Benutzer: Gast  Login
Titel:

SEN12MS-CR-TS Holdout Test Split

Dokumenttyp:
Forschungsdaten
Veröffentlichungsdatum:
25.05.2022
Verantwortlich:
Zhu, Xiaoxiang
Autorinnen / Autoren:
Ebel, Patrick; Schmitt, Michael; Zhu, Xiaoxiang
Institutionszugehörigkeit:
TUM
Herausgeber:
TUM
Identifikator:
doi:10.14459/2022mp1659251
Enddatum der Datenerzeugung:
01.12.2021
Fachgebiet:
BAU Bauingenieurwesen, Vermessungswesen; DAT Datenverarbeitung, Informatik; GEO Geowissenschaften
Quellen der Daten:
Abbildungen von Objekten / image of objects
Datentyp:
Bilder / images
Methode der Datenerhebung:
Semi-automatic download and image preparation using Google Earth Engine, Python and GDAL, semi-automatic processing and clean-up
Beschreibung:
This is the holdout test split of SEN12MS-CR-TS. You can find the train split under https://mediatum.ub.tum.de/1639953. The SEN12MS-CR-TS dataset contains time series of corresponding Sentinel-1 dual-pol SAR data as well as cloudy and cloud-free Sentinel-2 multi-spectral images. The patches are distributed across the land masses of the Earth, providing a global sample distribution. The time points of the samples are evenly spaced throughout the entire year, covering all meteorological seasons. T...     »
Links:

https://patrickTUM.github.io/cloud_removal/
https://ieeexplore.ieee.org/document/9691348

Schlagworte:
Remote sensing, deep learning, data fusion, synthetic aperture radar imagery, optical imagery, cloud removal, time series data
Technische Hinweise:
View and download (151 GB total, 10 Files)
The data server also offers downloads with FTP
The data server also offers downloads with rsync (password m1659251):
rsync rsync://m1659251@dataserv.ub.tum.de/m1659251/
Sprache:
en
Rechte:
by, http://creativecommons.org/licenses/by/4.0
 BibTeX