期刊
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
卷 16, 期 -, 页码 9011-9024出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2023.3310189
关键词
Convolution; Convolutional neural networks; Object detection; Kernel; Hyperspectral imaging; Feature extraction; Electronic mail; Background suppression; global spatial-spectral attention network (GS(2)A-Net); hyperspectral target detection (HTD); spectral variation
This study proposes a method based on three-dimensional convolution and global spatial-spectral attention network to address the issue of spectral variation in hyperspectral images. A new background suppression strategy is also proposed. Experimental results show that the proposed method achieves higher accuracy in target detection.
The accuracy of hyperspectral target detection is often affected by the problems of spectral variation and complex background distribution. Inspired by the powerful representational ability of deep learning, we proposed a three-dimensional (3-D) convolution-based global spatial-spectral attention network (GS(2)A-Net) to deal with spectral variation in hyperspectral images (HSIs). GS(2)A-Net uses 3-D convolution kernels of different sizes to capture local spatial and spectral features to achieve multiscale information interaction. Different from the previous 2-D attention mechanisms, GS(2)A-Net simultaneously considers the information in the spatial and spectral dimensions, and creates a weight map consistent with the size of the original HSI. Furthermore, we proposed a new background suppression strategy based on the spectral angle mapping to achieve more accurate target detection, which can preserve the targets as much as possible when suppressing the background. The method was validated through experiments on five real-world HSI datasets. Compared with several classical and deep-learning-based methods, the proposed method exhibits greater detection 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