Centralized multi-sensor multi-target tracking with labeled random finite set

Abstract

Tracking multiple objects with multiple sensors is widely recognized to be much more complex than the single-sensor scenario. This contribution proposes a computationally tractable multi-sensor multi-target tracker. Based on Bayes equation and multi-senor observation model, a new corrector for multi-senor is derived. To lower the complexity of update operation, a parallel track-to-measurement association strategy is applied to the corrector. Hypotheses truncation scheme along with first-moment approximation of multi-target density are also employed to improve the tracking efficiency. The tracker is applied to a couple-sensor scenario. Experiment results validate the advantages of proposed method compared to the standard single-sensor δ-generalized labeled multi-Bernoulli filter and the iterated-corrector probability hypothesis density filter.

Keywords

Multi-target tracking multi-sensor labeled random finite set multi-Bernoulli filter particle filter

Get full access to this article

View all access options for this article.

References

Mahler

. Multi-target Bayes filtering via first-order multi-target moments. IEEE Trans Aero Electron Syst 2003; 39: 1152–1178.

Mahler

. Statistical multisource-multitarget information fusion, Norwood, MA: Artech House, 2007.

Mahler

. PHD filters of higher order in target number. IEEE Trans Aero Electron Syst 2007; 43: 1523–1543.

Mahler

. “Statistic 102” for multisource-multitarget detection and tracking. IEEE J Sel Top Signal Process 2013; 7: 376–389.

Cantoni

. The cardinality balanced multi-target multi-Bernoulli filter and its implementations. IEEE Trans Signal Process 2009; 57: 409–423.

Nagappa S and Clark D. On the ordering of the sensors in the iterated-corrector probability hypothesis density filter. In: Proceedings of the SPIE conference on signal processing, sensor fusion and target recognition XX, Orlando, FL, USA, 25–27 April 2011, pp.1–6. Washington, USA: SPIE.

Mahler R. The multisensor PHD filter: I. General solution via multitarget calculus. In: Proceedings of the SPIE conference on signal processing, sensor fusion and target recognition XVIII, Orlando, FL, USA, 13–15 April 2009, pp.1–8. Washington, USA: SPIE.

Mahler R. Approximate multisensor CPHD and PHD filters. In: Proceedings of the 13th international conference on information fusion, Edinburgh, 26–29 July 2010, pp.1–6. New Jersey, USA: IEEE.

Ouyang C and Ji H. Scale unbalance problem in product multisenor PHD filter. Electron Lett 2011; 47: 1247–1249.

10.

Delande E, Duflos E, Vanheeghe P, et al. Multi-sensor PHD: construction and implementation by space partitioning. In: Proceedings of the IEEE international conference on acoustics, speech and signal processing, Prague, 22–27 May 2011, pp.3632–3635. New Jersey, USA: IEEE.

11.

Bozdoan AO, Efe M and Streit R. A new heuristic for multisensor PHD filter. In: Proceedings of the 17th international conference on information fusion, Salamanca, 7–10 July 2014, pp.1–8. New Jersey, USA: IEEE.

12.

Liu

Fan

. Improved iterated-corrector PHD with Gaussian mixture implementation. Signal Process 2015; 114: 89–99.

13.

. Labeled random finite sets and multi-object conjugate priors. IEEE Trans Signal Process 2013; 61: 3460–3475.

14.

Phung

. Labeled random finite sets and the Bayes multi-target tracking filter. IEEE Trans Signal Process 2014; 62: 6554–6567.

15.

Pattipati

Deb

Bar-Shalom

. A new relaxation algorithm and passive sensor data association. IEEE Trans Autom Control 1992; 37: 198–213.

16.

Miller

Stone

Cox

. Optimizing Murty’s ranked assignment method. IEEE Trans Aero Electron Syst 1997; 33: 851–862.

17.

Deb

Yeddanapudi

Pattipati

. A generalized S-D assignment algorithm for multisensor-multitarget state estimation. IEEE Trans Aero Electron Syst 1997; 33: 523–538.

18.

Reuter

. The labeled multi-Bernoulli filter. IEEE Trans Signal Process 2014; 62: 3246–3260.

19.

Beard

. Bayesian multi-target tracking with merged measurements using labeled random finite sets. IEEE Trans Signal Process 2015; 63: 1433–1447.

20.

Schuhmacher

. A consistent metric for performance evaluation of multi-object filters. IEEE Trans Signal Process 2008; 56: 3447–3457.