Convolutional neural networks for urban green areas semantic segmentation on Sentinel-2 data

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11310%2F24%3A10486258" target="_blank" >RIV/00216208:11310/24:10486258 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21110/24:00376522

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=2KJ7sDz~3g" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=2KJ7sDz~3g</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.rsase.2024.101238" target="_blank" >10.1016/j.rsase.2024.101238</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Convolutional neural networks for urban green areas semantic segmentation on Sentinel-2 data

Popis výsledku v původním jazyce

Urban green areas are essential components of any urban environment, providing a wide range of uses. However, there is currently a noticeable absence of an automated tool for their land use classification. The use of urban green areas depends on their size, shape, and relationship with their surroundings, all of which are fundamental features in convolutional neural networks. Various convolutional neural network architectures (FCN, U -Net, SegNet, DeepLabv3+) were evaluated on open and widely accessible Sentinel-2 data for semantic segmentation of land cover and land use in different levels of urban green areas nomenclature and band combinations. Moreover, we compared the CNNs with random forests model as a baseline to underline the CNNs&apos; strengths. The evaluation found that convolutional neural networks are capable of the land cover and land use semantic segmentation not only on the full-band Sentinel-2 scenes but also on limited subdatasets consisting only of RGB bands. U -Net is identified as the bestperforming architecture, achieving an overall accuracy of almost 95% for a simple binary vegetation detection, 90% for the land -use task, and almost 88% for the land -use task enhanced by a distinction between high and low vegetation, while random forests reached 93%, 84%, and 81%, respectively. CNNs&apos; misclassifications were primarily identified at the edges of two neighbouring competing classes where mixed pixels appear. Data augmentation improved the model&apos;s performance in 94% of cases. However, dropout layers led to an overall accuracy decrease in more than half of the cases. Additionally, we compared the segmented urban green area with a pan -European dataset, the Coordination of Information on the Environment Land Cover - and found that the latter omits 74% of the total urban vegetation. This is mainly due to its minimal mapping unit specification. It is concluded that the most suitable approach for automated urban green areas land cover and land use semantic segmentation is the use of convolutional neural networks, from the tested architectures particularly U -Net.

Název v anglickém jazyce

Convolutional neural networks for urban green areas semantic segmentation on Sentinel-2 data

Popis výsledku anglicky

Urban green areas are essential components of any urban environment, providing a wide range of uses. However, there is currently a noticeable absence of an automated tool for their land use classification. The use of urban green areas depends on their size, shape, and relationship with their surroundings, all of which are fundamental features in convolutional neural networks. Various convolutional neural network architectures (FCN, U -Net, SegNet, DeepLabv3+) were evaluated on open and widely accessible Sentinel-2 data for semantic segmentation of land cover and land use in different levels of urban green areas nomenclature and band combinations. Moreover, we compared the CNNs with random forests model as a baseline to underline the CNNs&apos; strengths. The evaluation found that convolutional neural networks are capable of the land cover and land use semantic segmentation not only on the full-band Sentinel-2 scenes but also on limited subdatasets consisting only of RGB bands. U -Net is identified as the bestperforming architecture, achieving an overall accuracy of almost 95% for a simple binary vegetation detection, 90% for the land -use task, and almost 88% for the land -use task enhanced by a distinction between high and low vegetation, while random forests reached 93%, 84%, and 81%, respectively. CNNs&apos; misclassifications were primarily identified at the edges of two neighbouring competing classes where mixed pixels appear. Data augmentation improved the model&apos;s performance in 94% of cases. However, dropout layers led to an overall accuracy decrease in more than half of the cases. Additionally, we compared the segmented urban green area with a pan -European dataset, the Coordination of Information on the Environment Land Cover - and found that the latter omits 74% of the total urban vegetation. This is mainly due to its minimal mapping unit specification. It is concluded that the most suitable approach for automated urban green areas land cover and land use semantic segmentation is the use of convolutional neural networks, from the tested architectures particularly U -Net.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10508 - Physical geography

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název periodika

Remote Sensing Applications: Society and Environment

ISSN

2352-9385

e-ISSN

2352-9385

Svazek periodika

36

Číslo periodika v rámci svazku

November

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

26

Strana od-do

101238

Kód UT WoS článku

001254375000001

EID výsledku v databázi Scopus

2-s2.0-85195846979