Yanyan Wang

Introduction: A core bottleneck of forestry remote sensing lies in accurate, real-time pine wilt disease monitoring on UAV-borne edge hardware, which suffers from constrained computing capacity and complicated field forest backgrounds. To fill this technical gap, we developed an ultra-lightweight real-time detection architecture named Edge-Forest YOLO in this work. Methods: Methods: Built upon the baseline YOLOv8n network, three targeted optimizations were embedded into the proposed model: (1) a domain-adaptive data augmentation workflow to mitigate poor generalization induced by variable illumination and uneven lesion sizes in complex woodland; (2) scale-aware asymmetric channel redistribution, cutting 37.5% shallow channels and expanding 75% deep channels to remove redundant spatial features and strengthen high-level pathological feature extraction; (3) Cross-layer ECA attention adopting 1D convolution to capture inter-channel correlation and concentrate on diseased regions with minimal computation overhead. All model validation was performed on the public high-resolution UAV pine wilt PDT dataset. Results: Edge-Forest YOLO only occupies 2.31 M storage with mAP@0.5 up to 92.7%. Its single-image inference costs 4.2 ms on regular computing equipment and runs at around 26 FPS on the Jetson Nano edge platform. Compared with YOLOv8s and customized YOLO-DP, our model cuts over half parameter quantity while retaining competitive detection precision. Discussion: The proposed lightweight detector supplies a low-power, practically deployable solution for on-board UAV real-time forest disease monitoring, supporting rapid in-field pine wilt diagnosis and facilitating scientific decision-making for forest health management and disease prevention.

Traditional surface defect detection methods for solid wood panels have gradually exposed many drawbacks, such as poor performance of the detection model, low detection efficiency, and the scarcity of defect detection models applied to wood, which are difficult to meet the increasing production demand. In order to address the above problems, this paper proposes a TL-ResNet50 (Transfer Learning, abbreviated as TL) method for surface defect detection of solid wood panels by integrating the attention mechanism. First, the TL-ResNet50 model is constructed by introducing transfer learning, which improves the feature extraction capability and detection accuracy of the model compared with the ResNet50 model. Secondly, the SE (Squeeze-and-Excitation) and CBAM (Convolutional Block Attention Module) modules were integrated, and through ablation experiments, it was found that the TL-ResNet50-SE model was able to effectively capture the local and global features of the wood surface, thus improving the defect detection accuracy. The accuracy of defect detection is improved. Finally, the performance of classical models ResNet50, VGG16, AlexNet, EfficientNetV2, and the improved TL-ResNet50 model is systematically evaluated by comparing and analyzing the performance of each model in the wood defect detection task. The detection accuracy of the proposed model is 88.2%, which significantly improves the accuracy of surface defect detection of solid wood panels compared with other models.

Underwater imaging is affected by spatially varying blur caused by water flow turbulence, light scattering, and camera motion, resulting in severe visual quality loss and diminished performance in downstream vision tasks. Although numerous underwater image enhancement methods have been proposed, the issue of addressing non-uniform blur under realistic underwater conditions remains largely underexplored. To bridge this gap, we propose PMSPNet, a Progressive Multi-Scale Perception Network, designed to handle underwater non-uniform blur. The network integrates a Hybrid Interaction Attention Module to enable precise modeling of feature ambiguity directions and regional disparities. In addition, a Progressive Motion-Aware Perception Branch is employed to capture spatial orientation variations in blurred regions, progressively refining the localization of blur-related features. A Progressive Feature Feedback Block is incorporated to enhance reconstruction quality by leveraging iterative feature feedback across scales. To facilitate robust evaluation, we construct the Non-uniform Underwater Blur Benchmark, which comprises diverse real-world blur patterns. Extensive experiments on multiple real-world underwater datasets demonstrate that PMSPNet consistently surpasses state-of-the-art methods, achieving on average 25.51 dB PSNR and an inference speed of 0.01 s, which provides high-quality visual perception and downstream application input from underwater sensors for underwater robots, marine ecological monitoring, and inspection tasks.

The increasing application of underwater robotic systems in deep-sea exploration, inspection, and resource extraction has created a strong demand for reliable visual perception under challenging conditions. However, image quality is severely degraded in low-light underwater environments due to the combined effects of light absorption and scattering, resulting in color imbalance, low contrast, and illumination instability. These factors limit the effectiveness of visual-based autonomous operations. We propose ATS-UGAN, a Dual-domain Adaptive Synergy Generative Adversarial Network for low-light underwater image enhancement to confront the above issues. The network integrates Multi-scale Hybrid Attention (MHA) that synergizes spatial and frequency domain representations to capture key image features adaptively. An Adaptive Parameterized Convolution (AP-Conv) module is introduced to handle non-uniform scattering by dynamically adjusting convolution kernels through a multi-branch design. In addition, a Dynamic Content-aware Markovian Discriminator (DCMD) is employed to perceive the dual-domain information synergistically, enhancing image texture realism and improving color correction. Extensive experiments on benchmark underwater datasets demonstrate that ATS-UGAN surpasses state-of-the-art approaches, achieving 28.7/0.92 PSNR/SSIM on EUVP and 28.2/0.91 on UFO-120. Additional reference and no-reference metrics further confirm the improved visual quality and realism of the enhanced images.