© The Institution of Engineering and Technology
The conventional probability hypothesis density filter is suitable for practical calculations but gives a result that shows a dependence on the sensor order. Since the multisensor version of the probability hypothesis density (PHD) filter is possible but computationally intractable, Mahler proposed a product multisensor PHD approximation recently. However, this algorithm is not verified by simulation experiments, and it is found that there is a scale unbalance problem in its sequential Monte Carlo implementation. To solve this problem, an ad hoc approach is proposed, which calculates the joint likelihood function in the product form but the scale factor in the summation form, respectively. Simulation results show that the proposed algorithm can solve the problem effectively.
References
-
-
1)
-
D. Schuhmacher ,
B.T. Vo ,
B.N. Vo
.
A consistent metric for performance evaluation of multi-object filters.
IEEE Trans. Signal Process.
,
8 ,
3447 -
3457
-
2)
-
I. Goodman ,
R. Mahler ,
H. Nguyen
.
(1997)
Mathematics of data fusion.
-
3)
-
B.N. Vo ,
S. Singh ,
A. Doucet
.
Sequential Monte Carlo methods for Bayesian multi-target filtering with random finite sets.
IEEE Trans. Aerosp. Electron. Syst.
,
4 ,
1224 -
1245
-
4)
-
B.N. Vo ,
W.K. Ma
.
The Gaussian mixture probability hypothesis density filter.
IEEE Trans. Signal Process.
,
11 ,
4091 -
4104
-
5)
-
R. Mahler
.
Multi-target Bayes filtering via first-order multi-target moments.
IEEE Trans. Aerosp. Electron. Syst.
,
4 ,
1152 -
1178
-
6)
-
Mahler, R.: `Approximate multisensor CPHD and PHD filters', 13thInt. Conf. on Information Fusion, 2010, Edinburgh, UK, p. 1152–1178.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2011.1843
Related content
content/journals/10.1049/el.2011.1843
pub_keyword,iet_inspecKeyword,pub_concept
6
6