No abstract

No abstract

No abstract

Endmember extraction algorithms (EEAs) are among the most commonly discussed types of hyperspectral image processing in the past three decades. This article proposes a spatial energy prior constrained maximum simplex volume (SENMAV) approach for spatial-spectral endmember extraction of hyperspectral images. SENMAV investigates the spatial information from the perspective of the spatial energy prior of a Markov random field (MRF), which is used as a regularization term of the traditional maximum volume simplex model to simultaneously constrain the selection of the endmembers in both the spatial and spectral viewpoints. This article sheds new light on spatial-spectral-based EEAs, as SEN-MAV well balances the tradeoff between endmember extraction accuracy and spatial attribute requirements of endmembers. Based on the spectral angle distance and root-mean-square error, experimental results on both synthetic and real hyperspectral datasets indicate that the proposed approach significantly improves the endmember extraction performance over current state-of-the-art spatial-spectral-based EEAs.

Recently, generative adversarial network (GAN)-based methods for hyperspectral image (HSI) classification have attracted research attention due to their ability to alleviate the challenges brought by having limited labeled samples. However, several studies have demonstrated that existing GAN-based HSI classification methods are limited in redundant spectral knowledge and cannot extract discriminative characteristics, thus affecting classification performance. In addition, GAN-based methods always suffer from the model collapse, which seriously hinders their development. In this study, we proposed a semi-supervised adaptive weighting feature fusion generative adversarial network (AWF2-GAN) to alleviate these problems. We introduced unlabeled data to address the issue of having a small number of samples. First, to build valid spectral–spatial feature engineering, the discriminator learns both the dense global spectrum and neighboring separable spatial context via well-designed extractors. Second, a lightweight adaptive feature weighting component is proposed for feature fusion; it considers four predictive fusion options, that is, adding or concatenating feature maps with similar or adaptive weights. Finally, for the mode collapse, the proposed AWF2-GAN combines supervised central loss and unsupervised mean minimization loss for optimization. Quantitative results on two HSI datasets show that our AWF2-GAN achieves superior performance over state-of-the-art GAN-based methods.