Qi Wang

Unmanned Aerial Vehicle (UAV) object detection is a core technology for cross-modal, wide-area surveillance. However, operating at high altitudes under complex flight conditions imposes extreme physical constraints, generating massive sub-pixel targets, elongated morphologies, and dense object clustering. These challenges are critically important because conventional lightweight detectors deployed on edge devices often suffer from severe high-frequency edge loss during spatial downsampling, morphological distortion of anisotropic targets, and the mathematical suppression of weak feature gradients during cross-scale fusion, ultimately leading to severe missed detections. To overcome these inherent bottlenecks, this paper proposes WaveUAV-YOLO, a lightweight architecture prioritizing frequency-domain edge preservation and stable gradient propagation. First, a Wavelet High-Frequency Downsampling (WHFD) module augments standard convolutions by utilizing Haar wavelet decomposition to explicitly capture and compensate for the lost boundary cues of sub-pixel targets. Second, an Asymmetric Multi-scale Bottleneck without Dimensionality Compression (C2f_AMSB) cancels forced channel compression and introduces asymmetric convolutions to effectively adapt to elongated targets. Third, a Mean-Normalized Feature Aggregation (FFM_Concat) prevents deep background features from suppressing weak shallow signals during fusion. Extensive experiments on VisDrone2019, DIOR, NWPU, and HIT-UAV demonstrate that WaveUAV-YOLO (11.70 M parameters) achieves competitive or superior detection precision against recent lightweight UAV detectors. Furthermore, it achieves an end-to-end inference speed of ≈50 FPS on a standard desktop GPU, validating a favorable balance between sub-pixel detection reliability and computational efficiency for adverse UAV environments.

Object detection in remote sensing imagery plays an irreplaceable role in critical fields such as military reconnaissance and disaster monitoring. However, when dealing with minute targets characterised by an extremely low pixel proportion, a lack of textural information, and severe background interference, existing algorithms still face the challenge of balancing detection accuracy with computational efficiency. To address this, this paper proposes a lightweight frequency-domain-aware end-to-end detection model, LE-DETR, based on an improved version of RT-DETR. Firstly, a Lightweight Feature Extraction Module (LFEM) is designed. Through a heterogeneous dual-path architecture and reparameterisation techniques, it significantly reduces computational complexity whilst enhancing the capture of fine-grained spatial features. Secondly, an Efficient Spatio-Frequency Fusion Module (ESFFM) is introduced. This utilises a multi-head self-attention mechanism to construct a global view whilst combining the Fourier transform to reconstruct target features from a frequency-domain perspective, thereby effectively suppressing background noise and enhancing the target’s edge signals. Finally, we propose the Efficient Frequency-Aware Fusion Feature Pyramid Network (EFAM-FPN), which utilises SPD Conv to mitigate the loss of key features during downsampling and introduces a frequency-domain attention mechanism to suppress complex background noise, thereby improving the model’s detection accuracy for extremely small objects. The experimental results show that, whilst reducing the number of parameters by 41.7% compared to the baseline model, LE-DETR achieved improvements of 2.6%, 1.7% and 2.4%, respectively, in the mAP50 metric across the three mainstream remote sensing datasets—VisDrone2019, NWPU VHR-10 and DIOR. This demonstrates an effective balance between detection accuracy and inference efficiency, fully validating its robustness and practical value in complex remote sensing application scenarios.

Object detection in UAV imagery is hindered by micro-scale targets, dense distributions, and cluttered backgrounds, where existing detectors fail to simultaneously achieve high accuracy and real-time throughput. We propose ECP-YOLO, a lightweight framework built on YOLOv12s, incorporating four modules: Pinwheel Convolution (PConv) for direction-selective geometric modeling, a Context Refiner Block (CRB) for spatially gated background suppression, an Edge-Aware Attention Fusion Module (EAFM) for structural boundary preservation, and a Progressive Inter-Scale Feature Fusion (PISF) strategy for cascaded cross-scale detail propagation, alongside a high-resolution P2 detection head. On VisDrone2019, ECP-YOLO achieves 38.1% mAP@0.5 and 22.1% mAP@0.5:0.95, surpassing YOLOv12s by 6.3% and 3.5% at 79 FPS. On UAVDT, Precision improves from 27.0% to 34.1% and mAP@0.5 from 28.7% to 30.4%, demonstrating cross-dataset transferability. These results demonstrate that ECP-YOLO achieves competitive accuracy–efficiency trade-offs for real-time UAV detection in complex environments.

Plant disease detection in natural environments is significantly challenged by variations in lesion scales and interference from complicated background clutter. Nevertheless, current models often remain limited in effectively capturing multi-scale features and mitigating background interference simultaneously. To tackle these challenges, we present TGL-YOLO, an improved detection network built on the YOLO11 framework. Methodologically, we introduce the Tri-Scale Dynamic Block (TSDBlock) to adaptively extract fine-grained features across highly variable lesion sizes. Furthermore, a Gated Pyramid Spatial Transformer (GPST) is designed to fuse cross-scale features and suppress background interference, while a Large Separable Pyramid Attention (LSPA) module expands the spatial receptive field to capture global context. Experimental results on two public datasets show that TGL-YOLO demonstrates improved performance over the YOLO11s baseline. On the PlantDoc dataset, it improves mAP50 and mAP50:95 by 4.7% and 3.7%, reaching 0.591 and 0.449, respectively. On the FieldPlant dataset, it reaches 0.793 and 0.608, yielding improvements of 2.3% and 1.9%. The proposed method demonstrates the capability to reduce missed detections and false positives caused by multi-scale lesions and environmental noise, providing a competitive and computationally viable solution for agricultural disease monitoring in natural environments.

With the rapid advancement of remote sensing technology, target detection in remote sensing imagery plays a crucial role in military reconnaissance, urban planning, and other fields. However, there are problems such as large variations in target scale, arbitrary angles, and complex background interference in remote sensing images, making it difficult for existing target detection methods to achieve precise recognition and localization. To address these issues, this paper proposes a small target detection model for remote sensing images based on a dual-path attention mechanism and multi-scale frequency domain awareness. First, we propose the GDSC module, a gated deep separable spatial convolution module that enhances the extraction of local details and improves feature extraction efficiency. Additionally, the DAMF-DETR model uses a dual-path attention feature fusion module (DAFF) to capture fine details of densely packed small objects more effectively. We also introduce a novel and efficient multi-scale frequency domain pyramid network, termed EMSF-FPN, which employs multi-scale feature fusion and frequency domain attention mechanisms to focus on small object details, and maintains high detection accuracy even under low-contrast conditions. Finally, we introduce the Wise-Focaler-MPDIoU (WF-MPDIoU Loss), which dynamically adjusts weights using a scale factor to improve regression accuracy and accelerate convergence. Compared to the baseline model, DAMF-DETR achieves improvements of 4.1%, 3.6%, and 4.2% in the mAP50 metric on the VisDrone2019, NWPU VHR-10, and DOTA-v1.0 remote sensing image datasets, respectively, while reducing the number of parameters by 18.1%. These results demonstrate that DAMF-DETR enhances detection accuracy for small objects while maintaining a lightweight and efficient architecture.

Pinching-antenna systems (PASSs) offer a low-complexity and reconfigurable solution for near-field downlink communications by deploying multiple radiating elements along a single waveguide. Existing studies mainly assume simplified propagation conditions or focus on spectral efficiency, while the impact of environment-dependent interference patterns arising from user-specific blockage conditions on energy-efficient design remains unclear. An energy-efficient downlink design for single-waveguide PASS based on environment-division multiple access (EDMA) is investigated. Under a given propagation environment, EDMA exploits user-dependent blockage and visibility differences through proper pinching-antenna placement, thereby inducing different multi-user interference patterns without increasing radio-frequency hardware complexity. We examine how such blockage-dependent interference influences the relationship between spectral efficiency and energy efficiency, and develop an energy-aware EDMA framework that jointly considers pinching-antenna locations and transmit power allocation under quality-of-service constraints. The resulting coupled design problem is solved through an alternating optimization procedure. EDMA is compared with conventional time-division multiple access (TDMA) using a unified hardware and power-consumption model. Numerical results reveal clear energy-efficiency threshold behaviors with respect to blockage intensity, user population, and service requirements. The results further show that EDMA can significantly outperform TDMA in specific operating regimes.

To address the issues of poor adaptability to complex scenarios, high computational complexity, and difficulties in terminal deployment of existing steel surface defect detection models, a novel lightweight detection network named LHO-net is proposed, with the Lightweight Multi-Backbone (LM Backbone), the Hierarchical Scale-based Pyramid Attention Network (HSPAN), and the Occlusion-aware Detection Head (OAHead). The LM Backbone adopts a dual-branch structure with shared HGStem and a dynamic feature fusion mechanism, effectively capturing multi-dimensional features of irregular defects while extremely compressing model parameters. The HSPAN module realizes efficient fusion of multi-scale features through dynamic feature selection and adaptive upsampling strategies, balancing background noise suppression and defect detail preservation. The OAHead completes adaptive compensation of features in occluded regions by means of deep feature aggregation and exponential normalization technology, significantly enhancing the ability to recognize complex defects. On the NEU-DET dataset, LHO-net achieves a mAP@0.5 of 75.0%, a mAP@0.5:0.95 of 44.0%, and a recall of 73.6%, with a computational complexity of only 2.3 GFLOPS. Compared with the baseline model YOLOv12, it reduces parameters by 64% and computational cost by 60.3%. On the GC-10 dataset, its mAP@0.5 reaches 67.2%, and its detection stability for complex defects such as slender creases and low-contrast water spots is superior to that of mainstream lightweight YOLO variants. Visualization results confirm that the model can effectively avoid common problems such as redundant annotations and false detections and maintains stable recognition performance for various defects. It solves the core contradiction between detection accuracy and lightweight deployment in industrial scenarios, providing an efficient and practical technical solution for real-time steel surface defect detection on resource-constrained terminal devices.

With the rapid evolution of remote sensing earth observation technology, high-resolution object detection is crucial in military and civilian domains but faces challenges from expansive views and complex backgrounds. Small objects are particularly challenging due to their low pixel coverage, poor textures, and susceptibility to drastic illumination changes and background clutter. To address these problems, this paper proposes MDCA-YOLO for oriented object detection. A Dual-Branch Perception Module (DBPM) is designed utilizing a synergistic mechanism of large-kernel and strip convolutions to establish long-range dependencies, accurately capturing geometric features of tiny objects even in the absence of local details; Multi-Adaptive Selection Fusion (MASF) is proposed to address cross-scale feature loss by adaptively enhancing feature response while suppressing background noise; furthermore, a reconstructed decoupled detection head, CoordAttOBB, significantly improves angle regression accuracy while reducing complexity. Experimental results on the DIOR-R dataset show MDCA-YOLO surpasses YOLO11s, improving mAP50 and mAP50:95 by 2.5% and 2.7%, respectively, effectively proving the algorithm’s superiority in remote sensing tasks.

Pinching antenna systems (PASS) are waveguide-based antenna architectures featuring structural flexibility and high energy efficiency, making them attractive for indoor near-field communication (NFC). However, rich multipath propagation and spatial non-stationarity in practical indoor environments pose significant challenges to accurate channel estimation, especially under limited antenna activation and pilot resources. In this paper, the PASS channel estimation problem is reformulated from a generative inference perspective. A diffusion-model-driven channel estimation framework is proposed, where received signals are interpreted as noisy observations of latent near-field channel states, and channel estimation is performed via conditional reverse denoising diffusion. By exploiting waveguide-mediated near-field structures and sparse antenna activation, the proposed framework enables robust channel recovery in highly underdetermined settings. To better match indoor propagation characteristics, the diffusion-based inference emphasizes multipath-aware channel distributions, allowing joint modeling of deterministic waveguide effects and stochastic scattering, thereby alleviating model mismatch in conventional estimators. Simulation results show that the proposed method achieves stable channel estimation performance across different SNRs and antenna activation scales, while the computational complexity of the proposed framework is explicitly analyzed to assess its practical applicability.