Advertisement

Road Detection in Urban Areas Using Random Forest Tree-Based Ensemble Classification

  • Safaa M. BedawiEmail author
  • Mohamed S. Kamel
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9164)

Abstract

The rapid growth in using remote sensing data highlights the need to have computationally efficient geospatial analysis available in order to semantically interpret and rapidly update current geospatial databases. Object identification and extraction in urban areas is a challenging problem and it becomes even more so when very high-resolution data, such as aerial images, are used. In this paper, we use Random Forest Classifier tree based ensemble to enhance the extracting accuracy for roads from very dense urban areas from aerial images. Both the spatial and the spectral features of the data are used for pre-classification and classification. Comparisons are made between the RF ensemble and other ensembles of statistic classifiers and neural networks.

The proposed method is tested to aerial and satellite imagery of an urban area. The result shows that the RF ensemble enhances the overall classification accuracy for roads by 8 %. Also, it demonstrates that the approach is viable for large datasets due to its faster computational time performance in comparison to other ensembles.

Keywords

Random forest classifier Ensemble of classifiers Remote sensing Very high resolution Aerial images Road extraction 

Notes

Acknowledgement

We would to express our gratitude to the Geospatial Centre at the University of Waterloo for providing the datasets.

References

  1. 1.
    Mayer, H.: Object extraction in photogrammetric computer vision. ISPRS J. Photogram. Remote Sens. 63(2), 213–222 (2008)CrossRefGoogle Scholar
  2. 2.
    Campbell, J.: Introduction to Remote Sensing, 4th edn. The Guilford Press, New York (2007)Google Scholar
  3. 3.
    Lu, D., Weng, Q.: A survey of image classification methods and techniques for improving classification performance. Int. J. Remote Sens. 28, 823–870 (2007)CrossRefGoogle Scholar
  4. 4.
    Kuncheva, L.I.: Combining Pattern Classifiers: Methods and Algorithms. Wiley, Chichester (2004)CrossRefGoogle Scholar
  5. 5.
    Bo, Y.C., Wang, J.F.: Combining multiple classifiers for thematic classification of remotely sensed data. J. Remote Sens. 5, 555–564 (2005)Google Scholar
  6. 6.
    Benediktsson, J.A., Chanussot, J., Fauvel, M.: Multiple classifier systems in remote sensing: from basics to recent developments. In: Haindl, M., Kittler, J., Roli, F. (eds.) MCS 2007. LNCS, vol. 4472, pp. 501–512. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  7. 7.
    Del Frate, F., Pacifici, F., Schiavon, G., Solimini, C.: Use of neural networks for automatic classification from high-resolution images. IEEE Trans. Geosci. Remote Sens. 45, 800–809 (2007)CrossRefGoogle Scholar
  8. 8.
    Du, P., Zhang, W., Sun, H.: Multiple classifier combination for hyperspectral remote sensing image classification. In: Benediktsson, J.A., Kittler, J., Roli, F. (eds.) MCS 2009. LNCS, vol. 5519, pp. 52–61. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  9. 9.
    Giacinto, G., Roli, F.: Design of effective neural network ensembles for image classification processes. Image Vis. Comput. J. 19(9/10), 699–707 (2001)CrossRefGoogle Scholar
  10. 10.
    Baltsavias, E.P.: Object extraction and revision by image analysis using existing geodata and knowledge: current status and steps towards operational systems. ISPRS J. Photogram. Remote Sens. 58(3–4), 129–151 (2004)CrossRefGoogle Scholar
  11. 11.
    Kluckner, S., Mauthner, T., Roth, P.M., Bischof, H.: Semantic classification in aerial imagery by integrating appearance and height information. In: Zha, H., Taniguchi, R.-i., Maybank, S. (eds.) ACCV 2009, Part II. LNCS, vol. 5995, pp. 477–488. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  12. 12.
    Yu-Chang, T., Kun-Shan, C.: An adaptive thresholding multiple classifiers system for remote sensing image classification. Photogram. Eng. Remote Sens. 75, 679–687 (2009)CrossRefGoogle Scholar
  13. 13.
    Breiman, L.: Random forest. Mach. Learn. 45(1), 5–32 (2001)zbMATHCrossRefGoogle Scholar
  14. 14.
    Waske, B., Benediktsson, J.A., Arnason, K., Sveinsson, J.R.: Mapping of hyperspectral aviris data using machine learning algorithms. Can. J. Remote Sens. 35(S1), 106–116 (2009)CrossRefGoogle Scholar
  15. 15.
    Kang, H.J., Doermann, D.: Selection of classifiers for the construction of multiple classifier systems. In: Proceedings of the Eight International Conference on Document Analysis and Recognition, pp. 263–268 (2005)Google Scholar
  16. 16.
    Smits, P.C.: Multiple classifier systems for supervised remote sensing image classification based on dynamic classifier selection. IEEE Trans. Geosci. Remote Sens. 40(4), 801–813 (2002)CrossRefGoogle Scholar
  17. 17.
    Nguyen, T., Kluckner, S., Bischof, H., Leberl, F.: Aerial photo building classification by stacking appearance and elevation measurements. In: Proceedings ISPRS, 100 Years ISPRS-Advancing Remote Sensing Science on CDROM (2010)Google Scholar
  18. 18.
    Tri-Cities and Surrounding Communities Orthomosaics [computer file]. Waterloo, Ontario: The Regional Municipality of Waterloo (2014)Google Scholar
  19. 19.
    Greater Toronto Area Orthoimagery 2007 [computer file]. Ontario Ministry of Natural Resources (2007)Google Scholar
  20. 20.
    QuickBird Satellite Imagery {computer file}, Digital Globe, Longmont, Colorado, USA (2006)Google Scholar
  21. 21.
    Bedawi, S.M., Kamel, M.S.: Segmentation of very high resolution remote sensing imagery of urban areas using particle swarm optimization algorithm. In: Campilho, A., Kamel, M. (eds.) ICIAR 2010. LNCS, vol. 6111, pp. 81–88. Springer, Heidelberg (2010)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.National Authority for Remote Sensing and Space SciencesCairoEgypt
  2. 2.Center of Pattern Analysis and Machine IntelligenceWaterlooCanada

Personalised recommendations