Browse > Article
http://dx.doi.org/10.7848/ksgpc.2015.33.1.45

Automatic Matching of Building Polygon Dataset from Digital Maps Using Hierarchical Matching Algorithm  

Yeom, Junho (Department of Civil and Environmental Engineering, Seoul National University)
Kim, Yongil (Department of Civil and Environmental Engineering, Seoul National University)
Lee, Jeabin (Department of Civil Engineering, Institute of New & Renewable Energy Technology Research, Mokpo National University)
Publication Information
Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography / v.33, no.1, 2015 , pp. 45-52 More about this Journal
Abstract
The interoperability of multi-source data has become more important due to various digital maps, produced from public institutions and enterprises. In this study, the automatic matching algorithm of multi-source building data using hierarchical matching was proposed. At first, we divide digital maps into blocks and perform the primary geometric registration of buildings with the ICP algorithm. Then, corresponding building pairs were determined by evaluating the similarity of overlap area, and the matching threshold value of similarity was automatically derived by the Otsu binary thresholding. After the first matching, we extracted error matching candidates buildings which are similar with threshold value to conduct the secondary ICP matching and to make a matching decision using turning angle function analysis. For the evaluation, the proposed method was applied to representative public digital maps, road name address map and digital topographic map 2.0. As a result, the F measures of matching and non-matching buildings increased by 2% and 17%, respectively. Therefore, the proposed method is efficient for the matching of building polygons from multi-source digital maps.
Keywords
Hierarchical Matching; ICP Algorithm; Turning Angle Function; Automatic Building Matching; Road Name Address Map; Digital Topographic Map 2.0;
Citations & Related Records
Times Cited By KSCI : 7  (Citation Analysis)
연도 인용수 순위
1 Kim, J. and Yu, K. (2012), Automatic detection of the updating object by areal feature matching based on shape similarity, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 30, No. 1, pp. 59-65. (in Korean with English abstract)   DOI   ScienceOn
2 Zhang, X., Zhao, X., Molenaar, M., Stoter, J., Kraak, M., and Ai, T.(2012), Pattern classification approachesto matching building polygons at multiple scales, Proceedings of the XXII ISPRS Congress, ISPRS, 25 August-1 September, Melbourne, Australia, Vol. I-2, pp. 19–24.
3 Zhongliang, F. and Jianhua, W. (2008), Entity matching in vector spatial data, Proceedings of the XXI ISPRS Congress, ISPRS, 3-11 July, Beijing, China, Vol. 37, pp.1467–1472.
4 Kim, J., Kim, J., Bae, Y., and Yu, K. (2008), An efficient update for attribute data of the digital map using building registers: focused on building numbers of the new address, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 26, No. 3, pp. 275-284. (in Korean with English abstract)
5 Kim, J., Kim, J., Yu, K., and Huh, Y. (2013), Evaluation of classifiers performance for areal features matching, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 31, No. 1, pp. 49-55. (in Korean with English abstract)   DOI   ScienceOn
6 Kim, J., Kim, K., Lee, W., and Yu, K. (2010), A study on the building information integration method between e-AIS and KLIS-rn, The Journal of the Korea Institute of Intelligent Transport Systems, Vol. 9, No. 1, pp. 121-130. (in Korean with English abstract)
7 Moon, Y., Kim, M., Jo, E., and Choi, S. (2012), Generation for attribution information of digital map using space matching, Journal of the Korean Society for Geospatial Information System, Vol. 20, No. 3, pp. 101-108. (in Korean with English abstract)   DOI
8 Otsu, N. (1975), A threshold selection method from graylevel histograms, Automatica, Vol. 11, pp. 285-296.   DOI   ScienceOn
9 Besl, P. and Mckay, N. (1992), A method for registration of 3-D shapes, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 14, No. 2, pp. 239-256.   DOI   ScienceOn
10 Yeom, J., Huh, Y., and Lee, J. (2014), Building matching analysis and new building update for the integrated use of the digital map and the road name address map, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 32, No. 5, pp. 459-467. (in Korean with English abstract)   DOI   ScienceOn
11 Arkin, E., Chew, L., Huttenlocher, D., Kedem, K., and Mitchell, J. (1991), An efficiently computable metric for comparing polygonal shapes, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 13, No.3, pp. 209–216.   DOI   ScienceOn
12 Bang, Y., Ga, C., and Yu, K. (2012), Matching and attribute conflating method for linking the digital map with the road name address system - focused on the road centerline layer -, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 30, No. 4, pp.379-388. (in Korean with English abstract)   DOI   ScienceOn
13 Chen, Y. and Medioni, G. (1992), Object modelling by registration of multiple range images, Image and Vision Computing, Vol. 10, No. 3, pp. 145-155.   DOI   ScienceOn
14 Huang, L., Wang, S., Ye, Y., Wang, B., and Wu, L. (2010), Feature matching in cadastral map integration with a case study of Beijing, Proceedings of 2010 18th International Conference on Geoinformatics, IEEE, 18-20 June, Beijing, China, pp. 1–4.
15 Huh, Y. and Lee, J. (2013), Development of polygon object set matching algorithm between heterogeneous digital maps - using the genetic algorithm based on the shape similarities, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 31, No. 1, pp. 1-9. (in Korean with English abstract)   DOI   ScienceOn
16 Kang, Y., Lee, J., and Park, M. (2006), Guidelines for the improvement of accuracy on building related registers information, Journal of Korea Spatial Information Society, Vol. 8, No. 3, pp. 15-26. (in Korean with English abstract)