Print Email Facebook Twitter Pattern classification approaches to matching building polygons at multiple scales Title Pattern classification approaches to matching building polygons at multiple scales Author Zhang, X. Zhao, X. Molenaar, M. Stoter, J. Kraak, M.J. Ai, T. Faculty OTB Research Institute for the Built Environment Department OTB Research Date 2012-08-25 Abstract Matching of building polygons with different levels of detail is crucial in the maintenance and quality assessment of multi-representation databases. Two general problems need to be addressed in the matching process: (1) Which criteria are suitable? (2) How to effectively combine different criteria to make decisions? This paper mainly focuses on the second issue and views data matching as a supervised pattern classification. Several classifiers (i.e. decision trees, Naive Bayes and support vector machines) are evaluated for the matching task. Four criteria (i.e. position, size, shape and orientation) are used to extract information for these classifiers. Evidence shows that these classifiers outperformed the weighted average approach. Subject Data MatchingMulti-Scale ModelingMap GeneralizationPattern ClassificationBuilding Feature To reference this document use: http://resolver.tudelft.nl/uuid:c8f77d1b-6fb4-4bca-93b7-ed1069f40c3b Publisher International Society for Photogrammetry and Remote Sensing Source ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume I-2, XXII ISPRS Congress, August-September 2012, pp. 19-24 Part of collection Institutional Repository Document type conference paper Rights (c) 2012 Zhang, XZhao, X.Molenaar, M.Stoter, J.Kraak M.J.Ai, T. Files PDF Pattern_classification_ap ... oaches.pdf 442.13 KB Close viewer /islandora/object/uuid:c8f77d1b-6fb4-4bca-93b7-ed1069f40c3b/datastream/OBJ/view