BUILDING AND ROAD EXTRACTION ON URBAN VHR IMAGES USING SVM COMBINATIONS AND MEAN SHIFT SEGMENTATION

Christophe Simler, Charles Beumier

Abstract

A method is proposed for building and road detection on very high spatial resolution multispectral aerial image of dense urban areas. First, objects are extracted with a segmentation algorithm in order to use both spectral and spatial information. Second, a spectral-spatial object-level pattern is formed, and then classification is performed using a 3-class SVM classifier, followed by a post-processing using contextual information to handle conflicts. However, in the particular case where many building roofs are grey like the roads and have similar geometry, classification accuracy is inevitably limited. In order to overcome this limitation, different classifiers are combined and different patterns used, improving the accuracy of 10%.

References

  1. Bishop, C., 2006. Pattern recognition and machine learning, Springer.
  2. Lilesand, T., Kieffer, R., 1994. Remote sensing and image interpretation, Third edition, John Wiley & Sons, Inc.
  3. Jackson, Q., 2002. Adaptative Bayesian contextual classification based on Markov random fields, IEEE TGRS, Vol. 40, No. 11, pp. 2454-2463.
  4. Palmason, J. and all, 2005. Classification of hyperspectral data from urban areas using morphological preprocessing and independent component analysis. Proc. IGARSS, vol. 1, pp. 176-179.
  5. Fauvel, M., 2008. Spectral and spatial classification of hyperspectral data using SVMs and morphological profile. IEEE TGRS, Vol. 46, No. 11, pp. 3804-3814.
  6. Tuia, D., 2009. Classification of very high spatial resolution imagery using mathematical morphologie and support vector machine. IEEE TGRS, Vol. 47, No. 11, pp. 3866-3879.
  7. Fauvel, M and all, 2006. Decision fusion for the classification of urban remote sensing images. IEEE TGRS, Vol. 44, No. 10, pp. 2828-2838.
  8. Benediktsson, J., 1999. Classification of multisourse and hyperspectral data based on decision fusion. IEEE TGRS, Vol. 37, pp. 1367-1377.
  9. Benediktsson and all, 2007. Multiple classifier systems in remote sensing: from basics to recent developments. MCS, 7th International Workshop, Praque, Tchèque.
  10. Melgani, F., 2004. Classification of hyperspectral remote sensing images with support vector machines. IEEE TGRS, Vol. 42, No. 8, pp. 1778-1790.
  11. Foody, G., 2004. A relative evaluation of multiclass image classification by support vector machines. IEEE TGRS, Vol. 42, No. 6, pp. 1335-1343.
  12. Tarabalka, Y., and all, 2009. Spectral-spatial classification of hyperspectral Imagery based on partitional clustering techniques. IEEE TGRS, Vol. 47, No. 8, pp. 2973-2987.
  13. Debeir, O., Atoui H., Simler 2009. Weakened Watershed Assembly for Remote Sensing Image Segmentation and Change Detection. VISAPP, Portugal.
  14. Comaniciu, D., Meer, P., 2002. Mean Shift: A Robust Approach Toward Feature Space Analysis. IEEE PAMI, Vol. 24, No. 5.
  15. Tax, D., Duin, R., 2001. Uniform object generation for optimizing one-class classifiers. JMLR 2, pp. 155-173.
Download


Paper Citation


in Harvard Style

Simler C. and Beumier C. (2010). BUILDING AND ROAD EXTRACTION ON URBAN VHR IMAGES USING SVM COMBINATIONS AND MEAN SHIFT SEGMENTATION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-029-0, pages 451-457. DOI: 10.5220/0002851104510457


in Bibtex Style

@conference{visapp10,
author={Christophe Simler and Charles Beumier},
title={BUILDING AND ROAD EXTRACTION ON URBAN VHR IMAGES USING SVM COMBINATIONS AND MEAN SHIFT SEGMENTATION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={451-457},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002851104510457},
isbn={978-989-674-029-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)
TI - BUILDING AND ROAD EXTRACTION ON URBAN VHR IMAGES USING SVM COMBINATIONS AND MEAN SHIFT SEGMENTATION
SN - 978-989-674-029-0
AU - Simler C.
AU - Beumier C.
PY - 2010
SP - 451
EP - 457
DO - 10.5220/0002851104510457