TY - JOUR
T1 - The laser-induced damage change detection for optical elements using siamese convolutional neural networks
AU - Kou, Jingwei
AU - Zhan, Tao
AU - Zhou, Deyun
AU - Wang, Wei
AU - Da, Zhengshang
AU - Gong, Maoguo
N1 - Publisher Copyright:
© 2019 Elsevier B.V.
PY - 2020/2
Y1 - 2020/2
N2 - Due to the fact that weak and fake laser-induced damages may occur in the surface of optical elements in high-energy laser facilities, it is still a challenging issue to effectively detect the real laser-induced damage changes of optical elements in optical images. Different from the traditional methods, in this paper, we put forward a similarity metric optimization driven supervised learning model to perform the laser-induced damage change detection task. In the proposed model, an end-to-end siamese convolutional neural network is designed and trained which can integrate the difference image generating and difference image analysis into a whole network. Thus, the damage changes can be highlighted by the pre-trained siamese network that classifies the central pixel between input multi-temporal image patches into changed and unchanged classes. To address the problem of unbalanced distribution between positive and negative samples, a modified average frequency balancing based weighted softmax loss is used to train the proposed network. Experiments conducted on two real datasets demonstrate the effectiveness and superiority of the proposed model.
AB - Due to the fact that weak and fake laser-induced damages may occur in the surface of optical elements in high-energy laser facilities, it is still a challenging issue to effectively detect the real laser-induced damage changes of optical elements in optical images. Different from the traditional methods, in this paper, we put forward a similarity metric optimization driven supervised learning model to perform the laser-induced damage change detection task. In the proposed model, an end-to-end siamese convolutional neural network is designed and trained which can integrate the difference image generating and difference image analysis into a whole network. Thus, the damage changes can be highlighted by the pre-trained siamese network that classifies the central pixel between input multi-temporal image patches into changed and unchanged classes. To address the problem of unbalanced distribution between positive and negative samples, a modified average frequency balancing based weighted softmax loss is used to train the proposed network. Experiments conducted on two real datasets demonstrate the effectiveness and superiority of the proposed model.
KW - Change detection
KW - Laser-induced damage
KW - Siamese convolutional neural network
KW - Weighted softmax loss
UR - http://www.scopus.com/inward/record.url?scp=85076852552&partnerID=8YFLogxK
U2 - 10.1016/j.asoc.2019.106015
DO - 10.1016/j.asoc.2019.106015
M3 - 文章
AN - SCOPUS:85076852552
SN - 1568-4946
VL - 87
JO - Applied Soft Computing
JF - Applied Soft Computing
M1 - 106015
ER -