Due to the limited computational resources of portable devices, target detection models for drone detection face challenges in real-time deployment. To enhance the detection efficiency of low, slow, and small unmanned aerial vehicles (UAVs), this study introduces an efficient drone detection model based on YOLOv5s (EDU-YOLO), incorporating lightweight feature extraction and balanced feature fusion modules. The model employs the ShuffleNetV2 network and coordinate attention mechanisms to construct a lightweight backbone network, significantly reducing the number of model parameters. It also utilizes a bidirectional feature pyramid network and ghost convolutions to build a balanced neck network, enriching the model’s representational capacity. Additionally, a new loss function, EloU, replaces CIoU to improve the model’s positioning accuracy and accelerate network convergence. Experimental results indicate that, compared to the YOLOv5s algorithm, our model only experiences a minimal decrease in mAP by 1.1%, while reducing GFLOPs from 16.0 to 2.2 and increasing FPS from 153 to 188. This provides a substantial foundation for networked optoelectronic detection of UAVs and similar slow-moving aerial targets, expanding the defensive perimeter and enabling earlier warnings.
The compatibility of low infrared emission and wideband microwave absorption has drawn extensive attention, both theoretically and practically. In this paper, an infrared–radar-compatible stealth metasurface is designed using transparent conductive materials, namely indium tin oxide (ITO) and poly methacrylimide (PMI). The designed structure is a combination of a radar-absorbing layer (RAL) and a low-infrared-emission layer (IRSL), with an overall thickness of about 1.7 mm. It consists of three layers, a top-layer patch-type ITO frequency-selective surface, an intermediate layer of a four-fold rotationally symmetric ITO patterned structure, and a bottom reflective surface. The layers are separated by PMI. Simulation results show that the structure achieves over 90% broadband absorption in the microwave band from 7 to 58 GHz and low emissivity of 0.36 in the infrared band. In addition, due to the four-fold rotationally symmetric design, the structure also exhibits polarization insensitivity and excellent angular stability. Therefore, the designed structure possesses ultra-broadband radar absorption performance, low infrared emissivity, and polarization-insensitive properties at a thin thickness, and has a promising application in the field of multi-band-compatible stealth technology.
Ship detection is critical for maritime traffic management, as infrared imaging in complex marine environments encounters significant challenges, such as strong background interference and weak target features. Thus, we propose EISD-YOLO (Efficient Infrared Ship Detection-YOLO), a high-performance lightweight algorithm specifically designed for infrared ship detection. The algorithm aims to improve detection accuracy while simultaneously reducing model parameters and enhancing computational efficiency. It integrates three core architectural innovations: first, we optimized the backbone C3k2 module by replacing the traditional bottleneck with a PEMA block to significantly reduce the parameter count; second, we integrated a lightweight DS_ADNet module, using depth-wise separable convolution to reduce parameters and alleviate computational load while maintaining robust feature representation; and third, we adopted the DyTAHead detection head, which integrates classification and localization features through dynamic task alignment, thereby achieving robust performance in complex infrared ship detection scenarios. The experimental results on the IRShip dataset demonstrate that, compared with YOLOv11n, EISD-YOLO reduced the parameters by 48.83%, while mAP@0.50, precision, and recall all increased by 1.2%. This breaks the traditional rule that lightweight models inevitably lead to reduced accuracy. Additionally, the model size reduced from 10.1 MB to 5.7 MB, which highlights its enhanced computational efficiency and practical applicability in maritime deployment scenarios.
Complex marine infrared images, which suffer from background interference, blurred features, and indistinct contours, hamper detection accuracy. Meanwhile, the limited computing power, storage, and energy of maritime devices require target detection models suitable for real-time detection. To address these issues, we propose DSEE-YOLO (Dynamic Ship Edge-Enhanced YOLO), an efficient lightweight infrared ship detection algorithm. It integrates three innovative modules with pruning and self-distillation: the C3k2_MultiScaleEdgeFusion module replaces the original bottleneck with a MultiEdgeFusion structure to boost edge feature expression; the lightweight DS_ADown module uses DSConv (depthwise separable convolution) to reduce parameters while preserving feature capability; and the DyTaskHead dynamically aligns classification and localization features through task decomposition. Redundant structures are pruned via LAMP (Layer-Adaptive Sparsity for the Magnitude-Based Pruning), and performance is optimized via BCKD (Bridging Cross-Task Protocol Inconsistency for Knowledge Distillation) self-distillation, yielding a lightweight, efficient model. Experimental results show the DSEE-YOLO outperforms YOLOv11n when applied to our self-constructed IRShip dataset by reducing parameters by 42.3% and model size from 10.1 MB to 3.5 MB while increasing mAP@0.50 by 2.8%, mAP@0.50:0.95 by 3.8%, precision by 2.3%, and recall by 3.0%. These results validate its high-precision detection capability and lightweight advantages in complex infrared scenarios, offering an efficient solution for real-time maritime infrared ship monitoring.
In recent years, unmanned aerial vehicles (UAVs) have become increasingly prevalent across diverse application scenarios due to their high maneuverability, compact size, and cost-effectiveness. However, these advantages also introduce significant challenges for UAV detection in complex environments. This paper proposes an efficient feature perception network (EFPNet) for UAV detection, developed on the foundation of the RT-DETR framework. Specifically, a dual-branch HiLo-ConvMix attention (HCM-Attn) mechanism and a pyramid sparse feature transformer network (PSFT-Net) are introduced, along with the integration of a DySample dynamic upsampling module. The HCM-Attn module facilitates interaction between high- and low-frequency information, effectively suppressing background noise interference. The PSFT-Net is designed to leverage deep-level features to guide the encoding and fusion of shallow features, thereby enhancing the model’s capability to perceive UAV texture characteristics. Furthermore, the integrated DySample dynamic upsampling module ensures efficient reconstruction and restoration of feature representations. On the TIB and Drone-vs-Bird datasets, the proposed EFPNet achieves mAP50 scores of 94.1% and 98.1%, representing improvements of 3.2% and 1.9% over the baseline models, respectively. Our experimental results demonstrate the effectiveness of the proposed method for small UAV detection.
Vanadium dioxide (VO2) is a highly promising material for infrared laser protection due to the pronounced optical switching effect during its metal–insulator transition (MIT). However, due to the relatively high MIT temperature of VO2 and the low transmittance contrast before and after the MIT, practical applications face challenges in modulation depth and response time. In this study, we address these issues using a wafer-scale VO2/GaN/Al2O3 heterostructure fabricated by oxide molecular beam epitaxy. The conductive GaN interlayer enables local Joule heating of the VO2 film, permitting direct control of the MIT via an external bias with a threshold of 4.7 V. This structure exhibits a substantial resistance change of four orders of magnitude and enables adaptive limiting of a 3.7 μm laser, reducing transmittance from 60% to 10%. Our work demonstrates a practical, wafer-scale laser-protection device and introduces a pre-excitation strategy via external biasing to enhance response performance.