1. Comments on “Joint Detection and Estimation of Multiple Objects From Image Observations”.
- Author
-
Davey, Samuel J.
- Subjects
- *
EXPECTATION-maximization algorithms , *TRACKING algorithms , *GAUSSIAN processes , *ESTIMATION theory , *SIMULATION methods & models - Abstract
The above article [1] introduced an algorithm for multitarget track-before-detect based on a multi-Bernoulli random finite set model (MB-TBD). This new algorithm was compared with the Histogram Probabilistic Multi-Hypothesis Tracker (H-PMHT) on simulated data examples containing multiple targets with non-linear dynamics. The authors reported poor performance from H-PMHT and described several deficiencies of the algorithm. This note highlights unnecessary assumptions made in the assessment of H-PMHT and repeats two of the simulation examples after relaxing them. We demonstrate a substantial improvement in performance compared with the originally published results. The simulation example is also shown to be a relatively high signal to noise problem and good performance is obtained from a conventional detect-then-track algorithm. [ABSTRACT FROM PUBLISHER]
- Published
- 2012
- Full Text
- View/download PDF