SIA OpenIR  > 光电信息技术研究室
对抗网络实现单幅RGB重建高光谱图像
Alternative TitleHyperspectral images reconstruction using adversarial networks from single RGB image
刘鹏飞1,2,3,4,5; 赵怀慈1,2,4,5; 李培玄1,2,3,4,5
Department光电信息技术研究室
Source Publication红外与激光工程
ISSN1007-2276
2020
Volume49Issue:S1Pages:1-8
Indexed ByEI
EI Accession number20203609139677
Contribution Rank1
Funding Organization装备预研重点基金(JZX7Y2019025049301)
Keyword高光谱成像 特征金字塔 生成对抗网络 注意力机制
Abstract

高光谱成像能够提供比普通RGB图像更全的光谱信息,在监测自然环境变化、农业植被土壤分类等具有广泛的应用。从单幅RGB图像重建高光谱信息是严重欠约束问题,传统重建算法需要增加光学组件或已知相机光谱响应,在实际应用中往往不能满足要求。针对此问题,提出一种端到端对抗生成网络,设计一种改进残差结构作为对抗网络的基本模块,使用多尺度特征金字塔融合局部和全局特征并捕获像素空间上下文信息;提出了新的WNet网络,利用局部边缘图像引导模型学习到高频信号,进一步提升了高光谱重建精度。实验结果表明:无论是高光谱图像数据合成的RGB图像以及普通相机拍摄的真实RGB图像,所提方法的高光谱重建效果在定量和定性评价指标上均优于已有的代表性方法,对比稀疏字典算法,均方误差和相对均方误差分别降低了45%和50%。

Other Abstract

Hyperspectral imaging can provide more spectral information than an ordinary RGB camera. The spectral information has been beneficial to numerous applications, such as monitoring natural environment changes and classifying plants and soils in agriculture. The hyperspectral images reconstruction from a single RGB image is severely unconstrained problem. Previous methods need additional components or the spectral response by commercial camera. An end-to-end conditional generative adversarial network was proposed with modified residual network as backbone. The feature pyramid was used inside the network and a scale attention module was designed to fuse local and global information. In order to provide more accurate solution, another distinct architecture was proposed, named WNet. Experiments manifested the superiority of the proposed method over other representative methods in terms of quality and quantity. Experiments used both synthesized RGB images using public hyperspectral data and real-world image by ordinary camera demonstrate that proposed method outperforms the state-of-the-art. The WNet drops 45% and 50% in terms of RMSE and relative RMSE on the ICVL dataset than sparse coding. © 2020, Editorial Board of Journal of Infrared and Laser Engineering. All right reserved.

Language中文
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/27632
Collection光电信息技术研究室
Corresponding Author赵怀慈
Affiliation1.中国科学院沈阳自动化研究所
2.中国科学院机器人与智能制造创新研究院
3.中国科学院大学
4.中国科学院光电信息处理重点实验室
5.辽宁省图像理解与视觉计算重点实验室
Recommended Citation
GB/T 7714
刘鹏飞,赵怀慈,李培玄. 对抗网络实现单幅RGB重建高光谱图像[J]. 红外与激光工程,2020,49(S1):1-8.
APA 刘鹏飞,赵怀慈,&李培玄.(2020).对抗网络实现单幅RGB重建高光谱图像.红外与激光工程,49(S1),1-8.
MLA 刘鹏飞,et al."对抗网络实现单幅RGB重建高光谱图像".红外与激光工程 49.S1(2020):1-8.
Files in This Item:
File Name/Size DocType Version Access License
对抗网络实现单幅RGB重建高光谱图像.p(7396KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[刘鹏飞]'s Articles
[赵怀慈]'s Articles
[李培玄]'s Articles
Baidu academic
Similar articles in Baidu academic
[刘鹏飞]'s Articles
[赵怀慈]'s Articles
[李培玄]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[刘鹏飞]'s Articles
[赵怀慈]'s Articles
[李培玄]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 对抗网络实现单幅RGB重建高光谱图像.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.