Satimnet: Structured and harmonised training data for enhanced satellite imagery classification

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

Satimnet: Structured and harmonised training data for enhanced satellite imagery classification

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Satimnet: Structured and harmonised training data for enhanced satellite imagery classification

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20705 - Remote sensing

Projekt

—

Návaznosti

V - Vyzkumna aktivita podporovana z jinych verejnych zdroju

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Remote sensing

ISSN

2072-4292

e-ISSN

—

Svazek periodika

12

Číslo periodika v rámci svazku

20

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

22

Strana od-do

1-22

Kód UT WoS článku

000583019900001

EID výsledku v databázi Scopus

2-s2.0-85092915468