28, 1960–1972 (2006)CrossRefGoogle Scholar
- 13.Yu, Q., Medioni, G., Cohen, I.: Multiple target tracking using spatio-temporal markov chain monte carlo data association. In: Proc. IEEE CVPR, pp. 642–649 (2007)Google Scholar
- 14.Cai, Y., Freitas, N.D., Little, J.J.: Robust visual tracking for multiple targets. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 125–135. Springer, Heidelberg (2006)Google Scholar
- 15.Khan, Z., Balch, T., Dellaert, F.: Mcmc-based particle filtering for tracking a variable number of interacting targets. IEEE Trans. PAMI 27, 1805–1819 (2005)CrossRefGoogle Scholar
- 16.Qu, W., Schonfeld, D., Mohamed, M.: Real-time interactively distributed multi-object tracking using a magnetic-inertia potential model. In: Proc. IEEE ICCV, pp. 535–540 (2005)Google Scholar
- 17.Lanz, O., Manduchi, R.: Hybrid joint-separable multibody tracking. In: Proc. IEEE CVPR, pp. 413–420 (2005)Google Scholar
- 18.Sullivan, J., Carlsson, S.: Tracking and labeling of interacting multiple targets. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3953, pp. 661–675. Springer, Heidelberg (2006)Google Scholar
- 19.Nillius, P., Sullivan, J., Carlsson, S.: Multi-target tracking - linking identities using bayesian network inference. In: Proc. IEEE CVPR, pp. 2187–2194 (2006)Google Scholar
- 20.Li, Y., Ai, H.Z., Yamashita, T., Lao, S., Kawade, M.: Tracking in low frame rate video: A cascade particle filter with discriminative observers of different life-spans. In: Proc. IEEE CVPR, pp. 1–8 (2007)Google Scholar
- 21.Grabner, H., Bischof, H.: On-line boosting and vision. In: Proc. IEEE CVPR, pp. 260–267 (2006)Google Scholar
- 22.Zhe, L., Larry, S.D., David, D., Daniel, D.: Hierarchical part-template matching for human detection and segmentation. In: Proc. IEEE ICCV, pp. 351–358 (2007)Google Scholar
- 23.Leibe, B., Seemann, E., Schiele, B.: Pedestrian detection in crowded scenes. In: Proc. IEEE CVPR, pp. 661–668 (2005)Google Scholar
- 24.Stauffer, C., Grimson, W.: Adaptive background mixture models for real-time tracking. In: Proc. IEEE ICCV, pp. 37–63 (1999)Google Scholar
- 25.Davis, J., Sharma, V.: Fusion-based background-subtraction using contour saliency. In: Proc. IEEE CVPR, pp. 20–26 (2005)Google Scholar
- 26.Comaniciu, D., Visvanathan, R., Meer, P.: Kernel-based object tracking. IEEE Trans. PAMI 25, 564–575 (2003)CrossRefGoogle Scholar
- 27.Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. In: Proc. IEEE CVPR, pp. 142–149 (2000)Google Scholar
- 28.Isard, M., Blake, A.: Condensation - conditional density propagation for visual tracking. International Journal of Computer Vision 28, 5–28 (1998)CrossRefGoogle Scholar
- 29.Perez, P., Hue, C., Vermaak, J.: Color-based probabilistic tracking. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 661–675. Springer, Heidelberg (2002)CrossRefGoogle Scholar
- 30.Lu, L., Hager, G.: Dynamic foreground/background extraction from images and videos using random patches. In: Proc. NIPS, pp. 351–358 (2006)Google Scholar
- 31.Breiman, L., Friedman, J.H., Olshen, R., Stone, C.J.: Classification and regression trees. Wadsworth, Chapman Hall, New York (1984)zbMATHGoogle Scholar
- 32.Doucet, A., Godsill, S.J., Andrieu, C.: On sequential monte carlo sampling methods for bayesian filtering. Statistics and Computing 10, 197–208 (2000)CrossRefGoogle Scholar
- 33.SCEPTRE-Dataset, http://sceptre.king.ac.uk/sceptre/default.html
- 34.Davis, J., Sharma, V.: Otcbvs benchmark dataset 03, http://www.cse.ohio-state.edu/otcbvs-bench/
- 35.