INVESTIGATING THE POTENTIAL OF DEEP NEURAL NETWORKS FOR LARGE-SCALE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE IMAGES
Semantic classification is a core remote sensing task as it provides the fundamental input for land-cover map generation. The very recent literature has shown the superior performance of deep convolutional neural networks (DCNN) for many classification tasks including the automatic analysis of Ver...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2017-05-01
|
| Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/IV-1-W1/183/2017/isprs-annals-IV-1-W1-183-2017.pdf |
| _version_ | 1819099091737509888 |
|---|---|
| author | T. Postadjian A. Le Bris H. Sahbi C. Mallet |
| author_facet | T. Postadjian A. Le Bris H. Sahbi C. Mallet |
| author_sort | T. Postadjian |
| collection | DOAJ |
| description | Semantic classification is a core remote sensing task as it provides the fundamental input for land-cover map generation. The very
recent literature has shown the superior performance of deep convolutional neural networks (DCNN) for many classification tasks
including the automatic analysis of Very High Spatial Resolution (VHR) geospatial images. Most of the recent initiatives have focused
on very high discrimination capacity combined with accurate object boundary retrieval. Therefore, current architectures are perfectly
tailored for urban areas over restricted areas but not designed for large-scale purposes. This paper presents an end-to-end automatic
processing chain, based on DCNNs, that aims at performing large-scale classification of VHR satellite images (here SPOT 6/7). Since
this work assesses, through various experiments, the potential of DCNNs for country-scale VHR land-cover map generation, a simple
yet effective architecture is proposed, efficiently discriminating the main classes of interest (namely <i>buildings, roads, water, crops,
vegetated areas</i>) by exploiting existing VHR land-cover maps for training. |
| first_indexed | 2024-12-22T00:41:22Z |
| format | Article |
| id | doaj.art-f0da9e5ee51645b9910347fe9636e0ab |
| institution | Directory Open Access Journal |
| issn | 2194-9042 2194-9050 |
| language | English |
| last_indexed | 2024-12-22T00:41:22Z |
| publishDate | 2017-05-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-f0da9e5ee51645b9910347fe9636e0ab2022-12-21T18:44:40ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502017-05-01IV-1-W118319010.5194/isprs-annals-IV-1-W1-183-2017INVESTIGATING THE POTENTIAL OF DEEP NEURAL NETWORKS FOR LARGE-SCALE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE IMAGEST. Postadjian0A. Le Bris1H. Sahbi2C. Mallet3Univ. Paris Est, LASTIG MATIS, IGN, ENSG, F-94160 Saint-Mande, FranceUniv. Paris Est, LASTIG MATIS, IGN, ENSG, F-94160 Saint-Mande, FranceCNRS, LIP6 UPMC Sorbonne Universités, Paris, FranceUniv. Paris Est, LASTIG MATIS, IGN, ENSG, F-94160 Saint-Mande, FranceSemantic classification is a core remote sensing task as it provides the fundamental input for land-cover map generation. The very recent literature has shown the superior performance of deep convolutional neural networks (DCNN) for many classification tasks including the automatic analysis of Very High Spatial Resolution (VHR) geospatial images. Most of the recent initiatives have focused on very high discrimination capacity combined with accurate object boundary retrieval. Therefore, current architectures are perfectly tailored for urban areas over restricted areas but not designed for large-scale purposes. This paper presents an end-to-end automatic processing chain, based on DCNNs, that aims at performing large-scale classification of VHR satellite images (here SPOT 6/7). Since this work assesses, through various experiments, the potential of DCNNs for country-scale VHR land-cover map generation, a simple yet effective architecture is proposed, efficiently discriminating the main classes of interest (namely <i>buildings, roads, water, crops, vegetated areas</i>) by exploiting existing VHR land-cover maps for training.http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/IV-1-W1/183/2017/isprs-annals-IV-1-W1-183-2017.pdf |
| spellingShingle | T. Postadjian A. Le Bris H. Sahbi C. Mallet INVESTIGATING THE POTENTIAL OF DEEP NEURAL NETWORKS FOR LARGE-SCALE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE IMAGES ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | INVESTIGATING THE POTENTIAL OF DEEP NEURAL NETWORKS FOR LARGE-SCALE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE IMAGES |
| title_full | INVESTIGATING THE POTENTIAL OF DEEP NEURAL NETWORKS FOR LARGE-SCALE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE IMAGES |
| title_fullStr | INVESTIGATING THE POTENTIAL OF DEEP NEURAL NETWORKS FOR LARGE-SCALE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE IMAGES |
| title_full_unstemmed | INVESTIGATING THE POTENTIAL OF DEEP NEURAL NETWORKS FOR LARGE-SCALE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE IMAGES |
| title_short | INVESTIGATING THE POTENTIAL OF DEEP NEURAL NETWORKS FOR LARGE-SCALE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE IMAGES |
| title_sort | investigating the potential of deep neural networks for large scale classification of very high resolution satellite images |
| url | http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/IV-1-W1/183/2017/isprs-annals-IV-1-W1-183-2017.pdf |
| work_keys_str_mv | AT tpostadjian investigatingthepotentialofdeepneuralnetworksforlargescaleclassificationofveryhighresolutionsatelliteimages AT alebris investigatingthepotentialofdeepneuralnetworksforlargescaleclassificationofveryhighresolutionsatelliteimages AT hsahbi investigatingthepotentialofdeepneuralnetworksforlargescaleclassificationofveryhighresolutionsatelliteimages AT cmallet investigatingthepotentialofdeepneuralnetworksforlargescaleclassificationofveryhighresolutionsatelliteimages |