A linear multisensor PHD filters via the measurement product space

Volume 10, Issue 5, pp 2408--2422

Publication Date: 2017-05-25

http://dx.doi.org/10.22436/jnsa.010.05.12

Authors

Weifeng Liu - School of Automation, Hangzhou Dianzi University, Xiasha Higher Education Zone, 310018 Hangzhou, P. R. China.
Yimei Chen - School of Automation, Hangzhou Dianzi University, Xiasha Higher Education Zone, 310018 Hangzhou, P. R. China.
Chenglin Wen - School of Automation, Hangzhou Dianzi University, Xiasha Higher Education Zone, 310018 Hangzhou, P. R. China.
Hailong Cui - School of Automation, Hangzhou Dianzi University, Xiasha Higher Education Zone, 310018 Hangzhou, P. R. China.

Abstract

The probability hypothesis density (PHD) is the first moment of RFS. Its integral over any region gives the expectation number of targets in that region. In the finite set statistics (FISST) framework, the PHD recursion, or PHD filter, approximate the multi-target Bayes recursion. This paper deals with the multisensor PHD filter under a linear correlation condition through multisensor product space and the measurement dimension extension (MDE) approach, which remains the similar appearance like the conventional PHD filters except the product space and some parameters in the filters. However, in the product space the dimension extended measurements may greatly increase the computational load. Therefore, we propose a fast algorithm for the linear multisensor PHD (LM-PHD) filters to increase the running speed and with cost of slightly sacrificing the tracking performance.

Keywords

Linear correlation, random finite set, PHD filter, dimension extension of measurements, product space.

References

[1] Y. Bar-Shalom, Tracking methods in a multitarget environment, IEEE Trans. Autom. Control, 23 (1978), 618–626.
[2] K. Chang, M. E. Pollock, M. K. Skrehot, Space-based millimeter wave debris tracking radar, Proc. SPIE, Monolithic Microwave Integrated Circuits for Sensors, Radar, and Communications Systems, Orlando, FL, 1475 (1991), 257– 266.
[3] L. Chen, Z.-Y. Zhao, H. Yan, A Probabilistic Relaxation Labeling (PRL) based method for C. elegans cell tracking in microscopic image sequences, IEEE J. Sel. Topics Signal Process, 10 (2016), 185–192.
[4] H. Deusch, S. Reuter, K. Dietmayer, The labeled multi-Bernoulli SLAM filter, IEEE Trans. Signal Process., 22 (2015), 1561–1565.
[5] W. J. Farrell, Interacting multiple model filter for tactical ballistic missile tracking, IEEE Trans. Aerosp. Electron. Syst., 44 (2008), 418–426.
[6] C. Huang, Y. Li, R. Nevatia, Multiple target tracking by learning-based hierarchical association of detection responses, IEEE Trans. Pattern Anal. Mach. Intell., 35 (2013), 898–910.
[7] J.-W. Kim, P. Menon, E. Ohlmeyer, Motion models for use with the Maneuvering Ballistic Missile tracking estimators, Proceedings of the AIAA guidance, navigation, and control conference, Toronto, Ontario, Canada, (2010), 1–13.
[8] M. F. Kircher, S. S. Gambhir, J. Grimm, Noninvasive cell-tracking methods, Nat. Rev. Clin. Oncol., 8 (2011), 677–688.
[9] F. Lian, C.-Z. Han, W.-F. Liu, H. Chen, Joint spatial registration and multi-target tracking using an extended probability hypothesis density filter, IET radar, sonar & navigation, 5 (2011), 441–448.
[10] L. Lin, Y. Bar-Shalom, T. Kirubarajan, Track labeling and PHD filter for multitarget tracking, IEEE Trans. Aerosp. Electron. Syst., 42 (2006), 778–795.
[11] W.-F. Liu, C.-L. Wen, A linear multisensor PHD filter using the measurement dimension extension approach, Advances in Swarm Intelligence: the 2th International Conference on Swarm Intelligence, Chongqing, China, (2011), 486–493.
[12] W.-F. Liu , C.-L.Wen, The fast linear multisensor RFS-multitarget tracking filters, Proceedings of the 17th International Conference on Information Fusion, Slamanca, Spanish, (2014), 1-8.
[13] R. P. S. Mahler, Multitarget Bayes filtering via first-order multitarget moments, IEEE Trans. Aerosp. Electron. Syst, 39 (2003), 1152–1178.
[14] R. P. S. Mahler, PHD filters of higher order in target number, IEEE Trans. Aerosp. Electron. Syst., 43 (2007), 1523–1543.
[15] R. P. S. Mahler, Statistical multisource-multitarget information fusion, Artech House, Inc., Norwood, MA, USA, (2007).
[16] R. P. S. Mahler, Approximate multisensor CPHD and PHD filters, Proceedings of the 13th International Conference on Information Fusion, (2010), 1152–1178.
[17] R. P. S. Mahler, Advances in statistical multisource-multitarget information fusion, Artech House, Inc., Norwood, MA, USA, (2014).
[18] R. P. S. Mahler, B.-T. Vo, B.-N. Vo, Forward-backward probability hypothesis density smoothing, IEEE Trans. Aerosp. Electron. Syst., 48 (2012), 707–728.
[19] N. Nandakumaran, K. Punithakumar, T. Kirubarajan, Improved multi-target tracking using probability hypothesis density smoothing, Proceedings of the SPIE Conference on Signal and Processing of Small Targets, 6699 (2007), 1–6.
[20] K. Panta, B.-N. Vo, S. Singh, Novel data association schemes for the probability hypothesis density filter, IEEE Trans. Aerosp. Electron. Syst., 43 (2007), 556–570.
[21] J. N. Pelton, Tracking of orbital debris and avoidance of satellite collisions, Handbook of Satellite Applications, Springer, New York, (2016), 1–13.
[22] D. B. Reid, An algorithm for tracking multiple targets, IEEE Trans. Autom. Control, 24 (1979), 843–854.
[23] S. Reuter, B.-T. Vo, B.-N. Vo, K. Dietmayer, The labeled multi-Bernoulli filter, IEEE Trans. Signal Process., 62 (2014), 3246–3260.
[24] B. G. Saulson, K.-C. Chang, Nonlinear estimation comparison for ballistic missile tracking, Opt. Eng., 43 (2004), 1424– 1438.
[25] D. Schuhmacher, B.-T. Vo, B.-N. Vo, A consistent metric for performance evaluation of multi-object filters, IEEE Trans. Signal Process., 56 (2008), 3447–3457.
[26] H. Sidenbladh, Multi-target particle filtering for the probability hypothesis density, ArXiv, 2003 (2003), 7 pages.
[27] R. Suwantong, Development of the Moving HorizonEstimator with Pre-Estimation (MHE-PE), Application to Space Debris Tracking during the Re-Entries, Automatic, Supélec, (2014).
[28] B.-N. Vo, W.-K. Ma, The Gaussian mixture probability hypothesis density filter, IEEE Trans. Signal Process., 54 (2006), 4091–4104.
[29] B.-N. Vo, S. Singh, A. Doucet, Sequential Monte Carlo implementation of the PHD filter for multi-target tracking, PProceedings of the International Conference on Information Fusion, Cairns, Australia, (2003), 792–799.
[30] B.-T. Vo, B.-N. Vo, Labeled random finite sets and multi-object conjugate priors, IEEE Trans. Signal Process., 13 (2013), 3460–3475.
[31] B.-T. Vo, B.-N. Vo, A. Cantoni, Analytic implementations of the cardinalized probability hypothesis density filter, IEEE Trans. Signal Process., 55 (2007), 3553–3567.
[32] B.-T. Vo, B.-N. Vo, A. Cantoni, The cardinality balanced multi-target multi-Bernoulli filter and its implementations, IEEE Trans. Signal Process., 57 (2009), 409–423.
[33] B.-N. Vo, B.-T. Vo, R. P. S. Mahler, Closed-form solutions to forwardbackward smoothing, IEEE Trans. Signal Process., 60 (2012), 2–17.
[34] B.-N. Vo, B.-T. Vo, D. Phung, Labeled random finite sets and the Bayes multi-target tracking filter, IEEE Trans. Signal Process., 62 (2014), 6554–6567.
[35] Q. Yu, G. Medioni, Multiple-target tracking by spatiotemporal monte carlo markov chain data association, IEEE Trans. Pattern Anal. Mach. Intell., 31 (2009), 2196–2210.
[36] T. Zajic, R. Mahler, Particle-systems implementation of the PHD multitarget-tracking filter, Proc. SPIE, Signal Processing, Sensor Fusion, and Target Recognition XII, 5096 (2003), 291–299.

Downloads

XML export