Deepcloud - A fully convolutionnal neural network for cloud and shadow masking in optical satellite images

Matthieu Molinier; Niko Reunanen; Arttu Lämsä; Heikki Astola; Tomi Räty

doi:10.1109/IGARSS.2018.8517484

Deepcloud - A fully convolutionnal neural network for cloud and shadow masking in optical satellite images

Matthieu Molinier
, Niko Reunanen
, Arttu Lämsä
, Heikki Astola
, Tomi Räty

Ei julkaistu Aalto-yliopiston affiliaatiolla

VTT Technical Research Centre of Finland Ltd.

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference article in proceedings › Scientific › vertaisarvioitu

4 Sitaatiot (Scopus)

Abstrakti

Many cloud and shadow detection methods have been proposed already, but improvements can be made on accuracy or automation. In this study, we propose a Fully Convolutional Network model for the detection of clouds and shadows in optical satellite images. The proposed model was trained on 165 Landsat images in Finland, and tested on an independent set of images. The cloud and shadow detection accuracy reached 95%, outperforming both quantitatively and qualitatively a selection of other deep learning architectures.

Alkuperäiskieli	Englanti
Otsikko	2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings
Kustantaja	IEEE
Sivut	2107-2110
Sivumäärä	4
ISBN (elektroninen)	9781538671504
DOI - pysyväislinkit	https://doi.org/10.1109/IGARSS.2018.8517484
Tila	Julkaistu - 31 lokak. 2018
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	IEEE International Geoscience and Remote Sensing Symposium - Valencia, Espanja Kesto: 22 heinäk. 2018 → 27 heinäk. 2018 Konferenssinumero: 38 https://www.igarss2018.org/

Conference

Conference	IEEE International Geoscience and Remote Sensing Symposium
Lyhennettä	IGARSS
Maa/Alue	Espanja
Kaupunki	Valencia
Ajanjakso	22/07/2018 → 27/07/2018
www-osoite	https://www.igarss2018.org/

Rahoitus

This study was carried out in the project DeepCloud funded by VTT Technical Research Centre of Finland Ltd, and Mega-Mart2 funded by the Electronic Component Systems for European Leadership (ECSEL) Joint Undertaking (grant agreement No. 737494) of the Horizon 2020 European Union funding programme. The authors would like to thank Dr Tuomo Tuikka for his support in the VTT DeepCloud project.

Pääsy asiakirjaan

10.1109/IGARSS.2018.8517484

Siteeraa tätä

@inproceedings{7f6ad3972a35429e83599791e7c3f7cf,

title = "Deepcloud - A fully convolutionnal neural network for cloud and shadow masking in optical satellite images",

abstract = "Many cloud and shadow detection methods have been proposed already, but improvements can be made on accuracy or automation. In this study, we propose a Fully Convolutional Network model for the detection of clouds and shadows in optical satellite images. The proposed model was trained on 165 Landsat images in Finland, and tested on an independent set of images. The cloud and shadow detection accuracy reached 95\%, outperforming both quantitatively and qualitatively a selection of other deep learning architectures.",

keywords = "Cloud and shadow masking, Deep learning, Fully convolutional network, Landsat, Optical images",

author = "Matthieu Molinier and Niko Reunanen and Arttu L{\"a}ms{\"a} and Heikki Astola and Tomi R{\"a}ty",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE; IEEE International Geoscience and Remote Sensing Symposium , IGARSS ; Conference date: 22-07-2018 Through 27-07-2018",

year = "2018",

month = oct,

day = "31",

doi = "10.1109/IGARSS.2018.8517484",

language = "English",

pages = "2107--2110",

booktitle = "2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings",

publisher = "IEEE",

address = "United States",

url = "https://www.igarss2018.org/",

}

Molinier, M, Reunanen, N, Lämsä, A, Astola, H & Räty, T 2018, Deepcloud - A fully convolutionnal neural network for cloud and shadow masking in optical satellite images. julkaisussa 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings., 8517484, IEEE, Sivut 2107-2110, IEEE International Geoscience and Remote Sensing Symposium , Valencia, Espanja, 22/07/2018. https://doi.org/10.1109/IGARSS.2018.8517484

Deepcloud - A fully convolutionnal neural network for cloud and shadow masking in optical satellite images. / Molinier, Matthieu; Reunanen, Niko; Lämsä, Arttu et al.
2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings. IEEE, 2018. s. 2107-2110 8517484.

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference article in proceedings › Scientific › vertaisarvioitu

TY - GEN

T1 - Deepcloud - A fully convolutionnal neural network for cloud and shadow masking in optical satellite images

AU - Molinier, Matthieu

AU - Reunanen, Niko

AU - Lämsä, Arttu

AU - Astola, Heikki

AU - Räty, Tomi

N1 - Conference code: 38

PY - 2018/10/31

Y1 - 2018/10/31

N2 - Many cloud and shadow detection methods have been proposed already, but improvements can be made on accuracy or automation. In this study, we propose a Fully Convolutional Network model for the detection of clouds and shadows in optical satellite images. The proposed model was trained on 165 Landsat images in Finland, and tested on an independent set of images. The cloud and shadow detection accuracy reached 95%, outperforming both quantitatively and qualitatively a selection of other deep learning architectures.

AB - Many cloud and shadow detection methods have been proposed already, but improvements can be made on accuracy or automation. In this study, we propose a Fully Convolutional Network model for the detection of clouds and shadows in optical satellite images. The proposed model was trained on 165 Landsat images in Finland, and tested on an independent set of images. The cloud and shadow detection accuracy reached 95%, outperforming both quantitatively and qualitatively a selection of other deep learning architectures.

KW - Cloud and shadow masking

KW - Deep learning

KW - Fully convolutional network

KW - Landsat

KW - Optical images

U2 - 10.1109/IGARSS.2018.8517484

DO - 10.1109/IGARSS.2018.8517484

M3 - Conference article in proceedings

AN - SCOPUS:85063150877

SP - 2107

EP - 2110

BT - 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings

PB - IEEE

T2 - IEEE International Geoscience and Remote Sensing Symposium

Y2 - 22 July 2018 through 27 July 2018

ER -

Deepcloud - A fully convolutionnal neural network for cloud and shadow masking in optical satellite images

Abstrakti

Conference

Rahoitus

Pääsy asiakirjaan

Sormenjälki

Siteeraa tätä