Small target detection is a crucial research field, where small targets in large field-of-view scenarios approximate point targets. This letter presents an event-driven temporal profile evaluation method for detecting dim moving point targets with low signal-to-noise ratio (SNR). First, the method utilizes high-dimensional statistical distribution distance (HSD) to project pixel-level temporal signal features to a higher dimensional feature, identifying potential target pixels throughon/offevents triggered by the HSD. Second, the proposed peak-valley feature evaluation index (PVFEI) is designed to detect peak and valley features in the HSD of target-present pixels. It incorporates adaptive threshold segmentation to detect dim-moving point targets effectively. Experimental results demonstrate that the proposed method effectively balances detection accuracy and computational efficiency, providing a promising solution for detecting dim moving point targets.

Infrared (IR) small target detection is a central technology used in IR detection systems. However, it is challenging to quickly and accurately detect small targets of different sizes and shapes in complex scenes. In this letter, we propose a method based on energy difference and structural difference measurement (EDASDM) for the fast detection of small IR targets. First, based on a center-edge distribution, we categorize the target into central and edge regions to perform the novel three-layer window measurement (NTWM) and extract target candidate pixels. Subsequently, target and background clutter are further distinguished by their energy difference (ED) and structural difference (SD). Second, the small IR targets of different sizes and shapes are extracted using adaptive threshold segmentation. The experimental results showed that our algorithm achieves superior detection and real-time performance to some state-of-the-art algorithms.

Hyperspectral images (HSIs) are widely used as data formats for remote sensing. Correspondingly, the spectral super-resolution (SSR) technique used to generate high-spatial-resolution HSIs from high-spatial-resolution remote sensing multispectral images (MSIs) has emerged as a popular research topic owing to its high costs and hardware requirements. Generally, existing SSR methods obtain an HSI from the MSI of natural scenes. However, these methods barely learn the complex spectra found in remote sensing images and lack effective treatments for the degradation phenomenon in remote sensing scenes. In this study, a spectral-learning-based transformer network composed of a spectral-response-function (SRF)-guided multilevel feature extraction module (MFEM) and spectral nonlinear mapping learning module (NMLM) is cascaded. The NMLM uses different blocks to gradually learn spatial and spectral information from remote sensing images. Additionally, we focus on atmospheric effects and other factors that influence the generation of remote sensing images and design an MFEM to eliminate these effects. To augment the spectral dimension, an SRF is precisely added to the MFEM as a guide. Experimental results on the Obita Hyperspectral Satellites, Pavia Center, and Washington DC Mall datasets reveal that our method outperforms other state-of-the-art methods in terms of the root mean square error, mean relative absolute error, and relative root mean square error.

Remote sensing images (RSIs) are limited by low-resolution imaging and a variety of degradation effects, posing significant challenges for high-level visual tasks. Traditional deep learning-based super-resolution (SR) algorithms struggle to optimize these issues end-to-end, which inhibits the algorithm’s lightweight design and restricts its application in real-time scenarios. To address this, we introduce a multi-branch attention integration network (MAIN) for the degraded RSI SR. This network features two key functional components: the multi-scale feature perception (MsFP) module and the multi-branch attention integration block (MAIB). The MsFP module, a lightweight convolution-based architecture, is designed primarily to counteract degradation effects and depict low-dimensional features. MAIB, a multi-branch parallel layout, employs attention mechanisms to enable high-level semantic information extraction and context-aware learning. Furthermore, we utilize modulation transfer functions to emulate various degradation effects, thus creating a dedicated dataset for degraded RSI SR, called DeRSSA. Extensive experimental evidence shows that MAIN exceeds the performance of the existing state-of-the-art method for the degraded RSI SR task. Our code and dataset will be accessible at https://github.com/lbo0928/MAIN.

Remote sensing image ship fine-grained classification is a challenging vision problem due to factors such as inter-class similarity, real-world image scarcity, and class imbalance. Data augmentation aims to solve these problems from the data perspective. Most of these methods cannot work effectively in complex scenes, which restricts their practical application. Here, we propose a novel data augmentation pipeline based on local-aware image translation to achieve the representation mapping between cross-domain corresponding instances. Our pipeline contains three modules: Imaging Simulation System (ISS), Local-aware Progressive Image-to-Image Translation (LoPIT), and Image Harmonization (IH) modules. The ISS module generates simulated images with correct appearance and diverse features based on the input requirement information. To tackle the domain gap between simulated image and real-world image, we propose the Local-aware CycleGAN in the LoPIT module to achieve mapping based on local-aware learning and apply two sub-modules to progressively complete the remote sensing image global cross-domain translation. The IH module uses image harmonization technology to coordinate the visual appearance between the foreground and background to generate sufficient remote sensing ship images with precise representation, photorealistic style, and harmonious features. Moreover, we present a mixed dataset including real-world images and our synthetic images for remote sensing image fine-grained ship classification. Our dataset named RSSA-12 contains 12 categories of ship targets in 3831 images with high-quality annotated category labels, effectively alleviating the long-tail problem of existing datasets. Experimental results demonstrate that our progressive pipeline outperforms the state-of-the-art data augmentation method on the remote sensing fine-grained ship classification task.

This paper presents an approach for the detection of moving point targets on high frame-rate image sequences in situations when the spatial signal of the target is swamped by noise. A high frame-rate based moving point target detection framework is proposed, in which a target detector is used for analyzing the time domain evolution of image sequences for distinguishing between background and target, and a statistic based target detection model is used for target detection. The method is evaluated using both simulated and real-world high frame-rate data and we provide a comparison to other widely used point target detection approaches. Our experimental results demonstrate that the proposed framework can be used for robust moving point target detection in very low SNR.

This letter presents an approach for the detection of moving point targets on high-frame-rate image sequences with low spatial resolution and low SNR based on higher order statistical theory. We propose a novel method for analyzing the time-domain evolution of image data for distinguishing between the background and the target in situations when the spatial signal of the target is swamped by noise. Our method is formulated to detect a time-domain transient signal of unknown scale and arrival time in noisy background. We proposed a bispectrum-based model to characterize the temporal behavior of pixels, and the detection ability under different frame rates and SNRs is analyzed. The method is evaluated using both simulated and real-world data, and we provide a comparison to other widely used point target detection approaches. Our experimental results demonstrate that our algorithm can efficiently detect extremely low SNR targets that are virtually invisible to humans based on time-domain analysis of image sequences.