Target classification algorithm based on feature aided tracking

An effective target classification algorithm based on feature aided tracking (FAT) is proposed, using the length of target (target extent) as the classification information. To implement the algorithm, the Rao-Blackwellised unscented Kalman filter (RBUKF) is used to jointly estimate the kinematic state and target extent; meanwhile the joint probability data association (JPDA) algorithm is exploited to implement multi-target data association aided by target down-range extent. Simulation results under different condition show the presented algorithm is both accurate and robust, and it is suitable for the application of near spaced targets tracking and classification under the environment of dense clutters.

[1]  Subhash Challa,et al.  Joint target tracking and classification using radar and ESM sensors , 2001 .

[2]  L. Hong,et al.  Feature-aided tracking with GMTI and HRR measurements via mixture density estimation , 2006 .

[3]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[4]  H.F. Durrant-Whyte,et al.  A new approach for filtering nonlinear systems , 1995, Proceedings of 1995 American Control Conference - ACC'95.

[5]  Lyudmila Mihaylova,et al.  Joint target tracking and classification with particle filtering and mixture Kalman filtering using kinematic radar information , 2006, Digit. Signal Process..

[6]  Barbara F. La Scala,et al.  Feature aided probabilistic data association for multi-target tracking , 2008, 2008 11th International Conference on Information Fusion.

[7]  Lu Ma,et al.  Feature aided tracking algorithm based on Generalized Probability Data Association , 2009 .

[8]  Thia Kirubarajan,et al.  Probabilistic data association techniques for target tracking in clutter , 2004, Proceedings of the IEEE.

[9]  Lyudmila Mihaylova,et al.  A Monte Carlo Algorithm for State and Parameter Estimation of Extended Targets , 2006, International Conference on Computational Science.

[10]  D. J. Salmond,et al.  Track maintenance using measurements of target extent , 2003 .

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

[12]  Robert L. Williams,et al.  Signature-aided tracking using HRR profiles , 2001, SPIE Defense + Commercial Sensing.

[13]  S Julier,et al.  Comment on "A new method for the nonlinear transformation of means and covariances in filters and estimators" - Reply , 2002 .

[14]  M. Briers,et al.  Sequential Bayesian inference and the UKF 2 . 1 , 2004 .

[15]  Thia Kirubarajan,et al.  Estimation with Applications to Tracking and Navigation: Theory, Algorithms and Software , 2001 .

[16]  C. Yang,et al.  Pose angular-aiding for maneuvering target tracking , 2005, 2005 7th International Conference on Information Fusion.

[17]  Kevin J. Sullivan,et al.  Feature-aided tracking of ground targets using a class-independent approach , 2004, SPIE Defense + Commercial Sensing.