INCO Copernicus project no. 960174
 
 
Fast Segmentation of Planar Surfaces in Range Images
 
Michal Haindl     Pavel Zid




An algorithm for planar face segmentation in range images. The segmentation is based on a combination of recursive adaptive regression model prediction for detecting range image step discontinuities which are present at object face borders and of a region growing on surface lines. Border pixels are detected in two perpendicular directions and detection results are combined together. Two predictors in each direction use identical contextual information from the pixel's neighbourhood and they mutually compete for the most optimal discontinuity detection.

The structured light (ABW) range image and the intesity image, respectively.
Resulting segmentation.
Further information can be found in the paper:
ICPR'98
 Haindl, M. Zid, P.
Fast Segmentation of Planar Surfaces in Range Images
In: Proceedings of the 12th IAPR Int. Conf. on Pattern Recognition, Brisbane 1998, Anil K. Jain, Sveth Venkatesh, Brian C. Lovell Eds., ISBN: 0-8186-8512-3, vol. II, pp. 985 - 987, IEEE Press.
   Back to the demonstration page.