CASIA OpenIR  > 模式识别国家重点实验室  > 先进数据分析与学习
A label propagation method using spatial-spectral consistency for hyperspectral image classification
Haichang Li; Ying Wang; Shiming Xiang; Jiangyong Duan; Feiyun Zhu; Chunhong Pan; haichang516@gmail.com
Source PublicationInternational Journal of Remote Sensing
2016-01-04
Volume37Issue:1Pages:191-211
Abstract
In this article, a label propagation approach with automatic seed selection is developed for hyperspectral image classification. The core idea is to combine pixel-wise classification results with spatial information described by a data graph. Using only the support vector machine (SVM) classifier on spectral features to tackle the hyperspectral classification task will produce results with a salt and pepper appearance. To overcome this limitation, the spatial information is incorporated by label propagation. The performance of label propagation is dependent on two points: the seeds and the connection graph. Generally, a limited number of labelled samples are available, which are considered as seeds in label propagation. However, the limited seeds will result in bad label propagation. Therefore, pseudo-seeds are automatically selected in local windows. Specifically, the pixels whose initial labels according to SVM are consistent with their most spatial neighbours are selected as seeds. Through seed selection, the number of seeds is greatly increased. Then, the label information of the selected seeds is propagated to their spatial neighbours using a data graph which is constructed according to the local structures in the image. Through seed selection and label propagation
on the graph, the problem of salt-and-pepper appearance is solved elegantly – the noisy labels are highly suppressed and most of the structures are preserved. Competitive experimental results on a variety of hyperspectral data sets demonstrate the effectiveness of the proposed method.
KeywordHyperspectral Image Classification Label Propagation Spatial-spectral.
WOS Research AreaRemote Sensing ; Image Science & Photographic Technology
WOS SubjectRemote Sensing ; Image Science & Photographic Technology
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/11123
Collection模式识别国家重点实验室_先进数据分析与学习
Corresponding Authorhaichang516@gmail.com
AffiliationNational Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Haichang Li,Ying Wang,Shiming Xiang,et al. A label propagation method using spatial-spectral consistency for hyperspectral image classification[J]. International Journal of Remote Sensing,2016,37(1):191-211.
APA Haichang Li.,Ying Wang.,Shiming Xiang.,Jiangyong Duan.,Feiyun Zhu.,...&haichang516@gmail.com.(2016).A label propagation method using spatial-spectral consistency for hyperspectral image classification.International Journal of Remote Sensing,37(1),191-211.
MLA Haichang Li,et al."A label propagation method using spatial-spectral consistency for hyperspectral image classification".International Journal of Remote Sensing 37.1(2016):191-211.
Files in This Item: Download All
File Name/Size DocType Version Access License
Haichang Li.pdf(3399KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Haichang Li]'s Articles
[Ying Wang]'s Articles
[Shiming Xiang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Haichang Li]'s Articles
[Ying Wang]'s Articles
[Shiming Xiang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Haichang Li]'s Articles
[Ying Wang]'s Articles
[Shiming Xiang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Haichang Li.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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