Extracting Buildings by Using the Generalized Multi Directional Discrete Radon Transform

  • I. ELouedi
  • A. Hamouda
  • H. Rojbani
  • R. Fournier
  • A. Nait-Ali
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7340)

Abstract

This paper presents a new method to detect and accurately locate a rectangular form object in any given image. In order to find the right coordinates of those objects in the image, we develop the Generalized Multi Directional Discrete Radon Transform (GMDRT). The GMDRT can detect any given shape whatever its form and orientation are. Experimental results on high resolution QuickBird image to extract rectangular buildings form show the efficiency of our method.

Keywords

Generalized multi Directional Discrete Radon Transform High- Resolution QuickBird images Rectangular Buildings 

References

  1. 1.
    Tofts, P.: The RadonTransform: Theory and implementation. Ph.D.Thesis (1996)Google Scholar
  2. 2.
    Beylkin, G.: Discrete Radon transform. IEEE Transactions of Acoustics, Speech and Signal Processing 35, 162–172 (1987)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Magli, E., Olmo, G., LoPresti, L.: Pattern recognition by means of the Radon transform and the continuous wavelet transform. Signal Processing 73 (1999)Google Scholar
  4. 4.
    Milanfar, P.: A model of the effect of image motion in the Radon transform domain. IEEE Transactions on Image Processing 8, 1276–1281 (1999)CrossRefGoogle Scholar
  5. 5.
    Shepp, L.A., Krustal, J.B.: Computerized tomography: The new medical X-ray technology. Am. Math. Monthly 85, 420–439 (1978)MATHCrossRefGoogle Scholar
  6. 6.
    Courmontagne, P.: An improvement of ship wake detection based on the radon transform. Signal Processing 85 (2005)Google Scholar
  7. 7.
    Krishnaveni, M., Kumar Thakur, S., Subashini, P.: An optimal method for wake detection in SAR images using Radon transformation combined with wavelet filters. International Journal of Computer Science and Information Security 6, 066–069 (2009)Google Scholar
  8. 8.
    Zhang, Q., Couloigner, I.: Accurate Centerline Detection and Line Width Estimation of Thick Lines using the Radon Transform. IEEE Transactions On Image Processing 16, 310–316 (2007)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Wang, L., Hao, Y.: Radon Transform and Forstner Operator Applying in Buildings Contour Extraction. In: Sixth International Conference on FSKD, pp. 415–419 (2009)Google Scholar
  10. 10.
    Mukhopadhyay, S., Chanda, B.: An edge preserving noise smoothing technique using multi-scale morphology. Signal Processing 82, 527–544 (2002)MATHCrossRefGoogle Scholar
  11. 11.
    Lhomme, S., He, D.C., Weber, C., Morin, D.: A new approach to building identification from very-high-spatial-resolution images. International Journal of Remote Sensing 30, 1341–1354 (2009)CrossRefGoogle Scholar
  12. 12.
    Bouziani, M., Goita, K., He, D.-C.: Automatic change detection of buildings in urban environment from very high spatial resolution images using existing geodatabase and prior knowledge. ISPRS J. of Photogrammetry and Remote Sensing 65, 143–153 (2010)CrossRefGoogle Scholar
  13. 13.
    Elouedi, I., Fournier, R., Nait-Ali, A., Hammouda, A.: Generalized Multi Directional Discrete Radon Transform. Signal Processing (paper in revision)Google Scholar
  14. 14.
    Zhang, W., Bergholm, F.: Multi-scale blur estimation and edge type classification for scene analysis. International Journal of Computer Vision 24, 219–250 (1997)CrossRefGoogle Scholar
  15. 15.
    Hamouda, A., Rojbani, H., Elouedi, I.: A new shape descriptor based on the Radon transform: the Rθ-signature. Accepted paper in International Conference on Signal, Image Processing and Applications, ICSIA (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • I. ELouedi
    • 1
  • A. Hamouda
    • 1
  • H. Rojbani
    • 1
  • R. Fournier
    • 2
  • A. Nait-Ali
    • 2
  1. 1.Computer technology departmentThe Sciences instituteTunisTunisia
  2. 2.Laboratory of Images, Signal and Intelligent systems(LISSI)The University Paris Est-CreteilParisFrance

Personalised recommendations