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

Abstract

The accuracy of hyperspectral target detection (HTD) 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 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 multi-scale 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 spectral angle mapping (SAM) 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.  Index Terms-Hyperspectral target detection, spectral variation, global spatial-spectral attention network, background suppression. I. INTRODUCTION Hyperspectral sensors record hyperspectral images (HSIs) with hundreds of continuous and narrow bands, reaching a spectral resolution of around 10 nm. Due to its powerful representational ability, HSIs have been widely used in land cover classification [1], [2], target detection [3], [4], anomaly detection [5], [6], image unmixing [7], [8] and change detection [9]. Hyperspectral target detection (HTD) is one of the most challenging issues in these applications, due to the limited amount of known information about target spectra and the background. Indeed, HTD can be regarded as a problem of weakly supervised binary classification.

Hyperspectral Target Detection With Target Prior Augmentation and Background Suppression-Based Multidetector Fusion

“…In addition to the above shallow learning-based methods, some hierarchical learning-based methods have also been investigated for HSI applications [25][26][27][36][37][38][39]. For example, Gao et.al., [39] proposed the depth-wise feature interaction network with a depth-wise cross attention module to extract self-correlation and cross correlation from multisource feature pairs.…”