AN EXPERIMENTAL COMPARISON OF RANGE IMAGE SEGMENTATION ALGORITHMS

Authors
HOOVER A JEANBAPTISTE G JIANG XY FLYNN PJ BUNKE H GOLDGOF DB BOWYER K EGGERT DW FITZGIBBON A FISHER RB
Citation
A. Hoover et al., AN EXPERIMENTAL COMPARISON OF RANGE IMAGE SEGMENTATION ALGORITHMS, IEEE transactions on pattern analysis and machine intelligence, 18(7), 1996, pp. 673-689
Citations number
43
Categorie Soggetti
Computer Sciences","Computer Science Artificial Intelligence","Engineering, Eletrical & Electronic
Journal title
IEEE transactions on pattern analysis and machine intelligence → ACNP
ISSN journal
01628828
Volume
18
Issue
7
Year of publication
1996
Pages
673 - 689
Database
ISI
SICI code
0162-8828(1996)18:7<673:AECORI>2.0.ZU;2-H
Abstract
A methodology for evaluating range image segmentation algorithms is pr oposed. This methodology involves 1) a common set of 40 laser range fi nder images and 40 structured light scanner images that have manually specified ground truth and 2) a set of defined performance metrics for instances of correctly segmented, missed, and noise regions, over- an d under-segmentation, and accuracy of the recovered geometry. A tool i s used to objectively compare a machine generated segmentation against the specified ground truth. Four research groups have contributed to evaluate their own algorithm for segmenting a range image into planar patches.