Application of spectral mixture analysis to Amazonian land-use and land-cover classification.

Application of spectral mixture analysis to Amazonian land-use and land-cover classification.

Abundant vegetation species and associated complex forest stand structures in moist tropical regions often create difficulties in accurately classifying land-use and land-cover (LULC) features. This paper examines the value of spectral mixture analysis (SMA) using Landsat Thematic Mapper (TM) data for improving LULC classification accuracy in a moist tropical area in Rondbnia, Brazil. Different routines, such as constrained and unconstrained least-squares solutions, different numbers of endmembers, and minimum noise fraction transformation, were examined while implementing the SMA approach. A maximum likelihood classifier was also used to classify fraction images into seven LULC classes: mature forest, intermediate secondary succession, initial secondary succession, pasture, agricultural land, water, and bare land. The results of this study indicate that reducing correlation between image bands and using four endmembers improve classification accuracy. The overall classification accuracy was 86.6% for the seven LULC classes using the best SMA processing routine, which represents very good results for such a' complex environment. The overall classification accuracy using a maximum likelihood approach was 81.4%. Another finding is that use of constrained or unconstrained solutions for unmixing the atmospherically corrected or raw Landsat TM images does not have significant influence on LULC classification performances when image endmembers are used in a SMA approach.

Saved in:
Bibliographic Details
Main Authors: LU, D., BATISTELLA, M., MORAN, E., MAUSEL, P.
Other Authors: DENSHENG LU, INDIANA UNIVERSITY; MATEUS BATISTELLA, CNPM; EMILIO MORAN, INDIANA UNIVERSITY; P. MAUSEL, INDIANA STATE UNIVERSITY.
Format: Artigo de periódico biblioteca
Language:pt_BR
por
Published: 2014-09-16
Subjects:Landsat Thematic Mapper, Vegetation species.,
Online Access:http://www.alice.cnptia.embrapa.br/alice/handle/doc/995070
Tags: Add Tag
No Tags, Be the first to tag this record!
id dig-alice-doc-995070
record_format koha
spelling dig-alice-doc-9950702017-08-16T00:18:03Z Application of spectral mixture analysis to Amazonian land-use and land-cover classification. LU, D. BATISTELLA, M. MORAN, E. MAUSEL, P. DENSHENG LU, INDIANA UNIVERSITY; MATEUS BATISTELLA, CNPM; EMILIO MORAN, INDIANA UNIVERSITY; P. MAUSEL, INDIANA STATE UNIVERSITY. Landsat Thematic Mapper Vegetation species. Abundant vegetation species and associated complex forest stand structures in moist tropical regions often create difficulties in accurately classifying land-use and land-cover (LULC) features. This paper examines the value of spectral mixture analysis (SMA) using Landsat Thematic Mapper (TM) data for improving LULC classification accuracy in a moist tropical area in Rondbnia, Brazil. Different routines, such as constrained and unconstrained least-squares solutions, different numbers of endmembers, and minimum noise fraction transformation, were examined while implementing the SMA approach. A maximum likelihood classifier was also used to classify fraction images into seven LULC classes: mature forest, intermediate secondary succession, initial secondary succession, pasture, agricultural land, water, and bare land. The results of this study indicate that reducing correlation between image bands and using four endmembers improve classification accuracy. The overall classification accuracy was 86.6% for the seven LULC classes using the best SMA processing routine, which represents very good results for such a' complex environment. The overall classification accuracy using a maximum likelihood approach was 81.4%. Another finding is that use of constrained or unconstrained solutions for unmixing the atmospherically corrected or raw Landsat TM images does not have significant influence on LULC classification performances when image endmembers are used in a SMA approach. 2014-09-16T11:11:11Z 2014-09-16T11:11:11Z 2014-09-16 2004 2014-09-16T11:11:11Z Artigo de periódico International Journal of Remote Sensing, v. 25, n. 23, p. 5345-5358, 2004. http://www.alice.cnptia.embrapa.br/alice/handle/doc/995070 pt_BR por openAccess
institution EMBRAPA
collection DSpace
country Brasil
countrycode BR
component Bibliográfico
access En linea
databasecode dig-alice
tag biblioteca
region America del Sur
libraryname Sistema de bibliotecas de EMBRAPA
language pt_BR
por
topic Landsat Thematic Mapper
Vegetation species.
Landsat Thematic Mapper
Vegetation species.
spellingShingle Landsat Thematic Mapper
Vegetation species.
Landsat Thematic Mapper
Vegetation species.
LU, D.
BATISTELLA, M.
MORAN, E.
MAUSEL, P.
Application of spectral mixture analysis to Amazonian land-use and land-cover classification.
description Abundant vegetation species and associated complex forest stand structures in moist tropical regions often create difficulties in accurately classifying land-use and land-cover (LULC) features. This paper examines the value of spectral mixture analysis (SMA) using Landsat Thematic Mapper (TM) data for improving LULC classification accuracy in a moist tropical area in Rondbnia, Brazil. Different routines, such as constrained and unconstrained least-squares solutions, different numbers of endmembers, and minimum noise fraction transformation, were examined while implementing the SMA approach. A maximum likelihood classifier was also used to classify fraction images into seven LULC classes: mature forest, intermediate secondary succession, initial secondary succession, pasture, agricultural land, water, and bare land. The results of this study indicate that reducing correlation between image bands and using four endmembers improve classification accuracy. The overall classification accuracy was 86.6% for the seven LULC classes using the best SMA processing routine, which represents very good results for such a' complex environment. The overall classification accuracy using a maximum likelihood approach was 81.4%. Another finding is that use of constrained or unconstrained solutions for unmixing the atmospherically corrected or raw Landsat TM images does not have significant influence on LULC classification performances when image endmembers are used in a SMA approach.
author2 DENSHENG LU, INDIANA UNIVERSITY; MATEUS BATISTELLA, CNPM; EMILIO MORAN, INDIANA UNIVERSITY; P. MAUSEL, INDIANA STATE UNIVERSITY.
author_facet DENSHENG LU, INDIANA UNIVERSITY; MATEUS BATISTELLA, CNPM; EMILIO MORAN, INDIANA UNIVERSITY; P. MAUSEL, INDIANA STATE UNIVERSITY.
LU, D.
BATISTELLA, M.
MORAN, E.
MAUSEL, P.
format Artigo de periódico
topic_facet Landsat Thematic Mapper
Vegetation species.
author LU, D.
BATISTELLA, M.
MORAN, E.
MAUSEL, P.
author_sort LU, D.
title Application of spectral mixture analysis to Amazonian land-use and land-cover classification.
title_short Application of spectral mixture analysis to Amazonian land-use and land-cover classification.
title_full Application of spectral mixture analysis to Amazonian land-use and land-cover classification.
title_fullStr Application of spectral mixture analysis to Amazonian land-use and land-cover classification.
title_full_unstemmed Application of spectral mixture analysis to Amazonian land-use and land-cover classification.
title_sort application of spectral mixture analysis to amazonian land-use and land-cover classification.
publishDate 2014-09-16
url http://www.alice.cnptia.embrapa.br/alice/handle/doc/995070
work_keys_str_mv AT lud applicationofspectralmixtureanalysistoamazonianlanduseandlandcoverclassification
AT batistellam applicationofspectralmixtureanalysistoamazonianlanduseandlandcoverclassification
AT morane applicationofspectralmixtureanalysistoamazonianlanduseandlandcoverclassification
AT mauselp applicationofspectralmixtureanalysistoamazonianlanduseandlandcoverclassification
_version_ 1756019869179969536

Similar Items