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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9149715/ |
| _version_ | 1818890094118961152 |
|---|---|
| author | Danielle Dias Allan Pinto Ulisses Dias Rubens Lamparelli Guerric Le Maire Ricardo da S. Torres |
| author_facet | Danielle Dias Allan Pinto Ulisses Dias Rubens Lamparelli Guerric Le Maire Ricardo da S. Torres |
| author_sort | Danielle Dias |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-19T17:19:27Z |
| format | Article |
| id | doaj.art-e34bfb5315da4e3f9c43936718073e27 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-19T17:19:27Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-e34bfb5315da4e3f9c43936718073e272022-12-21T20:12:44ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352020-01-01134399440910.1109/JSTARS.2020.30121179149715A Multirepresentational Fusion of Time Series for Pixelwise ClassificationDanielle Dias0https://orcid.org/0000-0002-4960-0600Allan Pinto1https://orcid.org/0000-0003-3765-8300Ulisses Dias2https://orcid.org/0000-0002-4763-3046Rubens Lamparelli3https://orcid.org/0000-0003-4344-1263Guerric Le Maire4Ricardo da S. Torres5https://orcid.org/0000-0001-9772-263XInstitute of Computing, University of Campinas (Unicamp), Campinas, BrazilInstitute of Computing, School of Physical Education, University of Campinas (Unicamp), Campinas, BrazilSchool of Technology, University of Campinas (Unicamp), Limeira, BrazilNúcleo Interdisciplinar de Planejamento Energético, University of Campinas, Campinas, BrazilEco&Sols, CIRAD, INRA, IRD, Montpellier SupAgro, University of Montpellier, Montpellier cedex 2, FranceDepartment of ICT and Natural Sciences, Norwegian University of Science and Technology, Ålesund, NorwayThis 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.https://ieeexplore.ieee.org/document/9149715/Classifier fusioneucalyptuspixelwise classificationtime series representation |
| spellingShingle | Danielle Dias Allan Pinto Ulisses Dias Rubens Lamparelli Guerric Le Maire Ricardo da S. Torres A Multirepresentational Fusion of Time Series for Pixelwise Classification IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Classifier fusion eucalyptus pixelwise classification time series representation |
| title | A Multirepresentational Fusion of Time Series for Pixelwise Classification |
| title_full | A Multirepresentational Fusion of Time Series for Pixelwise Classification |
| title_fullStr | A Multirepresentational Fusion of Time Series for Pixelwise Classification |
| title_full_unstemmed | A Multirepresentational Fusion of Time Series for Pixelwise Classification |
| title_short | A Multirepresentational Fusion of Time Series for Pixelwise Classification |
| title_sort | multirepresentational fusion of time series for pixelwise classification |
| topic | Classifier fusion eucalyptus pixelwise classification time series representation |
| url | https://ieeexplore.ieee.org/document/9149715/ |
| work_keys_str_mv | AT danielledias amultirepresentationalfusionoftimeseriesforpixelwiseclassification AT allanpinto amultirepresentationalfusionoftimeseriesforpixelwiseclassification AT ulissesdias amultirepresentationalfusionoftimeseriesforpixelwiseclassification AT rubenslamparelli amultirepresentationalfusionoftimeseriesforpixelwiseclassification AT guerriclemaire amultirepresentationalfusionoftimeseriesforpixelwiseclassification AT ricardodastorres amultirepresentationalfusionoftimeseriesforpixelwiseclassification AT danielledias multirepresentationalfusionoftimeseriesforpixelwiseclassification AT allanpinto multirepresentationalfusionoftimeseriesforpixelwiseclassification AT ulissesdias multirepresentationalfusionoftimeseriesforpixelwiseclassification AT rubenslamparelli multirepresentationalfusionoftimeseriesforpixelwiseclassification AT guerriclemaire multirepresentationalfusionoftimeseriesforpixelwiseclassification AT ricardodastorres multirepresentationalfusionoftimeseriesforpixelwiseclassification |