期刊
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
卷 14, 期 -, 页码 12312-12331出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2021.3129818
关键词
Dimensionality reduction; folded linear discriminant analysis (F-LDA); hyperspectral remote sensing; small sample size (SSS) scenario; supervised feature extraction
类别
资金
- University of Strathclyde, Glasgow, U.K
This article introduces a method called folded Linear Discriminant Analysis (F-LDA) for dimensionality reduction of remotely sensed HSI data in small sample size scenarios. The F-LDA allows selecting more discriminant features and significantly improves accuracy in pixel classification, outperforming conventional LDA in terms of classification accuracy, computational complexity, and memory requirements.
The rich spectral information provided by hyperspectral imaging has made this technology very useful in the classification of remotely sensed data. However, classification of hyperspectral data is typically affected by noise and the Hughes phenomenon due to the presence of hundreds of spectral hands and correlation among them, with usually a limited number of samples for training. Linear discriminant analysis (LDA) is a well-known technique that has been widely used for supervised dimensionality reduction of hyperspectral data. However, the use of LDA in hyperspectral remote sensing is limited due to its poor performance on small training datasets and the limited number of features that can he selected i.e., c - 1, where c is the number of classes in the data. To solve these problems, this article presents a folded LDA (F-LDA) for dimensionality reduction of remotely sensed HSI data in small sample size scenarios. The proposed approach allows many more discriminant features to be selected in comparison to the conventional LDA since the selection is no longer hound by the limiting factor, leading to significantly higher accuracy in the classification of pixels under SSS restrictions. The proposed approach is evaluated on five different datasets, where the experimental results demonstrate the superiority of the F-LDA to the conventional IDA in terms of not only higher classification accuracy but also reduced computational complexity, and reduced contiguous memory requirements.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据