Change Detection in High Resolution Satellite Images Using an Ensemble of Convolutional Neural Networks

Kyungsun Lim, Dongkwon Jin, Chang-Su Kim

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

1 Citation (Scopus)

Abstract

In this paper, we propose a novel change detection algorithm for high resolution satellite images using convolutional neural networks (CNNs), which does not require any preprocessing, such as ortho-rectification and classification. When analyzing multi-temporal satellite images, it is crucial to distinguish viewpoint or color variations of an identical object from actual changes. Especially in urban areas, the registration difficulty due to high-rise buildings makes conventional change detection techniques unreliable, if they are not combined with preprocessing schemes using digital surface models or multi-spectral information. We design three encoder-decoder-structured CNNs, which yield change maps from an input pair of RGB satellite images. For the supervised learning of these CNNs, we construct a large fully-labeled dataset using Google Earth images taken in different years and seasons. Experimental results demonstrate that the trained CNNs detect actual changes successfully, even though image pairs are neither perfectly registered nor color-corrected. Furthermore, an ensemble of the three CNNs provides excellent performance, outperforming each individual CNN.

Original languageEnglish
Title of host publication2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages509-515
Number of pages7
ISBN (Electronic)9789881476852
DOIs
Publication statusPublished - 2019 Mar 4
Event10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Honolulu, United States
Duration: 2018 Nov 122018 Nov 15

Publication series

Name2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

Conference

Conference10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018
CountryUnited States
CityHonolulu
Period18/11/1218/11/15

Fingerprint

Satellites
Neural networks
Color
Supervised learning
Earth (planet)

ASJC Scopus subject areas

  • Information Systems

Cite this

Lim, K., Jin, D., & Kim, C-S. (2019). Change Detection in High Resolution Satellite Images Using an Ensemble of Convolutional Neural Networks. In 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings (pp. 509-515). [8659603] (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/APSIPA.2018.8659603

Change Detection in High Resolution Satellite Images Using an Ensemble of Convolutional Neural Networks. / Lim, Kyungsun; Jin, Dongkwon; Kim, Chang-Su.

2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 509-515 8659603 (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings).

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

Lim, K, Jin, D & Kim, C-S 2019, Change Detection in High Resolution Satellite Images Using an Ensemble of Convolutional Neural Networks. in 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings., 8659603, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 509-515, 10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018, Honolulu, United States, 18/11/12. https://doi.org/10.23919/APSIPA.2018.8659603
Lim K, Jin D, Kim C-S. Change Detection in High Resolution Satellite Images Using an Ensemble of Convolutional Neural Networks. In 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 509-515. 8659603. (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings). https://doi.org/10.23919/APSIPA.2018.8659603
Lim, Kyungsun ; Jin, Dongkwon ; Kim, Chang-Su. / Change Detection in High Resolution Satellite Images Using an Ensemble of Convolutional Neural Networks. 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 509-515 (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings).
@inproceedings{19c8b2729f214a9e9a5b09ba014d90f3,
title = "Change Detection in High Resolution Satellite Images Using an Ensemble of Convolutional Neural Networks",
abstract = "In this paper, we propose a novel change detection algorithm for high resolution satellite images using convolutional neural networks (CNNs), which does not require any preprocessing, such as ortho-rectification and classification. When analyzing multi-temporal satellite images, it is crucial to distinguish viewpoint or color variations of an identical object from actual changes. Especially in urban areas, the registration difficulty due to high-rise buildings makes conventional change detection techniques unreliable, if they are not combined with preprocessing schemes using digital surface models or multi-spectral information. We design three encoder-decoder-structured CNNs, which yield change maps from an input pair of RGB satellite images. For the supervised learning of these CNNs, we construct a large fully-labeled dataset using Google Earth images taken in different years and seasons. Experimental results demonstrate that the trained CNNs detect actual changes successfully, even though image pairs are neither perfectly registered nor color-corrected. Furthermore, an ensemble of the three CNNs provides excellent performance, outperforming each individual CNN.",
author = "Kyungsun Lim and Dongkwon Jin and Chang-Su Kim",
year = "2019",
month = "3",
day = "4",
doi = "10.23919/APSIPA.2018.8659603",
language = "English",
series = "2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "509--515",
booktitle = "2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings",

}

TY - GEN

T1 - Change Detection in High Resolution Satellite Images Using an Ensemble of Convolutional Neural Networks

AU - Lim, Kyungsun

AU - Jin, Dongkwon

AU - Kim, Chang-Su

PY - 2019/3/4

Y1 - 2019/3/4

N2 - In this paper, we propose a novel change detection algorithm for high resolution satellite images using convolutional neural networks (CNNs), which does not require any preprocessing, such as ortho-rectification and classification. When analyzing multi-temporal satellite images, it is crucial to distinguish viewpoint or color variations of an identical object from actual changes. Especially in urban areas, the registration difficulty due to high-rise buildings makes conventional change detection techniques unreliable, if they are not combined with preprocessing schemes using digital surface models or multi-spectral information. We design three encoder-decoder-structured CNNs, which yield change maps from an input pair of RGB satellite images. For the supervised learning of these CNNs, we construct a large fully-labeled dataset using Google Earth images taken in different years and seasons. Experimental results demonstrate that the trained CNNs detect actual changes successfully, even though image pairs are neither perfectly registered nor color-corrected. Furthermore, an ensemble of the three CNNs provides excellent performance, outperforming each individual CNN.

AB - In this paper, we propose a novel change detection algorithm for high resolution satellite images using convolutional neural networks (CNNs), which does not require any preprocessing, such as ortho-rectification and classification. When analyzing multi-temporal satellite images, it is crucial to distinguish viewpoint or color variations of an identical object from actual changes. Especially in urban areas, the registration difficulty due to high-rise buildings makes conventional change detection techniques unreliable, if they are not combined with preprocessing schemes using digital surface models or multi-spectral information. We design three encoder-decoder-structured CNNs, which yield change maps from an input pair of RGB satellite images. For the supervised learning of these CNNs, we construct a large fully-labeled dataset using Google Earth images taken in different years and seasons. Experimental results demonstrate that the trained CNNs detect actual changes successfully, even though image pairs are neither perfectly registered nor color-corrected. Furthermore, an ensemble of the three CNNs provides excellent performance, outperforming each individual CNN.

UR - http://www.scopus.com/inward/record.url?scp=85063456307&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063456307&partnerID=8YFLogxK

U2 - 10.23919/APSIPA.2018.8659603

DO - 10.23919/APSIPA.2018.8659603

M3 - Conference contribution

AN - SCOPUS:85063456307

T3 - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

SP - 509

EP - 515

BT - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -