OPT OpenIR  > 光谱成像技术实验室
Hyperspectral image classification based on adaptive segmentation
Wu, Yinhua; Hu, Bingliang; Gao, Xiaohui; Wei, Ruyi
作者部门光谱成像技术实验室
2018-11
发表期刊Optik
ISSN00304026
卷号172页码:612-621
产权排序1
摘要

Object-based hyperspectral image classification (OBHIC) converts the basic unit from ‘pixel’ to ‘object’ by image segmentation, in order to take advantage of the spatial distribution law of geographical substances, as well as increase classification performances. However, it involves the problem of scale selection, i.e. the segmentation parameters are set manually by empirical values. In this paper, a novel OBHIC algorithm based on adaptive segmentation is proposed. Here, hyperspectral images (HSIs) are first segmented through a new segmentation scheme with constraint ability, and the thresholds for segmentation are calculated adaptively by utilizing training samples. And then K-nearest neighbor algorithm (KNN) is applied to classify the centers of each region after segmentation. In addition, based on the semisupervised idea, semi-known samples are obtained to further improve the classification performance. Experimental results are presented on two HSI datasets. For different HSIs, the adaptive thresholds calculated are consistent with empirical ones, and the developed classification algorithm has achieved good classification results, thus demonstrating strong robustness of the algorithm. For the HSI Indian Pines from AVIRIS sensor, the Overall Accuracy (OA) and kappa are 95.13% and 0.9444 respectively with 10% training samples, and for the HSI Pavia University from ROSIS sensor, the OA and kappa are 95.52% and 0.9416 respectively with 2% training samples. And good classification performance is still maintained for small number of training samples. © 2018

关键词Hyperspectral Classification Object-based Segmentation Adaptive
DOI10.1016/j.ijleo.2018.07.058
收录类别SCI ; EI
语种英语
WOS记录号WOS:000445714700076
出版者Elsevier GmbH
EI入藏号20183005599681
EI主题词Classification (Of Information) ; Image Segmentation ; Independent Component Analysis ; Nearest Neighbor Search ; Sampling ; Spectroscopy
EI分类号Electronics And Communication Engineering::Electronic Equipment, Radar, Radio And Television::Information & Communication Theory
引用统计
文献类型期刊论文
条目标识符http://ir.opt.ac.cn/handle/181661/30528
专题光谱成像技术实验室
通讯作者Wu, Yinhua
作者单位Key Laboratory of Spectral Imaging Technology, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an, China
推荐引用方式
GB/T 7714
Wu, Yinhua,Hu, Bingliang,Gao, Xiaohui,et al. Hyperspectral image classification based on adaptive segmentation[J]. Optik,2018,172:612-621.
APA Wu, Yinhua,Hu, Bingliang,Gao, Xiaohui,&Wei, Ruyi.(2018).Hyperspectral image classification based on adaptive segmentation.Optik,172,612-621.
MLA Wu, Yinhua,et al."Hyperspectral image classification based on adaptive segmentation".Optik 172(2018):612-621.
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
Hyperspectral image (2214KB)期刊论文出版稿开放获取CC BY-NC-SA浏览 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
[Wu, Yinhua]的文章
[Hu, Bingliang]的文章
[Gao, Xiaohui]的文章
百度学术
百度学术中相似的文章
[Wu, Yinhua]的文章
[Hu, Bingliang]的文章
[Gao, Xiaohui]的文章
必应学术
必应学术中相似的文章
[Wu, Yinhua]的文章
[Hu, Bingliang]的文章
[Gao, Xiaohui]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Hyperspectral image classification based on adaptive segmentation.pdf
格式: Adobe PDF
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。