Reply to "Comments on 'Joint Detection and Estimation of Multiple Objects from Image Observations'"

In this paper we present three theoretical results on conjugate priors for point processes (or random finite sets), namely Poisson, i.i.d. cluster, and multi-Bernoulli. As an example of the use of these results, the multi-Bernoulli conjugate prior was applied to multi-object filtering for image data...

Full description

Bibliographic Details
Main Authors: Vo, Ba-Ngu, Vo, Ba Tuong, Pham, N., Suter, D.
Format: Journal Article
Published: IEEE 2012
Online Access:http://hdl.handle.net/20.500.11937/27587
Description
Summary:In this paper we present three theoretical results on conjugate priors for point processes (or random finite sets), namely Poisson, i.i.d. cluster, and multi-Bernoulli. As an example of the use of these results, the multi-Bernoulli conjugate prior was applied to multi-object filtering for image data, which covers various tracking problems, including track before-detect (TkBD). Davey's comments only concern our implementation of the HPMHT algorithm used to benchmark the performance of the multi-Bernoulli filter in a numerical example involving TkBD.