MLPDA and MLPMHT Applied to Some MSTWG Data

The MLPDA is based on maximizing statistical likelihood according to a precise model in which there is no process noise. The PMHT (probabilistic multi-hypothesis tracker) provides an alternative perspective: each contact may be taken as independent and a-priori equally-equipped to be target-generated. Our results indicate that the MLPMHT is the better tracker in multi-static data. A further advantage of the MLPMHT is that optimal data association with multiple targets is easily incorporated, whereas in the MLPDA it is approximated by excision of measurements that are "taken" by previously-discovered targets. In this paper we apply the MLPMHT and MLPDAF to several data-sets from the MSTWG (multi-static tracking working group) library: two synthetic and two real ones from NURC, plus one from ARL/UT. We also compare the ML trackers to the IMMPDAFAI, a tracker with no "depth" to its assignments: it is found that the IMMPDAFAI is not able to track effectively in such noisy data. Finally, we report on a new genetic implementation of the MLPMHT

[1]  Y. Bar-Shalom,et al.  Directed subspace search ML-PDA with application to active sonar tracking , 2008, IEEE Transactions on Aerospace and Electronic Systems.

[2]  Peter Willett,et al.  Tracking targets using matched field observations , 2004, SPIE Optics + Photonics.

[3]  Peter K. Willett,et al.  Track management in a multisensor MHT for targets with aspect-dependent SNR , 2006, SPIE Defense + Commercial Sensing.

[4]  Y. Bar-Shalom,et al.  ML-PDA track validation thresholds , 2006, 2006 IEEE Aerospace Conference.

[5]  T. Kirubarajan,et al.  EM-ML algorithm for track initialization using possibly noninformative data , 2005, IEEE Transactions on Aerospace and Electronic Systems.

[6]  D. Avitzour,et al.  A maximum likelihood approach to data association , 1992 .

[7]  Y. Bar-Shalom,et al.  Low observable target motion analysis using amplitude information , 1995, Proceedings of 1995 American Control Conference - ACC'95.

[8]  P. Willett,et al.  Comparison of soft and hard assignment ML trackers on multistatic data , 2006, 2006 IEEE Aerospace Conference.

[9]  R. Streit,et al.  Probabilistic Multi-Hypothesis Tracking , 1995 .

[10]  Peter Willett,et al.  Application oftheMLPDA toBistatic Sonar , 2005 .

[11]  Peter Willett,et al.  PMHT: problems and some solutions , 2002 .

[12]  P. Willett,et al.  Application of the MLPDA to bistatic sonar , 2005, 2005 IEEE Aerospace Conference.

[13]  Y. Bar-Shalom,et al.  Track formation with bearing and frequency measurements in clutter , 1990, 29th IEEE Conference on Decision and Control.

[14]  Paul M. Baggenstoss.  Class-specific feature sets in classification , 1999, IEEE Trans. Signal Process..

[15]  I. R. Savage,et al.  Contributions to the theory of rank order statistics , 1954 .

[16]  Yaakov Bar-Shalom,et al.  Interacting multiple model tracking with target amplitude feature , 1993 .

[17]  D. A. Abraham,et al.  Active sonar detection in shallow water using the Page test , 2002 .

[18]  Yakov Bar-Shalom,et al.  Multitarget-Multisensor Tracking: Principles and Techniques , 1995 .

[19]  Thiagalingam Kirubarajan,et al.  Estimation with Applications to Tracking and Navigation , 2001 .

[20]  Y. Bar-Shalom,et al.  The interacting multiple model algorithm for systems with Markovian switching coefficients , 1988 .