Advanced search
Start date
Betweenand
Related content
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

Examining region-based methods for land cover classification using stochastic distances

Full text
Author(s):
Negri, R. G. [1] ; Dutra, L. V. [2] ; Sant'Anna, S. J. S. [2] ; Lu, D. [3]
Total Authors: 4
Affiliation:
[1] UNESP Univ Estadual Paulista, Inst Ciencia & Tecnol, Sao Jose Campos, Sao Paulo - Brazil
[2] INPE, Div Proc Imagens, Sao Paulo - Brazil
[3] MSU, Ctr Global Change & Earth Observat, E Lansing, MI - USA
Total Affiliations: 3
Document type: Journal article
Source: International Journal of Remote Sensing; v. 37, n. 8, p. 1902-1921, 2016.
Web of Science Citations: 2
Abstract

A recent alternative to standard pixel-based classification of remote-sensing data is region-based classification, which has proved to be particularly useful when analysing high-resolution imagery of complex environments, such as urban areas, or when addressing noisy data, such as synthetic aperture radar (SAR) images. First, following certain criteria, the imagery is decomposed into homogeneous regions, and then each region is classified into a class of interest. The usual method for region-based classification involves using stochastic distances, which measure the distances between the pixel distributions inside an unknown region and the representative distributions of each class. The class, which is at the minimum distance from the unknown region distribution, is assigned to the region and this procedure is termed stochastic minimum distance classification (SMDC). This study reports the use of methods derived from the original SMDC, Support Vector Machine (SVM), and graph theory, with the objective of identifying the most robust and accurate classification methods. The equivalent pixel-based versions of region-based analysed methods were included for comparison. A case study near the Tapajos National Forest, in Para state, Brazil, was investigated using ALOS PALSAR data. This study showed that methods based on the nearest neighbour, derived from SMDC, and SVM, with a specific kernel function, are more accurate and robust than the other analysed methods for region-based classification. Furthermore, pixel-based methods are not indicated to perform the classification of images with a strong presence of noise, such as SAR images. (AU)

FAPESP's process: 14/14830-8 - Study and development of new Kernel functions with applications on remote sensing image classification
Grantee:Rogério Galante Negri
Support Opportunities: Regular Research Grants