| | This Article | |
| |
| |
| | Share | |
| |
| |
| | Bibliographic References | |
| |
| |
| | Add to: | |
| |
 Digg
 Furl
 Spurl
 Blink
 Simpy
 Google
 Del.icio.us
 Y!MyWeb
| |
| | Search | |
| |
| |
| | |
Spatio-Temporal Context for Robust Multitarget Tracking
January 2007 (vol. 29 no. 1)
pp. 52-64
In multitarget tracking, the main challenge is to maintain the correct identity of targets even under occlusions or when differences between the targets are small. The paper proposes a new approach to this problem by incorporating the context information. The context of a target in an image sequence has two components: the spatial context including the local background and nearby targets and the temporal context including all appearances of the targets that have been seen previously. The paper considers both aspects. We propose a new model for multitarget tracking based on the classification of each target against its spatial context. The tracker searches a region similar to the target while avoiding nearby targets. The temporal context is included by integrating the entire history of target appearance based on probabilistic principal component analysis (PPCA). We have developed a new incremental scheme that can learn the full set of PPCA parameters accurately online. The experiments show robust tracking performance under the condition of severe clutter, occlusions, and pose changes.
[1] 52 S. Avidan, “Support Vector Tracking,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 8, pp. 1064-1072, Aug. 2004.[2] Y. Bar-Shalom and T. Fortmann, Tracking and Data Association. Academic Press, 1988.[3] M. Brand, “Incremental Singular Value Decomposition of Uncertain Data with Missing Values,” Proc. European Conf. Computer Vision, p. 707ff, 2002.[4] E. Brunskill and N. Roy, “SLAM Using Incremental Probabilistic PCA and Dimensionality Reduction,” Proc. IEEE Int'l Conf. Robotics and Automation, 2005.[5] R. Collins and Y. Liu, “On-Line Selection of Discriminative Tracking Features,” Proc. IEEE Conf. Computer Vision, pp. 346-352, 2003.[6] P.M. Hall, D.R. Marshall, and R.R. Martin, “Merging and Splitting Eigenspace Models,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 9, pp. 1042-1049, Sept. 2000.[7] J. Ho, K.C. Lee, M.H. Yang, and D.J. Kriegman, “Visual Tracking Using Learned Linear Subspaces,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 782-789, 2004.[8] M. Isard, “PAMPAS: Real-Valued Graphical Models for Computer Vision,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 613-620, 2003.[9] M. Isard and J.P. MacCormick, “BraMBLe: A Bayesian Multiple-Blob Tracker,” Proc. IEEE Conf. Computer Vision, vol. 2, pp. 34-41, 2001.[10] Z. Khan, T. Balch, and F. Dellaert, “An MCMC-Based Particle Filter for Tracking Multiple Interacting Targets,” Proc. European Conf. Computer Vision, vol. 4, pp. 279-290, 2004.[11] Z. Khan, T. Balch, and F. Dellaert, “A Rao-Blackwellized Particle Filter for Eigentracking,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 980-986, 2004.[12] A. Levy and M. Lindenbaum, “Sequential Karhunen-Loeve Basis Extraction and Its Application to Images,” IEEE Trans. Image Processing, vol. 9, no. 8, pp. 1371-1374, 2000.[13] J. Lim, D. Ross, R.S. Lin, and M.H. Yang, “Incremental Learning for Visual Tracking,” Proc. Neural Information Processing Systems, 2004.[14] R.S. Lin, D. Ross, J. Lim, and M.H. Yang, “Adaptive Discriminative Generative Model and Its Applications,” Proc. Neural Information Processing Systems, 2004.[15] B. Moghaddam and A.P. Pentland, “Probabilistic Visual Learning for Object Detection,” Proc. IEEE Conf. Computer Vision, pp. 786-793, 1995.[16] H.T. Nguyen and A.W.M. Smeulders, “Tracking Aspects of the Foreground against the Background,” Proc. European Conf. Computer Vision, vol. 2, pp. 446-456, 2004.[17] H.T. Nguyen, M. Worring, and R. van den Boomgaard, “Occlusion Robust Adaptive Template Tracking,” Proc. IEEE Conf. Computer Vision, vol. 1, pp. 678-683, 2001.[18] W.H Press, S.A. Teukolsky, W.T Vetterling, and B.P Flannery, Numerical Recipes in C. Cambridge Univ. Press, 1992.[19] C. Rasmussen and G.D. Hager, “Probabilistic Data Association Methods for Tracking Complex Visual Objects,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 6, pp. 560-576, June 2001.[20] D.B. Reid, “An Algorithm for Tracking Multiple Targets,” IEEE Trans. Automation and Control, vol. 24, no. 6, pp. 843-854, 1979.[21] D. Ross, J. Lim, and M.H. Yang, “Adaptive Probabilistic Visual Tracking with Incremental Subspace Update,” Proc. European Conf. Computer Vision, vol. 2, pp. 470-482, 2004.[22] H. Tao, H.S. Sawhney, and R. Kumar, “Dynamic Layer Representation with Applications to Tracking,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 134-141, 2000.[23] M.E. Tipping and C.M. Bishop, “Probabilistic Principal Component Analysis,” J. Royal Statistical Soc., Series B, vol. 61, no. 3, pp.611-622, 1999.[24] D.M. Titterington, “Recursive Parameter Estimation Using Incomplete Data,” J. Royal Statistical Soc., Series B, vol. 46, no. 2, pp.257-267, 1984.[25] O. Williams, A. Blake, and R. Cipolla, “A Sparse Probabilistic Learning Algorithm for Real-Time Tracking,” Proc. IEEE Conf. Computer Vision, pp. 353-360, 2003.[26] T. Yu and Y. Wu, “Collaborative Tracking of Multiple Targets,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp.834-841, 2004.[27] T. Zhao and R. Nevatia, “Tracking Multiple Humans in Crowded Environment,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 406-413, 2004.
Index Terms:
Multitarget tracking, context-based tracking, probabilistic PCA.
Citation:
Hieu T. Nguyen, Qiang Ji, Arnold W.M. Smeulders, "Spatio-Temporal Context for Robust Multitarget Tracking," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 1, pp. 52-64, Jan. 2007, doi:10.1109/TPAMI.2007.18
