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
N1 - Funding Information:
Technology Research Center) support program(IITP-2018-2016-0-00464) supervised by the IITP(Institute for Information & communications TechnologyPromotion) and in part by the Agency for Defense Development (ADD) and Defense Acquisition Program Administration (DAPA) of Korea (UC160016FD)
Funding Information:
This work was supported in part by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information
Publisher Copyright:
© 2018 APSIPA organization.
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
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.
T2 - 10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018
Y2 - 12 November 2018 through 15 November 2018
ER -