Flood Detection On Low Cost Orbital Hardware

Gonzalo Mateo-Garcia; Silviu Oprea; Lewis Smith; Josh Veitch-Michaelis; Guy Schumann; Yarin Gal; Atılım Güneş Baydin; Dietmar Backes

Flood Detection On Low Cost Orbital Hardware

Gonzalo Mateo-Garcia, Silviu Oprea, Lewis Smith, Josh Veitch-Michaelis, Guy Schumann, Yarin Gal, Atılım Güneş Baydin, Dietmar Backes

Data Science CDT

Research output: Contribution to conference › Paper › peer-review

Abstract

Satellite imaging is a critical technology for monitoring and responding to natural disasters such as flooding. Despite the capabilities of modern satellites, there is still much to be desired from the perspective of first response organisations like UNICEF. Two main challenges are rapid access to data, and the ability to automatically identify flooded regions in images. We describe a prototypical flood segmentation system, identifying cloud, water and land, that could be deployed on a constellation of small satellites, performing processing on board to reduce downlink bandwidth by 2 orders of magnitude. We target ΦSat-1, part of the FSSCAT mission, which is planned to be launched by the European Space Agency (ESA) near the start of 2020 as a proof of concept for this new technology.

Original language	English
Number of pages	6
Publication status	Published - 13 Dec 2019
Event	Artificial Intelligence for Humanitarian Assistance and Disaster Response Workshop @ NeurIPS 2019 - Vancouver, Canada Duration: 13 Dec 2019 → 13 Dec 2019 https://www.hadr.ai/previous-years/2019/home-2019

Conference

Conference	Artificial Intelligence for Humanitarian Assistance and Disaster Response Workshop @ NeurIPS 2019
Abbreviated title	AI + HADR 2019
Country/Territory	Canada
City	Vancouver
Period	13/12/19 → 13/12/19
Internet address	https://www.hadr.ai/previous-years/2019/home-2019

Access to Document

Flood Detection_MATEO-GARCIA_DOA13122019_AFVAccepted author manuscript, 2.94 MBLicence: All Rights Reserved

Cite this

@conference{b746a7d7729c4600bc55aed084ea14a0,

title = "Flood Detection On Low Cost Orbital Hardware",

abstract = "Satellite imaging is a critical technology for monitoring and responding to natural disasters such as flooding. Despite the capabilities of modern satellites, there is still much to be desired from the perspective of first response organisations like UNICEF. Two main challenges are rapid access to data, and the ability to automatically identify flooded regions in images. We describe a prototypical flood segmentation system, identifying cloud, water and land, that could be deployed on a constellation of small satellites, performing processing on board to reduce downlink bandwidth by 2 orders of magnitude. We target ΦSat-1, part of the FSSCAT mission, which is planned to be launched by the European Space Agency (ESA) near the start of 2020 as a proof of concept for this new technology.",

author = "Gonzalo Mateo-Garcia and Silviu Oprea and Lewis Smith and Josh Veitch-Michaelis and Guy Schumann and Yarin Gal and Baydin, {Atılım G{\"u}ne{\c s}} and Dietmar Backes",

year = "2019",

month = dec,

day = "13",

language = "English",

note = "Artificial Intelligence for Humanitarian Assistance and Disaster Response Workshop @ NeurIPS 2019, AI + HADR 2019 ; Conference date: 13-12-2019 Through 13-12-2019",

url = "https://www.hadr.ai/previous-years/2019/home-2019",

}

TY - CONF

T1 - Flood Detection On Low Cost Orbital Hardware

AU - Mateo-Garcia, Gonzalo

AU - Oprea, Silviu

AU - Smith, Lewis

AU - Veitch-Michaelis, Josh

AU - Schumann, Guy

AU - Gal, Yarin

AU - Baydin, Atılım Güneş

AU - Backes, Dietmar

PY - 2019/12/13

Y1 - 2019/12/13

N2 - Satellite imaging is a critical technology for monitoring and responding to natural disasters such as flooding. Despite the capabilities of modern satellites, there is still much to be desired from the perspective of first response organisations like UNICEF. Two main challenges are rapid access to data, and the ability to automatically identify flooded regions in images. We describe a prototypical flood segmentation system, identifying cloud, water and land, that could be deployed on a constellation of small satellites, performing processing on board to reduce downlink bandwidth by 2 orders of magnitude. We target ΦSat-1, part of the FSSCAT mission, which is planned to be launched by the European Space Agency (ESA) near the start of 2020 as a proof of concept for this new technology.

AB - Satellite imaging is a critical technology for monitoring and responding to natural disasters such as flooding. Despite the capabilities of modern satellites, there is still much to be desired from the perspective of first response organisations like UNICEF. Two main challenges are rapid access to data, and the ability to automatically identify flooded regions in images. We describe a prototypical flood segmentation system, identifying cloud, water and land, that could be deployed on a constellation of small satellites, performing processing on board to reduce downlink bandwidth by 2 orders of magnitude. We target ΦSat-1, part of the FSSCAT mission, which is planned to be launched by the European Space Agency (ESA) near the start of 2020 as a proof of concept for this new technology.

M3 - Paper

T2 - Artificial Intelligence for Humanitarian Assistance and Disaster Response Workshop @ NeurIPS 2019

Y2 - 13 December 2019 through 13 December 2019

ER -

Flood Detection On Low Cost Orbital Hardware

Abstract

Conference

Access to Document

Fingerprint

Cite this