Multi-band supervised classification for polarimetric SAR
| Autor: | Alexandre Alakian, Valentine Wasik, Xavier Dupuis, Dominique Dubucq |
|---|---|
| Přispěvatelé: | DEMR, ONERA [Salon], ONERA, DTIS, ONERA, Université Paris Saclay (COmUE) [Palaiseau], ONERA-Université Paris Saclay (COmUE), Total, TOTAL S.A., TOTAL FINA ELF-TOTAL FINA ELF-Scientific Development Division, Catalysis & Process Engineering, TOTAL SA-TOTAL SA, André, Cécile |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Wishart distribution
[PHYS]Physics [physics] Computer science business.industry [SPI] Engineering Sciences [physics] Vegetation classification MULTI BAND 0211 other engineering and technologies Polarimetry Pattern recognition 02 engineering and technology CLASSIFICATION [PHYS] Physics [physics] Polarimetric sar Multi band [SPI]Engineering Sciences [physics] Artificial intelligence business Classifier (UML) 021101 geological & geomatics engineering SAR |
| Zdroj: | IGARSS 2019 IGARSS 2019, Jul 2019, YOKOHAMA, Japan IGARSS |
| Popis: | International audience; This work addresses the potential of multi-band polarimetric SAR imaging for terrains and vegetation classification. A classic supervised Wishart classifier is adapted to polarimetric multi-band datasets, and is applied on the X-, Land UHF-band acquisitions done during the NAOMI campaign (ONERA-Total) in Gabon (Africa) in 2015. The contributions of the different frequencies are shown and discussed. It is shown that the use of the multi-band dataset improves significantly the classification result. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|