APSYSYMar 31, 2016

A track-before-detect labelled multi-Bernoulli particle filter with label switching

arXiv:1604.0008235 citationsh-index: 27
Originality Synthesis-oriented
AI Analysis

This work addresses the problem of maintaining target identity in multitarget tracking under low-SNR conditions for practitioners in surveillance and remote sensing.

The paper develops a labelled multi-Bernoulli particle filter for track-before-detect multitarget tracking, incorporating a label switching improvement algorithm. In numerical tests, the filter demonstrates robust performance in challenging scenarios with closely spaced targets.

This paper presents a multitarget tracking particle filter (PF) for general track-before-detect measurement models. The PF is presented in the random finite set framework and uses a labelled multi-Bernoulli approximation. We also present a label switching improvement algorithm based on Markov chain Monte Carlo that is expected to increase filter performance if targets get in close proximity for a sufficiently long time. The PF is tested in two challenging numerical examples.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes