Global data association for multi-object tracking using network flows
Li Zhang, Yuan Li, Ramakant Nevatia · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2008
We propose a network flow based optimization method for data association needed for multiple object tracking. The maximum-a-posteriori (MAP) data association problem is mapped into a cost-flow network with a non-overlap constraint on trajectories. The optimal data association is found by a min-cost flow algorithm in the network. The network is augmented to include an Explicit Occlusion Model(EOM) to track with long-term inter-object occlusions. A solution to the EOM-based network is found by an iterative approach built upon the original algorithm. Initialization and termination of trajectories and potential false observations are modeled by the formulation intrinsically. The method is efficient and does not require hypotheses pruning. Performance is compared with previous results on two public pedestrian datasets to show its improvement.
Cited by 925 works. doi:10.1109/cvpr.2008.4587584
Authors
References
- Network Flows: Theory, Algorithms, and Applications.
- An algorithm for tracking multiple targets
- Depth and Appearance for Mobile Scene Analysis
- MCMC-based particle filtering for tracking a variable number of interacting targets
- Coupled Detection and Trajectory Estimation for Multi-Object Tracking
- Tracking of Multiple, Partially Occluded Humans based on Static Body Part Detection
- Multi-Object Tracking Through Simultaneous Long Occlusions and Split-Merge Conditions
- Robust People Tracking with Global Trajectory Optimization
- An Efficient Implementation of a Scaling Minimum-Cost Flow Algorithm
- A Linear Programming Approach for Multiple Object Tracking