Improving Hyperspectral Image Classification by Fusing Spectra and Absorption Features

	Improving Hyperspectral Image Classification by Fusing Spectra and Absorption Features
	Guo, B. F.; H. H. Shen and M. Y. Yang
	2017
发表期刊	Ieee Geoscience and Remote Sensing Letters
卷号	14 期号:8
摘要	Many features can be extracted to classify hypers-pectral imagery. Classification relying on a single feature set may lose some useful information due to the intrinsic limitation of each feature extraction model. To improve classification accuracy, we propose an information fusion approach, in which both the global and the local aspects of hyperspectral data are taken into account and are combined by a decision-level fusion method. The global features are hyperspectral reflectance curves representing the holistic response to the incident light, and the local features are absorption characteristics reflected by materials' individual constituents. The decision-level fusion is carried out by analyzing the entropy of the classification output from the global feature set and modifying this output via the results of a multilabel classification using the local feature set. Simulations of classification performance on 16 classes of vegetation from the AVIRIS 92AV3C and Salinas data set show the effectiveness of the method, which increases the classification accuracy compared to a popular support vector machine-based method and a production-rule-based decision fusion method.
收录类别	sci ; ei
语种	英语
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/58915
专题	中科院长春光机所知识产出
推荐引用方式 GB/T 7714	Guo, B. F.,H. H. Shen and M. Y. Yang. Improving Hyperspectral Image Classification by Fusing Spectra and Absorption Features[J]. Ieee Geoscience and Remote Sensing Letters,2017,14(8).
APA	Guo, B. F.,&H. H. Shen and M. Y. Yang.(2017).Improving Hyperspectral Image Classification by Fusing Spectra and Absorption Features.Ieee Geoscience and Remote Sensing Letters,14(8).
MLA	Guo, B. F.,et al."Improving Hyperspectral Image Classification by Fusing Spectra and Absorption Features".Ieee Geoscience and Remote Sensing Letters 14.8(2017).

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Improving Hyperspect（687KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载