2020 |
Chairet, Radhia; Salem, Yassine Ben; Aoun, Mohamed Land cover classification of GeoEye image based on Convolutional Neural Networks Conférence 2020, (Cited by: 2). Résumé | Liens | BibTeX | Étiquettes: Classification algorithm, Convolution, Convolutional neural networks, Decision trees, Deep neural networks, Ecosystem management, Environmental projects, Image classification, Land cover classification, Land cover mapping, Mapping, Overall accuracies, Pixel based classifications, Random forest classifier, Remote sensing @conference{Chairet2020458b,Land cover classification is an important topic in remote sensing. It provides useful information for environmental projects and ecosystem management. To succeed the mapping task, interest should be given to select a suitable classification algorithm. The recent advances in machine learning have shown the very great performances of the deep neural networks for many applications including the land cover mapping. The purpose of this work is to exploit the performance of Convolutional Neural Networks CNN to classify a GeoEye satellite image. Two CNN models with three and four convolution layers are tested to show the impact of the number of layers on the accuracy result. The two architectures outperform, with an overall accuracy more than 81%, the pixel based classification using Random Forest classifier. © 2020 IEEE. |
2019 |
Chairet, Radhia; Salem, Yassine Ben; Aoun, Mohamed Features extraction and land cover classification using Sentinel 2 data Conférence 2019, (Cited by: 6). Résumé | Liens | BibTeX | Étiquettes: Automation, Classification (of information), Extraction, Features extraction, GLCM, High spatial resolution, Image segmentation, Land cover classification, NDVI, Overall accuracies, Process control, Sentinel 2, supervised classification, Textures @conference{Chairet2019497b,Since 2015, the Sentinel 2 satellite provides a medium to high spatial resolution (10m-30m) images. For studying the land cover of Gabes area, located in the South- East of Tunisia, we exploited the 10 m bands of this satellite. We have tested the supervised classification with the SVM classifier. The classification is preceded by a segmentation step. The spectral data, the vegetation index and the texture metrics (GLCM) are used for training. The best Overall Accuracy OA (92, 12%) is obtained when all the used features are combined. © 2019 IEEE. |
Chairet, Radhia; Salem, Yassine Ben; Aoun, Mohamed Features extraction and land cover classification using Sentinel 2 data Conférence 2019, (Cited by: 6). Résumé | Liens | BibTeX | Étiquettes: Automation, Classification (of information), Extraction, Features extraction, GLCM, High spatial resolution, Image segmentation, Land cover classification, NDVI, Overall accuracies, Process control, Sentinel 2, supervised classification, Textures @conference{Chairet2019497,Since 2015, the Sentinel 2 satellite provides a medium to high spatial resolution (10m-30m) images. For studying the land cover of Gabes area, located in the South- East of Tunisia, we exploited the 10 m bands of this satellite. We have tested the supervised classification with the SVM classifier. The classification is preceded by a segmentation step. The spectral data, the vegetation index and the texture metrics (GLCM) are used for training. The best Overall Accuracy OA (92, 12%) is obtained when all the used features are combined. © 2019 IEEE. |
Publications
2020 |
Land cover classification of GeoEye image based on Convolutional Neural Networks Conférence 2020, (Cited by: 2). |
2019 |
Features extraction and land cover classification using Sentinel 2 data Conférence 2019, (Cited by: 6). |
Features extraction and land cover classification using Sentinel 2 data Conférence 2019, (Cited by: 6). |