Due to a lack of labeled samples, deep learning methods generally tend to have poor classification performance in practical applications. Few-shot learning (FSL), as an emerging learning paradigm, has been widely utilized in hyperspectral image (HSI) classification with limited labeled samples. However, the existing FSL methods generally ignore the domain shift problem in cross-domain scenes and rarely explore the associations between samples in the source and target domain. To tackle the above issues, a graph-based domain adaptation FSL (GDAFSL) method is proposed for HSI classification with limited training samples, which utilizes the graph method to guide the domain adaptation learning process in a uniformed framework. First, a novel deep residual hybrid attention network (DRHAN) is designed to extract discriminative embedded features efficiently for few-shot HSI classification. Then, a graph-based domain adaptation network (GDAN), which combines graph construction with domain adversarial strategy, is proposed to fully explore the domain correlation between source and target embedded features. By utilizing the fully explored domain correlations to guide the domain adaptation process, a domain invariant feature metric space is learned for few-shot HSI classification. Comprehensive experimental results conducted on three public HSI datasets demonstrate that GDAFSL is superior to the state-of-the-art with a small sample size.

Deep-learning methods have exhibited exceptional performance in numerous target-detection domains, and their application is steadily expanding to include infrared small-target detection as well. However, the effect of existing deep-learning methods is weakened due to the lack of texture information and the low signal-to-noise ratio of infrared small-target images. To detect small targets in infrared images with limited information, a depth feature-extraction network based on a residual module is proposed in this paper. First, a global attention guidance enhancement module (GAGEM) is used to enhance the original infrared small target image in a single frame, which considers the global and local features. Second, this paper proposes a depth feature-extraction module (DFEM) for depth feature extraction. Our IRST-Involution adds the attention mechanism to the classic Involution module and combines it with the residual module for the feature extraction of the backbone network. Finally, the feature pyramid with self-learning weight parameters is used for feature fusion. The comparative experiments on three public datasets demonstrate that our proposed infrared small-target detection algorithm exhibits higher detection accuracy and better robustness.

In Hyperspectral Image (HSI) classification, acquiring large quantities of high-quality labeled samples is typically costly and impractical. Traditional deep learning methods are limited in such scenarios due to their dependence on sample quantities. To address this challenge, researchers have turned to Few-Shot Learning (FSL). Although existing FSL methods improve classification performance by enhancing domain invariance through domain adaptation, they often overlook the critical issue of high inter-class similarity and large intra-class variability. Moreover, during domain alignment, features of different categories within the same domain may become confused. To address these issues, this paper proposes a novel Domain-Invariant Few-Shot Contrastive Learning (DIFSCL) method, which combines domain adaptation and contrastive learning strategies to not only learn domain-invariant features but also significantly enhance inter-class discriminability. Based on this, we further design a multi-scale adaptive attention mechanism for a hyperspectral feature extraction network to more effectively extract and optimize generalized features within the DIFSCL framework, significantly improving intra-class consistency and inter-class discriminative capability of features. Experimental results on three widely used HSI datasets demonstrate that our method significantly outperforms existing techniques in few-shot classification tasks.

In order to enhance the detection of maritime vessel targets, considering the causal relationship between the motion of vessels and their wakes, as well as the characteristics of ship wakes such as large diffusion range and distinctive features, this paper proposes a data-driven method based on Dynamic Mode Decomposition (DMD) for detecting and analyzing ship wakes in sea surface videos. The method, named Multi-dimensional Dynamic Mode Decomposition (MDDMD), segments the video sequence into smaller blocks and analyzes them at various resolution levels, effectively addressing the data analysis issues of large and complex systems. The MDDMD algorithm not only extracts key dynamic features but also reveals the intrinsic structure of the system at different scales, providing new perspectives for the in-depth understanding of nonlinear systems. Comparative experimental results with existing DMD and PCA algorithms demonstrate that the MDDMD algorithm has higher accuracy and robustness in ship wake detection. This study offers valuable insights for ship wake detection under complex maritime conditions and holds potential for practical application in the field of maritime surveillance.

Low-cost Laser Detection and Ranging (LiDAR) is crucial to three-dimensional (3D) imaging in applications such as remote sensing, target detection, and machine vision. In conventional nonscanning time-of-flight (TOF) LiDAR, the intensity map is obtained by a detector array and the depth map is measured in the time domain which requires costly sensors and short laser pulses. To overcome such limitations, this paper presents a nonscanning 3D laser imaging method that combines compressive sensing (CS) techniques and electro-optic modulation. In this novel scheme, electro-optic modulation is applied to map the range information into the intensity of echo pulses symmetrically and the measurements of pattern projection with symmetrical structure are received by the low bandwidth detector. The 3D imaging can be extracted from two gain modulated images that are recovered by solving underdetermined inverse problems. An integrated regularization model is proposed for the recovery problems and the minimization functional model is solved by a proposed algorithm applying the alternating direction method of multiplier (ADMM) technique. The simulation results on various subrates for 3D imaging indicate that our proposed method is feasible and achieves performance improvement over conventional methods in systems with hardware limitations. This novel method will be highly valuable for practical applications with advantages of low cost and flexible structure at wavelengths beyond visible spectrum.

Few-shot classification of hyperspectral images (HSI) faces the challenge of scarce labeled samples. Self-Supervised learning (SSL) and Few-Shot Learning (FSL) offer promising avenues to address this issue. However, existing methods often struggle to adapt to the spatial geometric diversity of HSIs and lack sufficient spectral prior knowledge. To tackle these challenges, we propose a method, Spectral-Spatial Self-Supervised Learning for Few-Shot Hyperspectral Image Classification (S4L-FSC), aimed at improving the performance of few-shot HSI classification. Specifically, we first leverage heterogeneous datasets to pretrain a spatial feature extractor using a designed Rotation-Mirror Self-Supervised Learning (RM-SSL) method, combined with FSL. This approach enables the model to learn the spatial geometric diversity of HSIs using rotation and mirroring labels as supervisory signals, while acquiring transferable spatial meta-knowledge through few-shot learning. Subsequently, homogeneous datasets are utilized to pretrain a spectral feature extractor via a combination of FSL and Masked Reconstruction Self-Supervised Learning (MR-SSL). The model learns to reconstruct original spectral information from randomly masked spectral vectors, inferring spectral dependencies. In parallel, FSL guides the model to extract pixel-level discriminative features, thereby embedding rich spectral priors into the model. This spectral-spatial pretraining method, along with the integration of knowledge from heterogeneous and homogeneous sources, significantly enhances model performance. Extensive experiments on four HSI datasets demonstrate the effectiveness and superiority of the proposed S4L-FSC approach for few-shot HSI classification.