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

Improving land cover classification through contextual-based optimum-path forest

Full text
Author(s):
Osaku, D. [1] ; Nakamura, R. Y. M. [2] ; Pereira, L. A. M. [3] ; Pisani, R. J. [4] ; Levada, A. L. M. ; Cappabianco, F. A. M. [5, 1] ; Falco, A. X. [3] ; Papa, Joao P. [6]
Total Authors: 8
Affiliation:
[1] UFSCar Univ Fed Sao Carlos, Dept Comp, Sao Carlos, SP - Brazil
[2] Big Data Brasil, Sao Paulo - Brazil
[3] Univ Estadual Campinas, Inst Comp, Campinas, SP - Brazil
[4] Western Univ Sao Paulo, Presidente Prudente, SP - Brazil
[5] Univ Fed Sao Paulo, Sao Jose Dos Campos - Brazil
[6] Sao Paulo State Univ, Dept Comp, Bauru - Brazil
Total Affiliations: 6
Document type: Journal article
Source: INFORMATION SCIENCES; v. 324, p. 60-87, DEC 10 2015.
Web of Science Citations: 12
Abstract

Traditional machine learning algorithms very often assume statistically independent data samples. However, this is clearly not the case in remote sensing image applications, in which pixels present spatial and/or temporal dependencies. In this work, it has been presented an approach to improve land cover image classification using a contextual approach based on optimum-path forest (OPF) and the well-known Markov random fields (MRFs), hereinafter called OPF-MRF. In addition, it is also introduced a framework to the optimization of the amount of contextual information used by OPF-MRF. Experiments over high- and medium-resolution satellite (CBERS-2B, Landsat 5 TM, lkonos-2 MS and Geoeye) and radar (ALOS-PALSAR) images covering the area of two Brazilian cities have shown the proposed approach can overcome several shortcomings related to standard OPF classification. In some cases, the proposed approach outperformed traditional OFF in about 9% of recognition rate, which is crucial for land cover classification. (C) 2015 Elsevier Inc. All rights reserved. (AU)

FAPESP's process: 14/16250-9 - On the parameter optimization in machine learning techniques: advances and paradigms
Grantee:João Paulo Papa
Support Opportunities: Regular Research Grants
FAPESP's process: 09/16206-1 - New trends on optimum-path forest-based pattern recognition
Grantee:João Paulo Papa
Support Opportunities: Research Grants - Young Investigators Grants
FAPESP's process: 12/06472-9 - Exploring Contextual Classification Approaches for Optimum-Path Forest
Grantee:Daniel Osaku
Support Opportunities: Scholarships in Brazil - Doctorate
FAPESP's process: 13/20387-7 - Hyperparameter optimization in deep learning arquitectures
Grantee:João Paulo Papa
Support Opportunities: Scholarships abroad - Research