A Comparative Study of Monte-Carlo Methods for Multitarget Tracking

François Septier (1, 2) , Julien Cornebise (3) , Simon J. Godsill (4) , Yves Delignon (5, 1)

1 Institut TELECOM/TELECOM Lille1
2 LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
3 UBC-Computer Science - Computer Science Department
4 Signal Processing Group Dept of Engineering
5 LAGIS-SI

In this paper, we address the problem of tracking an unknown and time varying number of targets and their states from noisy observa- tions available at discrete intervals of time. Attention has recently fo- cused on the role of simulation-based approaches, including Monte Carlo methods, in solving multitarget tracking problem, as these methods are able to perform well for nonlinear and non-Gaussian data models. In this paper, we present a comparative study of several Monte-Carlo methods in terms of estimation quality and complexity.

Domains: Engineering Sciences [physics]; Signal and Image processing; Computer Science [cs]; Signal and Image Processing; Statistics [stat]; Applications [stat.AP]

François Septier, Julien Cornebise, Simon J. Godsill, Yves Delignon. A Comparative Study of Monte-Carlo Methods for Multitarget Tracking. IEEE International Workshop on Statistical Signal Processing, Jun 2011, Nice, France. pp.205-208, ⟨10.1109/SSP.2011.5967660⟩. ⟨hal-00685919⟩