Soft-Data-Constrained Multi-Model Particle Filter for agile target tracking

Sepideh Seifzadeh, Bahador Khaleghi, Fakhri Karray

Abstract: The performance of Bayesian filtering based methods can be enhanced by using extra information incorporated as specific constraints into the filtering process. Following the same principle, this paper proposes a Soft-Data-Constrained Multi-Model Particle Filtering (SDCMMPF) method, in which the inherently vague human-generated data are modeled using a Fuzzy Inference System (FIS). The soft data are then transformed into a set of constraints, which enable the MMPF method to deal with tracking situations involving potentially highly agile targets. The experimental results demonstrate the capability of the proposed SDCMMPF to significantly outperform the conventional.