Due to the importance in many military and civilian applications, hyperspectral anomaly detection has attracted remarkable interest. Low-rank representation (LRR)-based anomaly detectors use the low-rank property to represent background pixels, and pixels that cannot be well represented are detected as anomalies. The ability of an LRR-based detector to separate background pixels and anomalous pixels depends on the dictionary representation ability, which usually can be enhanced by designing a proper prior for dictionary representation coefficients and constructing a better dictionary. However, it is not easy to handcraft effective and meaningful regularizers for dictionary coefficients. In this article, we propose a novel anomaly detection algorithm that uses a plug-and-play prior for representation coefficients and constructs a new dictionary based on clustering. Instead of cumbersomely handcrafting a regularizer for representation coefficients, we propose solving the anomaly detection problem using the plug-and-play framework, which enables us to plug state-of-the-art priors for representation coefficients. An effective convolutional neural network (CNN) denoiser is plugged into our framework to fully exploit the spatial correlation of representation coefficients. We also propose a modified background dictionary construction method, which carefully includes background pixels and excludes anomalous pixels from clustering results. We refer to the proposed anomaly detection method as plug-and-play denoising CNN regularized anomaly detection (DeCNN-AD) method. Extensive experiments were performed on five data sets in a comparison with eight state-of-the-art anomaly detection methods. The experimental results suggest that the proposed method is effective in anomaly detection and can produce better anomaly detection results than that of the comparison methods. The codes of this work will be available at https://github.com/FxyPd for the sake of reproducibility.

The ever-increasing spectral resolution of hyperspectral images (HSIs) is often obtained at the cost of a decrease in the signal-to-noise ratio of the measurements, thus calling for effective denoising techniques. HSIs from the real world lie in low-dimensional subspaces and are self-similar. The low dimensionality stems from the high correlation existing among the reflectance vectors, and self-similarity is common in real-world images. In this article, we exploit the above two properties. The low dimensionality is a global property that enables the denoising to be formulated just with respect to the subspace representation coefficients, thus greatly improving the denoising performance and reducing the computational complexity during processing. The self-similarity is exploited via a low-rank tensor factorization of nonlocal similar 3-D patches. The proposed factorization hinges on the optimal shrinkage/thresholding of the singular value decomposition (SVD) singular values of low-rank tensor unfoldings. As a result, the proposed method is user friendly and insensitive to its parameters. Its effectiveness is illustrated in a comparison with state-of-the-art competitors. A MATLAB demo of this work is available at https://github.com/LinaZhuang for the sake of reproducibility.

The high spectral resolution of hyperspectral images (HSIs) generally comes at the expense of low spatial resolution, which hinders the application of HSIs. Fusing an HSI and a multispectral image (MSI) from different sensors to get an image with the high spatial and spectral resolution is an economic and effective approach, but localized spatial and spectral changes between images acquired at different time instants can have negative impacts on the fusion results, which has rarely been considered in many fusion methods. In this article, we propose a novel group sparsity constrained fusion (GSFus) method to fuse hyperspectral and MSIs based on matrix factorization. Specifically, we imposed $\ell _{2,1}$ norm on the residual term of the MSI to account for the localized interimage changes occurring during the acquisition of the hyperspectral and MSIs. Furthermore, by exploiting the plug-and-play framework, we plugged a state-of-the-art denoiser, namely block-matching and 3-D filtering (BM3D), as the prior of the subspace coefficients. We refer to the proposed fusion method as GSFus method. We performed fusion experiments on two kinds of datasets, i.e., with and without obvious localized changes between the HSIs and MSIs, and a full resolution dataset. Extensive experiments in comparison with seven state-of-the-art fusion methods suggest that the proposed fusion method is more effective on fusing hyperspectral and MSIs than the competitors.

Hyperspectral anomaly detection (HAD) aims to identify anomalous objects from hyperspectral images (HSIs) whose spectral features significantly deviate from their surroundings. Existing HAD methods still reconstruct some anomalies during the background reconstruction process, which can seriously affect the detection accuracy. Consequently, inspired by Mamba’s ability to effectively model long sequences, we propose a multiscale Mamba reconstruction network for HAD (MMR-HAD) by enhancing the representation of the background and inhibit anomalies from being reconstructed. MMR-HAD first removes most of the anomalous pixels in HSIs using the random mask (RM) strategy, which reduces the interference of anomalous pixels on the background reconstruction and makes the background features more prominent. To further filter out the small amount of residual anomalous pixels, we propose the multiscale dilated attention background enhancement (MDABE) mechanism, which enhances the background representation. Finally, we apply the multiscale dynamic feature fusion (MDFF) strategy to reconstruct the background image, further extracting and strengthening the background information, thus obtaining a pure background image. MMR-HAD, which focuses on generating a pure background, has been experimentally validated on seven real hyperspectral datasets. The results demonstrate that it excels in background enhancement and anomaly suppression, significantly improving detection accuracy. Introducing Mamba offers a promising solution for HAD, with substantial potential for practical application.

This article proposes a smart hyperspectral sensing strategy, implemented in the spectral domain, conceived for spaceborne sensor systems, where physical space, storage resources, and communication bandwidth are extremely scarce and expensive. Smart sensing means faster and hardware-friendly imaging. Instead of acquiring all band samples in the spectral domain, we randomly select a few band samples per spatial pixel location. A periodic structure of spectral band selector array (SBSA) is designed so that we can learn a subspace basis from subsamples, which is essential to the underlying hyperspectral image (HSI) recovery algorithm. This spectral subsampling sensing strategy yields a demosaicing problem. We propose a blind hyperspectral reconstruction technique termed hyperspectral demosaicing (Hy-demosaicing) exploiting spectral low-rankness and spatial correlation of HSIs. It is blind in the sense that the signal subspace is learned from measured spectral subsamples. The subspace basis is data-adaptive and provides a more compact representation than other non-adaptive representations. This adaptiveness leads to improved image recovery as illustrated in experiments with real data.