Journal of Systems Engineering and Electronics ›› 2012, Vol. 23 ›› Issue (3): 364-371.doi: 10.1109/JSEE.2012.00045

• DEFENCE ELECTRONICS TECHNOLOGY • Previous Articles     Next Articles

Multiple-model Bayesian filtering with random finite set observation

Wei Yang∗, Yaowen Fu, and Xiang Li   

  1. School of Electronic Science and Engineering, National University of Defense Technology, Changsha 410073, P. R. China
  • Online:2012-06-25 Published:2010-01-03


The finite set statistics provides a mathematically rigorous single target Bayesian filter (STBF) for tracking a target that generates multiple measurements in a cluttered environment. However, the target maneuvers may lead to the degraded tracking performance and even track loss when using the STBF. The multiple-model technique has been generally considered as the mainstream approach to maneuvering the target tracking. Motivated by the above observations, we propose the multiple-model extension of the original STBF, called MM-STBF, to accommodate the possible target maneuvering behavior. Since the derived MMSTBF involve multiple integrals with no closed form in general, a sequential Monte Carlo implementation (for generic models) and a Gaussian mixture implementation (for linear Gaussian models) are presented. Simulation results show that the proposed MM-STBF outperforms the STBF in terms of root mean squared errors of  dynamic state estimates.