Search Results (40)

Aiming at the core pain point that in existing object detection models, it is difficult to balance detection accuracy and real-time inference efficiency on edge computing devices in UAV-based intelligent inspection of power transmission lines, this paper proposes a lightweight YOLO-PowerLiteV2 model for anomaly target detection in power transmission lines to address the shortcomings of YOLO-PowerLite. Based on YOLO11n as the baseline, the model achieves compression of model volume while guaranteeing detection performance through four core improvements: the C3k2-UIB lightweight backbone module, the MCA (Multi-scale Cross-Axis) attention mechanism, the MBConv lightweight detection head, and the MFM (Modulation Feature Fusion) module. Experiments were conducted on a dataset constructed from 5563 aerial images of transmission lines containing three types of targets: bird nests, defective insulators, and balloons. The results show that YOLO-PowerLiteV2 achieves a mAP@50 of 95.2%, with only 0.97 M parameters and 2.8 G floating point operations (FLOPs). Compared with the baseline model, the number of parameters is reduced by 62.5%, and FLOPs are decreased by 56.25%. On the NVIDIA Jetson Xavier NX edge platform, the model achieves 59.5 FPS with only 16.8 ms latency, outperforming the baseline by 31% in frame rate. Its comprehensive performance outperforms mainstream lightweight detection models. The model demonstrates excellent adaptability to UAV edge-terminal deployment requirements, thereby providing technical support for real-time intelligent inspection of power transmission lines. Full article

This article presents the design, implementation, and experimental validation of an autonomous drone system for search and rescue operations in cluttered GNSS-denied environments. The proposed platform integrates advanced navigation, mapping, and victim-detection capabilities, leveraging a suite of RGB-D cameras and edge-AI computation for real-time perception and decision-making. A key contribution is the integration of an eye-blink-detection pipeline for onboard assessment of the consciousness states of detected victims, enabling the drone to prioritize rescue efforts based on victim alertness. The system employs a modular software architecture with a pipeline that combines a U-Net segmentation network with a MultiScaleLSTM classifier, achieving approximately 97.73% accuracy and a combined inference latency of 6.35 ms on the NVIDIA Jetson Xavier-NX. Experimental results demonstrate the drone’s ability to autonomously explore unknown environments, accurately detect and classify victims, and operate effectively in real-world scenarios. The article also discusses observed challenges, such as computational bottlenecks and false positive detections, and outlines future directions for improving system robustness and autonomy. Full article

Ensuring the structural integrity and operational safety of oil and gas pipelines is a critical challenge due to their extensive geographical coverage and exposure to environmental and anthropogenic risks. Traditional inspection approaches including ground patrols and manned aerial surveys are labor-intensive, costly, and often lack real-time responsiveness. While unmanned aerial vehicles (UAVs) enable flexible and high-resolution monitoring, their practical deployment requires lightweight, robust detection models capable of real-time inference on embedded edge hardware under heterogeneous environmental conditions. This paper presents an end-to-end, edge-deployable UAV inspection framework for simultaneous detection of above-ground pipelines and visually observable anomaly/leak indicators using the official Ultralytics YOLOv26n object detector. A curated dataset of 6127 UAV images acquired across desert, semi-urban, and industrial environments was annotated with two classes (Pipeline and Anomaly/Leak) and partitioned into training 87.5%, validation 8.3%, and testing 4.2% subsets. The detector was fine-tuned from COCO-pretrained weights for 300 epochs at 600 × 600 resolution and evaluated using COCO-style metrics. On the held-out test set, the proposed model achieved 92.4% mAP@0.5 and 75.0% mAP@0.5:0.95, with 89.7% precision, 90.2% recall, and 89.9% F1-score at the selected operating threshold. Optimized TensorRT deployment on an NVIDIA Jetson Xavier NX sustained real-time inference at 18 FPS, demonstrating suitability for onboard UAV processing. Rather than proposing a new detector architecture, the study contributes a domain-specific annotated UAV dataset, deployment-oriented benchmarking, and an end-to-end edge inference workflow for corridor-scale monitoring. The proposed framework can help reduce environmental contamination risk and improve personnel safety during pipeline inspection. Full article

The precise, real-time delineation of rice lodging areas constitutes a fundamental prerequisite for the adaptive operation of unmanned combine harvesters. However, existing deep learning methods struggle to resolve a critical limitation: achieving an optimal equilibrium between robust regional morphological perception—which is crucial for irregular lodging patterns—and the ultra-low computational overhead demanded by resource-constrained edge terminals. To address this specific constraint, StarNet-RiceSeg is proposed as a lightweight semantic segmentation network explicitly tailored for unmanned harvesters. Initially, the architecture incorporates the minimalist StarNet as its backbone. By leveraging the unique “Star Operation,” it implicitly maps features into a high-dimensional nonlinear space, thereby significantly augmenting feature discriminability while drastically curtailing computational overhead. Furthermore, to mitigate the misdetection issues stemming from the textural similarity between lodged and upright rice, the Rice Spatial Attention (RSA) module was designed. By intensifying feature interaction within the spatial dimension, this module steers the network to focus on the cohesive morphology of lodged regions while effectively suppressing background noise. Experiments conducted on a self-constructed high-resolution rice lodging dataset demonstrate that StarNet-RiceSeg achieves a mIoU of 94.42%, significantly outperforming mainstream models such as U-Net, DeepLabV3+, SegNet and HRNet. Notably, the model maintains a compact footprint with only 8.01 million parameters and a computational load as low as 9.32 GFLOPs. Following optimization with TensorRT, the system achieved a real-time inference speed of 32.51 FPS on the NVIDIA Jetson Xavier NX embedded platform. These results indicate that StarNet-RiceSeg provides a high-precision, low-latency solution for perceiving rice lodging areas in complex field environments, facilitating unmanned precision harvesting. Full article

Severe foliage occlusion and dynamically changing lighting conditions in complex orchard environments pose significant challenges for visual perception systems in automated apple harvesting, including low detection accuracy, poor robustness, and insufficient real-time performance. To address these issues, this study proposes an improved lightweight detection network based on YOLOv11, named YOLO-WBL, along with a precise yield estimation algorithm based on 3D point clouds, termed CLV. The YOLO-WBL network is optimized in three aspects: (1) A C3K2_WT module integrating wavelet transform is introduced into the backbone network to enhance multi-scale feature extraction capability; (2) A weighted bidirectional feature pyramid network (BiFPN) is adopted in the neck network to improve the efficiency of multi-scale feature fusion; (3) A lightweight shared convolution separated batch normalization detection head (Detect-SCGN) is designed to significantly reduce the parameter count while maintaining accuracy. Based on this detection model, the CLV algorithm deeply integrates depth camera point cloud information through 3D coordinate mapping, irregular point cloud reconstruction, and convex hull volume calculation to achieve accurate estimation of individual fruit volume and total yield. Experimental results demonstrate that: (1) The YOLO-WBL model achieves a precision of 93.8%, recall of 79.3%, and mean average precision (mAP@0.5) of 87.2% on the apple test set; (2) The model size is only 3.72 MB, a reduction of 28.87% compared to the baseline model; (3) When deployed on an NVIDIA Jetson Xavier NX edge device, its inference speed reaches 8.7 FPS, meeting real-time requirements; (4) In scenarios with an occlusion rate below 40%, the mean absolute percentage error (MAPE) of yield estimation can be controlled within 8%. Experimental validation was conducted using apple images selected from the dataset under varying lighting intensities and fruit occlusion conditions. The results demonstrate that the CLV algorithm significantly outperforms traditional average-weight-based estimation methods. This study provides an efficient, accurate, and deployable visual solution for intelligent apple harvesting and yield estimation in complex orchard environments, offering practical reference value for advancing smart orchard production. Full article

Unmanned Aerial Vehicles provide a cost-effective solution for water environment monitoring, yet detecting floating litter remains challenging due to small target scales, complex geometries, and severe surface interferences. To bridge the data deficiency in this domain, this study introduces UAV-Flow, a multi-scenario benchmark dataset wherein small-scale targets constitute 78.9%. Building upon this foundation, we propose the Floating Litter Detection Network (FLD-Net), a lightweight, real-time detection framework tailored for edge deployment. Adopting a progressive optimization paradigm, FLD-Net integrates three cascaded enhancement modules to achieve holistic performance gains across feature extraction, cross-scale fusion, and noise suppression. Specifically, the Deformation Feature Extraction Module (DFEM) enhances backbone adaptability to small targets and non-rigid deformations; the Dynamic Cross-scale Fusion Network (DCFN) facilitates efficient cross-scale semantic fusion via content-aware upsampling and an asymmetric topology; and the Dual-domain Anti-noise Attention (DANA) mechanism achieves discriminative decoupling between target semantics and structural noise through spatial-channel interaction. Experimental results on UAV-Flow demonstrate that FLD-Net achieves an mAP₅₀ of 80.47%. Compared to the YOLOv11s baseline, it improves Recall and mAP₅₀ by 11.66% and 8.51%, respectively, with only 9.9 M parameters. Furthermore, deployment on the NVIDIA Jetson Xavier NX yields an inference latency of 14 ms and an energy efficiency of 4.80 FPS/W, confirming the system’s robustness and viability for automated pollution monitoring. Full article

To address the issues of a low single-seed qualification index and a high missed-seeding index in the process of leafy vegetable plug seedling sowing, this study proposes a lightweight seeding performance detection model named VS-YOLO based on YOLO11n. The model is then deployed on the edge device, the NVIDIA Jetson Xavier NX. A concise and intuitive graphical user interface (GUI) was developed and an automated detection system for vegetable seeding performance was constructed. Based on the empty cells identified by the system, a real-time data transmission mechanism between the Jetson device and a PLC-based control unit is established, enabling the intelligent reseeding device to perform precise reseeding at the designated cell location, achieving row-wise and cell-specific intelligent planting. VS-YOLO incorporates several innovative improvements, including the introduction of a Context Anchor Attention (CAA) module to form the C2PSA_CAA module, the adoption of the Wise Intersection over Union version 3 (WIoU v3) loss function, and the addition of an extra-small object detection head. These enhancements significantly improve the classification and recognition capability for small-sized vegetable seeds while notably reducing the number of model parameters. Experimental results show that VS-YOLO achieves a mAP@0.5 of 96.5% and an F1 Score of 93.45% in detecting the seeding performance of three types of vegetable seeds, outperforming YOLO11n’s 91.5% and 85.19% by 5.0% and 8.26%. The parameter count of VS-YOLO is only 1.61 M, which is 37.6% lower than YOLO11n’s 2.58 M, making it lightweight. Operating at a productivity rate of 120 trays per hour, the system achieved an accuracy of 99.03%, 89.83%, and 92.26% for single-seed prediction, multiple-seeding prediction, and missed-seeding prediction. The single-seed qualification index and missed-seeding index were 93.43% and 4.68%. After reseeding, these indices improved to 97.61% and 0.32%, representing an increase of 4.18% in the single-seed qualification index and a decrease of 4.36% in the missed-seeding index. The significant enhancement offers new ideas and technical approaches for the advancement of seeding performance detection and reseeding systems for vegetable plug seedling production. Full article

Early detection of small-scale fires is crucial for minimizing damage and enabling rapid emergency response. While recent deep learning-based fire detection systems have achieved high accuracy, they still face three key challenges: (1) limited deployability in resource-constrained edge environments due to high computational costs, (2) performance degradation caused by feature interference when jointly learning flame and smoke features in a single backbone, and (3) low sensitivity to small flames and thin smoke in the initial stages. To address these issues, we propose a lightweight dual-stream fire detection architecture based on YOLOv5n, which learns flame and smoke features separately to improve both accuracy and efficiency under strict edge constraints. The proposed method integrates two specialized attention modules: ESCFM++, which enhances spatial and channel discrimination for sharp boundaries and local flame structures (flame), and ESCFM-RS, which captures low-contrast, diffuse smoke patterns through depthwise convolutions and residual scaling (smoke). On the D-Fire dataset, the flame detector achieved 74.5% mAP@50 with only 1.89 M parameters, while the smoke detector achieved 89.2% mAP@50. When deployed on an NVIDIA Jetson Xavier NX (NVIDIA Corporation, Santa Clara, CA, USA)., the system achieved 59.7 FPS (single-stream) and 28.3 FPS (dual-tream) with GPU utilization below 90% and power consumption under 17 W. Under identical on-device conditions, it outperforms YOLOv9t and YOLOv12n by 36–62% in FPS and 0.7–2.0% in detection accuracy. We further validate deployment via outdoor day/night long-range live-stream tests on Jetson using our flame detector, showing reliable capture of small, distant flames that appear as tiny cues on the screen, particularly in challenging daytime scenes. These results demonstrate overall that modality-specific stream specialization and ESCFM attention reduce feature interference while improving detection accuracy and computational efficiency for real-time edge-device fire monitoring. Full article

Driver distraction, particularly mobile phone use while driving, remains one of the leading causes of road traffic incidents worldwide. In response to this issue and leveraging recent technological advances and increased access to intelligent systems, this research presents the development of an application running on an intelligent embedded architecture for the automatic detection of mobile phone use by drivers, integrating computer vision, inertial sensing, and edge computing. The system, based on the YOLOv8n model deployed on a Jetson Xavier NX 16Gb—Nvidia, combines real-time inference with an inertial activation mechanism and cloud storage via Firebase Firestore, enabling event capture and traceability through a lightweight web-based HMI interface. The proposed solution achieved an overall accuracy of 81%, an inference rate of 12.8 FPS, and an average power consumption of 8.4 W, demonstrating a balanced trade-off between performance, energy efficiency, and thermal stability. Experimental tests under diverse driving scenarios validated the effectiveness of the system, with its best performance recorded during daytime driving—83.3% correct detections—attributed to stable illumination and enhanced edge discriminability. These results confirm the feasibility of embedded artificial intelligence systems as effective tools for preventing driver distraction and advancing intelligent road safety. Full article

To address issues such as slow response speed and low detection accuracy in fallen walnut picking robots in complex orchard environments, this paper proposes a detection and path planning method that integrates star-shaped lightweight convolution with NDT-RRT. The method includes the improved lightweight detection model YOLO-FW and an efficient path planning algorithm NDT-RRT. YOLO-FW enhances feature extraction by integrating star-shaped convolution (Star Blocks) and the C3K2 module in the backbone network, while the introduction of a multi-level scale pyramid structure (CA_HSFPN) in the neck network improves multi-scale feature fusion. Additionally, the loss function is replaced with the PIoU loss, which incorporates the concept of Inner-IoU, thus improving regression accuracy while maintaining the model’s lightweight nature. The NDT-RRT path planning algorithm builds upon the RRT algorithm by employing node rejection strategies, dynamic step-size adjustment, and target-bias sampling, which reduces planning time while maintaining path quality. Experiments show that, compared to the baseline model, the YOLO-FW model achieves precision, recall, and mAP@0.5 of 90.6%, 90.4%, and 95.7%, respectively, with a volume of only 3.62 MB and a 30.65% reduction in the number of parameters. The NDT-RRT algorithm reduces search time by 87.71% under conditions of relatively optimal paths. Furthermore, a detection and planning system was developed based on the PySide6 framework on an NVIDIA Jetson Xavier NX embedded device. On-site testing demonstrated that the system exhibits good robustness, high precision, and real-time performance in real orchard environments, providing an effective technological reference for the intelligent operation of fallen walnut picking robots. Full article

The automation of quality control in agricultural food processing, particularly the detection of incomplete peeling in taro, constitutes a critical frontier for ensuring food safety and optimizing production efficiency in the Industry 4.0 era. However, this domain is fraught with significant technical challenges, primarily stemming from the inherent visual characteristics of residual peel: extremely minute scales relative to the vegetable body, highly irregular morphological variations, and the dense occlusion of objects on industrial conveyor belts. To address these persistent impediments, this study introduces a comprehensive solution comprising a specialized dataset and a novel detection architecture. We established the Taro Peel Industrial Dataset (TPID), a rigorously annotated collection of 18,341 high-density instances reflecting real-world production conditions. Building upon this foundation, we propose MDB-YOLO, a lightweight, multi-dimensional bionic detection model evolved from the YOLOv8s architecture. The MDB-YOLO framework integrates a synergistic set of innovations designed to resolve specific detection bottlenecks. To mitigate the conflict between background texture interference and tiny target detection, we integrated the C2f_EMA module with a Wise-IoU (WIoU) loss function, a combination that significantly enhances feature response to low-contrast residues while reducing the penalty on low-quality anchor boxes through a dynamic non-monotonic focusing mechanism. To effectively manage irregular peel shapes, a dynamic feature processing chain was constructed utilizing DySample for morphology-aware upsampling, BiFPN_Concat2 for weighted multi-scale fusion, and ODConv2d for geometric preservation. Furthermore, to address the issue of missed detections caused by dense occlusion in industrial stacking scenarios, Soft-NMS was implemented to replace traditional greedy suppression mechanisms. Experimental validation demonstrates the superiority of the proposed framework. MDB-YOLO achieves a mean Average Precision (mAP50-95) of 69.7% and a Recall of 88.0%, significantly outperforming the baseline YOLOv8s and advanced transformer-based models like RT-DETR-L. Crucially, the model maintains high operational efficiency, achieving an inference speed of 1.1 ms on an NVIDIA A100 and reaching 27 FPS on an NVIDIA Jetson Xavier NX using INT8 quantization. These findings confirm that MDB-YOLO provides a robust, high-precision, and cost-effective solution for real-time quality control in agricultural food processing, marking a significant advancement in the application of computer vision to complex biological targets. Full article

For unmanned aerial vehicle (UAV) ground crew marshalling tasks, the accuracy of skeleton-based action recognition is often limited by the high similarity of motion patterns across action categories as well as variations in individual performance. To address this issue, we propose an adaptive refined graph convolutional network with enhanced features for action recognition. First, a multi-order and motion feature modeling module is constructed, which integrates joint positions, skeletal structures, and angular encodings for multi-granularity representation. Static-domain and dynamic-domain features are then fused to enhance the diversity and expressiveness of the input representations. Second, a data-driven adaptive graph convolution module is designed, where inter-joint interactions are dynamically modeled through a learnable topology. Furthermore, an adaptive refinement feature activation mechanism is introduced to optimize information flow between nodes, enabling fine-grained modeling of skeletal spatial information. Finally, a frame-index semantic temporal modeling module is incorporated, where joint-type semantics and frame-index semantics are introduced in the spatial and temporal dimensions, respectively, to capture the temporal evolution of actions and comprehensively exploit spatio-temporal semantic correlations. On the NTU-RGB+D 60 and NTU-RGB+D 120 benchmark datasets, the proposed method achieves accuracies of 89.4% and 94.2% under X-Sub and X-View settings, respectively, as well as 81.7% and 83.3% on the respective benchmarks. On the self-constructed UAV Airfield Ground Crew Dataset, the proposed method attains accuracies of 90.71% and 96.09% under X-Sub and HO settings, respectively. Environmental robustness experiments demonstrate that under complex environmental conditions including illumination variations, haze, rain, shadows, and occlusions, the adoption of the Test + Train strategy reduces the maximum performance degradation from 3.1 percentage points to within 1 percentage point. Real-time performance testing shows that the system achieves an end-to-end inference latency of 24.5 ms (40.8 FPS) on the edge device NVIDIA Jetson Xavier NX, meeting real-time processing requirements and validating the efficiency and practicality of the proposed method on edge computing platforms. Full article

To address the challenges of real-time monitoring via highway vehicle-mounted cameras—specifically, the difficulty in detecting distant pedestrians and vehicles in real time—this study proposes an enhanced object detection algorithm, YOLOv5s-F. Firstly, the FasterNet network structure is adopted to improve the model’s runtime speed. Secondly, the attention mechanism BRA, which is derived from the Transformer algorithm, and a 160 × 160 small-object detection layer are introduced to enhance small target detection performance. Thirdly, the improved upsampling operator CARAFE is incorporated to boost the localization and classification accuracy of small objects. Finally, Focal EIoU is employed as the localization loss function to accelerate model training convergence. Quantitative experiments on high-speed sequences show that Focal EIoU reduces bounding box jitter by 42.9% and improves tracking stability (consecutive frame overlap) by 11.4% compared to CIoU, while accelerating convergence by 17.6%. Results show that compared with the YOLOv5s baseline network, the proposed algorithm reduces computational complexity and parameter count by 10.1% and 24.6%, respectively, while increasing detection speed and accuracy by 15.4% and 2.1%. Transfer learning experiments on the VisDrone2019 and Highway-100k dataset demonstrate that the algorithm outperforms YOLOv5s in average precision across all target categories. On NVIDIA Jetson Xavier NX, YOLOv5s-F achieves 32 FPS after quantization, meeting the real-time requirements of in-vehicle monitoring. The YOLOv5s-F algorithm not only meets the real-time detection and accuracy requirements for small objects but also exhibits strong generalization capabilities. This study clarifies core challenges in highway small-target detection and achieves accuracy–speed improvements via three key innovations, with all experiments being reproducible. If any researchers need the code and dataset of this study, they can consult the author through email. Full article

Accurate real-time detection of hawthorn by vision systems is a fundamental prerequisite for automated harvesting. This study addresses the challenges in hawthorn orchards—including target overlap, leaf occlusion, and environmental variations—which lead to compromised detection accuracy, high computational resource demands, and poor real-time performance in existing methods. To overcome these limitations, we propose YOLO-DCL (group shuffling convolution and coordinate attention integrated with a lightweight head based on YOLOv8n), a novel lightweight hawthorn detection model. The backbone network employs dynamic group shuffling convolution (DGCST) for efficient and effective feature extraction. Within the neck network, coordinate attention (CA) is integrated into the feature pyramid network (FPN), forming an enhanced multi-scale feature pyramid network (HSPFN); this integration further optimizes the C2f structure. The detection head is designed utilizing shared convolution and batch normalization to streamline computation. Additionally, the PIoUv2 (powerful intersection over union version 2) loss function is introduced to significantly reduce model complexity. Experimental validation demonstrates that YOLO-DCL achieves a precision of 91.6%, recall of 90.1%, and mean average precision (mAP) of 95.6%, while simultaneously reducing the model size to 2.46 MB with only 1.2 million parameters and 4.8 GFLOPs computational cost. To rigorously assess real-world applicability, we developed and deployed a detection system based on the PySide6 framework on an NVIDIA Jetson Xavier NX edge device. Field testing validated the model’s robustness, high accuracy, and real-time performance, confirming its suitability for integration into harvesting robots operating in practical orchard environments. Full article

The present-day issues related to the cotton-growing industry, namely yield estimation, pest effect, and growth phase diagnostics, call for integrated, scalable monitoring solutions. This write-up reveals Cotton Multitask Learning (CMTL), a transformer-driven multitask framework that launches three major agronomic tasks from UAV pictures at one go: boll detection, pest damage segmentation, and phenological stage classification. CMTL does not change separate pipelines, but rather merges these goals using a Cross-Level Multi-Granular Encoder (CLMGE) and a Multitask Self-Distilled Attention Fusion (MSDAF) module that both allow mutual learning across tasks and still keep their specific features. The biologically guided Stage Consistency Loss is the part of the architecture of the network that enables the system to carry out growth stage transitions that occur in reality. We executed CMTL on a tri-source UAV dataset that fused over 2100 labeled images from public and private collections, representing a variety of crop stages and conditions. The model showed its virtues state-of-the-art baselines in all the tasks: setting 0.913 mAP for boll detection, 0.832 IoU for pest segmentation, and 0.936 accuracy for growth stage classification. Additionally, it runs at the fastest speed of performance on edge devices such as NVIDIA Jetson Xavier NX (Manufactured in Shanghai, China), which makes it ideal for deployment. These outcomes evoke CMTL’s promise as a single and productive instrument of aerial crop intelligence in precision cotton agriculture. Full article