Core Concepts
Introducing augmented LRFSs for improved group target tracking performance.
Abstract
The paper addresses the problem of group target tracking using augmented labeled random finite sets (LRFSs). It introduces a new kind of LRFS, called augmented LRFSs, which incorporate group information into the definition. By utilizing the labeled multi-Bernoulli filter with augmented LRFSs, the paper achieves simultaneous estimation of kinetic states, track labels, and corresponding group information for multiple group targets. The simulation experiments demonstrate the effectiveness of this approach in improving GTT tracking performance.
Structure:
Introduction to Group Target Tracking (GTT)
Challenges and applications in civil and military fields.
Existing GTT Methods: ETT vs. RGTT based methods.
Proposed Augmented LRFSs Theory:
Definition and properties of RFSs and LRFSs.
System Model:
Dynamic model and measurement model for GTT scenario.
Application of Augmented LRFS to Group Target Tracking:
Multi-target likelihood function and transition kernel formulation.
LMB Filter with Augmented LRFS for Group Target Tracking:
State prediction, update, and group information update steps explained.
Performance Evaluation:
Parameters settings for two-dimensional scenario with up to 6 targets.
Stats
Li et al proposed the leader follower labeled multi-Bernoulli filter combining LMB filter with LF model.
Liu et al classified GTT issue into target state estimation and group state estimation steps.
Quotes
"The main contributions include proposing augmented LRFSs integrating group information."
"Simulation experiments demonstrate effectiveness in improving GTT tracking performance."