Generic Clustering Approach to Track-to-Track Correlation for Multisensor-Multitarget Environments

Simultaneously tracking multiple targets is a problem of interest for both civilian and military applications. The problem becomes increasingly difficult when the number of sensors ≥ 3, as the S-D assignment algorithm for track-to-track correlation has been shown to be NP-Hard. In small scenarios, solutions can be achieved in relatively fast times. However, as the number of sensors and targets increase, standard approaches fail to scale for real-time execution. This paper shows that near-optimal results can be achieved in real-time by decomposing the problem space by fuzzy c-means clustering, then exploiting the partition matrix to assist in cluster element modifications. Furthermore, the paper explores the correct number of clusters to utilize when the true number of targets in the environment is unknown.

[1]  Y. Bar Shalom On the sequential track correlation algorithm in a multisensor data fusion system , 2008 .

[2]  Y. Bar-Shalom On the track-to-track correlation problem , 1981 .

[3]  R. A. Singer,et al.  Computer control of multiple site track correlation , 1971 .

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

[5]  Yaakov Bar-Shalom,et al.  Evaluation of an approximate cross-covariance calculation for track-to-track fusion , 2004, SPIE Defense + Commercial Sensing.

[6]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[7]  Lance M. Kaplan,et al.  Assignment costs for multiple sensor track-to-track association , 2008, IEEE Transactions on Aerospace and Electronic Systems.

[8]  Huimin Chen,et al.  Multisensor track-to-track association for tracks with dependent errors , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[9]  Lawrence D. Stone,et al.  Improvement in track-to-track association from using an adaptive threshold , 2009, 2009 12th International Conference on Information Fusion.

[10]  Y. Bar-Shalom Tracking and data association , 1988 .

[11]  Krishna R. Pattipati,et al.  Fast data association using multidimensional assignment with clustering , 2001 .

[12]  Tzvetan Semerdjiev,et al.  A study of clustering applied to multiple target tracking algorithm , 2004, CompSysTech '04.

[13]  Xu Tao,et al.  Effect of the common process noise on performance of two-sensor fused-track , 2004, Proceedings of the 2004 IEEE Radar Conference (IEEE Cat. No.04CH37509).

[14]  Yaakov Bar-Shalom,et al.  Tracking with converted position and Doppler measurements , 2011, Optical Engineering + Applications.

[15]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[16]  Barbara F. La Scala,et al.  Choosing a track association method , 2002, Inf. Fusion.

[17]  Katta G. Murty,et al.  Letter to the Editor - An Algorithm for Ranking all the Assignments in Order of Increasing Cost , 1968, Oper. Res..

[18]  Y. Bar-Shalom,et al.  On optimal track-to-track fusion , 1997, IEEE Transactions on Aerospace and Electronic Systems.

[19]  Y. Bar-Shalom,et al.  m-best S-D assignment algorithm with application to multitarget tracking , 2001 .

[20]  Chee-Yee Chong,et al.  Track association and track fusion with nondeterministic target dynamics , 2002 .

[21]  Samuel S. Blackman,et al.  Multiple-Target Tracking with Radar Applications , 1986 .

[22]  Huimin Chen,et al.  Track-to-Track Association Using Attributes , 2007, J. Adv. Inf. Fusion.

[23]  A. Farina,et al.  Effects of cross-covariance and resolution on track association , 2000, Proceedings of the Third International Conference on Information Fusion.

[24]  Thiagalingam Kirubarajan,et al.  Performance limits of track-to-track fusion versus centralized estimation: theory and application [sensor fusion] , 2003 .