期刊
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
卷 15, 期 11, 页码 1755-1759出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2018.2857804
关键词
Convolutional neural networks (CNNs); end-to-end model; spectral unmixing; spectral-spatial information
类别
资金
- National Natural Science Foundation of China [61772400, 61501353, 61772399, 91438201, 61573267]
Hyperspectral unmixing (HU) is a method used to estimate the fractional abundances corresponding to endmembers in each of the mixed pixels in the hyperspectral remote sensing image. In recent times, deep learning has been recognized as an effective technique for hyperspectral image classification. In this letter, an end-to-end HU method is proposed based on the convolutional neural network (CNN). The proposed method uses a CNN architecture that consists of two stages: the first stage extracts features and the second stage performs the mapping from the extracted features to obtain the abundance percentages. Furthermore, a pixel-based CNN and cube-based CNN, which can improve the accuracy of HU, are presented in this letter. More importantly, we also use dropout to avoid overfitting. The evaluation of the complete performance is carried out on two hyperspectral data sets: Jasper Ridge and Urban. Compared with that of the existing method, our results show significantly higher accuracy.
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