Please use this identifier to cite or link to this item: http://www.alice.cnptia.embrapa.br/alice/handle/doc/31577
Research center of Embrapa/Collection: Embrapa Territorial - Artigo em periódico indexado (ALICE)
Date Issued: 2008
Type of Material: Artigo em periódico indexado (ALICE)
Authors: LU, D.
BATISTELLA, M.
MIRANDA, E. E. de
Additional Information: DENGSHENG LU, Indiana University; MATEUS BATISTELLA, CNPM; EVARISTO EDUARDO DE MIRANDA, CNPM.
Title: A comparative study of landsat TM and SPOT HRG images of vegetation classification in the brazilian Amazon.
Publisher: Photogrammetric Engineering & Remote Sensing, v. 74, n. 3, p. 311-321, mar. 2008.
Language: en
Keywords: Comparative study
Landsat TM and SPOT HRG Images
Brazilian Amazon
Moist tropical regions
Machadinho d´Oeste
Description: Complex forest structure and abundant tree species in the moist tropical regions often couse difficulties in classifying vegetation classes with remotely sensed data. This paper explores improvement in vegetation classification accuracies through a comparative study of different image combinations based on the integration of Landsat Thematic Mapper (TM) and SPOT High Resolution Geometric (HRG) instrument data, as well as the combination of spectral signatures and textures. A maximum likelihood classifier was used to classify the different image combinations into thematic maps. This research indicated that data fusion based on HBG multispectral and panchromatic data slightly improved vegetation classification accuracies: a 3.1 to 4.6 percent increase in the kappa coefficient compared with the classification results based on original HRG of TM multispectral images. A combination of HRG spectral signatures and two textural images improved the kappa coefficient by 6.3 percent compared with pure HRG multispectral images. The textural images based on entropy or second-moment texture measures with a window size of 9 pixels X 9 pixels played an important role in improving vegetation classification accuracy. Overall, optical remote-sensing data are still insufficient for accurate vegetation classifications in the Amazon basin.
Data Created: 2009-03-02
ISBN: 0099-1112
Appears in Collections:Artigo em periódico indexado (CNPM)

Files in This Item:
File Description SizeFormat 
2284.pdf2,29 MBAdobe PDFThumbnail
View/Open

FacebookTwitterDeliciousLinkedInGoogle BookmarksMySpace