| Titre : | Big Data Technologies for processing and interpreting spatial data. | | Type de document : | projet fin études | | Auteurs : | Abdessamad ABOUZAID, Auteur | | Langues : | Français (fre) | | Catégories : | BIG DATA
| | Index. décimale : | mast 281/19 | | Résumé : | Timely and accurate information on crop yield is critical to many applications within agriculture monitoring.
Thanks to its coverage and temporal resolution, coarse spatial resolution satellite imagery has always been
a source of valuable information for yield forecasting and assessment at national and regional scales. With
availability of free images acquired by Landsat-8 and Sentinel-2 remote sensing satellites, it becomes possible
to enable temporal resolution of an image every 3–5 days, and therefore, to develop next generation agriculture
products at higher spatial resolution (30 m). Various indices are used for assessing vegetation and soil properties
in satellite remote sensing applications. Some indices, such as NDVI and NDWI, are defined based on the
sensitivity and significance of specific bands. a novel dataset based on Sentinel-2 satellite images covering 13
spectral bands and consisting out of 10 classes with in total 27,000 labeled and geo-referenced images have been
used for classification. We demonstrate how this classification system can be used for detecting land use and
land cover changes and how it can assist in improving geographical maps. |
Big Data Technologies for processing and interpreting spatial data. [projet fin études] / Abdessamad ABOUZAID, Auteur . - [s.d.]. Langues : Français ( fre) | Catégories : | BIG DATA
| | Index. décimale : | mast 281/19 | | Résumé : | Timely and accurate information on crop yield is critical to many applications within agriculture monitoring.
Thanks to its coverage and temporal resolution, coarse spatial resolution satellite imagery has always been
a source of valuable information for yield forecasting and assessment at national and regional scales. With
availability of free images acquired by Landsat-8 and Sentinel-2 remote sensing satellites, it becomes possible
to enable temporal resolution of an image every 3–5 days, and therefore, to develop next generation agriculture
products at higher spatial resolution (30 m). Various indices are used for assessing vegetation and soil properties
in satellite remote sensing applications. Some indices, such as NDVI and NDWI, are defined based on the
sensitivity and significance of specific bands. a novel dataset based on Sentinel-2 satellite images covering 13
spectral bands and consisting out of 10 classes with in total 27,000 labeled and geo-referenced images have been
used for classification. We demonstrate how this classification system can be used for detecting land use and
land cover changes and how it can assist in improving geographical maps. |
|
Faire une suggestion Affiner la recherche
Big Data Technologies for processing and interpreting spatial data. / Abdessamad ABOUZAID
