Littoral tracking using particle filter

M. Mallick1, S. Maskell2,3, T. Kirubarajan4, N. Gordon3
1Alpha Technologies, Inc., Burlington, MA, USA
2Department of Engineering, University of Cambridge, Cambridge, UK
3QinetiQ Limited, Malvern, Worcestershire, UK
4Electrical and Computer Engineering Department, McMaster University, Hamilton, ONT, Canada

Tóm tắt

Littoral tracking refers to the tracking of targets on land and in sea near the boundary of the two regions. A ground-moving target continues to move on land and can not enter the sea. Similarly, a sea-moving target moves in the sea and the land serves as an infeasible region. Enforcing infeasible regions or hard constraints in the framework of the Kalman filter or interacting multiple model (IMM) estimator is not natural. However, these hard constraints can be easily enforced using the particle filter algorithm. We formulate the littoral tracking problem as a joint tracking and classification problem, where we assign a target class for each isolated land or water region. We use a reflecting boundary condition to enforce the region constraint. We demonstrate this concept for a single target using the airborne ground moving target indicator measurements. Numerical results show that the proposed algorithm produces robust classification probabilities using kinematic measurements.

Từ khóa

#Particle tracking #Particle filters #Target tracking #Sea measurements #Kinematics #Particle measurements #Sea surface #Sampling methods #Boundary conditions #Robustness

Tài liệu tham khảo

10.1109/AERO.2002.1036873 10.1109/7.826310 mallick, 2001, Comparison of nonlinear filtering algorithms in ground moving target indicator (GMTI) tracking, Proceedings of the International Conference on Information Fusion gordon, 2002, Efficient particle filters for joint tracking and classification, Proc SPIE Conf Signal and Data Processing of Small Targets, 4728 10.1109/AERO.2002.1036892 gelb, 1974, Applied Optima! Estimation 10.1049/ip-f-2.1993.0015 doucet, 1998, On sequential Monte Carlo sampling methods for Bayesian filtering doucet, 2000, On sequential Monte Carlo sampling methods for Bayesian filtering, 10, 197 10.1109/9.50348 10.1002/0471221279 musick, 2001, Comparison of particle method and finite difference nonlinear filters for low snr target tracking, Proceedings of the International Conference on Information Fusion 10.1109/78.978374 10.1007/978-1-4757-3437-9 arulampalarn, 2000, Comparison of the particle filter with range-parametrised and modified polar ekfs for angle-only tracking, Proc SPIE Conf Signal and Data Processing of Small Targets, 4048, 288 boers, 2001, Integrated tracking and classification: An application of hybrid state estimation, Proc SPIE Conf Signal and Data Processing of Small Targets, 4473, 198 blom, 1977, The interacting multiple model algorithm for systems with markovian switching coefficients, IEEE Transactions on Automatic Control, 22, 302 blackman, 1999, Design and Analysis of Modern Tracking Systems best, 1996, Integrated Tracking and Guidance 10.1109/7.953266 challa, 2000, Target tracking incorporating flight envelope information, Proc 3rd Int Conf Inform Fusion, 10.1109/IFIC.2000.859891