Title :
A parallel implementation on CM5 of a multi-spectral cooperative segmentation
Author :
Bonnin, P. ; Maurette, C. ; Hoelzener-Douarin, B. ; Pissaloux, E.
Author_Institution :
Univ. de Paris-Nord, Villetaneuse, France
Abstract :
The paper focuses on the problem of the multi-spectral image segmentation, which leads-through the data fusion of several mono-spectral images-to reliable and robust vision systems for military or industrial purposes. The proposed approach does not fit the classical taxonomy of image data fusion methods: indeed, data fusion is performed during the segmentation, in parallel, of different images. The presented algorithm has been implemented on the Connection Machine CM5 with the data programming style
Keywords :
computer vision; cooperative systems; image segmentation; parallel algorithms; parallel machines; parallel programming; sensor fusion; CM5; Connection Machine; algorithm; data fusion; data programming style; industrial applications; military applications; mono-spectral images; multi-spectral cooperative segmentation; parallel implementation; vision systems; Computer vision; Data mining; Defense industry; Image edge detection; Image segmentation; Machine vision; Multispectral imaging; Pixel; Redundancy; Robustness;
Conference_Titel :
Algorithms and Architectures for Parallel Processing, 1995. ICAPP 95. IEEE First ICA/sup 3/PP., IEEE First International Conference on
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-7803-2018-2
DOI :
10.1109/ICAPP.1995.472280
