期刊
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
卷 17, 期 3, 页码 469-473出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2019.2921225
关键词
Feature extraction; Image reconstruction; Data mining; Training; Artificial neural networks; Hyperspectral imaging; Autoencoder (AE); feature learning; hyperspectral imaging (HSI); land cover classification; unsupervised learning
In this letter, we discuss unsupervised feature extraction on hyperspectral imagery (HSI) and propose a novel approach based on autoencoder (AE) networks to extract spectral-spatial features from HSI. Our approach takes the data relations into consideration, i.e., the input dependency with adjacent inputs, which the normal AE-based feature extractors often disregard. Specifically, the loss function of the normal AE is modified so as to make pixels share the common features among the neighboring pixels. The process enables the generation of smooth compressed images represented by features provided by the AE. Numerical experiments were conducted on real-world HSI data sets for land cover classification. The results demonstrated that spectral-spatial features extracted by our approach are more discriminative for land cover classification than those done by conventional approaches.
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