Hyperspectral image (HSI) target detection plays a pivotal role in both military and civilian sectors. Nevertheless, this task is fraught with challenges because of the limited availability samples intricate nature background within real-world HSIs. In study, we present an innovative learning model based on orthogonal subspace-guided variational autoencoder, tailored to discern distribution hyperspectral imagery. Given scarcity samples, our exclusively trained spectral enabling precise...

Typical high-level vision tasks in hyperspectral image (HSI) processing, such as target detection, often suffer from insufficient information inherent real-world sampled data. Super-resolution, a powerful tool HSI low-level vision, is expected to enhance the accuracy of detection results by computationally providing high-resolution with additional information. However, existing solutions for super-resolution and have always been implemented independently. This conventionally adopted paradigm...

Low-rank tensor representation philosophy has enjoyed a reputation in many hyperspectral image (HSI) low-level vision applications, but previous studies often failed to comprehensively exploit the low-rank nature of HSI along different modes low-dimensional subspace, and unsurprisingly handled only one specific task. To address these challenges, this paper, we figured out that addition spatial correlation, spectral dependency also implicitly exists coefficient its crucial was not fully...

During the process of signal sampling and digital imaging, hyperspectral images (HSI) inevitably suffer from contamination mixed noises. The fidelity efficiency subsequent applications are considerably reduced along with this degradation. Recently, as a formidable implement for image processing, low-rank regularization has been widely extended to restoration HSI. Meanwhile, further exploration non-local self-similarity proven useful in exploiting spatial redundancy Better preservation...

In this letter, using the sparse unmixing framework, a weighted collaborative and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$L_{1/2}$ </tex-math></inline-formula> low-rank regularization with superpixel segmentation method is proposed for hyperspectral unmixing. The outlined here first uses to obtain local homogeneous regions. reason approach that shape size of superpixels are adaptive, which better...

With the rapid advancement of spectrometers, imaging range electromagnetic spectrum starts growing narrower. The reduction wave energy received in a single wavelength leads more complex noise into generated hyperspectral image (HSI), thus causing severe cripple accuracy subsequent applications. requirement for HSI mixed denoising algorithm’s is further lifted. To address this challenge, letter, we propose novel difference continuity-regularized nonlocal tensor subspace low-rank learning...

Recently, tensor singular value decomposition (t-SVD) has demonstrated excellent performance in various high-dimensional information processing applications. However, adapting t-SVD to handle the typical data restoration tasks, such as hyperspectral image (HSI) denoising, following questions remain inadequately addressed: 1) The existing nuclear norm minimization (TNN) regime treats all values alike; thus, it lacks flexibility and dominance dealing with sophisticated HSI tensor. 2)...

Abstract Load forecasting, as the baseline for decision-making, plays a key role in management and control of grid. Nevertheless, rapid evolution smart grid has brought dramatic increase volume user-side data, traditional load forecasting approaches have to face challenge ensuring accuracy dynamic under circumstance widespread application big data. Meanwhile, advance Industrial Internet Things (IIoT) enables meters acquire more plentiful which improves short-term with appropriate...

In this paper, superpixel features and extended multi-attribute profiles (EMAPs) are embedded in a multiple kernel learning framework to simultaneously exploit the local multiscale information both spatial spectral dimensions for hyperspectral image (HSI) classification. First, original HSI is reduced three principal components domain using component analysis (PCA). Then, fast efficient segmentation algorithm named simple linear iterative clustering utilized segment into certain number of...

The recently proposed high-order tensor algebraic framework generalizes the singular value decomposition (t-SVD) induced by invertible linear transform from order-3 to order-d (d > 3). However, derived t-SVD rank essentially ignores implicit global discrepancy in quantity distribution of non-zero transformed values across higher modes tensors. This oversight leads sub-optimal restoration processing real-world multi-dimensional visual datasets. To address this challenge, study, we look...

During the imaging process, hyperspectral image (HSI) is inevitably affected by various noises, such as Gaussian noise, impulse stripes or deadlines. As one of pre-processing steps, removal mixed noise for HSI has a vital impact on subsequent applications, and it also most challenging tasks. In this paper, novel spectral-smoothness non-local self-similarity regularized subspace low-rank learning (termed SNSSLrL) method was proposed HSI. First, under decomposition framework, original...