The target tracking based on cubature Kalman filter
Yuanyuan Fang · The Journal of the Acoustical Society of America · 2012
A new extension of Kalman Filter to nonlinear system-- Cubature Kalman Filter is introduced.This algorithm has its theory basis consisted of Gaussian Bayesian theory and Spherical-radial rules.In the light of the unique properties of Cubature Kalman Filter:a derivative-free on-line sequential-state estimator, computational complexity grows as n3 and it eases the curse-of-dimensionality problem.The paper focuses on studying the CKF algorithm in depth, and applys it to bearing-only maneuvering target tracking.Two typical tracking model about tracking maneuvering ship from both non-maneuvering and maneuvering platform is selected.The Monte-Carlo simulations' results illustrate that the CKF algorithm outperforms EKF in accuracy and calculation efficiency of filter, and which make Cubature Kalman Filter easy and feasible to broad application prospect.