Title :
Range image segmentation: the user´s dilemma
Author :
Hoover, A. ; Jean-Baptiste, G. ; Xiaoyi Jiang ; Flynn, P.J. ; Bunke, H. ; Goldgof, D. ; Bowyer, K.
Author_Institution :
Dept. of Comput. Sci. & Eng., Univ. of South Florida, Tampa, FL, USA
Abstract :
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.
Keywords :
image segmentation; common set of images; defined performance metrics; machine generated segmentation; manually specified ground truth; planar patches; range image segmentation; Acoustic noise; Acoustical engineering; Computer science; Computer vision; Image motion analysis; Image segmentation; Informatics; Measurement standards; Testing; Topology;
Conference_Titel :
Computer Vision, 1995. Proceedings., International Symposium on
Conference_Location :
Coral Gables, FL, USA
Print_ISBN :
0-8186-7190-4
DOI :
10.1109/ISCV.1995.477022
