초록 ▼

We describe an efficient algorithm for evaluating the (weighted bipartite graph of) associations between two sets of data with gaussian error, e.g., between a set of measured state vectors and a set of estimated state vectors. First a general method is developed for determining, from the covariance

We describe an efficient algorithm for evaluating the (weighted bipartite graph of) associations between two sets of data with gaussian error, e.g., between a set of measured state vectors and a set of estimated state vectors. First a general method is developed for determining, from the covariance matrix, minimal d-dimensional error ellipsoids for the state vectors which always overlap when a gating criterion is satisfied. Circumscribing boxes, or d-ranges, for the data ellipsoids are then found and whenever they overlap the association probability is computed. For efficiently determining the intersections of the d-ranges a multidimensional search tree method is used to reduce the overall scaling of the evaluation of associations. Very few associations that lie outside the predetermined error threshold or gate are evaluated. Empirical testing for variously distributed data in both three and eight dimensions indicate that the scaling is significantly reduced from N.sup.2, where N is the size of the data set. Computational loads for many large scale (N>10-100) data association tasks may therefore be significantly reduced by this or related methods.

대표청구항 ▼

[ What is claimed is:] [1.]1. A method of correlating a plurality of objects comprising:scanning said plurality of objects;producing at a first time a set {.alpha.} of d dimensional data vectors, each of whose members a.epsilon.{.alpha.} corresponds to a corresponding one of said plurality of object

[ What is claimed is:] [1.]1. A method of correlating a plurality of objects comprising:scanning said plurality of objects;producing at a first time a set {.alpha.} of d dimensional data vectors, each of whose members a.epsilon.{.alpha.} corresponds to a corresponding one of said plurality of objects, each element of each of said members a corresponding to a physical property of said corresponding one of said plurality of objects at said first time;producing at a second time a second set {.beta.} of d dimensional data vectors, each of whose members b.epsilon.{.beta.} corresponds to one of said plurality of objects, each element of each of said members b corresponding to a physical property of said corresponding one of said plurality of objects at said second time;wherein the uncertainty if each element if each said data vector a or b is Gaussian and thus has respective covariance matrices A and B;selecting a numerical value .gamma..sub.AB ;determining which vector pairs a, b satisfy the gating criterion: mma..sub.A.gtoreq..gamma..sub.AB, and .gamma..sub.B.gtoreq..gamma..sub.AB, where re r is some d dimensional vector;selecting a relatedness criterion for determining the degree of association between any such vector pair a,b;for all said vector pairs which satisfy said gating criterion, applying said relatedness criterion;using the results of said applying of said relatedness criterion to fuse the data vectors of sets {.alpha.} and {.beta.} into a fused set {c} of data vectors each of whose members corresponds to one of said objects.