A multirepresentational fusion of time series for pixelwise classification

Dias Danielle, Pinto Allan, Dias Ulisses, Lamparelli Rubens Augusto Camargo, Le Maire Guerric, da S. Torres Ricardo. 2020. A multirepresentational fusion of time series for pixelwise classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13 : 4399-4409.

https://doi.org/10.1109/JSTARS.2020.3012117

Article de revue ; Article de recherche ; Article de revue à facteur d'impact

Prévisualisation

Version publiée - Anglais
Sous licence

.
598326.pdf
Télécharger (1MB) | Prévisualisation

Quartile : Q2, Sujet : ENGINEERING, ELECTRICAL & ELECTRONIC / Quartile : Q2, Sujet : GEOGRAPHY, PHYSICAL / Quartile : Q2, Sujet : IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY / Quartile : Q2, Sujet : REMOTE SENSING

Résumé : 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.

Mots-clés Agrovoc : télédétection, analyse de séries chronologiques, imagerie par satellite, analyse d'image, classification, Eucalyptus, plantations, indice de végétation

Mots-clés libres : Term-Classifier, Fusion, Eucalyptus, Pixelwise classification, Time series representation

Classification Agris : U30 - Méthodes de recherche
U10 - Informatique, mathématiques et statistiques
K01 - Foresterie - Considérations générales

Champ stratégique Cirad : CTS 5 (2019-) - Territoires

Auteurs et affiliations