A Multirepresentational Fusion of Time Series for Pixelwise Classification

This article addresses the pixelwise classification problem based on temporal profiles, which are encoded in 2-D representations based on recurrence plots, Gramian angular/ difference fields, and Markov transition field. We propose a multirepresentational fusion scheme that exploits the complementar...

Full description

Saved in:
Bibliographic Details
Published inIEEE journal of selected topics in applied earth observations and remote sensing Vol. 13; pp. 4399 - 4409
Main Authors Dias, Danielle, Pinto, Allan, Dias, Ulisses, Lamparelli, Rubens, Le Maire, Guerric, Torres, Ricardo da S.
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Classification
Classifier fusion
Earth
Electronic mail
Eucalyptus
Feature extraction
Image classification
Indexes
pixelwise classification
Profiles
Remote sensing
Representations
Time series
Time series analysis
time series representation
Vegetation mapping
Online AccessGet full text

Cover

More Information
Summary:This article addresses the pixelwise classification problem based on temporal profiles, which are encoded in 2-D representations based on recurrence plots, Gramian angular/ difference fields, and Markov transition field. We propose a multirepresentational fusion scheme that exploits the complementary view provided by those time series representations and different data-driven feature extractors and classifiers. We validate our ensemble scheme in the problem related to the classification of eucalyptus plantations in remote sensing images. Achieved results demonstrate that our proposal overcomes recently proposed baselines, and now represents the new state-of-the-art classification solution for the target dataset.
ISSN:1939-1404
2151-1535
DOI:10.1109/JSTARS.2020.3012117