Track-to-track fusion of out-of-sequence tracks

Abstract

Fusing out-of-sequence information is a problem of growing importance due to an increased reliance on networked sensors embedded in complicated network architectures. The problem of fusing out-of-sequence measurements (OOSM) has received some attention in literature; however, most practical fusion systems, owing to compatibility with legacy sensors and limited communication bandwidth, send track information instead of raw measurements to the fusion node. Delays introduced by the network can result in the reception of out-of-sequence tracks (OOST). This paper considers the problem of fusing out-of-sequence measurements in general, and proposes an optimal Bayesian solution involving a joint probability density of current and past target states, referred to as augmented states. By representing tracks using equivalent measurements, the relationship between OOSM and OOST-based fusion is shown. The special case of Gaussian statistics is also addressed.