An Efficient Multi-Frame Track-Before-Detect Algorithm for Multi-Target Tracking

This paper considers the multi-target tracking (MTT) problem through the use of dynamic programming based track-before-detect (DP-TBD) methods. The usual solution of this problem is to adopt a multi-target state, which is the concatenation of individual target states, then search the estimate in the expanded multi-target state space. However, this solution involves a high-dimensional joint maximization which is computationally intractable for most realistic problems. Additionally, the dimension of the multi-target state has to be determined before implementing the DP search. This is problematic when the number of targets is unknown. We make two contributions towards addressing these problems. Firstly, by factorizing the joint posterior density using the structure of MTT, an efficient DP-TBD algorithm is developed to approximately solve the joint maximization in a fast but accurate manner. Secondly, we propose a novel detection procedure such that the dimension of the multi-target state no longer needs be to pre-determined before the DP search. Our analysis indicates that the proposed algorithm could achieve a computational complexity which is almost linear to the number of processed frames and independent of the number of targets. Simulation results show that this algorithm can accurately estimate the number of targets and reliably track multiple targets even when targets are in proximity.

[1]  Yaakov Bar-Shalom,et al.  Multitarget-Multisensor Tracking: Applications and Advances , 1992 .

[2]  U. Schwarz.  MATHEMATICAL-STATISTICAL DESCRIPTION OF ITERATIVE BEAM REMOVING TECHNIQUE (METHOD CLEAN) , 1978 .

[3]  Jr. G. Forney,et al.  Viterbi Algorithm , 1973, Encyclopedia of Machine Learning.

[4]  Mark R. Morelande,et al.  Signal-to-noise ratio threshold effect in track before detect , 2009 .

[5]  Wei Yi,et al.  Multi-target tracking via dynamic-programming based track-before-detect , 2012, 2012 IEEE Radar Conference.

[6]  David Suter,et al.  Joint Detection and Estimation of Multiple Objects From Image Observations , 2010, IEEE Transactions on Signal Processing.

[7]  Robin J. Evans,et al.  Peformance of dynamic programming techniques for Track-Before-Detect , 1996 .

[8]  Danilo Orlando,et al.  Track-Before-Detect Strategies for STAP Radars , 2010, IEEE Transactions on Signal Processing.

[9]  R. Larson,et al.  A dynamic programming approach to trajectory estimation , 1966 .

[10]  A. Hero,et al.  Multitarget tracking using the joint multitarget probability density , 2005, IEEE Transactions on Aerospace and Electronic Systems.

[11]  Yair Barniv,et al.  Dynamic Programming Solution for Detecting Dim Moving Targets , 1985, IEEE Transactions on Aerospace and Electronic Systems.

[12]  Jianyu Yang,et al.  A tracking approach based on Dynamic Programming Track-Before-Detect , 2009, 2009 IEEE Radar Conference.

[13]  S.J. Davey,et al.  A Comparison of Three Algorithms for Tracking Dim Targets , 2007, 2007 Information, Decision and Control.

[14]  S. Buzzi,et al.  Track-before-detect procedures in a multi-target environment , 2008, IEEE Transactions on Aerospace and Electronic Systems.

[15]  W. S. Reid,et al.  Track-before-detect processing for a range-ambiguous radar , 1993, The Record of the 1993 IEEE National Radar Conference.

[16]  Vikram Krishnamurthy,et al.  Performance analysis of a dynamic programming track before detect algorithm , 2002 .

[17]  S. W. Shaw,et al.  Efficient target tracking using dynamic programming , 1993 .

[18]  Jianyu Yang,et al.  An efficient particle filter for multi-target tracking using an independence assumption , 2012, 2012 15th International Conference on Information Fusion.

[19]  William Fitzgerald,et al.  A Bayesian approach to tracking multiple targets using sensor arrays and particle filters , 2002, IEEE Trans. Signal Process..

[20]  S. Buzzi,et al.  Track-before-detect procedures for early detection of moving target from airborne radars , 2005, IEEE Transactions on Aerospace and Electronic Systems.

[21]  Yaakov Bar-Shalom,et al.  Track-Before-Detect Algorithms for Targets with Kinematic Constraints , 2011, IEEE Transactions on Aerospace and Electronic Systems.

[22]  Danilo Orlando,et al.  Batch tracking algorithm for multistatic sonars , 2012 .

[23]  Taejeong Kim,et al.  Optimization of multiframe target detection schemes , 1999 .

[24]  Jr. G. Forney,et al.  The viterbi algorithm , 1973 .

[25]  B. G. Clark,et al.  An efficient implementation of the algorithm 'CLEAN' , 1980 .

[26]  W. Blair,et al.  Unresolved Rayleigh target detection using monopulse measurements , 1998 .

[27]  J. L. Harmon,et al.  Track-before-detect performance for a high PRF search mode , 1991, Proceedings of the 1991 IEEE National Radar Conference.

[28]  Jack K. Wolf,et al.  Finding the best set of K paths through a trellis with application to multitarget tracking , 1989 .

[29]  D. Castañón.  Efficient algorithms for finding the K best paths through a trellis , 1990 .

[30]  Danilo Orlando,et al.  Track-before-detect algorithms for bistatic sonars , 2010, 2010 2nd International Workshop on Cognitive Information Processing.

[31]  Offer Kella,et al.  Dynamic Programming Solution for Detecting Dim Moving Targets Part II: Analysis , 1987, IEEE Transactions on Aerospace and Electronic Systems.

[32]  Dimitri P. Bertsekas,et al.  Dynamic Programming: Deterministic and Stochastic Models , 1987 .

[33]  Y. Boers,et al.  Multitarget particle filter track before detect application , 2004 .

[34]  Mark R. Morelande,et al.  A Bayesian Approach to Multiple Target Detection and Tracking , 2007, IEEE Transactions on Signal Processing.

[35]  Atef Z. Elsherbeni,et al.  MATLAB Simulations for Radar Systems Design , 2003 .