OPT OpenIR  > 空间光学应用研究室
A Deep Learning Approach to Real-Time Recovery for Compressive Hyper Spectral Imaging
Li, Ruimin1,2; Zeng, Yang1,2; Wen, Desheng1; Song, Zongxi1; Li, RM (reprint author), Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian, Shaanxi, Peoples R China.
2017
会议名称3rd IEEE Information Technology and Mechatronics Engineering Conference (ITOEC)
会议录名称2017 IEEE 3RD INFORMATION TECHNOLOGY AND MECHATRONICS ENGINEERING CONFERENCE (ITOEC)
页码1030-1034
会议日期2017-10-03
会议地点Chongqing, PEOPLES R CHINA
出版地NEW YORK
出版者IEEE
产权排序1
摘要

Compressive coded hyper spectral (HS) imaging actualizes compressed sampling and snapshot acquisition of HS data, whereas current recovery algorithms take too long time to make real-time HS imaging satisfactory. This paper proposes a deep learning approach for compressive HS imaging to shorten the recovery time. A fully-connected network is designed to train a block-based non-linear reconstruction operator. There is a mergence after obtaining the recovery 3D blocks, followed with a block edge mean filter. The contribution of this approach is that it uses deep neural network to do the reconstruction of the HS data for the first time and it has low-complexity and needs less memory because of operating on local patches. The proposed method was validated on a public available HS dataset and the experimental results show that this approach is superior to the state-of-the-art in the recovery accuracy, and dramatically improves the reconstruction speed by 400 similar to 760 times.

关键词Compressive Coded Hs Imaging Deep Learning Fully-connected Network Real-time
学科领域Automation & Control Systems
作者部门空间光学应用研究室
DOI10.1109/ITOEC.2017.8122510
收录类别EI ; ISTP
ISBN号978-1-5090-5363-6
语种英语
引用统计
文献类型会议论文
条目标识符http://ir.opt.ac.cn/handle/181661/29890
专题空间光学应用研究室
通讯作者Li, RM (reprint author), Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian, Shaanxi, Peoples R China.
作者单位1.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian, Shaanxi, Peoples R China
2.Univ Chinese Acad Sci, Beijing, Peoples R China
推荐引用方式
GB/T 7714
Li, Ruimin,Zeng, Yang,Wen, Desheng,et al. A Deep Learning Approach to Real-Time Recovery for Compressive Hyper Spectral Imaging[C]. NEW YORK:IEEE,2017:1030-1034.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
A Deep Learning Appr(935KB)会议论文 开放获取CC BY-NC-SA请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Li, Ruimin]的文章
[Zeng, Yang]的文章
[Wen, Desheng]的文章
百度学术
百度学术中相似的文章
[Li, Ruimin]的文章
[Zeng, Yang]的文章
[Wen, Desheng]的文章
必应学术
必应学术中相似的文章
[Li, Ruimin]的文章
[Zeng, Yang]的文章
[Wen, Desheng]的文章
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。