Multi-image Region Growing for Integrating Disparity Maps

  • Uĝur M. Leloĝlu
  • Uĝur Halici
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1689)


In this paper, a multi-image region growing algorithm to obtain planar 3-D surfaces in the object space from multiple dense disparity maps, is presented. A surface patch is represented by a plane equation and a set of pixels in multiple images. The union of back projections of all pixels in the set onto the infinite plane, forms the surface patch. Thanks to that hybrid representation of planar surfaces, region growing (both region aggregation and region merging) is performed on all images simultaneously. Planar approximation is done in object space by linear least square estimation using all data points of the region under question in all images. Linear edge segments detected on colour images are used for constraining the region growing during the region aggregation phase as well as for detection of borders of surface patches. Experimental results on disparity maps obtained from high-resolution aerial images of urban areas demonstrate the performance of the algorithm.


Object Space Seed Point Surface Patch Region Aggregation Planar Approximation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    L.-H. Chen and W.-C. Lin. Visual surface segmentation from stereo. Image and Vision Computing, 15:95–106, 1997.CrossRefGoogle Scholar
  2. 2.
    P. Fua. From multiple stereo views to multiple 3-d surfaces. International Journal of Computer Vision, 24(1):19–35, 1997.CrossRefGoogle Scholar
  3. 3.
    C. Fuchs and Stephan Heuel. Feature extraction. In W. Förstner, editor, Proc. of Third Course in Digital Photogrammetry, Bonn, Germany, 1998.Google Scholar
  4. 4.
    S. Girard, P. Guérin, M. Roux, and H. Maître. Building detection from high resolution colour images. In International Symposium on Remote Sensing, Europhoto98, Barselona, Spain, 1998.Google Scholar
  5. 5.
    A. A. Goshtasby. Three-dimensional model construction from multi-view range images: Survey with new results. Pattern Recognition, 31(11):1705–1714, 1998.CrossRefGoogle Scholar
  6. 6.
    A. Hilton, A. J. Stoddart, J. Illingworth, and T. Windeatt. Implicit surface-based geometric fusion. Computer Vision and Image Understanding, 69(3):273–291, 1998.CrossRefGoogle Scholar
  7. 7.
    H. Hoppe, T. DeRose, T. Duchamp, J. McDonald, and W. Stuetzle. Surface reconstruction from unorganised points. In Computer Graphics 26: SIGGRAPH'92 Conference Proceedings, volume 26, pages 71–78, 1992.CrossRefGoogle Scholar
  8. 8.
    R. Koch. Surface segmentation and modeling of 3-d polygonal objects from stereoscopic image pairs. In International Conference on Pattern Recognition 96, Vienna, Austria, 1996.Google Scholar
  9. 9.
    R. Koch, M. Pollefeys, and L. Van Gool. Multi viewpoint stereo from uncalibrated video sequences. In Proc. ECCV'98, LNCS, Freiburg, Germany, 1998. Springer-Verlag.Google Scholar
  10. 10.
    U. M. Leloĝlu, M. Roux, and H. Maître. Dense urban dem with three or more high-resolution aerial images. In D. Frisch, M. Englich, and M. Sester, editors, GIS — Between Visions and Applications, pages 347–352, Stuttgart, Germany, 1998. ISPRS.Google Scholar
  11. 11.
    G. Maître, H. Hügli, and J. P. Amann. Range image segmentation based on function approximation. In A. Gruen and E. Baltsavias, editors, Close Range Phogrammetry Meets Machine Vision, SPIE vol. 1395, pages 275–282, 1990.Google Scholar
  12. 12.
    C. Schütz, T. Jost, and H. Hügli. Free-form 3d object reconstruction from range images. In The Proceeding of Virtual Systems and Multimedia, VSMM97, Geneva, Switzerland, 1997.Google Scholar
  13. 13.
    D. Zhao and X. Zhang. Range-data-based object surface segmentation via edges and critical points. IEEE-PAMI, 6(6):826–830, 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Uĝur M. Leloĝlu
    • 1
    • 2
  • Uĝur Halici
    • 2
  1. 1.UBíTAK-BíLTENAnkaraTurkey
  2. 2.Computer Vision and Neural Networks Research GroupMiddle East Technical UniversityAnkaraTurkey

Personalised recommendations