A New Unified Description of Multisource-Heterogeneous Information

The paper incorporates fuzzy logic methodologies into multisensor-multitarget system under the framework of random set theory, and presents the logical unified description of the unambiguous information (data) and a type of the uncertain information (ambiguous evidence) so as to construct qualitative measurement models for data and ambiguous evidence fusion. The procedure is as follows: firstly, strong random set and week random set are defined, based on which, the unified description of data and ambiguous evidence is introduced; secondly, according to characters of ambiguous evidences, two Bayesian-Markov nonlinear measurement models for the data and ambiguous evidence fusion are presented; thirdly using "the models-based signature-matching scheme", the operation of the statistics of ambiguous evidence defined as random sets can be simplified to that of the membership functions of relative point state variables