Search Results (1,880)

This study was conducted to address the demand for interpretable intelligent recognition of fruit tree diseases in smart horticultural environments. A KAD-Former framework integrating an agricultural knowledge graph with a visual Transformer was proposed and systematically validated through extensive cross-regional, multi-variety, and multi-disease experiments. The primary objective of this work was to overcome the limitations of conventional deep models, including insufficient interpretability, unstable recognition of weak disease features, and poor cross-regional generalization. In the experimental evaluation, the model achieved significant advantages across multiple representative tasks: in the overall performance comparison, KAD-Former reached an accuracy of $0.946$, an F1-score of $0.933$, and a mAP of $0.938$, outperforming classical models such as ResNet50, EfficientNet, and Swin-T. In the cross-regional generalization assessment, a DGS of $0.933$ was obtained, notably surpassing competing models. In terms of explainability consistency, a Consistency@5 score of $0.826$ indicated strong alignment between the model’s attention regions and expert annotations. The ablation experiments further demonstrated that the three core modules—AKG (agricultural knowledge graph), SAM (semantic alignment module), and KGA (knowledge-guided attention)—each contributed substantially to final performance, with the complete model exhibiting the best results. These findings collectively demonstrate the comprehensive advantages of KAD-Former in disease classification, symptom localization, model interpretability, and cross-domain transfer. The proposed method not only achieved state-of-the-art performance in pure visual tasks but also advanced knowledge-enhanced and interpretable reasoning by emulating the diagnostic logic employed by agricultural experts in real orchard scenarios. Through the integration of the agricultural knowledge graph, semantic alignment, and knowledge-guided attention, the model maintained stable performance under challenging conditions such as complex illumination, background noise, and weak lesion features, while exhibiting strong robustness in cross-region and cross-variety transfer tests. Furthermore, the experimental results indicated that the approach enhanced fine-grained recognition capabilities for various fruit tree diseases, including apple ring rot, brown spot, powdery mildew, and downy mildew. Full article

Maritime vision systems for unmanned surface vehicles confront challenges in small-object detection, specular reflections and low-light conditions. This paper introduces WA-YOLO, a water-aware training framework that incorporates lightweight attention modules (ECA/CBAM) to enhance the model’s discriminative capacity for small objects and critical features, particularly against cluttered water ripples and glare backgrounds; employs advanced bounding box regression losses (e.g., SIoU) to improve localization stability and convergence efficiency under wave disturbances; systematically explores the efficacy trade-off between high-resolution input and tiled inference strategies to tackle small-object detection, significantly boosting small-object recall (APS) while carefully evaluating the impact on real-time performance on embedded devices; and introduces physically inspired data augmentation techniques for low-light and strong-reflection scenarios, compelling the model to learn more robust feature representations under extreme optical variations. WA-YOLO achieves a compelling +2.1% improvement in mAP@0.5 and a +6.3% gain in APS over YOLOv8 across three test sets. When benchmarked against the advanced RT-DETR model, WA-YOLO not only surpasses its detection accuracy (0.7286 mAP@0.5) but crucially maintains real-time performance at 118 FPS on workstations and 17 FPS on embedded devices, achieving a superior balance between precision and efficiency. Our approach offers a simple, reproducible and readily deployable solution, with full code and pre-trained models publicly released. Full article

Multi-sensor fusion represents a primary approach for enhancing environmental perception in intelligent transportation scenes. Among diverse fusion strategies, Bird’s-Eye View (BEV) perspective-based fusion methods have emerged as a prominent research focus owing to advantages such as unified spatial representation. However, current BEV fusion methods still face challenges with insufficient robustness in cross-modal alignment and weak perception of dynamic objects. To address these challenges, this paper proposes a Bidirectional Complementary Cross-Attention Module (BCCA), which achieves deep fusion of image and point cloud features by adaptively learning cross-modal attention weights, thereby significantly improving cross-modal information interaction. Secondly, we propose a Temporal Adaptive Fusion Module (TAFusion). This module effectively incorporates temporal information within the BEV space and enables efficient fusion of multi-modal features across different frames through a two-stage alignment strategy, substantially enhancing the model’s ability to perceive dynamic objects. Based on the above, we integrate these two modules to propose the Dual Temporal and Transversal Attention Network (DTTANet), a novel camera and LiDAR fusion framework. Comprehensive experiments demonstrate that our proposed method achieves improvements of 1.42% in mAP and 1.26% in NDS on the nuScenes dataset compared to baseline networks, effectively advancing the development of 3D object detection technology for intelligent transportation scenes. Full article

Anti-UAV detection is paramount for safeguarding airspace security. However, existing methodologies often exhibit low detection accuracy due to their inability to adaptively address target scale variations and complex backgrounds. To enhance detection precision, this paper introduces a UAV detection method founded on non-local feature learning. Initially, we design a Cross-scale Non-local Feature Interaction (CNFI) module. This module explicitly models long-range dependencies between features at disparate scales, thereby effectively integrating multi-scale information and adapting to target scale variations. Subsequently, a Non-local Feature Enhancement (NFE) module is proposed, which fuses global contextual information, acquired via non-local attention, with low-level structural cues such as gradients, to bolster the boundary and detail features of UAV targets amidst complex backgrounds. The proposed method was experimentally validated on the DUT-Anti-UAV and Det-Fly dataset. In comparison with the state-of-the-art model, our approach demonstrates improvements of 0.93%, 1.09%, and 2.12% in Precision (P), Recall (R), and mAP50 on DUT-Anti-UAV dataset, respectively. Experimental results affirm that our proposed enhancements yield superior performance in the anti-UAV detection task. Full article

A 3D multi-modal detection method using a monocular camera and LiDAR has drawn much attention due to its low cost and strong applicability, making it highly valuable for autonomous driving and unmanned aerial vehicles (UAVs). However, conventional fusion approaches relying on static arithmetic operations often fail to adapt to dynamic, complex scenarios. Furthermore, existing ROI alignment techniques, such as local projection and cross-attention, are inadequate for mitigating the feature misalignment triggered by depth estimation noise in pseudo-point clouds. To address these issues, this paper proposes a pseudo-point-based 3D object detection method that achieves biased fusion of multi-modal data. First, a meta-weight fusion module dynamically generates fusion weights based on global context, adaptively balancing the contributions of point clouds and images. Second, a module combining bidirectional cross-attention and a gating filter mechanism is introduced to eliminate the ROI feature misalignment caused by depth completion noise. Finally, a class-agnostic box fusion strategy is introduced to aggregate highly overlapping detection boxes at the decision level, improving localization accuracy. Experiments on the KITTI dataset show that the proposed method achieves APs of 92.22%, 85.03%, and 82.25% on Easy, Moderate, and Hard difficulty levels, respectively, demonstrating leading performance. Ablation studies further validate the effectiveness and computational efficiency of each module. Full article

Azidophenylselenylation (APS) of glycals is a straightforward transformation for preparing phenylseleno 2-azido-2-deoxy derivatives, which are useful blocks in the synthesis of 2-amino-2-deoxy-glycoside-containing oligosaccharides. However, the previously developed APS methods employing the CH₂Cl₂ as solvent, Ph₂Se₂-PhI(OAc)₂ (commonly known as BAIB), and a source of N₃⁻ are still not universal and show limited efficiency for glycals with gluco- and galacto-configurations. To address this limitation, we revisited both heterogeneous (using NaN₃) and homogeneous (using TMSN₃) APS approaches and optimized the reaction conditions. We found that glycal substrates with galacto- and gluco-configurations require distinct conditions. Galacto-substrates react relatively rapidly, and their conversion depends mainly on efficient azide-ion transfer into the organic phase, which is promoted by nitrile solvents (CH₃CN, EtCN). In contrast, for the slower gluco-configured substrates, complete conversion requires a non-polar solvent still capable of azide-ion transfer, such as benzene. These observations were applied to the optimized synthesis of phenylseleno 2-azido-2-deoxy derivatives of d-galactose, d-glucose, l-fucose, l-quinovose, and l-rhamnose. Full article

Synthetic Aperture Radar (SAR) target detection faces significant challenges including speckle noise interference, weak small object features, and multi-category imbalance. To address these issues, this paper proposes LSDA-YOLO, an enhanced SAR target detection framework built upon the YOLO architecture that integrates Large Kernel Attention and SimAM dual attention mechanisms. Our method effectively overcomes these challenges by synergistically combining global context modeling and local detail enhancement to improve robustness and accuracy. Notably, this framework leverages the inherent symmetry properties of typical SAR targets (e.g., geometric symmetry of ships and bridges) to strengthen feature consistency, thereby reducing interference from asymmetric background clutter. By replacing the baseline C2PSA module with Deformable Large Kernel Attention and incorporating parameter-free SimAM attention throughout the detection network, our approach achieves improved detection accuracy while maintaining computational efficiency. The deformable large kernel attention module expands the receptive field through synergistic integration of deformable and dilated convolutions, enhancing geometric modeling for complex-shaped targets. Simultaneously, the SimAM attention mechanism enables adaptive feature enhancement across channel and spatial dimensions based on visual neuroscience principles, effectively improving discriminability for small targets in noisy SAR environments. Experimental results on the RSAR dataset demonstrate that LSDA-YOLO achieves 80.8% mAP50, 53.2% mAP50-95, and 77.6% F1 score, with computational complexity of 7.3 GFLOPS, showing significant improvement over baseline models and other attention variants while maintaining lightweight characteristics suitable for real-time applications. Full article

This research article presents a novel road defect detection methodology that integrates deep learning techniques and a federated learning approach. Existing road defect detection systems heavily rely on manual inspection and sensor-based techniques, which are prone to errors. To overcome these limitations, a data-acquisition system utilizing a GoPro HERO 9 camera was used to capture high-quality videos and images of road surfaces. A comprehensive dataset consist of multiple road defects, such as cracks, potholes, and uneven surfaces, that were pre-processed and augmented to prepare them for effective model training. A Real-Time Detection Transformer-based architecture model was used that achieved mAP50 of 99.60% and mAP50-95 of 99.55% in cross-validation of road defect detection and object detection tasks. Federated learning helped to train the model in a decentralized manner that enhanced data protection and scalability. The proposed system achieves higher detection accuracy for road defects by increasing speed and efficiency while enhancing scalability, which makes it a potential asset for real-time monitoring. Full article

Traffic sign detection is crucial for intelligent transportation and autonomous driving, yet faces challenges such as illumination variations, occlusions, and scale changes that impact accuracy. To address these issues, the paper proposes the LSTM-CA-YOLOv11 model. This approach pioneers the integration of a Bi-LSTM (Bi-directional Long-Short Term Memory) into the YOLOv11 backbone network to model spatial-sequence dependencies, thereby enhancing structured feature extraction capabilities. The lightweight CA (Coordinate Attention) module encodes precise positional information by capturing horizontal and vertical features. The MSEF (Multi-Scale Enhancement Fusion) module addresses scale variations through parallel convolutional and pooling branches with adaptive fusion processing. We further introduce the SPP-Plus (Spatial Pyramid Pooling-Plus) module to expand the receptive field while preserving fine details, and employ a focus IoU (Intersection over Union) loss to prioritise challenging samples, thereby improving regression accuracy. On a private dataset comprising 10,231 images, experiments demonstrate that this model achieves a mAP@0.5 of 93.4% and a mAP@0.5:0.95 of 79.5%, representing improvements of 5.3% and 4.7% over the baseline, respectively. Furthermore, the model’s generalisation performance on the public TT100K (Tsinghua-Tencent 100K) dataset surpassed the latest YOLOv13n by 5.3% in mAP@0.5 and 3.9% in mAP@0.5:0.95, demonstrating robust cross-dataset capabilities and exceptional practical deployment feasibility. Full article

The work aims to leverage computer vision and artificial intelligence technologies to quantify key components in food catering services. Specifically, it focuses on content identification and portion size estimation in a dining hall setting, typical of corporate and educational settings. An RGB camera is employed to capture the tray delivery process in a self-service restaurant, providing test images for content identification algorithm comparison, using standard evaluation metrics. The approach utilizes the YOLO architecture, a widely recognized deep learning model for object detection and computer vision. The model is trained on labeled image data, and its performance is assessed using a precision–recall curve at a confidence threshold of 0.5, achieving a mean Average Precision (mAP) of 0.873, indicating robust overall performance. The weight estimation procedure combines computer vision techniques to measure food volume using both RGB and depth cameras. Subsequently, density models specific to each food type are applied to estimate the detected food weight. The estimation model’s parameters are calibrated through experiments that generate volume-to-weight conversion tables for different food items. Validation of the system was conducted using rice and chicken, yielding error margins of 5.07% and 3.75%, respectively, demonstrating the feasibility and accuracy of the proposed method. Full article

With the rapid development of Unmanned Aerial Vehicle (UAV) technology, it plays an increasingly important role in electrical power inspection. Automated approaches that generate inspection waypoints based on tower features have emerged in recent years. However, these solutions commonly rely on tower coordinates, which can be difficult to obtain at times. To address this issue, this study presents an autonomous inspection waypoint generation method based on object detection. The main contributions are as follows: (1) After acquiring and constructing the distribution tower dataset, we propose a lightweight object detector based on You Only Look Once (YOLOv8). The model integrates the Generalized Efficient Layer Aggregation Network (GELAN) module in the backbone to reduce model parameters and incorporates Powerful Intersection over Union (PIoU) to enhance the accuracy of bounding box regression. (2) Based on detection results, a three-stage waypoint generator is designed: Stage 1 estimates the initial tower’s coordinates and altitude; Stage 2 refines these estimates; and Stage 3 determines the positions of subsequent towers. The generator ultimately provides the target’s position and heading information, enabling the UAV to perform inspection maneuvers. Compared to classic models, the proposed model runs at 56 Frames Per Second (FPS) and achieves an approximate 2.1% improvement in mAP50:95. In addition, the proposed waypoint estimator achieves tower position estimation errors within 0.8 m and azimuth angle errors within 0.01 rad. Multiple consecutive tower inspection flights in actual environments further validate the effectiveness of the proposed method. The proposed method’s effectiveness is validated through actual flight tests involving multiple consecutive distribution towers. Full article

The rapid advancement of high-resolution remote sensing technology has significantly expanded observational capabilities in the oil and gas sector, enabling more precise identification of petroleum infrastructure. Remote sensing now plays a critical role in providing real-time, continuous monitoring. Manual interpretation remains the predominant approach, yet is plagued by multiple limitations. To overcome the limitations of manual interpretation in large-scale monitoring of upstream petroleum assets, this study develops an end-to-end, deep learning-driven framework for intelligent extraction of key oilfield targets from high-resolution remote sensing imagery. Specific aims are as follows: (1) To leverage temporal diversity in imagery to construct a representative training dataset. (2) To automate multi-class detection of well sites, production discharge pools, and storage facilities with high precision. This study proposes an intelligent monitoring framework based on deep learning for the automatic extraction of petroleum-related features from high-resolution remote sensing imagery. Leveraging the temporal richness of multi-temporal satellite data, a geolocation-based sampling strategy was adopted to construct a dedicated petroleum remote sensing dataset. The dataset comprises over 8000 images and more than 30,000 annotated targets across three key classes: well pads, production ponds, and storage facilities. Four state-of-the-art object detection models were evaluated—two-stage frameworks (Faster R-CNN, Mask R-CNN) and single-stage algorithms (YOLOv3, YOLOv4)—with the integration of transfer learning to improve accuracy, generalization, and robustness. Experimental results demonstrate that two-stage detectors significantly outperform their single-stage counterparts in terms of mean Average Precision (mAP). Specifically, the Mask R-CNN model, enhanced through transfer learning, achieved an mAP of 89.2% across all classes, exceeding the best-performing single-stage model (YOLOv4) by 11 percentage points. This performance gap highlights the trade-off between speed and accuracy inherent in single-shot detection models, which prioritize real-time inference at the expense of precision. Additionally, comparative analysis among similar architectures confirmed that newer versions (e.g., YOLOv4 over YOLOv3) and the incorporation of transfer learning consistently yield accuracy improvements of 2–4%, underscoring its effectiveness in remote sensing applications. Three oilfield areas were selected for practical application. The results indicate that the constructed model can automatically extract multiple target categories simultaneously, with average detection accuracies of 84% for well sites and 77% for production ponds. For multi-class targets over 100 square kilometers, manual detection previously required one day but now takes only one hour. Full article

In operations involving the replacement of shield machine disc cutters, challenges such as limited space, poor lighting, and slurry contamination frequently lead to occlusions and incomplete data when using direct point cloud-based localization for disc cutter bolts. To overcome these issues, this study introduces an indirect visual localization technique for bolts that utilizes image-point cloud fusion. Initially, an SCMamba-YOLO instance segmentation model is developed to extract feature surface masks from the cutterbox. This model, trained on the self-constructed HCB-Dataset, delivers a mAP50 of 90.7% and a mAP50-95 of 82.2%, which indicates a strong balance between its accuracy and real-time performance. Following this, a non-overlapping point cloud registration framework that integrates image and point cloud data is established. By linking dual-camera coordinate systems and applying filtering through feature surface masks, essential corner coordinates are identified for pose calibration, allowing for the estimation of the three-dimensional coordinates of the bolts. Experimental results demonstrate that the proposed method achieves a localization error of less than 2 mm in both ideal and simulated tunnel environments, significantly enhancing stability in low-overlap and complex settings. This approach offers a viable technical foundation for the precise operation of shield disc cutter changing robots and the intelligent advancement of tunnel boring equipment. Full article

Against the backdrop of growing demand for rapid soil testing technologies in precision agriculture, this study proposes a detection method based on pyrolysis-electronic nose and machine olfaction signal analysis to achieve precise measurement of key soil nutrients. An electronic nose system comprising 10 metal oxide semiconductor gas sensors was constructed to collect response signals from 112 black soil samples undergoing pyrolysis at 400 °C. By extracting time-domain and frequency-domain features from sensor responses, an initial dataset of 180 features was constructed. A novel feature fusion method combining Pearson correlation coefficients (PCC) with recursive feature elimination cross-validation (RFECV) was proposed to optimize the feature space, enhance representational power, and select key sensitive features. In predicting soil organic matter (SOM), total nitrogen (TN), available potassium (AK), and available phosphorus (AP) content, we compared support vector machines (SVM), support vector machine-random forest models (SVM-RF), and particle swarm optimization-enhanced support vector machine-random forest models (PSO-SVM-RF). Results indicate that PSO-SVM-RF demonstrated optimal performance across all nutrient predictions, achieving a coefficient of determination (R²) of 0.94 for SOM and TN, with a performance-to-bias ratio (RPD) exceeding 3.8. For AK and AP, R² improved to 0.78 and 0.74, respectively. Compared to the SVM model, the root mean square error (RMSE) decreased by 25.4% and 21.6% for AK and AP, respectively, with RPD values approaching the practical threshold of 2.0. This study validated the feasibility and application potential of combining electronic nose technology with a time-frequency domain feature fusion strategy for precise quantitative analysis of soil nutrients, providing a new approach for soil fertility assessment in precision agriculture. Full article

Detecting active failures is important for the Industrial Internet of Things (IIoT). The IIoT aims to connect devices and machinery across industries. The devices connect via the Internet and provide large amounts of data which, when processed, can generate information and even make automated decisions on the administration of industries. However, traditional active fault management techniques face significant challenges, including highly imbalanced datasets, a limited availability of failure data, and poor generalization to real-world conditions. These issues hinder the effectiveness of prompt and accurate fault detection in real IIoT environments. To overcome these challenges, this work proposes a data augmentation mechanism which integrates generative adversarial networks (GANs) and the synthetic minority oversampling technique (SMOTE). The integrated GAN-SMOTE method increases minority class data by generating failure patterns that closely resemble industrial conditions, increasing model robustness and mitigating data imbalances. Consequently, the dataset is well balanced and suitable for the robust training and validation of learning models. Then, the data are used to train and evaluate a variety of models, including deep learning architectures, such as convolutional neural networks (CNNs) and long short-term memory networks (LSTMs), and conventional machine learning models, such as support vector machines (SVMs), K-nearest neighbors (KNN), and decision trees. The proposed mechanism provides an end-to-end framework that is validated on both generated and real-world industrial datasets. In particular, the evaluation is performed using the AI4I, Secom and APS datasets, which enable comprehensive testing in different fault scenarios. The proposed scheme improves the usability of the model and supports its deployment in a real IIoT environment. The improved detection performance of the integrated GAN-SMOTE framework effectively addresses fault classification challenges. This newly proposed mechanism enhances the classification accuracy up to 0.99. The proposed GAN-SMOTE framework effectively overcomes the major limitations of traditional fault detection approaches and proposes a robust, scalable and practical solution for intelligent maintenance systems in the IIoT environment. Full article