Imagen de Portada

A Local Approach to Optimise the Scale Parameter in Multiresolution Segmentation for Multispectral Imagery

The results obtained using the object-based image analysis approach for remote sensing image analysis depend strongly on the quality of the segmentation step. In this paper, to optimize the scale parameter in a multiresolution segmentation, we analyse a high-resolution image of a large and heterogen...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor Principal: C?novas Garc?a, Fulgencio Jos?
Formato: Artículos
Lenguaje:eng
Publicado: 2016
Materias:
OBJECT-BASED IMAGE ANALYSIS
SEGMENTATION
OPTIMIZATION
ECOGNITION
Acceso en línea:http://repositorio.educacionsuperior.gob.ec/handle/28000/3089
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:localhost:28000-3089
recordtype dspace
spelling oai:localhost:28000-30892017-04-12T14:41:39Z A Local Approach to Optimise the Scale Parameter in Multiresolution Segmentation for Multispectral Imagery C?novas Garc?a, Fulgencio Jos? OBJECT-BASED IMAGE ANALYSIS SEGMENTATION OPTIMIZATION ECOGNITION The results obtained using the object-based image analysis approach for remote sensing image analysis depend strongly on the quality of the segmentation step. In this paper, to optimize the scale parameter in a multiresolution segmentation, we analyse a high-resolution image of a large and heterogeneous agricultural area. This approach is based on using a set of agricultural plots extracted from official maps as uniform spatial units. The scale parameter is then optimized in each uniform spatial unit. Intra-object and inter-object heterogeneity measurements are used to evaluate each segmentation. To avoid subsegmentation, some oversegmentation is allowed, but is attenuated in a second step using the spectral difference segmentation algorithm. The statistical distribution of the scale parameter is not equal in all land uses, indicating the soundness of this local approach. A quantitative assessment of the results was also conducted for the different land covers. The results indicate that the spectral contrast between objects is larger with the local approach than with the global approach. These differences were statistically significant in all land uses except irrigated fruit trees and greenhouses. In the absence of subsegmentation, this suggests that the objects will be placed far apart in the space of variables, even if they are very close in the physical space. This is an obvious advantage in a subsequent classification of the objects. Universidad De Cuenca http://www.tandfonline.com/doi/abs/10.1080/10106049.2015.1004131?journalCode=tgei20 2016-11-09T17:22:52Z 2016-11-09T17:22:52Z 2015 article C?novas Garc?a, Fulgencio Jos?.; Sarria, Alonso. (2015). A Local Approach to Optimise the Scale Parameter in Multiresolution Segmentation for Multispectral Imagery. Geocarto International. Vol.30, N?8. pp.937-961 1010-6049 http://repositorio.educacionsuperior.gob.ec/handle/28000/3089 eng restrictedAccess pp.937-961
institution SENESCYT
collection Repositorio SENESCYT
biblioteca Biblioteca Senescyt
language eng
format Artículos
topic OBJECT-BASED IMAGE ANALYSIS
SEGMENTATION
OPTIMIZATION
ECOGNITION
spellingShingle OBJECT-BASED IMAGE ANALYSIS
SEGMENTATION
OPTIMIZATION
ECOGNITION
C?novas Garc?a, Fulgencio Jos?
A Local Approach to Optimise the Scale Parameter in Multiresolution Segmentation for Multispectral Imagery
description The results obtained using the object-based image analysis approach for remote sensing image analysis depend strongly on the quality of the segmentation step. In this paper, to optimize the scale parameter in a multiresolution segmentation, we analyse a high-resolution image of a large and heterogeneous agricultural area. This approach is based on using a set of agricultural plots extracted from official maps as uniform spatial units. The scale parameter is then optimized in each uniform spatial unit. Intra-object and inter-object heterogeneity measurements are used to evaluate each segmentation. To avoid subsegmentation, some oversegmentation is allowed, but is attenuated in a second step using the spectral difference segmentation algorithm. The statistical distribution of the scale parameter is not equal in all land uses, indicating the soundness of this local approach. A quantitative assessment of the results was also conducted for the different land covers. The results indicate that the spectral contrast between objects is larger with the local approach than with the global approach. These differences were statistically significant in all land uses except irrigated fruit trees and greenhouses. In the absence of subsegmentation, this suggests that the objects will be placed far apart in the space of variables, even if they are very close in the physical space. This is an obvious advantage in a subsequent classification of the objects.
author C?novas Garc?a, Fulgencio Jos?
author_facet C?novas Garc?a, Fulgencio Jos?
author_sort C?novas Garc?a, Fulgencio Jos?
title A Local Approach to Optimise the Scale Parameter in Multiresolution Segmentation for Multispectral Imagery
title_short A Local Approach to Optimise the Scale Parameter in Multiresolution Segmentation for Multispectral Imagery
title_full A Local Approach to Optimise the Scale Parameter in Multiresolution Segmentation for Multispectral Imagery
title_fullStr A Local Approach to Optimise the Scale Parameter in Multiresolution Segmentation for Multispectral Imagery
title_full_unstemmed A Local Approach to Optimise the Scale Parameter in Multiresolution Segmentation for Multispectral Imagery
title_sort local approach to optimise the scale parameter in multiresolution segmentation for multispectral imagery
publishDate 2016
url http://repositorio.educacionsuperior.gob.ec/handle/28000/3089
_version_ 1634995107680747520
score 11,871979

Ejemplares similares