Method for associating the features of two geographic databases
AssigneeNavigation Technologies Corp.
InventorRajashri Joshi
Life of this patent
Estimating the term…
Abstract
A method of determining geographic feature association between geographic features of a first geographic database and a second geographic database builds a proximity matrix having a proximity value element for each of the features of the first geographic database as compared to each of the features of the second geographic database. A singular value decomposition of the proximity matrix is computed, and the singular value decomposition is converted into an association matrix. Using the association matrix, the method identifies an associated feature pair having one feature of the first geographic database and one feature of the second geographic database.
Claims20
A method of determining geographic feature association between the features of a first geographic database and geographic features of a second geographic database comprising the steps of:
- building an m×n proximity matrix G comprising a proximity value element for each of the m features of the first geographic database compared to each of the n features of the second geographic database;
- computing a singular value decomposition of the proximity matrix G into a form G=TDUT where T is an m×m orthogonal matrix, U is an n×n orthogonal matrix, and D is a m×n diagonal matrix having a plurality of diagonal elements;
- converting the singular value decomposition into an association matrix by forming matrix E by replacing each of the diagonal elements of the diagonal matrix with one and computing the association matrix P using the following product P=TEUT;
- and
- identifying an associated feature pair comprising the feature in the first geographic database and the feature of the second geographic database that is a largest element in both one of the rows and one of the columns of the association matrix.
A method of determining geographic feature association between geographic features of a first geographic database and geographic features of a second geographic database comprising the steps of:
- determining a plurality of proximity relationship values comparing the geographic features of the first geographic database to the geographic features of the second geographic database;
- amplifying the proximity relationship values representing the geographic features of the first geographic database likely related to the geographic features of the second geographic database;
- attenuating the proximity relationship values representing the geographic features of the first geographic database unlikely related to the geographic features of the second geographic database;
- identifying an associated feature pair comprising one geographic feature of the first geographic database and one geographic feature of the second geographic database, the associated feature pair having a best proximity relationship value from a set of proximity relationship values comparing the one geographic feature of the first geographic database to a plurality of geographic features of the second geographic database.
A program for determining a feature association between two geographic databases comprising:
- a proximity routine determining a proximity measurement between each feature of the two geographic databases;
- an exclusion routine excluding the proximity measurements representing the features of the two databases unlikely to be related;
- and
- an identification routine identifying a plurality of associated feature pairs, each associated feature pairs comprise one feature from each of the two geographic databases, the associated feature pair having a best proximity measurement from a set of proximity measurements comparing one feature of one of the databases to each feature of the other database.
Dependencies are inferred from the claim text.