Unconstrained Multiple-People Tracking
This work presents two main contributions to achieve robust multiple-target tracking in uncontrolled scenarios. A novel system which consists on a hierarchical architecture is proposed. Each level is devoted to one of the main tracking functionalities: target detection, low-level tracking, and high-level tasks such as target-appearance representation, or event management. Secondly, tracking performances are enhanced by on-line building and updating multiple appearance models. Successful experimental results are accomplished on sequences with significant illumination changes, grouping, splitting and occlusion events.
KeywordsTarget Appearance Occlusion Event Bhattacharyya Distance Feature Pool Blob Detection
Unable to display preview. Download preview PDF.
- 1.Arulampalam, S., Maskell, S., Gordon, N., Clapp, T.: A Tutorial on PFs for On-line Non-linear/Non-Gaussian Bayesian Tracking. SP 50(2), 174–188 (2002)Google Scholar
- 2.Bar-Shalom, Y., Fortran, T.: Tracking and Data Association. A. Press (1988)Google Scholar
- 3.Collins, R., Liu, Y., Leordeanu, M.: Online Selection of Discriminative Tracking Features. PAMI 27(10), 1631–1643 (2005)Google Scholar
- 4.Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based Object Tracking. PAMI 25(5), 564–577 (2003)Google Scholar
- 6.Gonzàlez, J.: Human Sequence Evaluation: The Key-frame Approach. PhD thesis, UAB, Spain (2004)Google Scholar
- 7.Horprasert, T., Harwood, D., Davis, L.: A Robust Background Subtraction and Shadow Detection. In: 4th ACCV, Taipei, Taiwan, vol. 1, pp. 983–988 (2000)Google Scholar
- 10.Nummiaro, K., Koller-Meier, E., Van Gool, L.: An Adaptive Color-Based Particle Filter. IVC 21(1), 99–110 (2003)Google Scholar