Object tracking aims at finding the locations of objects of the scene on each frame of the sequence. It has been a popular research area for decades of years, as it can provide motion information for semantic scene understanding and human behavior analysis.
We have several projects based on tracking such as counting vehicles, trajectory analysis and semantic region modeling.
Counting Vehicles from Semantic Regions
R. Zhao and X. Wang. IEEE Transactions on Intelligent Transportation Systems (TITS) 2013
Trajectory Analysis and Semantic Region Modeling Using Nonparametric Bayesian Models.
X. Wang, K. T. Ma, G. Ng, and E. Grimson. International Journal of Computer Vision (IJCV), Vol. 96, pp. 287-321, 2011.
Multi-class Object Tracking Algorithm that Handles Fragmentation and Grouping
B. Bose, X. Wang, and E. Grimson. in Proceedings of IEEE Computer Society Conference on Computer Vision and Patter Recognition (CVPR) 2007.