The laser-induced damage change detection for optical elements using siamese convolutional neural networks
Jingwei Kou1,3; Tao Zhan2; Deyun Zhou3; Wei Wang1; Zhengshang Da1; Maoguo Gong2
刊名Applied Soft Computing
2020
卷号87页码:106015
关键词Laser-induced Damage Change Detection Siamese Convolutional Neural Network Weighted Softmax Loss
ISSN号1568-4946
DOIhttps://doi.org/10.1016/j.asoc.2019.106015
产权排序1
英文摘要

 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 multitemporal 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.

学科主题人工智能 ; 计算机科学技术其他学科
URL标识查看原文
语种英语
内容类型期刊论文
源URL[http://ir.opt.ac.cn/handle/181661/67897]  
专题西安光学精密机械研究所_先进光学仪器研究室
通讯作者Maoguo Gong
作者单位1.The Advanced Optical Instrument Research Department, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences
2.Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University
3.School of Electronics and Information, Northwestern Polytechnical University
推荐引用方式
GB/T 7714
Jingwei Kou,Tao Zhan,Deyun Zhou,et al. The laser-induced damage change detection for optical elements using siamese convolutional neural networks[J]. Applied Soft Computing,2020,87:106015.
APA Jingwei Kou,Tao Zhan,Deyun Zhou,Wei Wang,Zhengshang Da,&Maoguo Gong.(2020).The laser-induced damage change detection for optical elements using siamese convolutional neural networks.Applied Soft Computing,87,106015.
MLA Jingwei Kou,et al."The laser-induced damage change detection for optical elements using siamese convolutional neural networks".Applied Soft Computing 87(2020):106015.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace