Improving deep hyperspectral image classification performance with spectral unmixing
Improving deep hyperspectral image classification performance with spectral unmixing
复制标题
通过光谱分解提高深度高光谱图像分类性能
DOI：
10.1016/j.sigpro.2020.107949
复制
发表时间：
2021-01-21
影响因子：
4.4
通讯作者：
Zhu, Fei
中科院分区：
文献类型：
--
作者：
Guo, Alan J. X.;Zhu, Fei
近年来，神经网络在高光谱图像分类中取得了很大的进展。然而，主要由模型结构复杂和训练集小引起的过拟合效应仍然是一个主要问题。降低神经网络的复杂性可以在一定程度上防止过拟合，但也会降低网络表达更抽象特征的能力。扩大训练集也很困难，因为获取和手动标记的费用很高。本文提出了一种基于丰度的多HSI分类方法。首先，我们通过一个特定于数据集的自动编码器将每个HSI从谱域转换到丰度域。其次，从多个HSI中收集丰度表示，形成一个扩展的数据集。最后，我们训练了一个基于丰度的分类器，并使用该分类器对所有涉及到的HSI数据集进行预测。与通常高度混合的光谱不同，丰度特征在降维和低噪声方面更具代表性。这有利于所提出的方法使用简单的分类器和更大的训练数据，并预期较少的过度匹配问题。烧蚀实验和对比实验验证了该方法的有效性。(C)2021年爱思唯尔B.V.保留所有权利。
Recent advances in neural networks have made great progress in the hyperspectral image (HSI) classification. However, the overfitting effect, which is mainly caused by complicated model structure and small training set, remains a major concern. Reducing the complexity of the neural networks could prevent overfitting to some extent, but also declines the networks' ability to express more abstract features. Enlarging the training set is also difficult, for the high expense of acquisition and manual labeling. In this paper, we propose an abundance-based multi-HSI classification method. Firstly, we convert every HSI from the spectral domain to the abundance domain by a dataset-specific autoencoder. Secondly, the abundance representations from multiple HSIs are collected to form an enlarged dataset. Lastly, we train an abundance-based classifier and employ the classifier to predict over all the involved HSI datasets. Different from the spectra that are usually highly mixed, the abundance features are more representative in reduced dimension with less noise. This benefits the proposed method to employ simple classifiers and enlarged training data, and to expect less overfitting issues. The effectiveness of the proposed method is verified by the ablation study and the comparative experiments. (C) 2021 Elsevier B.V. All rights reserved.