Satimnet: Structured and harmonised training data for enhanced satellite imagery classification
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21110%2F20%3A00346121" target="_blank" >RIV/68407700:21110/20:00346121 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.3390/rs12203358" target="_blank" >https://doi.org/10.3390/rs12203358</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.3390/rs12203358" target="_blank" >10.3390/rs12203358</a>
Alternative languages
Result language
angličtina
Original language name
Satimnet: Structured and harmonised training data for enhanced satellite imagery classification
Original language description
Automatic supervised classification with complex modelling such as deep neural networks requires the availability of representative training data sets. While there exists a plethora of data sets that can be used for this purpose, they are usually very heterogeneous and not interoperable. In this context, the present work has a twofold objective: (i) to describe procedures of open-source training data management, integration, and data retrieval, and (ii) to demonstrate the practical use of varying source training data for remote sensing image classification. For the former, we propose SatImNet, a collection of open training data, structured and harmonized according to specific rules. For the latter, two modelling approaches based on convolutional neural networks have been designed and configured to deal with satellite image classification and segmentation.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
20705 - Remote sensing
Result continuities
Project
—
Continuities
V - Vyzkumna aktivita podporovana z jinych verejnych zdroju
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Remote sensing
ISSN
2072-4292
e-ISSN
—
Volume of the periodical
12
Issue of the periodical within the volume
20
Country of publishing house
CH - SWITZERLAND
Number of pages
22
Pages from-to
1-22
UT code for WoS article
000583019900001
EID of the result in the Scopus database
2-s2.0-85092915468