Mostrar el registro sencillo del ítem
dc.contributor.author
Baumgartner, Josef Sylvester
dc.contributor.author
Gimenez Romero, Javier Alejandro
dc.contributor.author
Scavuzzo, Marcelo
dc.contributor.author
Pucheta, Julián Antonio
dc.date.available
2016-09-07T19:09:30Z
dc.date.issued
2015-06
dc.identifier.citation
Baumgartner, Josef Sylvester; Gimenez Romero, Javier Alejandro; Scavuzzo, Marcelo; Pucheta, Julián Antonio; A New Approach to Segmentation of Multispectral Remote Sensing Images Based on MRF; Institute Of Electrical And Electronics Engineers; Ieee Geoscience And Remote Sensing Letters; 12; 8; 6-2015; 1720-1724
dc.identifier.issn
1545-598X
dc.identifier.uri
http://hdl.handle.net/11336/7511
dc.description.abstract
Segmentation of multispectral remote sensing images is a key competence for a great variety of applications. Many of the applied segmentation algorithms are generative models based on Markov random fields. These approaches are generally limited to multivariate probability densities like the normal distribution. Besides that, it is usually impossible to adjust the contextual parameters separately for each frequency band. In this work, we present a new segmentation algorithm that avoids the mentioned problems and allows the use of any univariate density function as emission probability in each band. The approach consists of three steps: First, calculate feature vectors for each frequency band. Second, estimate contextual parameters for each band and apply local smoothing. Third, merge the feature vectors of the frequency bands to obtain a final segmentation. This procedure can be iterated but experiments show, that after the first iteration most of the pixels are already in their final state. We call our approach Successive Band Merging (SBM). To evaluate the performance of SBM, we segment a Landsat 8 and an AVIRIS image. In both cases, the κ coefficients show, that SBM outperforms the benchmark algorithms.
dc.format
application/pdf
dc.language.iso
eng
dc.publisher
Institute Of Electrical And Electronics Engineers
dc.rights
info:eu-repo/semantics/openAccess
dc.rights.uri
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.subject
Image Segmentation
dc.subject
Markov Random Fields
dc.subject
Multispectral Imaging
dc.subject
Probability Density Function
dc.subject.classification
Ingeniería de Sistemas y Comunicaciones
dc.subject.classification
Ingeniería Eléctrica, Ingeniería Electrónica e Ingeniería de la Información
dc.subject.classification
INGENIERÍAS Y TECNOLOGÍAS
dc.title
A New Approach to Segmentation of Multispectral Remote Sensing Images Based on MRF
dc.type
info:eu-repo/semantics/article
dc.type
info:ar-repo/semantics/artículo
dc.type
info:eu-repo/semantics/publishedVersion
dc.date.updated
2016-07-22T13:45:20Z
dc.journal.volume
12
dc.journal.number
8
dc.journal.pagination
1720-1724
dc.journal.pais
Estados Unidos
dc.journal.ciudad
Nueva York
dc.description.fil
Fil: Baumgartner, Josef Sylvester. Universidad Nacional de Cordoba. Facultad de Cs.exactas Fisicas y Naturales. Departamento de Electronica; Argentina
dc.description.fil
Fil: Gimenez Romero, Javier Alejandro. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico San Juan. Instituto de Automática; Argentina
dc.description.fil
Fil: Scavuzzo, Marcelo. Comision Nacional de Actividades Espaciales; Argentina
dc.description.fil
Fil: Pucheta, Julián Antonio. Universidad Nacional de Cordoba. Facultad de Cs.exactas Fisicas y Naturales. Departamento de Electronica; Argentina
dc.journal.title
Ieee Geoscience And Remote Sensing Letters
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/http://ieeexplore.ieee.org/document/7098347/?arnumber=7098347
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.1109/LGRS.2015.2421736
Archivos asociados