An EM‐based adaptive multiple target tracking filter

Jeong, Hong; Park, Jeong-Ho

doi:10.1002/acs.661

Cited by 4 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the additional measurement noise covariances also lead to tracking accuracy degradation. The multimodel implementation in homothetic PMHT inspired many PMHT modifications such as multi-frame PMHT [22], spirograph PMHT [29], and adaptive homothetic PMHT [30]. Unfortunately, these multi-model PMHT approaches fail to show consistent improvements to homothetic PMHT.…”

Section: Introductionmentioning

confidence: 99%

Variational Probabilistic Multi-Hypothesis Tracking

Xu¹,

Shin²,

Tsourdos³

2022

Preprint

View full text Add to dashboard Cite

This paper proposes a novel multi-target tracking (MTT) algorithm for scenarios with arbitrary numbers of measurements per target. We propose the variational probabilistic multi-hypothesis tracking (VPMHT) algorithm based on the variational Bayesian expectation-maximisation (VBEM) algorithm to resolve the MTT problem in the classic PMHT algorithm. With the introduction of variational inference, the proposed VPMHT handles track-loss much better than the conventional probabilistic multi-hypothesis tracking (PMHT) while preserving a similar or even better tracking accuracy. Extensive numerical simulations are conducted to demonstrate the effectiveness of the proposed algorithm.

show abstract

Section: Introductionmentioning

confidence: 99%

Variational Probabilistic Multi-Hypothesis Tracking

Xu¹,

Shin²,

Tsourdos³

2022

Preprint

View full text Add to dashboard Cite

show abstract

Least‐squares‐based adaptive target localization by mobile distance measurement sensors

Fi̇dan

Çamlıca

Güler

2014

Adaptive Control & Signal

View full text Add to dashboard Cite

A least-squares-based adaptive algorithm with forgetting factor is proposed for localization of a target by a mobile distance measurement sensor. This problem, in its most general form, was tackled in a recent paper using a gradient adaptive algorithm, assuming distance measurements are directly available. We establish that the proposed algorithm bears the same stability and convergence properties as the gradient algorithm previously studied. It is demonstrated via simulations that the proposed algorithm converges significantly faster to the location estimates than the gradient algorithm for high forgetting factor values and significantly reduces the noise effects for small values of the forgetting factor. Furthermore, a more challenging form of the original problem is considered, where distance information is required to be deduced from time of flight measurements, considering a time of flight-based active distance measurement sensor and an environment with unknown signal permittivity/speed; the proposed algorithm is redesigned to solve this problem.

show abstract