CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

Performance Evaluation of MHT and GM-CPHD in a Ground Target Tracking Scenario

Daniel Svensson (Institutionen för signaler och system, Signalbehandling) ; Johannes Wintenby ; Lennart Svensson (Institutionen för signaler och system, Signalbehandling)
Proceedings of the 12th International Conference on Information Fusion p. 300-307. (2009)
[Konferensbidrag, refereegranskat]

Performance evaluations of multi-target tracking algorithms are often limited to consider comparisons within the same algorithm family. In this paper, two conceptually different multi-target tracking algorithms are evaluated, namely a multiple-hypothesis tracking (MHT) algorithm and the Gaussian mixture cardinalized probability hypothesis density (GM-CPHD) filter. As a reference, a conventional single-hypothesis tracking algorithm is included in the evaluation. The performance is assessed using the root-mean square error of the estimated number of targets, and the recently published optimal subpattern assignment (OSPA) measure. The scenario under consideration is tracking of nine closely spaced ground targets, using simulated measurements from an airborne radar. By observing the estimation of the number of targets, as well as of the target states, conclusions are drawn regarding the behavior of MHT and GM-CPHD. For example, GM-CPHD is more responsive to changes in the number of targets, whereas MHT is less responsive, but produces a more stable output.

Nyckelord: GM-CPHD, MHT, Multi-target tracking, OSPA, ground target tracking, performance evaluation



Denna post skapades 2009-10-22. Senast ändrad 2014-12-09.
CPL Pubid: 100612

 

Läs direkt!


Länk till annan sajt (kan kräva inloggning)


Institutioner (Chalmers)

Institutionen för signaler och system, Signalbehandling

Ämnesområden

Signalbehandling
Elektroteknik

Chalmers infrastruktur

Relaterade publikationer

Denna publikation ingår i:


Target Tracking in Complex Scenarios