Title :
Histogram-PMHT with an evolving Poisson prior
Author :
Vu, Han X. ; Davey, Samuel J. ; Arulampalam, Sanjeev ; Fletcher, Fiona K. ; Cheng-Chew Lim
Author_Institution :
Defence Sci. & Technol. Organ., Edinburgh, SA, Australia
Abstract :
The Histogram-Probabilistic Multi-Hypothesis Tracker (H-PMHT) is an efficient multi-target tracking approach to the Track-Before-Detect (TkBD) problem. However, it cannot adequately deal with fluctuating targets and this can degrade track management performance. By assuming an alternative measurement model based on a Poisson distribution, the H-PMHT algorithm can be re-derived to incorporate a time-correlated estimate of the component mixing terms, allowing for an improved measure for track quality.
Keywords :
Poisson distribution; correlation theory; target tracking; Poisson distribution; TkBD problem; evolving Poisson prior; histogram-PMHT; histogram-probabilistic multihypothesis tracker; time-correlated estimation; track management performance; track-before-detect problem; Signal to noise ratio; Track-Before-Detect;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on
Conference_Location :
South Brisbane, QLD
DOI :
10.1109/ICASSP.2015.7178734