OPT OpenIR  > 空间光学技术研究室
Dimensionality reduction method based on a tensor model
Yan, Ronghua1,2; Peng, Jinye1,3; Ma, Dongmei4; Wen, Desheng2; Yan, RH (reprint author), Northwestern Polytech Univ, Sch Elect & Informat, Xian, Peoples R China.
作者部门空间光学应用研究室
2017-05-31
发表期刊JOURNAL OF APPLIED REMOTE SENSING
ISSN1931-3195
卷号11
产权排序1
摘要

Dimensionality reduction is a preprocessing step for hyperspectral image (HSI) classification. Principal component analysis reduces the spectral dimension and does not utilize the spatial information of an HSI. Both spatial and spectral information are used when an HSI is modeled as a tensor, that is, the noise in the spatial dimension is decreased and the dimension in a spectral dimension is reduced simultaneously. However, this model does not consider factors affecting the spectral signatures of ground objects. This means that further improving classification is very difficult. The authors propose that the spectral signatures of ground objects are the composite result of multiple factors, such as illumination, mixture, atmospheric scattering and radiation, and so on. In addition, these factors are very difficult to distinguish. Therefore, these factors are synthesized as within-class factors. Within-class factors, class factors, and pixels are selected to model a third-order tensor. Experimental results indicate that the classification accuracy of the new method is higher than that of the previous methods. (C) 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)

文章类型Article
关键词Dimensionality Reduction Tensor Processing Hyperspectral Image Spectral Tensor
学科领域Environmental Sciences
WOS标题词Science & Technology ; Life Sciences & Biomedicine ; Technology
DOI10.1117/1.JRS.11.025011
收录类别SCI ; EI
关键词[WOS]SPATIAL FEATURE-EXTRACTION ; HYPERSPECTRAL IMAGES ; DECOMPOSITIONS ; ALIGNMENT
语种英语
WOS研究方向Environmental Sciences & Ecology ; Remote Sensing ; Imaging Science & Photographic Technology
项目资助者National Natural Science Foundation of China(61272285) ; Program for Changjiang Scholars and Innovative Research Team in University(IRT13090)
WOS类目Environmental Sciences ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号WOS:000402812000001
引用统计
被引频次:3[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.opt.ac.cn/handle/181661/29038
专题空间光学技术研究室
通讯作者Yan, RH (reprint author), Northwestern Polytech Univ, Sch Elect & Informat, Xian, Peoples R China.
作者单位1.Northwestern Polytech Univ, Sch Elect & Informat, Xian, Peoples R China
2.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian, Peoples R China
3.Northwest Univ Xian, Sch Informat & Technol, Xian, Peoples R China
4.Xian Janssen Pharmaceut Ltd, Xian, Peoples R China
推荐引用方式
GB/T 7714
Yan, Ronghua,Peng, Jinye,Ma, Dongmei,et al. Dimensionality reduction method based on a tensor model[J]. JOURNAL OF APPLIED REMOTE SENSING,2017,11.
APA Yan, Ronghua,Peng, Jinye,Ma, Dongmei,Wen, Desheng,&Yan, RH .(2017).Dimensionality reduction method based on a tensor model.JOURNAL OF APPLIED REMOTE SENSING,11.
MLA Yan, Ronghua,et al."Dimensionality reduction method based on a tensor model".JOURNAL OF APPLIED REMOTE SENSING 11(2017).
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
Dimensionality reduc(3839KB)期刊论文作者接受稿限制开放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
[Yan, Ronghua]的文章
[Peng, Jinye]的文章
[Ma, Dongmei]的文章
百度学术
百度学术中相似的文章
[Yan, Ronghua]的文章
[Peng, Jinye]的文章
[Ma, Dongmei]的文章
必应学术
必应学术中相似的文章
[Yan, Ronghua]的文章
[Peng, Jinye]的文章
[Ma, Dongmei]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。