A Deep Network Approach to Multitemporal Cloud Detection

Devis Tuia; Benjamin Kellenberger; Adrian Perez-suey; Gustau Camps-valls

doi:10.1109/IGARSS.2018.8517312

A Deep Network Approach to Multitemporal Cloud Detection

Devis Tuia, Benjamin Kellenberger, Adrian Perez-suey, Gustau Camps-valls

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › Academic › peer-review

12 Citations (Scopus)

Abstract

We present a deep learning model with temporal memory to detect clouds in image time series acquired by the Seviri imager mounted on the Meteosat Second Generation (MSG) satellite. The model provides pixel-level cloud maps with related confidence and propagates information in time via a recurrent neural network structure. With a single model, we are able to outline clouds along all year and during day and night with high accuracy.

Original language	English
Title of host publication	2018 IEEE International Geoscience & Remote Sensing Symposium Proceedings
Subtitle of host publication	Observing, Understanding And Forecasting The Dynamics Of Our Planet
Publisher	IEEE
Pages	4351-4354
ISBN (Electronic)	9781538671504, 9781538671498
ISBN (Print)	9781538671511
DOIs	https://doi.org/10.1109/IGARSS.2018.8517312
Publication status	Published - 5 Nov 2018
Event	IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain Duration: 22 Jul 2018 → 27 Jul 2018

Conference/symposium

Conference/symposium	IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium
Country/Territory	Spain
City	Valencia
Period	22/07/18 → 27/07/18

Keywords

Cloud detection
Convolutional neural networks
Deep learning
Recurrent neural networks
Seviri

Access to Document

10.1109/IGARSS.2018.8517312

http://isp.uv.es/papers/Tuia18igarss.pdf

Cite this

@inproceedings{a9917052715b43fa8dbdb56f0c38dc2d,

title = "A Deep Network Approach to Multitemporal Cloud Detection",

abstract = "We present a deep learning model with temporal memory to detect clouds in image time series acquired by the Seviri imager mounted on the Meteosat Second Generation (MSG) satellite. The model provides pixel-level cloud maps with related confidence and propagates information in time via a recurrent neural network structure. With a single model, we are able to outline clouds along all year and during day and night with high accuracy.",

keywords = "Cloud detection, Convolutional neural networks, Deep learning, Recurrent neural networks, Seviri",

author = "Devis Tuia and Benjamin Kellenberger and Adrian Perez-suey and Gustau Camps-valls",

year = "2018",

month = nov,

day = "5",

doi = "10.1109/IGARSS.2018.8517312",

language = "English",

isbn = "9781538671511",

pages = "4351--4354",

booktitle = "2018 IEEE International Geoscience \& Remote Sensing Symposium Proceedings",

publisher = "IEEE",

address = "United States",

note = "IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium ; Conference date: 22-07-2018 Through 27-07-2018",

}

Tuia, D, Kellenberger, B, Perez-suey, A & Camps-valls, G 2018, A Deep Network Approach to Multitemporal Cloud Detection. in 2018 IEEE International Geoscience & Remote Sensing Symposium Proceedings: Observing, Understanding And Forecasting The Dynamics Of Our Planet. IEEE, pp. 4351-4354, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain, 22/07/18. https://doi.org/10.1109/IGARSS.2018.8517312

A Deep Network Approach to Multitemporal Cloud Detection. / Tuia, Devis; Kellenberger, Benjamin; Perez-suey, Adrian et al.
2018 IEEE International Geoscience & Remote Sensing Symposium Proceedings: Observing, Understanding And Forecasting The Dynamics Of Our Planet. IEEE, 2018. p. 4351-4354.

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › Academic › peer-review

TY - GEN

T1 - A Deep Network Approach to Multitemporal Cloud Detection

AU - Tuia, Devis

AU - Kellenberger, Benjamin

AU - Perez-suey, Adrian

AU - Camps-valls, Gustau

PY - 2018/11/5

Y1 - 2018/11/5

N2 - We present a deep learning model with temporal memory to detect clouds in image time series acquired by the Seviri imager mounted on the Meteosat Second Generation (MSG) satellite. The model provides pixel-level cloud maps with related confidence and propagates information in time via a recurrent neural network structure. With a single model, we are able to outline clouds along all year and during day and night with high accuracy.

AB - We present a deep learning model with temporal memory to detect clouds in image time series acquired by the Seviri imager mounted on the Meteosat Second Generation (MSG) satellite. The model provides pixel-level cloud maps with related confidence and propagates information in time via a recurrent neural network structure. With a single model, we are able to outline clouds along all year and during day and night with high accuracy.

KW - Cloud detection

KW - Convolutional neural networks

KW - Deep learning

KW - Recurrent neural networks

KW - Seviri

U2 - 10.1109/IGARSS.2018.8517312

DO - 10.1109/IGARSS.2018.8517312

M3 - Conference paper

SN - 9781538671511

SP - 4351

EP - 4354

BT - 2018 IEEE International Geoscience & Remote Sensing Symposium Proceedings

PB - IEEE

T2 - IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium

Y2 - 22 July 2018 through 27 July 2018

ER -

A Deep Network Approach to Multitemporal Cloud Detection

Abstract

Conference/symposium

Keywords

Access to Document

Fingerprint

Cite this