Analysis of satellite images for disaster detection

Siti Nor Khuzaimah Binti Amit, Soma Shiraishi, Tetsuo Inoshita, Yoshimitsu Aoki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Analysis of satellite images plays an increasingly vital role in environment and climate monitoring, especially in detecting and managing natural disaster. In this paper, we proposed an automatic disaster detection system by implementing one of the advance deep learning techniques, convolutional neural network (CNN), to analysis satellite images. The neural network consists of 3 convolutional layers, followed by max-pooling layers after each convolutional layer, and 2 fully connected layers. We created our own disaster detection training data patches, which is currently focusing on 2 main disasters in Japan and Thailand: landslide and flood. Each disaster's training data set consists of 30000∼40000 patches and all patches are trained automatically in CNN to extract region where disaster occurred instantaneously. The results reveal accuracy of 80%∼90% for both disaster detection. The results presented here may facilitate improvements in detecting natural disaster efficiently by establishing automatic disaster detection system.

Original languageEnglish
Title of host publication2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5189-5192
Number of pages4
Volume2016-November
ISBN (Electronic)9781509033324
DOIs
Publication statusPublished - 2016 Nov 1
Event36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Beijing, China
Duration: 2016 Jul 102016 Jul 15

Other

Other36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016
CountryChina
CityBeijing
Period16/7/1016/7/15

Fingerprint

Disasters
disaster
Satellites
natural disaster
Neural networks
satellite image
detection
analysis
Landslides
landslide
learning
climate
monitoring
Monitoring

Keywords

  • convolutional neural network
  • difference extraction
  • disaster detection
  • satellite images

ASJC Scopus subject areas

  • Computer Science Applications
  • Earth and Planetary Sciences(all)

Cite this

Amit, S. N. K. B., Shiraishi, S., Inoshita, T., & Aoki, Y. (2016). Analysis of satellite images for disaster detection. In 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings (Vol. 2016-November, pp. 5189-5192). [7730352] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2016.7730352

Analysis of satellite images for disaster detection. / Amit, Siti Nor Khuzaimah Binti; Shiraishi, Soma; Inoshita, Tetsuo; Aoki, Yoshimitsu.

2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Vol. 2016-November Institute of Electrical and Electronics Engineers Inc., 2016. p. 5189-5192 7730352.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Amit, SNKB, Shiraishi, S, Inoshita, T & Aoki, Y 2016, Analysis of satellite images for disaster detection. in 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. vol. 2016-November, 7730352, Institute of Electrical and Electronics Engineers Inc., pp. 5189-5192, 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016, Beijing, China, 16/7/10. https://doi.org/10.1109/IGARSS.2016.7730352
Amit SNKB, Shiraishi S, Inoshita T, Aoki Y. Analysis of satellite images for disaster detection. In 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Vol. 2016-November. Institute of Electrical and Electronics Engineers Inc. 2016. p. 5189-5192. 7730352 https://doi.org/10.1109/IGARSS.2016.7730352
Amit, Siti Nor Khuzaimah Binti ; Shiraishi, Soma ; Inoshita, Tetsuo ; Aoki, Yoshimitsu. / Analysis of satellite images for disaster detection. 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Vol. 2016-November Institute of Electrical and Electronics Engineers Inc., 2016. pp. 5189-5192
@inproceedings{bf53e110bbb34ff488d4533e01ff1ef7,
title = "Analysis of satellite images for disaster detection",
abstract = "Analysis of satellite images plays an increasingly vital role in environment and climate monitoring, especially in detecting and managing natural disaster. In this paper, we proposed an automatic disaster detection system by implementing one of the advance deep learning techniques, convolutional neural network (CNN), to analysis satellite images. The neural network consists of 3 convolutional layers, followed by max-pooling layers after each convolutional layer, and 2 fully connected layers. We created our own disaster detection training data patches, which is currently focusing on 2 main disasters in Japan and Thailand: landslide and flood. Each disaster's training data set consists of 30000∼40000 patches and all patches are trained automatically in CNN to extract region where disaster occurred instantaneously. The results reveal accuracy of 80{\%}∼90{\%} for both disaster detection. The results presented here may facilitate improvements in detecting natural disaster efficiently by establishing automatic disaster detection system.",
keywords = "convolutional neural network, difference extraction, disaster detection, satellite images",
author = "Amit, {Siti Nor Khuzaimah Binti} and Soma Shiraishi and Tetsuo Inoshita and Yoshimitsu Aoki",
year = "2016",
month = "11",
day = "1",
doi = "10.1109/IGARSS.2016.7730352",
language = "English",
volume = "2016-November",
pages = "5189--5192",
booktitle = "2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Analysis of satellite images for disaster detection

AU - Amit, Siti Nor Khuzaimah Binti

AU - Shiraishi, Soma

AU - Inoshita, Tetsuo

AU - Aoki, Yoshimitsu

PY - 2016/11/1

Y1 - 2016/11/1

N2 - Analysis of satellite images plays an increasingly vital role in environment and climate monitoring, especially in detecting and managing natural disaster. In this paper, we proposed an automatic disaster detection system by implementing one of the advance deep learning techniques, convolutional neural network (CNN), to analysis satellite images. The neural network consists of 3 convolutional layers, followed by max-pooling layers after each convolutional layer, and 2 fully connected layers. We created our own disaster detection training data patches, which is currently focusing on 2 main disasters in Japan and Thailand: landslide and flood. Each disaster's training data set consists of 30000∼40000 patches and all patches are trained automatically in CNN to extract region where disaster occurred instantaneously. The results reveal accuracy of 80%∼90% for both disaster detection. The results presented here may facilitate improvements in detecting natural disaster efficiently by establishing automatic disaster detection system.

AB - Analysis of satellite images plays an increasingly vital role in environment and climate monitoring, especially in detecting and managing natural disaster. In this paper, we proposed an automatic disaster detection system by implementing one of the advance deep learning techniques, convolutional neural network (CNN), to analysis satellite images. The neural network consists of 3 convolutional layers, followed by max-pooling layers after each convolutional layer, and 2 fully connected layers. We created our own disaster detection training data patches, which is currently focusing on 2 main disasters in Japan and Thailand: landslide and flood. Each disaster's training data set consists of 30000∼40000 patches and all patches are trained automatically in CNN to extract region where disaster occurred instantaneously. The results reveal accuracy of 80%∼90% for both disaster detection. The results presented here may facilitate improvements in detecting natural disaster efficiently by establishing automatic disaster detection system.

KW - convolutional neural network

KW - difference extraction

KW - disaster detection

KW - satellite images

UR - http://www.scopus.com/inward/record.url?scp=85007489161&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85007489161&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2016.7730352

DO - 10.1109/IGARSS.2016.7730352

M3 - Conference contribution

VL - 2016-November

SP - 5189

EP - 5192

BT - 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -