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.

Deep learning, especially convolutional neural network (CNN) techniques, has been shown to have superior performance in ship classification, as have small-target recognition studies in safety inspections of hydraulic structures such as ports and dams. High-resolution synthetic aperture radar (SAR)-based maritime ship classification plays an increasingly important role in marine surveillance, marine rescue, and maritime ship management. To improve ship classification accuracy and training efficiency, we proposed a CNN-based ship classification method. Firstly, the image characteristics of different ship structures and the materials of ship SAR images were analyzed. We then constructed a ship SAR image dataset and performed preprocessing operations such as averaging. Combined with a classic neural network structure, we created a new convolutional module, namely, the Inception-Residual Controller (IRC) module. A convolutional neural network was built based on the IRC module to extract image features and establish a ship classification model. Finally, we conducted simulation experiments for ship classification and analyzed the experimental results for comparison. The experimental results showed that the average accuracy of ship classification of the model in this paper reached 98.71%, which was approximately 3% more accurate than the traditional network model and approximately 1% more accurate compared with other recently improved models. The new module also performed well in evaluation metrics, such as the recall rate, with accurate classifications. The model could satisfactorily describe different ship types. Therefore, it could be applied to marine ship classification management with the possibility of being extended to hydraulic building target recognition tasks.

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.