Orthophotoplan Segmentation and Colorimetric Invariants for Roof Detection

  • Youssef El Merabet
  • Cyril Meurie
  • Yassine Ruichek
  • Abderrahmane Sbihi
  • Rajaa Touahni
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6979)

Abstract

In this paper, we use a morphological segmentation method called watershed for segmenting roof of “orthophotoplan” images. This work takes place in a global approach which consists in recognizing a roof of aerial images among a knowledge database and bending out 3D models automatically generated from geographical data. The main aim of this work consists in defining the best couple of colorimetric invariant/gradient (among 24 colorimetric invariants and 14 gradients tested) used as input of watershed algorithm in order to obtain the best segmentation of roof. The tests are made on a database of 67 roofs containing a certain heterogeneity (illumination changes, shadows, etc) and evaluated with the Vinet criteria (including a ground truth image) in order to prove the robustness of the proposed strategy.

Keywords

watershed color gradient colorimetric invariant orthophotoplan 

References

  1. 1.
    Gevers, T., Smeulders, A.: Object Recognition based on Photometric Colour Invariants. In: Proceedings of SCIA, Lappeenranta, Finland (1997)Google Scholar
  2. 2.
    Cong, T., Khoudour, L., Achard, C., Meurie, C., Lezoray, O.: People re-identification by spectral classification of silhouettes. Signal Processing 90(8), 2362–2374 (2010)CrossRefMATHGoogle Scholar
  3. 3.
    Gouiffès, M.: Apports de la Couleur et des Modéles de Rèflexion pour l’Extraction et le Suivi de Primitives, Thése de doctorat, Université Poitiers (Décembrer 2005)Google Scholar
  4. 4.
    Gevers, T., Smeulders, A.: Colour based object recognition. Pattern Recognition 32, 453–464 (1999)CrossRefGoogle Scholar
  5. 5.
    Golland, P., Bruckstein, A.M.: Motion from color. Computer Vision and Image Understading 68(3), 346–362 (1997)CrossRefGoogle Scholar
  6. 6.
    Schaefer, G.: How useful are colour invariants for image retrieval. In: Computational Imaging and Vision, Proc. Int. Conference on Computer Vision and Graphics, Warsaw, Poland, vol. xx. Kluwer Academic Publishers, Dordrecht (2004)Google Scholar
  7. 7.
    Hordley, D., Finlayson, G.D., Schaefer, G., Tian, G.Y.: Illuminant and device invariant colour using histogram equalization. Pattern Recognition 28, 179–190 (2005)Google Scholar
  8. 8.
    Fusiello, A., Trucco, E., Tommasini, T., Roberto, V.: Improving feature tracking with robust statistics. Pattern Analysis & Applications 2(4), 312–320 (1999)CrossRefGoogle Scholar
  9. 9.
    Gevers, T., Stockman, H.: Robust histogram construction from color invariants for object recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 26, 113–118 (2004)CrossRefGoogle Scholar
  10. 10.
    Hordley, S.D., Finlayson, G.D., Schaefer, G., Tian, G.Y.: Illuminant and device invariant colour using histogram equalization. Elsevier Science, Amsterdam (2002)Google Scholar
  11. 11.
    Latecki, L.J., Rajagopal, V., Gross, A.: Image retrieval and reversible illumination normalization. In: Proc. of the IS&T/SPIE. Internet Imaging VI, San Jose (2005)Google Scholar
  12. 12.
    Dargham, J.A.: Lip detection by the use of neural networks. Artif. Life Robotics 12, 301–306 (2008)CrossRefGoogle Scholar
  13. 13.
    Cousty, J.: Lignes de partage des eaux discrétes: théorie et application a la segmentation d’images cardiaques. PhD thesis, Université Marne-la-Vallé (2007)Google Scholar
  14. 14.
    Meyer, F.: Un algorithme optimal de ligne de partage des eaux. In: Dans Actes du 8éme Congrés AFCET, Lyon-Villeurbanne, France, pp. 847–859 (1991)Google Scholar
  15. 15.
    Vincent, L., Soille, P.: Watersheds in digital spaces. An efficient algorithm based on immersion simulations. IEEE Trans. Pattern Analysis and Machine Intelligence 13(6), 583–598 (1991)CrossRefGoogle Scholar
  16. 16.
    Cousty, J.: Lignes de partage des eaux discrétes: théorie et application a la segmentation d’images cardiaques. PhD thesis, Université Marne-la-Vallé (2007)Google Scholar
  17. 17.
    Di Zenzo, R.: A note on the gradient of a multiimage. Computer Vision, Graphics and Image Processing 33, 116–125 (1986)CrossRefMATHGoogle Scholar
  18. 18.
    Lezoray, O., Elmoataz, A., Cardot, H., Revenu, M.: Segmentation d’images couleur: applications en microscopie cellulaire. Traitement du Signal 17, 33–45 (2007)MATHGoogle Scholar
  19. 19.
    Carron, T.: Segmentation d’images couleur dans la base Teinte Luminance Saturation: approche numérique et symbolique. Thèse de doctorat, Thèse de l’Université Savoie soutenue (décembre 1995)Google Scholar
  20. 20.
    Cohen, A., Attia, D., Meurie, C., Ruichek, Y.: Une méthode de segmentation hybride par combinaison adaptative des informations texture et couleur. In: Conférence MAJESTIC, Bordeaux, France (2010)Google Scholar
  21. 21.
    Vinet, L.: Segmentation et mise en correspondance de régions de paires d’images stéréoscopiques. PhD thesis, Université Paris IX Dauphine, Juillet (1991)Google Scholar
  22. 22.
    Gevers, T., Stockman, H.: Classifying of color edges in video into shadow-geometry, highlight, or material transitions. IEEE Transactions on Multimedia 5(2), 237–243 (2003)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Youssef El Merabet
    • 1
    • 2
  • Cyril Meurie
    • 1
  • Yassine Ruichek
    • 1
  • Abderrahmane Sbihi
    • 3
  • Rajaa Touahni
    • 2
  1. 1.Systems and Transportation LaboratoryUniversité de Technologie de Belfort-MontbliardBelfortFrance
  2. 2.Laboratoire LASTID, Département de Physique, Faculté des SciencesUniversité Ibn TofailKénitraFrance
  3. 3.ENSA, Université Abdelmalek EssadiTangerFrance

Personalised recommendations