Search Results (519)

Despite over two decades of advancement in object detection, achieving high accuracy for small target detection in practical applications remains an unresolved challenge. This paper proposes a novel small-object detection model to address this issue. The model incorporates three key innovations: first, the RCSOSA module, which optimizes feature information transmission through dynamic channel interaction and multi-scale feature coordination; second, the HFPN module, a three-branch multi-scale feature fusion network that integrates local and global features by combining CNN and Transformer architectures to enhance semantic details; and third, the NWD-CIoU loss function, which dynamically adjusts the weights of NWD and CIoU losses based on the training phase. Experimental results on the COCO dataset demonstrate that our model improves detection accuracy by 4% over YOLOv11 and achieves state-of-the-art performance among mainstream models while maintaining a real-time inference speed of no less than 60 FPS. Furthermore, validation on the VisDrone dataset confirms the model’s strong generalization capability. The proposed algorithm significantly enhances small target detection accuracy, effectively mitigating a critical limitation in current practical object detection applications. Full article

The rapid proliferation of low-altitude drones has led to increasingly congested and heterogeneous electromagnetic environments, posing significant challenges to fine-grained spectrum awareness and reliable drone management. Specific emitter identification (SEI), which exploits inherent hardware-dependent radio frequency fingerprints, provides an effective physical-layer solution for emitter-level discrimination. However, practical SEI systems often suffer from two critical issues: extremely limited labeled samples for newly emerging emitters and heterogeneous data distributions collected by geographically distributed receivers with mismatched label spaces. To address these challenges, this paper proposes a heterogeneous federated learning (HFL)-based framework for few-shot specific emitter identification (FS-SEI). The proposed framework decouples feature embedding learning from task-specific classification and enables collaborative representation learning across distributed receivers without sharing raw signal data. A metric learning-based training strategy is adopted, where only the feature embedding models are aggregated in the federated process, effectively alleviating the impact of label space mismatch by utilizing center loss and an improved triplet loss. Moreover, two federated optimization schemes, namely gradient averaging (GA) and model averaging (MA), are systematically investigated to analyze their effectiveness under fully heterogeneous settings. Extensive experiments conducted on a real-world dataset demonstrate that the proposed HFL framework significantly outperforms isolated local training. In particular, the GA-based scheme achieves a few-shot identification performance that closely approaches centralized learning while preserving data privacy and robustness against data heterogeneity. The results validate the effectiveness of the proposed approach for practical FS-SEI in low-altitude drone management scenarios. Full article

Drones have proven effective for acquiring aerial imagery, and when equipped with onboard analysis tools, they can automatically identify objects of interest. Neural-network methods for image analysis typically require large training datasets and substantial computational resources. By contrast, algorithmic techniques can detect objects using simple features, such as pixel colors, thereby reducing the need for extensive training and computational resources. Once trained, both types of system can analyze images in a short time. In our experiments, each approach has distinct strengths. The YOLO-based detector is more accurate for complex-shaped objects, such as trees, whereas the pixel-color approach performs better on sparser objects. This paper proposes YOLO-C3, a hybrid system designed for onboard drone image processing. By leveraging the strengths of both YOLO-based and pixel-based approaches, YOLO-C3 balances detection accuracy with estimation confidence. Trained on Mediterranean imagery dataset, the system is optimized for identifying natural objects, including citrus groves and trees.To assess the robustness of the image classifier, a K-fold cross-validation is performed.Compared to existing models, YOLO-C3 detects a wider range of natural objects with high accuracy and minimal latency, achieving a processing speed of 0.01 s per image. By performing object detection locally, drones can adapt their trajectories to support emergency response, helping to map safe corridors and locate buildings where people may be awaiting rescue after a natural disaster. Full article

Unmanned Aerial Systems (UAS) offer sustainable solutions for urban last-mile logistics, yet existing navigation algorithms struggle with the complexity of dynamic metropolitan environments. This study optimises a reinforcement learning (RL)-based guidance, navigation, and control (GNC) algorithm using a Proximal Policy Optimisation (PPO) model within a high-fidelity simulation of Bristol City Centre. The primary contribution is training the RL model to autonomously detect and avoid dynamic obstacles, specifically manned aircraft, to ensure safe and legal drone operations. Additionally, flight operations are continuously monitored via a Structured Query Language (SQL) database to verify compliance with low airspace regulations. Simulation results demonstrate that the proposed framework achieves high obstacle detection accuracy under nominal conditions, while the implementation of curriculum learning significantly enhances the system’s adaptability and recovery capabilities during high-speed, dynamic encounters. Full article

Detecting small objects in drone imagery remains challenging because of extreme object scale variations, dense scenes, and limited pixel information. Although recent YOLOv8 variants provide multiple model scales and architectural options, systematic guidance on their practical use in UAV-based detection remains limited. Rather than proposing novel network architectures, this study provides a quantitative cost–benefit analysis and empirical deployment guidelines by comprehensively evaluating the complete YOLOv8 family on the VisDrone dataset to assess the effects of the model capacity, input resolution, and architectural modifications on the small-object detection performance. The results showed that increasing the model capacity exhibited diminishing returns: YOLOv8l achieved the best overall accuracy (15.9% mAP50), while the larger YOLOv8x model exhibited a substantial performance degradation (7.32% mAP50) owing to training instability under data-constrained conditions. Scaling the input resolution from 640 to 1280 yielded a 25% improvement in detection performance, substantially exceeding the gains obtained through architectural modifications, such as adding a P2 detection layer (+6%). The optimal configuration (YOLOv8l @ 1280) achieved a 488% improvement compared to the YOLOv5 baseline. These findings demonstrate that, for UAV-based small-object detection, prioritizing an appropriate model capacity and input resolution is more effective than increasing the architectural complexity. Full article

The rapid advancement of smart agricultural technologies has transformed modern farming practices, enhancing productivity, precision, and sustainability while introducing new ergonomic challenges. This study aimed to evaluate and prioritize ergonomic criteria associated with three major smart agricultural technologies—GPS-guided tractors, agricultural drones, and automatic irrigation systems—within a multi-stakeholder decision-making framework. The Analytic Hierarchy Process (AHP) was applied to data collected from 53 experts representing four stakeholder groups: academia, operators/farmers, manufacturers, and sectoral organizations. Five ergonomic criteria—physical workload reduction, task duration, user safety, training requirement, and cost/applicability—were analyzed to determine their relative importance. The results indicate that user safety emerged as the most influential ergonomic factor for academia, farmers, and sectoral organizations, highlighting the importance of risk reduction and operator protection in smart farming environments. In contrast, manufacturers prioritized cost and applicability, reflecting economic feasibility considerations in technology development and deployment. These findings demonstrate that ergonomic priorities differ across stakeholder groups and emphasize the need for human-centered design approaches in the development of smart agricultural systems. The proposed multi-stakeholder AHP framework provides a practical and evidence-based decision-support tool for integrating ergonomic considerations into agricultural technology design, implementation, and policy development. Full article

Open-vocabulary object detection in unmanned aerial vehicle (UAV) imagery remains challenging under zero-shot cross-dataset transfer because tiny and cluttered targets are highly sensitive to early resolution reduction under domain shift. This study aims to improve transferable open-vocabulary UAV detection by revisiting stride-2 downsampling in YOLO-World v2 as a transfer-critical bottleneck. AeroPinWorld is introduced as a pinwheel-augmented YOLO-World v2 that selectively replaces four key stride-2 transitions with pinwheel-shaped convolution (PConv) so as to reduce aliasing, alleviate sampling-phase sensitivity, and preserve fine-grained local structures, while keeping the original detection head unchanged to ensure a fair and efficient comparison. The model is trained on COCO2017 for 24 epochs from official pretrained weights and directly evaluated, without target-domain fine-tuning, on VisDrone2019-DET and UAVDT using fixed offline prompt vocabularies. Compared with YOLO-World v2-S, AeroPinWorld improves zero-shot transfer performance on VisDrone from 0.112 to 0.135 mAP and from 0.054 to 0.063 AP_S, and it also yields consistent gains on UAVDT. Ablation studies show that both early backbone replacements and head bottom–up replacements contribute to the final gains, with their combination achieving the best accuracy–efficiency trade-off. These results indicate that selectively redesigning transfer-critical downsampling operators is an effective and lightweight way to improve zero-shot open-vocabulary UAV detection under aerial domain shift. Full article

Weed identification and quantification are processes that are usually manual, subjective, and error-prone. Weeds compete with crops for nutrients, minerals, physical space, sunlight, and water. Thus, weed identification is a crucial component of precision agriculture for autonomous removal and site-specific treatments, efficient weed control, and sustainability. Convolutional Neural Networks (CNNs) are very common in weed identification. This work implemented CNN models for semantic segmentation based on the U-Net architecture for automatically segmenting and quantifying weeds in potato crops using RGB images acquired by a drone at 9–10 m height, flying at 1 m/s. Remote sensing images are affected by factors that degrade image quality and the model’s accuracy. Five U-Net variants were evaluated: the original U-Net, Residual U-Net, Double U-Net, Modified U-Net, and AU-Net. The models were trained using the TensorFlow/Keras frameworks on Google Colab Pro+, following the Knowledge Discovery in Databases (KDD) methodology for image analysis. Each model was trained using a diverse custom dataset in uncontrolled environments, considering six classes: background, Broadleaf dock (Rumex obtusifolius), Dandelion (Taraxacum officinale), Kikuyu grass (Cenchrus clandestinum), other weed species, and the crop potato (Solanum tuberosum L.). The models’ segmentation was widely assessed using Mean Dice Coefficient, Mean IoU, and Dice Loss metrics. The results showed that the Residual U-Net model performed the best in multi-class segmentation, achieving a Mean IoU of 0.8021, a performance comparable to or superior to that reported by other authors. Additionally, a Student’s t-test was applied to complement the data analysis, suggesting that the model is reliable for weed quantification. Full article

Identifying the plant species comprising a pasture, among other aspects, is crucial for assessing its nutritional value for grazing animals and facilitating its effective management. Traditionally, it requires labor-intensive visual inspection. Artificial Intelligence (AI) offers a solution for automatic classification, yet robust datasets for training such models in natural, uncontrolled environments are scarce. This data descriptor presents a dataset of 741 images collected in pasture lands in the Centre of Portugal using standard cameras at a height of 50 cm. A semi-automated annotation pipeline was employed, utilizing a Faster R-CNN model followed by manual verification and refinement. The dataset contains 1744 annotations across four categories: ‘Shrubs’, ‘Grasses’, ‘Legumes’, and ‘Others’. It includes diverse morphological variations and captures real-world challenges such as occlusion and lighting variability. This dataset serves as a benchmark for training object detection models in agricultural settings, facilitating the development of automated monitoring systems for precision agriculture. Such a mechanism could be incorporated into a mobile application, mounted on a drone, or embedded in an animal-worn device, enabling automated sampling and identification of the plant composition within a pasture. Full article

The present study investigated the detection performance of the YOLOv8s, YOLO11s, and YOLO12s models, implemented within convolutional neural network architectures, for identifying floricane raspberry (Rubus idaeus L.) shrubs using RGB imagery and multispectral data acquired in the near-infrared, red-edge, red, and green spectral bands with a DJI Mavic 3 Multispectral drone. Model training and validation were conducted to evaluate both within-modality detection performance and cross-modality transferability. Under all training scenarios, the YOLO-based detectors reached near-saturated accuracy levels. However, cross-domain assessments demonstrated substantial variability depending on the spectral configuration of the input imagery. Overall, the combination of UAV-based multispectral sensing with convolutional neural network detection frameworks establishes a technological basis for automated shrub monitoring and constitutes a meaningful advancement toward intelligent raspberry production systems. This integration further creates new prospects for the technological development of cultivation practices for this crop within the rapidly evolving landscape of artificial intelligence-driven agriculture. Full article

Out-of-hospital cardiac arrest (OHCA) remains a leading cause of sudden death worldwide, with wide variation in reported incidence and outcomes driven by heterogeneity in registries, emergency medical services (EMS) organization, and case definitions. Despite substantial advances in resuscitation systems, survival after EMS-treated OHCA generally remains below 10%, and outcomes are critically time dependent. Delays in emergency call activation, bystander cardiopulmonary resuscitation (CPR), and—most importantly—early defibrillation are associated with a rapid decline in return of spontaneous circulation and favorable neurological recovery. This narrative review synthesizes current evidence and implementation strategies aimed at reducing “time-to-CPR” and “time-to-shock,” with a specific focus on public-access defibrillation (PAD) as a tool to mitigate avoidable delay. Randomized trials and large registry studies consistently demonstrate that automated external defibrillator (AED) use before EMS arrival is a key determinant of survival in patients with shockable rhythms. However, the real-world effectiveness of PAD remains limited by suboptimal AED placement, restricted 24/7 accessibility, low public awareness, and underutilization driven by fear and lack of confidence. We compare different PAD delivery models—including EMS-based, police and first-responder-based, and fully integrated community systems—and summarize evidence supporting targeted, high-yield AED deployment and cost-effectiveness. In addition, we review emerging strategies to reduce avoidable delay and strengthen the early links of the chain of survival, such as school-based training programs, smartphone- and SMS-based citizen-responder networks, improved dispatch recognition of cardiac arrest (including artificial intelligence–supported tools), and drone-enabled AED delivery. Across these approaches, patient benefit critically depends on system integration, alert performance, and true AED accessibility. Finally, we describe the Italian “Progetto Vita” experience as a community-integrated model explicitly designed to minimize avoidable delay through widespread AED deployment, lay responder training, and real-time integration with EMS. We conclude by outlining future priorities, including the development of robust national OHCA registries and scalable solutions for the high burden of cardiac arrests occurring at home, such as population-level deployment of low-cost, ultra-portable AEDs. Full article

Accurate and reliable vehicle detection, tracking, and counting across different surveillance platforms are fundamental requirements for developing smart Traffic Management Systems (TMS) and promoting sustainable urban mobility. Recent advances in both ground-level surveillance and remote sensing using deep learning have opened new opportunities for extracting detailed vehicular information from high-resolution aerial and surveillance video data. Our research reported here aims to present a unified, real-time vehicle analysis framework that integrates lightweight deep learning–based detection, robust multi-object tracking, and trajectory-driven counting within a single modular pipeline. The proposed framework employs a “You Only Look Once” system, YOLOv10-S as the detection backbone and enhances its robustness through supervision-level knowledge distillation without introducing any architectural modifications. Temporal consistency is enforced using an observation-centric multi-object tracking algorithm (OC-SORT), enabling stable identity preservation under camera motion and dense traffic conditions. Vehicle counting is performed using a trajectory-based virtual gate strategy, reducing duplicate counts and improving counting reliability. Comprehensive experiments conducted on the UA-DETRAC and VisDrone benchmarks show that the proposed framework effectively balances detection performance, tracking robustness, counting accuracy, and real-time efficiency in both ground-based and aerial surveillance settings. Furthermore, cross-dataset evaluations under direct train–test transfer highlight the inherent challenges of domain shift while showing that knowledge distillation consistently improves robustness in detection, tracking identity consistency, and vehicle counting. Overall, this framework enables effective real-world traffic monitoring by adopting a scalable and practical system design, where reliability is prioritized over architectural complexity. Full article

Road safety depends heavily on the timely identification and repair of potholes; however, detecting potholes is challenging due to various lighting and weather conditions. This work presents an attention-enhanced object detection framework for aerial pothole detection design that relies on a pre-trained backbone, YOLOv8, and a custom feature-extraction network, the Feature Pyramid Network (FPN). An enhanced detection head is used to make the model aware of discriminative areas in space to get accurate localization of a pothole to overcome the major limitations of the standard YOLOv8 used in aerial road inspection, irrespective of the road surface. The underlying architecture incorporates a purpose-built data layer and a preprocessing engine that can accommodate scenarios such as seasonal changes and bad weather. To further enhance learning dynamics, a customized loss function and a new optimizer framework are incorporated to improve convergence towards overall detection reliability. Specifically, a custom differential optimizer that uses layer-wise adaptive learning rates and momentum-based gradient updates to help suppress false positives and accelerate convergence. Conversely, the IoU-based personal loss function, combined with real-time validation, stabilizes training across a range of road conditions. A major feature of the proposed system is its ability to process aerial imagery from unmanned drone platforms. Empirical analysis proves a good result: an average precision of 0.980 with the IoU of 0.5 and an F1-score of 0.97 with a confidence threshold of 0.30. Precision is high (0.97 at the 90-percent confidence level). These metrics show how well the model will be able to balance false positives and false negatives—a critical need in a safety-critical deployment. The results make the framework a potential, scalable, and reliable candidate for integrating smart transportation systems and autonomous vehicle navigation. Full article

To resolve the issue of degraded detection accuracy for unmanned aerial vehicle object detection under low-illumination environments, this paper introduces a parallel object detection model. First, a dual-branch architecture is established by parallelly integrating a Zero-Reference Deep Curve Estimation (Zero-DCE) illumination enhancement network with a You Only Look Once (YOLOv11n)-based object detection network, enabling collaborative feature training and real-time updates. Through a feature-sharing mechanism, the two branches are jointly optimized during training, thus enhancing the model’s generalization capability in low-illumination environments. Furthermore, to further improve detection accuracy, a Dynamic Pooling Synergy Attention (DPSA) module is introduced into the backbone of YOLOv11n. By integrating dynamic pooling-based channel attention with spatial attention, this module improves feature representation, improves performance under complex environments, and increases adaptability to multi-scale targets. In addition, a High and Low Frequency Spatially-adaptive Feature Modulation (HLSAFM) module is added to the detection network’s Neck. Through high- and low-frequency feature refinement, segmented feature processing, and dynamic modulation, the network is able to capture richer feature information, thereby strengthening feature representation and discriminative capability. Extensive experiments on the VisDrone (Night) and DroneVehicle (Night) datasets demonstrate superior performance over multiple existing methods under low-illumination object detection tasks. Compared with the original YOLOv11n model, the proposed model $mAP50$ increases by 6.0% and 1.0% and $mAP50:95$ increases by 3.1% and 0.8%, respectively. These results confirm the enhanced detection capability achieved by our method in challenging low-illumination unmanned aerial vehicle (UAV) scenarios. Full article

Remote photoplethysmography (rPPG) enables contactless estimation of cardiovascular signals from video, but most existing studies assume a fixed, stationary camera. This study investigates the feasibility of performing real-time moving-average rPPG (MA-rPPG) using a drone-mounted camera, where platform motion, vibration, and viewing distance introduce additional challenges. Building on our previously validated real-time MA-rPPG smart mirror platform, we reuse the smart mirror interface as a unified frontend for visualization, synchronization, and logging while adapting the MA-rPPG pipeline to operate on live video streamed from an off-the-shelf DJI Tello micro-drone. Feasibility experiments were conducted with 10 participants under controlled indoor lighting and constrained flight conditions, where the drone maintained a stable hover in front of a standing subject and facial video was processed in real time to estimate heart rate from a forehead region of interest. To avoid cross-modality bias and clarify the effect of the aerial imaging platform, drone-derived MA-rPPG outputs were compared against a fixed desktop-camera MA-rPPG reference using the same trained model, enabling a controlled, like-for-like evaluation. The results indicate that continuous heart-rate estimation from a drone camera is feasible in our controlled hover-only setup, while agreement tended to vary with hover stability and effective facial resolution. This work is presented strictly as a feasibility-stage investigation and does not claim clinical validity. The findings provide an experimental baseline and operating-envelope insight for future motion-robust rPPG on mobile and aerial health-sensing platforms. Full article