Multitarget tracking in a cluttered environment is a significant problem in a wide variety of applications. A typical approach to deal with such problem is the joint probabilistic data association filter. The joint probabilistic data association filter determines the joint probabilities over all targets and hits and updates the predicted target state estimate using a probability weighted sum of residuals. This paper proposes a new all-neighbor fuzzy association technique. Unlike the joint probabilistic data association filter, in which the similarity measures are determined in terms of the conditional probability for all feasible data association hypothesis, the proposed all-neighbor approach determines the similarity measures between measurements and tracks in terms of fuzzy weights. It associates measurements into tracks using fuzzy scores and updates the predicted target state estimate using a fuzzy weighted sum of residuals. The proposed technique performs data association based on a single possibility matrix between measurements and tracks; thus it highly reduces the computational complexity compared to other all-neighbor fuzzy techniques reported in the literature. The proposed technique can be applied to non-maneuvering targets as well as maneuvering targets in a cluttered environment. Its performance is compared to the joint probabilistic data association technique, the nearest-neighbor standard filter, and perfect data association. The results showed the efficiency of the proposed technique.
展开▼
