TY - JOUR
T1 - Change detection in unlabeled optical remote sensing data using siamese CNN
AU - Hedjam, Rachid
AU - Abdesselam, Abdelhamid
AU - Melgani, Farid
N1 - Publisher Copyright:
© 2008-2012 IEEE.
PY - 2020
Y1 - 2020
N2 - In this article, we propose a new semisupervised method to detect the changes occurring in a geographical area after a major damage. We detect the changes by processing a pair of optical remote sensing images. The proposed method adopts a patch-based approach, whereby we use a Siamese convolutional neural network (S-CNN), trained with augmented data, to compare successive pairs of patches obtained from the input images. The main contribution of this work lies in developing an S-CNN training phase without resorting to class labels that are actually not available from the input images. We train the S-CNN using genuine and impostor patch-pairs defined in a semisupervised way from the input images. We tested the proposed change detection model on four real datasets and compared its performance to those of two existing models. The obtained results were very promising.
AB - In this article, we propose a new semisupervised method to detect the changes occurring in a geographical area after a major damage. We detect the changes by processing a pair of optical remote sensing images. The proposed method adopts a patch-based approach, whereby we use a Siamese convolutional neural network (S-CNN), trained with augmented data, to compare successive pairs of patches obtained from the input images. The main contribution of this work lies in developing an S-CNN training phase without resorting to class labels that are actually not available from the input images. We train the S-CNN using genuine and impostor patch-pairs defined in a semisupervised way from the input images. We tested the proposed change detection model on four real datasets and compared its performance to those of two existing models. The obtained results were very promising.
KW - Remote sensing change detection (CD)
KW - Siamese convolutional neural network (CNN)
KW - semisupervised CD
UR - http://www.scopus.com/inward/record.url?scp=85090337765&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090337765&partnerID=8YFLogxK
U2 - 10.1109/JSTARS.2020.3009116
DO - 10.1109/JSTARS.2020.3009116
M3 - Article
AN - SCOPUS:85090337765
SN - 1939-1404
VL - 13
SP - 4178
EP - 4187
JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
M1 - 9140297
ER -