Robust Multi-target Tracking with Bootstrapped-GLMB Filter
This dissertation presents novel multi-target tracking algorithms that obviate the need for prior knowledge of system parameters such as clutter rate, detection probabilities, and birth models. Information on these parameters is unknown but important to tracking performance. The proposed algorithms...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
Curtin University
2022
|
| Online Access: | http://hdl.handle.net/20.500.11937/88811 |
| Summary: | This dissertation presents novel multi-target tracking algorithms that obviate the need for prior knowledge of system parameters such as clutter rate, detection probabilities, and birth models. Information on these parameters is unknown but important to tracking performance. The proposed algorithms exploit the advantages of existing RFS trackers and filters by bootstrapping them. This configuration inherits the efficiency of tracking target trajectories from the RFS trackers and low complexity in parameter estimation from the RFS filters. |
|---|