Skip to Content
No preview available

Actions

Download Analytics Citations

Export to: EndNote  |  Zotero  |  Mendeley

Collections

This file is not currently in any collections.

Global Scale Attention-based Deep Learning for river landscape classification [dataset] Open Access

This dataset is composed of a series of images and manually labelled masks. The goal is to train and test semantic classification models for riverine landscapes. In the masks, class 1 is rivers, class 2 is lakes and class 3 is sediment bars. All files are in geotif format and will open directly in any geospatial software package (QGIS, ArcGIS, etc..).

Descriptions

Resource type
Dataset
Contributors
Creator: Carbonneau, Patrice 1
1 Durham University, UK
Funder
Research methods
Semantic Image classification with Deep Learning
Other description
The main zip file contains 3 archives: SeenTrainingTiles.xz which incudes 610 pairs of images and masks and is intended to provide training and validation data. SeenTestingTiles.xz has 67 pairs iof images and masks drawn from the same geographical locations as the above training tiles. It is intended as a preliminary test dataset. UnseenTestTiles.xz has an additional 100 pairs of images and masks and is intented as an independent testing set never seen in the training stages of the model. Each tile covers 0.15 x 0.15 degrees in area. The imagery is taken from the Sentinel-2 satellite and has 3 channels of NIR (band 8), Red (band 4) and green (band 3)
Keyword
Attention mechanism
Unet
Riverine landscapes
Subject
Geography
Location
Language
Cited in
Identifier
ark:/32150/r36682x393c
doi:10.15128/r36682x393c
Rights
Creative Commons Attribution 4.0 International (CC BY)

Publisher
Durham University
Date Created

File Details

Depositor
P. Carbonneau
Date Uploaded
Date Modified
17 September 2024, 14:09:08
Audit Status
Audits have not yet been run on this file.
Characterization
not yet characterized
Activity of users you follow
User Activity Date
User N. Syrotiuk has updated Global Scale Attention-based Deep Learning for river landscape classification [dataset] 22 days ago