Optimal nonlinear filtering for track-before-detect in IR image sequences

The 3D matched filter proposed by Reed et al. and its generalizations provide a powerful processing technique for detecting moving low observable targets. This technique is a centerpiece of various track-before-detect (TBD) systems. However, the 3D matched filter was designed for constant velocity targets and its applicability to more complicated patterns of target dynamics is not obvious. In this paper the 3D matched filter and BAVF are extended to the case of switching multiple models of target dynamics. We demonstrate that the 3D matched filtering can be cast into a general framework of optimal spatio-temporal nonlinear filtering for hidden Markov models. A robust and computationally efficient Bayesian algorithm for detection and tracking of low observable agile targets in IR Search and Track (IRST) systems is presented. The proposed algorithm is fully sequential. It facilitates optimal fusion of sensor measurements and prior information regarding possible threats. The algorithm is implemented as a TBD subsystem for IRST, however the general methodology is equally applicable for other imaging sensors.

[1]  A. Jazwinski.  Stochastic Processes and Filtering Theory , 1970 .

[2]  S. Kligys,et al.  STATE ESTIMATION IN HIDDEN MARKOV MODELS WITH DISTRIBUTED OBSERVATION , 1999 .

[3]  B. Rozovskii.  Stochastic Evolution Systems , 1990 .

[4]  Paul Frank Singer.  Performance analysis of a velocity filter bank , 1997, Optics & Photonics.

[5]  I. Reed,et al.  A recursive moving-target-indication algorithm for optical image sequences , 1990 .

[6]  Larry B. Stotts,et al.  Optical moving target detection with 3-D matched filtering , 1988 .

[7]  R.M. Gagliardi,et al.  Application of Three-Dimensional Filtering to Moving Target Detection , 1983, IEEE Transactions on Aerospace and Electronic Systems.

[8]  James Arnold,et al.  Detection and tracking of low-observable targets through dynamic programming , 1990, Defense + Commercial Sensing.

[9]  Oliver E. Drummond,et al.  Multiple-model filters for boost-to-coast transition of theater ballistic missiles , 1998, Defense, Security, and Sensing.

[10]  S. Eddy.  Hidden Markov models. , 1996, Current opinion in structural biology.

[11]  Alexander G. Tartakovsky,et al.  Adaptive sequential algorithms for detecting targets in a heavy IR clutter , 1999, Optics & Photonics.

[12]  Sergey V. Lototsky,et al.  Fast nonlinear filter for continuous-discrete time multiple models , 1996, Proceedings of 35th IEEE Conference on Decision and Control.

[13]  B. Rozovskii,et al.  Nonlinear Filtering Revisited: A Spectral Approach , 1997 .

[14]  Boris Rozovskii,et al.  Recursive Nonlinear Filter for a Continuous-Discrete Time Model: Separation of Parameters and Observations , 1998 .

[15]  James F. Arnold,et al.  Detection and tracking of low-observable targets through dynamic programming , 1990 .

[16]  Samuel S. Blackman,et al.  New Bayesian track-before-detect design and performance study , 1998, Defense, Security, and Sensing.

[17]  Alexander G. Tartakovsky,et al.  Domain Pursuit Method for Tracking Ballistic Targets , 1998 .

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

[19]  Z. S. Haddad,et al.  Filtering Image Records Using Wavelets and the Zakai Equation , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Yaakov Bar-Shalom,et al.  Estimation and Tracking: Principles, Techniques, and Software , 1993 .