Accurate Murty's algorithm for multitarget top hypothesis extraction

In most hypothesis-oriented Multiple Hypothesis Tracking (MHT) implementations, the target-to-measurement data association is typically solved by using the Murty's algorithm. However, the Murty's algorithm has no control over the diversity of target-to-measurement associations — often the top associations vary only slightly. In addition, in practical tracking solutions, tracks are often grouped as tentative or continued. It was observed with real data sets that in the associations, the top hypotheses consist of mostly similar associations with the same confirmed tracks along with some permutations of new measurements. The result is that a fixed set of confirmed tracks dominate diversity of the association tree. To overcome this problem, a modified Murty's algorithm, which can achieve any user defined (or adaptable) diversity of track-to-measurement association of different types of tracks, is proposed in this paper. Numerical examples are provided to demonstrate the improved efficiency in hypotheses generation by the proposed method.

[1]  Oliver E. Drummond,et al.  Performance metrics for multiple-sensor multiple-target tracking , 2000, SPIE Defense + Commercial Sensing.

[2]  R. Danchick,et al.  A fast method for finding the exact N-best hypotheses for multitarget tracking , 1993 .

[3]  M.L. Miller,et al.  A comparison of two algorithms for determining ranked assignments with application to multitarget tracking and motion correspondence , 1997, IEEE Transactions on Aerospace and Electronic Systems.

[4]  Ingemar J. Cox,et al.  On Finding Ranked Assignments With Application to Multi-Target Tracking and Motion Correspondence , 1995 .

[5]  Pavlina D. Konstantinova,et al.  An Accelerated IMM JPDA Algorithm for Tracking Multiple Manoeuvring Targets in Clutter , 2002, Numerical Methods and Application.

[6]  D. Bertsekas.  The auction algorithm: A distributed relaxation method for the assignment problem , 1988 .

[7]  Chee-Yee Chong,et al.  Generalized Murty's algorithm with application to multiple hypothesis tracking , 2007, 2007 10th International Conference on Information Fusion.

[8]  Cristian I. Coman,et al.  Evaluation of the tracking process in ground surveillance applications , 2009, 2009 European Radar Conference (EuRAD).

[9]  Ljudmil Bojilov,et al.  An Accelerated IMM-JPDA Algorithm for Tracking Multiple Maneuvering Targets in Clutter , 2002 .

[10]  Zhen Ding,et al.  A modified Murty algorithm for multiple hypothesis tracking , 2006, SPIE Defense + Commercial Sensing.

[11]  Krishna R. Pattipati,et al.  Dynamically adaptable m-best 2-D assignment algorithm and multilevel parallelization , 1999 .

[12]  R. Danchick,et al.  Reformulating Reid's MHT method with generalised Murty K-best ranked linear assignment algorithm , 2006 .

[13]  K. G. Murty.  An Algorithm for Ranking All the Assignment in Order of Increasing Cost , 1968 .

[14]  M.L. Miller,et al.  Optimizing Murty's ranked assignment method , 1997, IEEE Transactions on Aerospace and Electronic Systems.

[15]  A. Volgenant,et al.  A shortest augmenting path algorithm for dense and sparse linear assignment problems , 1987, Computing.

[16]  Abhijit Sinha,et al.  Track quality based multitarget tracking algorithm , 2006, SPIE Defense + Commercial Sensing.