Huinan Guo

Detecting unmanned aerial vehicles (UAVs) remains a difficult task, primarily due to their tiny size, rapid motion, and complex backgrounds. Fusing visible and infrared imagery offers complementary advantages for robust detection, yet existing methods rely on spatial feature aggregation that overlooks spectral disparities, coupling noise with textures. Moreover, the small scale and high dynamics of UAVs hinder standard convolution from decoupling target signals from background interference due to limited receptive fields. To solve these limitations, the Wavelet-guided Frequency–Spatial Decoupling Network (WFSD-Net) is designed for visible–infrared UAV detection. First, to tackle fusion noise, the Discrete Wavelet Band-Differentiated Fusion (DWBF) module is designed to explicitly decouple noise-dominant sub-bands from information-rich components by performing spectral decomposition. It aligns low-frequency distributions via adaptive spatial weighting and disentangles high-frequency details using physics-aware rules, achieving source-level noise suppression. Second, an Axial Strip Contextual Attention (ASCA) module is proposed. By utilizing anisotropic strip convolution via orthogonal decomposition, this module captures global contextual dependencies to effectively decouple weak target features from background clutter, enhancing the spatial position encoding capability for weak targets. Finally, the proposed WFSD-Net method is validated on Anti-UAV300 and Multi-Sensor and Multi-View Fixed-Wing UAV (MMFW-UAV) datasets, and experiments demonstrate that the proposed method is superior to existing state-of-the-art (SOTA) methods.

Remote sensing image super-resolution (RSISR) has gained significant attention in recent years due to its critical role in enhancing image analysis capabilities. While existing methods often focus on nonlocal feature extraction, they frequently overlook the importance of local information integration. Moreover, many methods reconstruct images by introducing more complex structures, which poses a challenge to resource-limited devices. To address these issues, we present a local–nonlocal dual-branch feature complementary fusion network (DFCFNet) featuring two key components: a lightweight dual-branch feature aggregation (DBFA) module and an Efficient Feed-Forward Network (EFFN). The DBFA employs a dual-branch structure comprising a Focused Local Feature Branch (FLFB) with novel Partial Convolution Channel Mixers for localized pattern modeling and a Non-Focal Exploration Branch (NFEB) utilizing global variance analysis for comprehensive feature extraction. This dual-branch design enables simultaneous capture of local and global contextual information. The EFFN is designed to further refine the features of the DBFA output in order to make full use of the detailed information of the image. Extensive experimental results show that the proposed DFCFNet reconstructs optimally on remote sensing datasets and is also optimal in terms of computational efficiency and network complexity. The framework’s versatility is further confirmed through successful adaptation to natural image SR tasks, showing consistent performance improvements across five standard datasets.

Infrared small target detection remains challenging in applications such as long-range surveillance and early warning due to the fact that infrared images rely on thermal radiation, which results in limited texture cues and a low signal-to-noise ratio for the targets. Although recent deep networks have improved representation capability, they often exhibit two persistent limitations. Fine target details are gradually weakened through successive downsampling, and edge-related priors are not sufficiently exploited to stabilize target responses under background interference. To alleviate these issues, an Edge-Prior Guided Dual-Branch Enhancement Network (EGDENet) is proposed, a dual-branch framework that injects edge priors into feature learning for infrared small target detection. An auxiliary edge-aware branch is introduced to complement the main encoder–decoder stream. Specifically, a Multi-directional Sobel Edge Extraction (MSEE) module is designed to adaptively reweight multi-directional edge responses, thereby strengthening boundary-sensitive representations. Furthermore, a Difference-Aware Gated Fusion (DAGF) module leverages Gated Spatial Convolution to capture subtle variations in the features and employs depthwise separable convolution along with adaptive enhancement to effectively integrate the extracted edge information. In addition, an Edge Pixel Integration (EPI) Loss is present to couple edge sensitivity with pixel-wise supervision. This loss improves the edge sensitivity of infrared small targets. The proposed EGDENet is evaluated on three benchmark datasets: NUAA-SIRST, IRSTD-1K, and SIRST-Aug. The experimental results show that our method outperforms or matches the performance of state-of-the-art methods.

With the increasing number of satellites and the growing complexity of space missions, accurate recognition of spacecraft components has become a critical requirement for on-orbit servicing tasks. However, existing deep learning-based methods often struggle to detect small-scale components due to the significant size disparity among different spacecraft parts, leading to recognition degradation. To address this issue, a Coordinate-Aware Multiscale Feature Fusion Network for Spacecraft Component Recognition(CAMFFN) is proposed in order to enhance multi-scale representation and spatial sensitivity. The proposed architecture comprises two key components: the Multi-branch Feature Enhancement Module(MFEM) and the Multi-scale Coordinate-aware Pyramid Aggregation Module(MCPAM). MFEM employs a multi-branch convolutional framework, which contains three parallel branches to capture fine-grained local texture and long-range context information simultaneously, aiming at enhancing spatial structure representation and directional sensitivity. MCPAM first extracts fused features through adaptive pyramid pooling and a hierarchical separable convolutional fusion operation, and then applied a coordinate attention mechanism to these fused features to precisely capture spatial dependencies along horizontal and vertical directions. Experimental results on two publicly available datasets, UESD and URSO, show that CAMFFN outperforms existing state-of-the-art methods, especially in the recognition of fine-grained and small-scale components such as instruments and thrusters.

Object detection in remote sensing images is crucial for airport management, hazard prevention, traffic monitoring, and more. The precise ability for object localization and identification enables remote sensing imagery to provide early warnings, mitigate risks, and offer strong support for decision-making processes. While traditional deep learning-based object detection techniques have achieved significant results in single-modal environments, their detection capabilities still encounter challenges when confronted with complex environments, such as adverse weather conditions or situations where objects are obscured. To overcome the limitations of existing fusion methods in terms of complexity and insufficient information utilization, we innovatively propose a Cosine Similarity-based Image Feature Fusion (CSIFF) module and integrate it into a dual-branch YOLOv8 network, constructing a lightweight and efficient target detection network called Multi-Modality YOLO Fusion Network (MMYFNet). This network utilizes cosine similarity to divide the original features into common features and specific features, which are then refined and fused through specific modules. Experimental and analytical results show that MMYFNet performs excellently on both the VEDAI and FLIR datasets, achieving mAP values of 80% and 76.8%, respectively. Further validation through parameter sensitivity experiments, ablation studies, and visual analyses confirms the effectiveness of the CSIFF module. MMYFNet achieves high detection accuracy with fewer parameters, and the CSIFF module, as a plug-and-play module, can be integrated into other CNN-based cross-modality network models, providing a new approach for object detection in remote sensing image fusion.

Infrared Small Target (IST) detection involves identifying objects that occupy fewer than 81pixels in a 256×256 image. Because the target is small and lacks texture, structure, and shape information on its surface, this task is highly challenging. CNN-based methods can extract rich features of the target. However, overly deep network structures may increase the risk of losing small targets. Additionally, pixel-level positional deviations can also reduce the detection accuracy of IST. To address these challenges, we propose the Location-Guided Dense Nested Attention Network (LG-DNANet) for IST detection. The proposed network consists of a Pixel Attention Guided Feature Extraction Module (PAG-FEM), a Channel Attention Guided Feature Fusion Module (CAG-FFM), and a detection module. Firstly, the pixel attention-guided feature extraction module utilizes the DNIM dense nested blocks from the DNANet as the backbone, integrating both channel and pixel attention mechanisms. This method focuses on the semantic and positional information of the targets, yielding semantic features that emphasize the positions of small targets. Secondly, the channel attention guided feature fusion module employs upsampling and convolution operations to align the feature sizes, while utilizing the channel attention mechanism to obtain effective channel information. Then, these features are fused through stacking, addition, and averaging operations to obtain more discriminative features. Finally, the detection module uses eight-connected neighborhood clustering method to obtain the centroid coordinates of the targets for subsequent detection evaluation.Three datasets are utilized to verify our method, and experimental results show that our method performs better than other advanced methods.

Remote-sensing image dehazing (RSID) is crucial for applications such as military surveillance and disaster assessment. However, current methods often rely on complex network architectures, compromising computational efficiency and scalability. Furthermore, the scarcity of annotated remote-sensing-dehazing datasets hinders model development. To address these issues, a Dual-View Knowledge Transfer (DVKT) framework is proposed to generate a lightweight and efficient student network by distilling knowledge from a pre-trained teacher network on natural image dehazing datasets. The DVKT framework includes two novel knowledge-transfer modules: Intra-layer Transfer (Intra-KT) and Inter-layer Knowledge Transfer (Inter-KT) modules. Specifically, the Intra-KT module is designed to correct the learning bias of the student network by distilling and transferring knowledge from a well-trained teacher network. The Inter-KT module is devised to distill and transfer knowledge about cross-layer correlations. This enables the student network to learn hierarchical and cross-layer dehazing knowledge from the teacher network, thereby extracting compact and effective features. Evaluation results on benchmark datasets demonstrate that the proposed DVKT framework achieves superior performance for RSID. In particular, the distilled model achieves a significant speedup with less than 6% of the parameters and computational cost of the original model, while maintaining a state-of-the-art dehazing performance.

Targeting the dynamic image-motion problem of aerial cameras in the process of swing imaging, the image-motion compensation technology of aerial cameras based on the multi-dimensional motion of the secondary mirror was adopted. The secondary mirror was used as the image-motion compensation element, and the comprehensive image-motion compensation of the aerial camera was realized through the multi-dimensional motion of the secondary mirror. However, in the process of compensating for the image motion, the secondary mirror would be eccentric and inclined, which would cause the secondary mirror to be off-axis and affect the image quality. Therefore, a misalignment optical system model was established to study the relationship between the deviation vector and the misalignment of the secondary mirror, and the influence of the secondary mirror’s motion on the distribution of the aberration was analyzed. In order to verify the image-motion compensation ability of the multi-dimensional motion of the secondary mirror, an experimental platform was built to conduct a laboratory imaging experiment and flight experiment on the aerial camera. The experimental results showed that the dynamic resolution of the aerial camera using the image-motion compensation technology could reach 74 lp/mm, and the image-motion compensation accuracy was better than 0.5 pixels, which met the design expectation. In conclusion, the image-motion compensation technology is expected to be applied to various high-precision optical imaging as well as optical detection systems.

In the athermal and apochromatic design of optical systems, the distribution of lens’ optical powers and the selection of optical glass and structural materials are crucial. In this paper, an athermal and apochromatic design method is proposed for optical systems with a long focal length, large relative aperture, and wide spectrum. Firstly, a complex optical system composed of multiple lenses is equivalent to a two-component, single-lens system consisting of a replacement and an equivalent lens group. The optical glass for the replacement lens group is selected based on weight and the principle of material replacement in the 3D glass diagram, thus achieving an athermal and apochromatic design. Secondly, an athermal and apochromatic optical system with a focal length of 130 mm, an F-number of 2.0, a spectral range of 480 nm~800 nm, a field of view angle of 22°, and an operating temperature of −40 °C~+60 °C is designed. The modulation transfer function (MTF) at each field of view is greater than 0.6 at 50 lp/mm in the −40 °C~+60 °C temperature range, and the secondary spectrum aberration is 0.0056 mm, which is within the focal depth range of the optical system.

Capturing images under extremely low-light conditions usually suffers from various types of noise due to the limited photon and low signal-to-noise ratio (SNR), which makes low-light denoising a challenging task in the field of imaging technology. Nevertheless, existing methods primarily focus on investigating the precise modeling of real noise distributions while neglecting improvements in the noise modeling capabilities of learning models. To address this situation, a novel self-adaptive deformable-convolution-based U-Net (SD-UNet) model is proposed in this paper. Firstly, deformable convolution is employed to tackle noise patterns with different geometries, thus extracting more reliable noise representations. After that, a self-adaptive learning block is proposed to enable the network to automatically select appropriate learning branches for noise with different scales. Finally, a novel structural loss function is leveraged to evaluate the difference between denoised and clean images. The experimental results on multiple public datasets validate the effectiveness of the proposed method.