Abstract
A neural network approach for semi-automatic detection of oil spills ERS-SAR imagery is presented in this paper. The network input is a vector containing the values of a set of features, previously calculated by using dedicated routines, characterizing the oil spill candidate either from the point of view of its geometry or of its physical behaviour. The algorithm classification performance has been evaluated on a data set containing verified examples of oil spill and look-alike.
Lingua originale | Inglese |
---|---|
Pagine | 215-217 |
Numero di pagine | 3 |
Stato di pubblicazione | Pubblicato - 1999 |
Pubblicato esternamente | Sì |
Evento | Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS'99) 'Remote Sensing of the Systems Earth - A Challenge for the 21st Century' - Hamburg, Ger Durata: 28 giu 1999 → 2 lug 1999 |
???event.eventtypes.event.conference???
???event.eventtypes.event.conference??? | Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS'99) 'Remote Sensing of the Systems Earth - A Challenge for the 21st Century' |
---|---|
Città | Hamburg, Ger |
Periodo | 28/06/99 → 2/07/99 |