GeoInformatica

, Volume 16, Issue 2, pp 281–306 | Cite as

Automatic classification of building types in 3D city models

Using SVMs for semantic enrichment of low resolution building data
  • André Henn
  • Christoph Römer
  • Gerhard Gröger
  • Lutz Plümer
Article

Abstract

This article presents a classifier based on Support Vector Machines (SVMs), an advanced machine learning method for semantic enrichment of coarse 3D city models by deriving the building type. The information on the building type (detached building, terraced building, etc.) is essential for a variety of relevant applications of 3D city models like spatial marketing, real estate management and marketing, and for visualization. The derivation of the building type from coarse data (mainly 2D footprints, building heights and functions) seems impossible at first sight. However it succeeds by incorporating the spatial context of a building. Since the input data can be derived easily and at very low cost, this method is widely applicable. Nevertheless, as with all supervised learning algorithms, obtaining labelled training data is very time-consuming. Herewith, we provide a method which uses outlier detection and clustering methods to support users in efficiently and rapidly obtaining adequate training data.

Keywords

Machine learning Semantic enrichment Building type Support Vector Machines 

References

  1. 1.
    Alpaydin E (2004) Introduction to machine learning. MIT Press, Cambridge, MAGoogle Scholar
  2. 2.
    Baldauf M, Simon R (2010) Getting context on the go: mobile urban exploration with ambient tag clouds. In: Proceedings of the 6th workshop on geographic information retrieval, ACM, New York, NY, pp 11:1–11:2. doi:10.1145/1722080.1722094 Google Scholar
  3. 3.
    Bishop C (2007) Pattern recognition and machine learning. Springer, New York, NYGoogle Scholar
  4. 4.
    Boyd S, Vandenberghe L (2004) Convex optimization. Cambridge University Press, New York, NY, USAGoogle Scholar
  5. 5.
    Breunig M, Kriegel HP, Ng R, Sander J (2000) LOF: identifying density-based local outliers. In: Proceedings of the 2000 ACM SIGMOD international conference on Management of data, ACM, New York, NY, pp 93–104. doi:10.1145/342009.335388 CrossRefGoogle Scholar
  6. 6.
    Brinker K (2003) Incorporating diversity in active learning with support vector machines. In: Proceedings of the 20th international conference on machine learning, ACM, New York, NY, pp 59–66Google Scholar
  7. 7.
    Chang CC, Lin CJ (2001) LIBSVM: a library for support vector Machines. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm. Accessed 3 February 2011
  8. 8.
    Chapelle O, Schölkopf B, Zien A (2006) Semi-supervised learning. MIT Press, Cambridge, MassGoogle Scholar
  9. 9.
    Chi M, Bruzzone L (2007) Semi-supervised classification of hyperspectral images by SVMs optimized in the primal. IEEE Trans Geosci Remote Sens 45(6):1870–1880. doi:10.1109/TGRS.2007.894550 CrossRefGoogle Scholar
  10. 10.
    Czerwinski A, Sandmann S, Stöcker-Meier E, Plümer L (2007) Sustainable SDI for EU noise mapping in NRW – best practice for INSPIRE. Int J Spat Data Infrastruct Res (IJSDIR) 2(1):90–111Google Scholar
  11. 11.
    Gröger G, Kolbe TH, Czerwinski A, Nagel C (2008) OpenGIS City Geography Markup Language (CityGML) Encoding Standard. Version 1.0.0, Open Geospatial Consortium, OGC Doc. No. 08-007r1Google Scholar
  12. 12.
    Guyon I, Weston J, Barnhill S, Vapnik V (2002) Gene selection for cancer classification using support vector machines. Mach Learn 46(1-3):389–422CrossRefGoogle Scholar
  13. 13.
    Haitao L, Haiyan G, Yanshun H, Jinghui Y (2007) Fusion of high-resolution aerial imagery and Lidar data for object-oriented urban land-cover classification based on SVM. In: Jiang J, Zhao R (eds) Proceedings of the ISPRS workshop on updating geo-spatial databases with imagery & the 5th ISPRS workshop on dynamic and multi-dimensional GIS, ISPRS, Urumqi, China, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol XXXVI, pp 111–119Google Scholar
  14. 14.
    Hsu CW, Lin CJ (2002) A comparison of methods for multiclass support vector machines. IEEE Trans Neural Netw 13, Issue:2(2):415–425. doi:10.1109/72.991427 Google Scholar
  15. 15.
    Hsu CW, Chang CC, Lin CJ (2003) A practical guide to support vector classification. Tech. rep., Department of Computer Science, National Taiwan UniversityGoogle Scholar
  16. 16.
    Huang B, Xie C, Tay R (2010) Support vector machines for urban growth modeling. GeoInformatica 14(1):83–99. doi:10.1007/s10707-009-0077-4 CrossRefGoogle Scholar
  17. 17.
    Koch KR (1999) Parameter estimation and hypothesis testing in linead models. Springer Verlang, BonnGoogle Scholar
  18. 18.
    Kolbe TH, Gröger G, Plümer L (2008) CityGML - 3D city models for emergency response. In: Zlatanova S, Li J (eds) Geospatial information technology for emergency response, vol 6. Taylor & Francis, London, International Society for Photogrammetry and Remote Sensing book series, pp 257–274Google Scholar
  19. 19.
    Lodha SK, Kreps EJ, Helmbold DP, Fitzpatrick D (2006) Aerial lidar data classification using support vector machines (SVM). In: Proceedings of international symposium on 3D data processing visualization and transmission, IEEE Computer Society, Chapel Hill, USA, pp 567–574. doi:10.1109/3DPVT.2006.23 Google Scholar
  20. 20.
    Lüscher P, Weibel R, Mackaness A (2008) Where is the terraced house? On the use of ontologies for recognition of urban concepts in cartographic databases. In: Ruas A, Gold C (eds) Headway in spatial data handling: 13th international symposium on spatial data handling. Lecture Notes in Geoinformation and Cartography, Springer, Berlin, Heidelberg, pp 449–466CrossRefGoogle Scholar
  21. 21.
    Lüscher P, Weibel R, Burghardt D (2009) Integrating ontological modelling and bayesian inference for pattern classification in topographic vector data. Comput Environ Urban 33(5):363–374. doi:10.1016/j.compenvurbsys.2009.07.005 CrossRefGoogle Scholar
  22. 22.
    Malpica J, Alonso M (2009) Identification of vegetation changes using bi-temporal SPOT 5 images. In: Proceedings of ASPRS 2009 annual conference Baltimore, Baltimore, MarylandGoogle Scholar
  23. 23.
    Marconcini M, Camps-Valls G, Bruzzone L (2009) A composite semisupervised SVM for classification of hyperspectral images. IEEE Geosci Remote Sens Lett 6(2):234–238. doi:10.1109/LGRS.2008.2009324 CrossRefGoogle Scholar
  24. 24.
    Mierswa I, Wurst M, Klinkenberg R, Scholz M, Euler T (2006) YALE: Rapid prototyping for complex data mining tasks. In: Ungar L, Craven M, Gunopulos D, Eliassi-Rad T (eds) Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, New York, NY, USA, pp 935–940CrossRefGoogle Scholar
  25. 25.
    Mitchell T (2004) Machine learning. McGraw-Hill Series in Computer Science, McGraw-Hill, New YorkGoogle Scholar
  26. 26.
    Muller KR, Mika S, Ratsch G, Tsuda K, Scholkopf B (2001) An introduction to kernel-based learning algorithms. IEEE Trans Neural Netw 12(2):181–201. doi:10.1109/72.914517 CrossRefGoogle Scholar
  27. 27.
    Pelleg D, Moore A (2000) X-means: extending K-means with efficient estimation of the number of clusters. In: Langley P (ed) Proceedings of the seventeenth international conference on machine learning (ICML 2000). Stanford University, Stanford, CA, USA, pp 727–734Google Scholar
  28. 28.
    Platt J (1998) Sequential minimal optimization: a fast algorithm for training support vector machines. Tech. Rep. MSR-TR-98-14, Microsoft ResearchGoogle Scholar
  29. 29.
    Quinn J, Smart P, Jones C (2009) 3D city registration and enrichment. In: Proceedings of ISPRS workshop on quality, scale and analysis aspects of urban city models, Lund, SwedenGoogle Scholar
  30. 30.
    Römer C, Plümer L (2010) Identifying architectural style in 3d city models with support vector machines. Photogramm Fernerkund Geoinf (PFG) 2010(5)(14):371–384. doi:10.1127/1432-8364/2010/0063 CrossRefGoogle Scholar
  31. 31.
    Römer C, Bürling K, Rumpf T, Hunsche M, Noga G, Plümer L (2010) Early identification of leaf rust on wheat leaves with robust fitting of hyperspectral signatures. In: Proceedings of 10th international conference precision agriculture, Denver, USAGoogle Scholar
  32. 32.
    Rumpf T, Mahlein AK, Steiner U, Oerke EC, Dehne HW, Plümer L (2010) Early detection and classification of plant diseases with support vector machines based on hyperspectral reflectance. Comput Electron Agric 74(1):91–99. doi:10.1016/j.compag.2010.06.009 CrossRefGoogle Scholar
  33. 33.
    Schenk S, Saathoff C, Staab S, Scherp A (2009) Semaplorer–interactive semantic exploration of data and media based on a federated cloud infrastructure. J Web Semant 7(4):298–304. doi:10.1016/j.websem.2009.09.006 CrossRefGoogle Scholar
  34. 34.
    Schmittwilken J, Dörschlag D, Plümer L (2009) Attribute grammar for 3D city models. In: Krek A, Rumor M, Zlatanova S, Fendel EM (eds) Urban and regional data management: Udms annual 2009: proceedings of the urban data management society symposium 2009, CRC Press, Leiden, The Netherlands, pp 49–58Google Scholar
  35. 35.
    Schölkopf B (1998) Support vector machines. IEEE Intell Syst 7:18–28Google Scholar
  36. 36.
    Schölkopf B, Smola A (2002) Learning with kernels: Support vector machines, regularization, optimization, and beyond. Adaptive computation and machine learning, MIT Press, Cambridge, MassGoogle Scholar
  37. 37.
    Schölkopf B, Giesen J, Spalinger S (2005) Kernel Methods for implicit surface modeling. In: Saul L, Weiss Y, Bottou L (eds) Advances in neural information processing systems 17, MIT Press, Cambridge, MA, USA, pp 1193–1200Google Scholar
  38. 38.
    Schwarz G (1978) Estimating the dimension of a model. Ann Stat 6(2):461–464CrossRefGoogle Scholar
  39. 39.
    Shafri H, Ramle F (2009) A comparison of support vector machine and decision tree classifications using satellite data of Langkawi Island. IT J 8(1):64–70. doi:10.3923/itj.2009.64.70 Google Scholar
  40. 40.
    Shuhe Z (2004) Remote sensing data fusion using support vector machine. In: Proceedings of IEEE international geoscience and remote sensing symposium, 2004. IGARSS ’04, Piscataway, NJ, pp 2575–2578. doi:10.1109/IGARSS.2004.1369823
  41. 41.
    Song M, Civco D (2004) Road extraction using SVM and image segmentation. Photogramm Eng Remote Sensing 70(12):1365–1371Google Scholar
  42. 42.
    Thrall G (2002) Business geography and new real estate market analysis. Spatial information systems, Oxford University Press, OxfordGoogle Scholar
  43. 43.
    Vapnik V (1998) Statistical learning theory. A Wiley-Interscience publication, Wiley, New YorkGoogle Scholar
  44. 44.
    Weis M, Rumpf T, Gerhards R, Plümer L (2009) Comparison of different classification algorithms for weed detection from images based on shape parameters, In: Image analysis for agricultural products and processes, Bornimer Agrartechnische Berichte, vol 69, pp 53–64Google Scholar
  45. 45.
    Zhang R, Ma J (2008) An improved SVM method P-SVM for classification of remotely sensed data. Int J Remote Sens 29:6029–6036. doi:10.1080/01431160802220151 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • André Henn
    • 1
  • Christoph Römer
    • 1
  • Gerhard Gröger
    • 1
  • Lutz Plümer
    • 1
  1. 1.Institute for Geodesy and GeoinformationUniversity of BonnBonnGermany

Personalised recommendations