TY - GEN
T1 - Change detection of SAR images based on supervised contractive autoencoders and fuzzy clustering
AU - Geng, Jie
AU - Wang, Hongyu
AU - Fan, Jianchao
AU - Ma, Xiaorui
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/6/23
Y1 - 2017/6/23
N2 - In this paper, supervised contractive autoencoders (SCAEs) combined with fuzzy c-means (FCM) clustering are developed for change detection of synthetic aperture radar (SAR) images, which aim to take advantage of deep neural networks to capture changed features. Given two original SAR images, Lee filter is used in preprocessing and the difference image (DI) is obtained by log ratio method. Then, FCM is adopted to analyse DI, which yields pseudo labels for guiding the training of SCAEs. Finally, SCAEs are developed to learn changed features from bitemporal images and DI, which can obtain discriminative features and improve detection accuracies. Experiments on three data demonstrate that the proposed method outperforms some related approaches.
AB - In this paper, supervised contractive autoencoders (SCAEs) combined with fuzzy c-means (FCM) clustering are developed for change detection of synthetic aperture radar (SAR) images, which aim to take advantage of deep neural networks to capture changed features. Given two original SAR images, Lee filter is used in preprocessing and the difference image (DI) is obtained by log ratio method. Then, FCM is adopted to analyse DI, which yields pseudo labels for guiding the training of SCAEs. Finally, SCAEs are developed to learn changed features from bitemporal images and DI, which can obtain discriminative features and improve detection accuracies. Experiments on three data demonstrate that the proposed method outperforms some related approaches.
KW - autoencoder
KW - Change detection
KW - deep neural network
KW - synthetic aperture radar (SAR) image
UR - http://www.scopus.com/inward/record.url?scp=85025695841&partnerID=8YFLogxK
U2 - 10.1109/RSIP.2017.7958819
DO - 10.1109/RSIP.2017.7958819
M3 - 会议稿件
AN - SCOPUS:85025695841
T3 - RSIP 2017 - International Workshop on Remote Sensing with Intelligent Processing, Proceedings
BT - RSIP 2017 - International Workshop on Remote Sensing with Intelligent Processing, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 International Workshop on Remote Sensing with Intelligent Processing, RSIP 2017
Y2 - 19 May 2017 through 21 May 2017
ER -