Synergy of multitemporal ERS-1 SAR and Landsat TM data for classification of agricultural crops
- 1 January 2003
- journal article
- Published by Taylor & Francis in Canadian Journal of Remote Sensing
- Vol. 29 (4) , 518-526
- https://doi.org/10.5589/m03-014
Abstract
The objective of this research was to evaluate the synergistic effects of multitemporal European remote sensing satellite 1 (ERS-1) synthetic aperture radar (SAR) and Landsat thematic mapper (TM) data for crop classification using a per-field artificial neural network (ANN) approach. Eight crop types and conditions were identified: winter wheat, corn (good growth), corn (poor growth), soybeans (good growth), soybeans (poor growth), barley/oats, alfalfa, and pasture. With the per-field approach using a feed-forward ANN, the overall classification accuracy of three-date early- to mid-season SAR data improved almost 20%, and the best classification of a single-date (5 August) SAR image improved the overall accuracy by about 26%, in comparison to a per-pixel maximum-likelihood classifier (MLC). Both single-date and multitemporal SAR data demonstrated their abilities to discriminate certain crops in the early and mid-season; however, these overall classification accuracies (<60%) were not sufficiently high for... L'objectif de cette recherche consistait à évaluer les effets de la synergie des données multitemporelles ROS de ERS-1 et Landsat TM pour la classification des cultures utilisant l'approche par champ individuel basée sur les réseaux de neurones artificiels (RNA). Huit types de cultures et conditions ont été identifiés : blé d'hiver, maïs (bonne croissance), maïs (faible croissance), soja (bonne croissance), soja (faible croissance), orge-avoine, luzerne et pâturage. Avec l'approche par champ individuel basée sur un réseau de neurones artificiels à action directe, la précision globale de classification des données ROS pour trois dates, s'étendant de la période du début au milieu de la saison de croissance, a été améliorée de près de 20 % et la meilleure classification pour une date unique pour une image ROS (5 août) a amélioré la précision globale d'environ 26 % comparativement à une approche utilisant un classificateur basé sur la méthode du maximum de vraisemblance par pixel. Les données unidate et multi...Keywords
This publication has 10 references indexed in Scilit:
- Land cover discrimination from multitemporal ERS images and multispectral Landsat images: A study case in an agricultural area in FranceInternational Journal of Remote Sensing, 2000
- Multitemporal ERS-1 SAR Data for Crop Classification: A Sequential-Masking ApproachCanadian Journal of Remote Sensing, 1999
- Classification of multisource and hyperspectral data based on decision fusionIEEE Transactions on Geoscience and Remote Sensing, 1999
- Orbital effects on ERS-1 SAR temporal backscatter profiles of agricultural cropsInternational Journal of Remote Sensing, 1998
- Classification of Mediterranean crops with multisensor data: per-pixel versus per-object statistics and image segmentationInternational Journal of Remote Sensing, 1996
- A review and analysis of backpropagation neural networks for classification of remotely-sensed multi-spectral imageryInternational Journal of Remote Sensing, 1995
- Improving the Accuracy of Synthetic Aperture Radar Analysis for Agricultural Crop ClassificationCanadian Journal of Remote Sensing, 1995
- Forest mapping from multi‐source satellite data using neural network classifiers—an experiment in PortugalRemote Sensing Reviews, 1995
- Crop classification from C-band polarimetric radar dataInternational Journal of Remote Sensing, 1994
- A Backscatter Model for a Randomly Perturbed Periodic SurfaceIEEE Transactions on Geoscience and Remote Sensing, 1982