Adaptive data fusion processing: thoughts and perspectives

The focus of this paper is on stating the architecture of data fusion, revisiting the standard representation conceived of by the Data Fusion panels and describing the work carried out at the Center for Multisource Information Fusion (CMIF) at the State University of New York at Buffalo on the development of an adaptive fuzzy /spl alpha/-/spl beta/ target tracker. This paper discusses in detail, the /spl alpha/-/spl beta/-/spl gamma/ filter which is a sampled data target tracker, which can asymptotically track a constant acceleration target. The /spl alpha/-/spl beta/-/spl gamma/ filter is analyzed by determining the bounds on the /spl alpha/-/spl beta/-/spl gamma/ parameters for stability and for its noise filtering capability.