Adopting deep learning methods for airborne RGB fluvial scene classification

Rivers are among the world’s most threatened ecosystems. Enabled by the rapid development of drone technology, hyperspatial resolution (5 billion pixels were labelled and partitioned for the tasks of training (1 billion pixels) and validation (4 billion pixels). We develop a novel supervised learnin...

Full description

Bibliographic Details

Main Authors:	Patrice Carbonneau, Stephen Dugdale, Toby Breckon, James Dietrich, Mark Fonstad, Hitoshi Miyamoto, Amy Woodget
Format:	Default Article
Published:	2020
Subjects:	Land cover classification Fluvial remote sensing Deep learning Airborne imagery
Online Access:	https://hdl.handle.net/2134/12967187.v1
Tags:	Add Tag No Tags, Be the first to tag this record!