Cubature information filters with correlated noises and their applications in decentralized fusion

• Published in: Signal processing Vol. 94; pp. 434 - 444
• Main Authors: Ge, Quanbo, Xu, Daxing, Wen, Chenglin
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.01.2014; Elsevier
• Subjects: Algorithms; Applied sciences; Correlated noises; Correlation; Correlation analysis; Cuba; Cubature Kalman filter; Decentralized; Decentralized fusion; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; Information filter; Information theory; Information, signal and communications theory; Kalman filters; Noise; Noise measurement; Nonlinear system; Signal and communications theory; Signal, noise; Target tracking; Telecommunications and information theory; Cubature Kalman filter; Target tracking; Correlated noises; Nonlinear system; Decentralized fusion; Information filter; Matrix diagonalization; Performance evaluation; Parameter estimation; Multisensor; Kalman filter; Non linear filter; Correlated noise; Non linear system; Algorithm; Extended Kalman filter; Simulation; Decentralized system; Information processing; Signal processing; Data fusion; State estimation; Unscented Kalman filter
• ISSN: 0165-1684; 1872-7557
• DOI: 10.1016/j.sigpro.2013.06.015

Data fusion for nonlinear systems is one of the challenging topics in state estimation and target tracking recently. We study decentralized cubature Kalman fusion in this paper. Cubature Kalman filter (CKF) is a more effective method than the conventional nonlinear filters, such as extended Kalman filter (EKF) and unscented Kalman filter (UKF). For most of the practical cases, there are correlative between process and measurement noises (Correlation I) and among measurement noises (Correlation II). So, it is more attractive to design fusion algorithms based on the CKF for the systems with complex correlated noises. Firstly, a cubature Kalman filter with correlation I (CKF-CN) is derived. Secondly, by introducing the EKF with correlated noises (EKF-CN) and its information filter EIF-CN, the CKF-CN is embedded in the EIF-CN framework to get a cubature information filter with correlated noises (CIF-CN). Consequently, a square-root cubature Kalman filter with noise correlation I (SCKF-CN) and the associated information filter SCIF-CN are presented to improve computational performance. Finally, based on the proposed SCIF-CN and matrix diagonalization, a decentralized nonlinear fusion algorithm is proposed for the multisensor system with Correlation I and Correlation II. Simulation examples are demonstrated to validate the proposed filters and fusion algorithms. •Several CKFs with correlated noises are presented.•The associated square-root forms of the CKFs are designed successfully.•A decentralized nonlinear fusion estimator is proposed based on the CKFs.•Four simulation examples are demonstrated.