Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/48668
Title: Multispectral cooperative partition sequence fusion for joint classification and hierarchical segmentation
Authors: Calderero, Felipe
Eugenio, Francisco 
Marcello, Javier 
Marques, Ferran
UNESCO Clasification: 250616 Teledetección (Geología)
Keywords: Image Segmentation
Image region analysis
multispectral images
region merging
information fusion
Issue Date: 2012
Publisher: 1545-598X
Journal: IEEE Geoscience and Remote Sensing Letters 
Abstract: In this letter, a region-based fusion methodology is presented for joint classification and hierarchical segmentation of specific ground cover classes from high-spatial-resolution remote sensing images. Multispectral information is fused at the partition level using nonlinear techniques, which allows the different relevance of the various bands to be fully exploited. A hierarchical segmentation is performed for each individual band, and the ensuing segmentation results are fused in an iterative and cooperative way. At each iteration, a consensus partition is obtained based on information theory and is combined with a specific ground cover classification. Here, the proposed approach is applied to the extraction and segmentation of vegetation areas. The result is a hierarchy of partitions with the most relevant information of the vegetation areas at different levels of resolution. This system has been tested for vegetation analysis in high-spatial-resolution images from the QuickBird and GeoEye satellites.
URI: http://hdl.handle.net/10553/48668
ISSN: 1545-598X
DOI: 10.1109/LGRS.2012.2188776
Source: IEEE Geoscience and Remote Sensing Letters[ISSN 1545-598X],v. 9 (6177220), p. 1012-1016
Appears in Collections:Artículos
Show full item record

SCOPUSTM   
Citations

4
checked on Jul 3, 2022

WEB OF SCIENCETM
Citations

4
checked on Jul 3, 2022

Page view(s)

10
checked on Apr 30, 2022

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.