ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., I-2, 19-24, 2012
http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/I-2/19/2012/
doi:10.5194/isprsannals-I-2-19-2012
© Author(s) 2012. This work is distributed
under the Creative Commons Attribution 3.0 License.
 
11 Jul 2012
PATTERN CLASSIFICATION APPROACHES TO MATCHING BUILDING POLYGONS AT MULTIPLE SCALES
X. Zhang1,2, X. Zhao1,2, M. Molenaar2, J. Stoter3, M.-J. Kraak2, and T. Ai1 1School of Resource and Environmental Science, Wuhan University, China
2ITC, University of Twente, The Netherlands
3Delft University of Technology, The Netherlands
Keywords: Data Matching, Multi-Scale Modeling, Map Generalization, Pattern Classification, Building Feature 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.
Conference paper (PDF, 2203 KB)


Citation: Zhang, X., Zhao, X., Molenaar, M., Stoter, J., Kraak, M.-J., and Ai, T.: PATTERN CLASSIFICATION APPROACHES TO MATCHING BUILDING POLYGONS AT MULTIPLE SCALES, ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., I-2, 19-24, doi:10.5194/isprsannals-I-2-19-2012, 2012.

BibTeX EndNote Reference Manager XML