Advertisement

Building Information Extraction Based on Electronic Map Points of Interest

  • Yifei Wang
  • Hefeng WangEmail author
  • Yuan Cao
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 980)

Abstract

The extraction of urban building information has important practical implications for the dynamic monitoring of urban land use, urban planning, and construction. Modern remote sensing technology provides the capacity and methods to effectively meet these goals. At present, image classification is an important means of extracting building features but often requires the manual selection of samples. The process is complex as well as time- and labor-consuming, and is somewhat subjective. For these reasons, this paper used points of interest (POI) data from electronic map as samples to develop a method for extracting urban buildings without manual training samples for supervised classification. The experimental results showed that POI data-supervised classification is an effective method for extracting urban buildings. The classification accuracy was similar to that of the manual sampling classification method and far superior to the unsupervised classification results. Further testing for sample size selection showed that the classification accuracy could be maintained at about 80% with 100 or more POI samples. Finally, the method adopted in this paper did not require manual interpretation, was low-cost, and had both high and objective classification accuracy.

Keywords

Baidu Map POI Remote sensing Building extraction 

References

  1. 1.
    Mei, A.X., Peng, W.L., Qing, Q.M., et al.: An introduction to remote sensing. Higher Education Press, Beijing (2001). (in Chinese)Google Scholar
  2. 2.
    Tong, X.H., Zhang, X., Liu, M.L.: Urban land use change detection based on high accuracy classification of multi spectral remote sensing imagery. Spectrosc. Spectral Anal. 29(8), 2131–2135 (2009). (in Chinese)Google Scholar
  3. 3.
    Cha, Y., Ni, S.X., Yang, S.: An effective approach to automatically extract Urban land-use from TM imagery. J. Remote Sens. 7(1), 37–40 (2003). (in Chinese)Google Scholar
  4. 4.
    Chen, Z.Q., Chen, J.F.: Investigation on extracting the space information of Urban land-use from high spectrum resolution image of ASTER by NDBI method. J. Geo-Inf. Sci. 8(2), 137–140 (2006). (in Chinese)Google Scholar
  5. 5.
    Wu, H.A., Jiang, J.J., Zhang, H.L., et al.: Application of ratio resident-area index to retrieve Urban residential areas based on landsat TM data. J. Nanjing Normal Univ. (Nat. Sci. Ed.) 29(3), 118–121 (2006). (in Chinese)Google Scholar
  6. 6.
    Lou, J.C., Wang, M., Ma, J.H.: The EM-based maximum likelihood classifier for remotely sensed data. Acta Geodaetica Cartogr. Sin. 31(3), 234–239 (2002). (in Chinese)Google Scholar
  7. 7.
    Yang, B.L., Fang, Y., Feng, H.H., et al.: Construction land expansion in urbanization process of Dongguan City. J. Geo-Inf. Sci. 11(5), 684–690 (2009). (in Chinese)Google Scholar
  8. 8.
    Guindon, B., Zhang, Y., Dillabaugh, C.: Landsat urban mapping based on a combined spectral-spatial methodology. Remote Sens. Environ. 92(2), 218–232 (2004)CrossRefGoogle Scholar
  9. 9.
    Hou, D., Chen, J., Wu, H., et al.: Active collection of land cover sample data from geo-tagged web texts. Remote Sens. 7(5), 5805–5827 (2015)CrossRefGoogle Scholar
  10. 10.
    Han, G., Chen, J., He, C., et al.: A web-based system for supporting global land cover data production. ISPRS J. Photogrammetry Remote Sens. 103, 66–80 (2015)CrossRefGoogle Scholar
  11. 11.
    Wang, Y.Z., Jin, X.L., Cheng, X.L., Cheng, X.Q.: Network big data: present and future. Chin. J. Comput. 36(6), 1125–1138 (2013). (in Chinese)CrossRefGoogle Scholar
  12. 12.
    Qi, W.H., Yang, H., Wang, S.L., et al.: Study on evaluation and planning of urban parks based on baidu POI data. Chin. Landscape Archit. 34(3), 32–37 (2018). (in Chinese)Google Scholar
  13. 13.
    Xu, Z.N., Gao, X.L.: A novel method for identifying the boundary of urban built-up areas with POI data. Acta Geog. Sin. 71(6), 928–939 (2016). (in Chinese)MathSciNetGoogle Scholar
  14. 14.
    Xing, H., Meng, Y., Hou, D., et al.: Employing crowdsourced geographic information to classify land cover with spatial clustering and topic model. Remote Sens. 9(6), 602 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.School of Mining and GeomaticsHebei University of EngineeringHandanChina

Personalised recommendations