A methodology for evaluating range image segmentation algorithms is proposed. This methodology involves (a) a common set of images that have manually specified ground truth and (b) a set of defined performance metrics for instances of correctly segmented, missed and noise regions, over- and under-segmentation, and accuracy of the recovered geometry. A tool is used to objectively compare a machine generated segmentation against the specified ground truth. Three research groups have contributed to evaluate their own algorithm for segmenting a range image into planar patches.
Range image segmentation: the user's dilemma
1995-01-01
635979 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Range Image Segmentation: The User's Dilemma
British Library Conference Proceedings | 1995
|Design story - Peugeot 607, range-topping dilemma
Online Contents | 2000
|Fast Range Image Segmentation Using High-Level Segmentation Primitives
British Library Conference Proceedings | 1996
|Range Image Segmentation Via Distance Slicing
SPIE | 1988
|Blob tracking technique to range image segmentation
SPIE | 1994
|