Hyperspectral Target Detection via Global Spatial-Spectral Attention Network and Background Suppression

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.