Machine Vision and Applications

, Volume 7, Issue 2, pp 115–122 | Cite as

Fast segmentation of range images into planar regions by scan line grouping

  • Xiaoyi Jiang
  • Horst Bunke
Short Communication


A novel technique is presented for rapid partitioning of surfaces in range images into planar patches. The method extends and improves Pavlidis' algorithm (1976), proposed for segmenting images from electron microscopes. The new method is based on region growing where the segmentation primitives are scan line grouping features instead of individual pixels. We use a noise variance estimation to automatically set thresholds so that the algorithm can adapt to the noise conditions of different range images. The proposed algorithm has been tested on real range images acquired by two different range sensors. Experimental results show that the proposed algorithm is fast and robust.

Key words

Algorithm Range data Segmentation Region growing Planar surfaces 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Besl PJ (1988) Surfaces in range image understanding. Springer, Berlin Heidelberg New YorkGoogle Scholar
  2. Dunham JG (1986) Optimum uniform piecewise linear approximation of planar curves. IEEE Trans Pattern Anal Machine Intell 8(l):67–75Google Scholar
  3. Duda RO, Hart PE (1972) Pattern classification and scene analysis. Wiley, New YorkGoogle Scholar
  4. Jiang XY, Bunke H (1992) Fast segmentation of range images into planar regions by scan line grouping. Tech Rep IAM-92-006Google Scholar
  5. Jolion JM, Meer P, Bataouche S (1991) Robust clustering with applications in computer vision. IEEE Trans Patt Anal Machine Intell 13(8):791–802Google Scholar
  6. Krishnapuram R, Freg CP (1992) Fitting an unknown number of lines and planes to image data through compatible cluster merging. Patt Recogn 25(4):385–400Google Scholar
  7. Lozano-Pérez T, Grimson WEL, White SJ (1987) Finding cylinders in range data. In: Proc IEEE Conference on Robotics and Automation, pp 202–207Google Scholar
  8. Maitre C, Hügli H, Tièche F, Amann JP (1990) Range image segmentation based on function approximation. In: Proc ISPRS Conf SPIE 1395:275–282Google Scholar
  9. Paeth AW (1990) Median finding on a 3 x 3 grid. In: Glassner AS (ed) Graphics gems. Academic Press, pp 171–275Google Scholar
  10. Parvin B, Medioni G (1986) Segmentation of range images into planar surfaces by split and merge. In: Proc Computer Vision Pattern Recogn, pp415–417Google Scholar
  11. Pavlidis T, Horowitz SL (1974) Segmentation of plane curves. IEEE Trans Comput C23:860–870Google Scholar
  12. Pavlidis T (1976) Segmentation of pictures and maps through functional approximation. Comput Graphics Image Processing 1:360–372Google Scholar
  13. Pham DT, Abdollahi M (1988) Image compression using polylines, Patt Recogn 21(6):631–637Google Scholar
  14. Schmitt F, Chen X (1991) Fast segmentation of range images into planar regions. In: Proc Comput Vision Patt Recogn, pp 710–711Google Scholar
  15. Shao L, Volz R (1991) Finding cones from multi-scan range images. In: Proc Intelligent Robots and Computer Vision X: Neural, Biological and 3-D Methods, SPIE 1608:378–384Google Scholar
  16. Stahs TG, Wahl FM (1990) Fast and robust range data acquisition in a low-cost environment. In: Proc ISPRS-Conference, SPIE, 1395:496–503Google Scholar
  17. Taylor RW, Savini M, Reeves AP (1989) Fast segmentation of range imagery into planar regions. Comput Vision Graphics Image Processing 45:42–60Google Scholar
  18. Yokoya N, Levine MD (1990) Volumetric description of solids of revolution in a range image. In: Proc 10th Int Conf Pattern Recogn, pp 303–307Google Scholar

Copyright information

© Springer-Verlag 1994

Authors and Affiliations

  • Xiaoyi Jiang
    • 1
  • Horst Bunke
    • 1
  1. 1.Institute of Informatics and Applied MathematicsUniversity of BerneBerneSwitzerland

Personalised recommendations