Target Motion Analysis in Clutter With ML-PDA and ML-PMHT Using Partial Prior Information

M. Phil Lowney

doi:10.1109/TAES.2025.3628313

Target Motion Analysis in Clutter With ML-PDA and ML-PMHT Using Partial Prior Information

2026-01-01

0

PRE

AI

DOI：10.1109/TAES.2025.3628313

Original

Original request for help

Save

Abstract

En 中文

This work expands upon a recently introduced concept of using pseudomeasurements to incorporate partial prior information into the process of target motion analysis. The prior information may include knowledge of the initial target range and/or speed, which is modeled as a pseudomeasurement with a specific distribution. Rather than assuming a “clean” environment, this research considers a more realistic tracking setting, where the target may be missed and false alarms may be detected. Two estimators are derived, as extensions to the maximum likelihood probabilistic data association algorithm as well as the maximum likelihood probabilistic multihypothesis tracker. The performance bounds follow as an extension to the Cramer–Rao lower bound in clutter. A track validation method is presented. The statistical efficiency and increased performance due to the partial prior are confirmed using Monte-Carlo simulations.

Keywords:

Target tracking

Noise measurement

Clutter

Observers

Vectors

Maximum likelihood estimation

Frequency measurement

Probabilistic logic

Observability

Time measurement

Target Motion Analysis in Clutter With ML-PDA and ML-PMHT Using Partial Prior Information

Abstract

Journal

Organization