Search Results (91)

Parakeets exhibit many similar traits across species, with only subtle differences in features and coloration used for classification, which complicates detection and identification for birdwatchers, breeders, and researchers. Traditional classification methods rely on observation, while more expensive options involve DNA sampling. We developed a bird classification system that identifies Asiatic parakeets by combining You Only Look Once Version 5 (YOLOv5) for detection with ResNet-50 for the classification of four specific species: Alexandrine, Moustache, Plum-headed, and Indian Ringneck parakeets. Using a Raspberry Pi 4B and a Raspberry Pi Camera housed in a customized enclosure to capture images of the birds, the evaluation indicated an overall accuracy of 95.05% through a multi-class confusion matrix, demonstrating the effectiveness of the system as a reliable tool for avian identification and research. Full article

We developed an automated system to address orchard crop damage caused by Formosan macaques, a problem where traditional deterrent methods have proven to be ineffective. The system integrates an Internet Protocol camera with a You Only Look Once version 5 (YOLOv5) object detection model, which was trained on an augmented 6000-image dataset featuring a simulated monkey puppet in an indoor setting to validate its real-time identification capability through simulation. Upon target detection, a high-power laser, controlled via the Message Queuing Telemetry Transport protocol, is actuated to perform dynamic and non-invasive repelling. A web-based Human–Machine Interface (HMI) is provided, allowing users to remotely monitor and adjust strategies. This system offers a low-cost, highly efficient, and scalable solution for smart agriculture, with potential for expansion to other scenarios requiring a high degree of security and defense, such as warehouses and construction sites. Full article

We developed a real-time guinea pig breed classification system using You Only Look Once Version 9 (YOLOv9)-small, deployed on a Raspberry Pi 5 with Camera Module 3 and Hailo-8L acceleration module. The system targeted three breeds, Abyssinian, American, and Peruvian, using a dataset of 4500 images split into a 70:20:10 ratio for training, validation, and testing. After optimization for Hailo-8L, the model was tested on live samples, with hamsters included as an unknown class. A total of 600 frame blocks were extracted from the video input and analyzed using a multi-class confusion matrix. Results showed an 89% overall accuracy (94.67% for Abyssinian, 94.33% for American, 98.67% for Peruvian, and 90.33% for unknown classification accuracy). The results showed the feasibility of deploying YOLOv9-small on embedded devices for accurate and real-time animal classification. Full article

Recent advances in ear biometrics have yielded increasingly accurate detection and recognition methods, driven by the ear’s uniqueness and permanence as a non-invasive biometric modality. Nonetheless, several limitations persist, including computationally demanding models, inconsistent evaluation metrics, and portable systems restricted by manual capture and limited datasets. To address these challenges, we developed a lightweight, video-based ear biometric system implemented on the Raspberry Pi 5. The system integrates You Only Look Once Version 12 (YOLOv12) for ear detection, EfficientNet-4 for feature extraction, and k-Nearest Neighbors (k-NNs) for recognition. Its robust hardware platform combines Raspberry Pi 5 with the Raspberry Pi AI Camera and AI HAT+. To train, fine-tune, and optimize YOLOv12 and EfficientNet-4, we used the Visual Geometry Group (VGG)Face-Ear dataset for training and the Unconstrained Ear Recognition Challenge 2019 dataset for validation, with k-NN employed for classification. The system is evaluated for classification accuracy and system-level performance. 13 participants, comprising 10 enrolled and three unenrolled subjects, participated in testing the system. The enrolled participants registered in the system were correctly identified, whereas unenrolled participants were excluded and rejected. The system achieved 92.31% accuracy, 95.45% precision, 96.97% recall, and an F1-score of 0.95, confirming the feasibility of deploying advanced ear biometric methods on embedded, resource-constrained devices. Full article

The application of three-dimensional ground-penetrating radar (3D GPR) for intelligent pavement defect analysis is often constrained by the limited availability of labeled samples. To address this challenge, this study employed Ground Penetrating Radar Maxwell (GprMax) to simulate typical pavement defects, including cracks, loose materials, and interlayer debonding. A Cycle-Consistent Generative Adversarial Network (Cycle-GAN) was then introduced to perform style transfer on the simulated images, thereby reducing the domain gap between simulated and real radar images. Furthermore, four You Only Look Once (YOLO) models—YOLO version 5, YOLOX, YOLO version 7, and YOLO version 8—were systematically compared using real datasets to identify the best-performing model, which was subsequently used to evaluate the effect of different proportions of synthetic data on detection performance. The results demonstrated that the moderate inclusion of synthetic data improved the recognition accuracy of loose defects (from 76.7% to 78.9%), whereas its impact on crack and debonding detection was negative. Moreover, excessive reliance on synthetic data led to overfitting, thereby reducing the model’s generalization capability. Among the four models, YOLOv7 achieved the best overall performance, with a mean Average Precision (mAP) of 83.4% and a crack detection rate of 88.2%. This study thus provides a feasible technical pathway and model selection reference for automated GPR-based pavement defect identification, offering practical value for efficient and accurate road maintenance inspections. Full article

Position-Based Visual Servoing (PBVS) and Image-Based Visual Servoing (IBVS) struggle to balance end effector pose accuracy and robustness in apple picking. They are also prone to target loss and control singularities. A progressive Hybrid Automatic Switching Visual Servoing (HAVS) method is proposed and applied to an apple-picking robotic system. HAVS integrates PBVS and IBVS to coordinate control of the manipulator end effector pose. A depth-based switching function is designed. When target depth is below an optimal threshold, the controller switches to PBVS for precise final positioning. This reduces target loss and control singularities. An adaptive proportional-derivative (PD) controller with fuzzy gain scheduling updates the control gains online to enhance responsiveness and stability. The hardware consists of a six-axis manipulator, a depth camera, and a mobile base. You Only Look Once version 5 (YOLOv5) performs apple detection and generates control commands. Indoors, success rate was 96%, which was 4 and 10 percentage points higher than PBVS only and IBVS only. Average picking time was 12.5 s, 0.3 s, and 1.1 s shorter. Outdoors, success rate was 87.5%, average time was 13.2 s, and damage rate was 4.2%. This method provides a reference implementation for visual servo control in agricultural picking robots. Full article

Accurate and timely crop yield estimation remains a major challenge in agriculture due to the limitations of traditional field-based methods, which are labor-intensive, destructive, and unsuitable for large-scale applications. While recent advances in Unmanned Aerial Vehicles (UAVs) and Deep Learning (DL) have enabled non-destructive and scalable alternatives, melons (Cucumis melo L.) remain relatively understudied, and datasets for yield estimation are scarce. This study presents a computer vision pipeline for UAV-based fruit detection and yield estimation in melon crops. High-resolution UAV RGB imagery was processed using YOLOv12 (You Only Look Once, version 12) for fruit detection, followed by a volume-based regression model for weight estimation. The experiment was conducted during the May–August 2025 growing season in Apulia, southern Italy. The detection model achieved high accuracy, with strong agreement between estimated and actual fruit counts (R² = 0.99, MAPE = 5%). The regression model achieved an R² of 0.79 for individual weight estimation and a total yield error of 2.9%. By addressing the scarcity of melon-specific data, this work demonstrates that integrating UAV imagery with deep learning provides an effective and scalable approach for accurate yield estimation in melons. Full article

Accurate extrinsic calibration between radar and camera sensors is essential for reliable multi-modal perception in robotics and autonomous navigation. Traditional calibration methods often rely on artificial targets such as checkerboards or corner reflectors, which can be impractical in dynamic or large-scale environments. This study presents a fully targetless calibration framework that estimates the rigid spatial transformation between radar and camera coordinate frames by aligning their observed trajectories of a moving object. The proposed method integrates You Only Look Once version 5 (YOLOv5)-based 3D object localization for the camera stream with Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Random Sample Consensus (RANSAC) filtering for sparse and noisy radar measurements. A passive temporal synchronization technique, based on Root Mean Square Error (RMSE) minimization, corrects timestamp offsets without requiring hardware triggers. Rigid transformation parameters are computed using Kabsch and Umeyama algorithms, ensuring robust alignment even under millimeter-wave (mmWave) radar sparsity and measurement bias. The framework is experimentally validated in an indoor OptiTrack-equipped laboratory using a Skydio 2 drone as the dynamic target. Results demonstrate sub-degree rotational accuracy and decimeter-level translational error (approximately 0.12–0.27 m depending on the metric), with successful generalization to unseen motion trajectories. The findings highlight the method’s applicability for real-world autonomous systems requiring practical, markerless multi-sensor calibration. Full article

This paper proposes a fruit-harvesting robot system that improves harvesting efficiency by utilizing a Reachability Map (RM) and an Inverse Reachability Map (IRM). The proposed system accurately detects fruit locations using You Only Look Once version 5 (YOLOv5)–based object detection and camera calibration. Through coordinate transformation and hand–eye calibration, the manipulator is precisely guided to the fruit’s 3D position. During the construction of the reachability map, the reachability index, manipulability isotropy, and harvesting index are jointly considered to quantitatively evaluate manipulator performance. Fruits accessible by the manipulator are prioritized for harvesting. For fruits that cannot be directly reached, the system computes the optimal base pose using the inverse reachability map, enabling the mobile manipulator to reposition itself for harvesting. To further enhance efficiency, multiple fruits are grouped to minimize unnecessary movements. The integrated system is implemented on the Robot Operating System 2 (ROS 2), where fruit detection, autonomous navigation, and harvesting are executed as independent nodes to support scalable and modular operation. Finally, the proposed system is validated in a simulated orchard environment, confirming its effectiveness in improving autonomous fruit-harvesting performance. Full article

Printed circuit board (PCB) defect detection is critical to manufacturing quality, yet tiny, low-contrast defects and limited annotations challenge conventional systems. This study develops an ECA–DCN-lite–BiFPN–CARAFE-enhanced YOLOv5 detector by modifying You Only Look Once (YOLO) version 5 (YOLOv5) with Efficient Channel Attention (ECA) for channel re-weighting, a lightweight Deformable Convolution (DCN-lite) for geometric adaptability, a Bi-Directional Feature Pyramid Network (BiFPN) for multi-scale fusion, and Content-Aware ReAssembly of FEatures (CARAFE) for content-aware upsampling. A single-cycle semi-supervised training pipeline is further introduced: a detector trained on labeled images generates high-confidence pseudo-labels for unlabeled data, and the combined set is used for retraining without ratio heuristics. Evaluated on PKU-PCB under label-scarce regimes, the full model improves supervised mean Average Precision at an Intersection-over-Union threshold of 0.5 (mAP@0.5) from 0.870 (baseline) to 0.910, and reaches 0.943 mAP@0.5 with semi-supervision, with consistent class-wise gains and faster convergence. Ablation experiments validate the contribution of each module and identify robust pseudo-label thresholds, while comparisons with recent YOLO variants show favorable accuracy–efficiency trade-offs. These findings indicate that the proposed design delivers accurate, label-efficient PCB inspection suitable for Automated Optical Inspection (AOI) in production environments. This work supports SDG 9 by enhancing intelligent manufacturing systems through reliable, high-precision AI-driven PCB inspection. Full article

Collisions between ships and sea ice pose a significant threat to maritime safety, making it essential to detect sea ice and perform safety-oriented path planning for polar navigation. This paper utilizes an optimized You Only Look Once version 5 (YOLOv5) model, designated as YOLOv5-ICE, for the detection of sea ice in satellite imagery, with the resultant detection data being employed to input obstacle coordinates into a ship path planning system. The enhancements include the Squeeze-and-Excitation (SE) attention mechanism, improved spatial pyramid pooling, and the Flexible ReLU (FReLU) activation function. The improved YOLOv5-ICE shows enhanced performance, with its mAP increasing by 3.5% compared to the baseline YOLOv5 and also by 1.3% compared to YOLOv8. YOLOv5-ICE demonstrates robust performance in detecting small sea ice targets within large-scale satellite images and excels in high ice concentration regions. For path planning, the Any-Angle Path Planning on Grids algorithm is applied to simulate routes based on detected sea ice floes. The objective function incorporates the path length, number of ship turns, and sea ice risk value, enabling path planning under varying ice concentrations. By integrating detection and path planning, this work proposes a novel method to enhance navigational safety in polar regions. Full article

With rapid urbanization and increasing emphasis on sustainable mobility, slow-moving traffic systems, including pedestrian and cycling infrastructure, have become critical to urban transportation and quality of life. Conventional assessment methods are labor-intensive, time-consuming, and limited in coverage. Leveraging advances in deep learning and computer vision, this study develops a framework for bottleneck detection using street-level imagery and the You Only Look Once version 5 (YOLOv5) model. An evaluation system comprising 15 indicators across continuity, safety, and comfort is established. In a case study of Wuhan’s Third Ring Road, the YOLOv5 model achieved 98.9% mean Average Precision (mAP)@0.5, while spatial hotspot analysis (p < 0.05) identified severe demand–infrastructure mismatches in southeastern Wuhan, contrasted with fewer problems in the northern region due to stronger management. To ensure adaptability, a dynamic optimization mechanism integrating temporal imagery updates, transfer learning, and collaborative training is proposed. The findings demonstrate the effectiveness of street-level remote sensing for large-scale urban diagnostics, extend the application of deep learning in mobility research, and provide practical insights for data-driven planning and governance of slow-moving traffic systems in high-density cities. Full article

Mass shootings are forms of loosely defined violent crimes typically involving four or more casualties by firearm and have become increasingly more frequent, and organized and speedy responses from police are necessary to mitigate harm and neutralize the perpetrator. Recent, widely publicized police responses to mass shooting events have been criticized by the media, government, and public. With the advancements in artificial intelligence, specifically single-shot detection (SSD) models, computer programs can detect harmful weapons within efficient time frames. We utilized YOLO (You Only Look Once), an SSD with a Convolutional Neural Network, and used versions 5, 7, 8, 9, 10, and 11 to develop our detection system. For our data, we used a Roboflow dataset that contained almost 17,000 images of real-life handgun scenarios, designed to skew towards positive instances. We trained each model on our dataset and exchanged different hyperparameters, conducting a randomized trial. Finally, we evaluated the performance based on precision metrics. Using a Python-based design, we tested our model’s capabilities for surveillance functions. Our experimental results showed that our best-performing model was YOLOv10s, with an mAP-50 (mean average precision 50) of 98.2% on our dataset. Our model showed potential in edge computing settings. Full article

During traditional aircraft landings, pilots face significant challenges in identifying runway numbers with the naked eye, particularly at decision height under adverse weather conditions. To address this issue, this study proposes a novel detection algorithm based on an optimized version of the YOLOv5s model (You Only Look Once, version 5) for recognizing runway markings during civil aircraft landings. By integrating a data augmentation strategy with external datasets, the method effectively reduces both false detections and missed targets through expanded feature representation. An Alpha Complete Intersection over Union (CIOU) Loss function is introduced in place of the original CIOU Loss function, offering improved gradient optimization. Additionally, the model incorporates several advanced modules and techniques, including a Convolutional Block Attention Module (CBAM), Soft Non-Maximum Suppression (Soft-NMS), cosine annealing learning rate scheduling, the FReLU activation function, and deformable convolutions into the backbone and neck of the YOLOv5 architecture. To further enhance detection, a specialized small-target detection layer is added to the head of the network and the resolution of feature maps is improved. These enhancements enable better feature extraction and more accurate identification of smaller targets. As a result, the optimized model shows significantly improved recall (R) and precision (P). Experimental results, visualized using custom-developed software, demonstrate that the proposed optimized YOLOv5s model achieved increases of 5.66% in P, 2.99% in R, and 2.74% in mean average precision (mAP) compared to the baseline model. This study provides valuable data and a theoretical foundation to support the accurate visual identification of runway numbers and other reference markings during aircraft landings. Full article

Magnetic tiles are an important component of permanent magnet motors, and the quality of magnetic tiles directly affects the performance and service life of a motor. It is necessary to perform defect detection on magnetic tiles in industrial production and remove those with defects. The YOLOv8-AHF algorithm is proposed to improve the ability of network feature information extraction and solve the problem of missed detection or poor detection results in surface defect detection due to the small volume of permanent magnet motor tiles, which reduces the deviation between the predicted box and the true box simultaneously. Firstly, a hybrid module of a combination of atrous convolution and depthwise separable convolution (ADConv) is introduced in the backbone of the model to capture global and local features in magnet tile detection images. In the neck section, a hybrid attention module (HAM) is introduced to focus on the regions of interest in the magnetic tile surface defect images, which improves the ability of information transmission and fusion. The Focal-Enhanced Intersection over Union loss function (Focal-EIoU) is optimized to effectively achieve localization. We conducted comparative experiments, ablation experiments, and corresponding generalization experiments on the magnetic tile surface defect dataset. The experimental results show that the evaluation metrics of YOLOv8-AHF surpass mainstream single-stage object detection algorithms. Compared to the You Only Look Once version 8 (YOLOv8) algorithm, the performance of the YOLOv8-AHF algorithm was improved by 5.9%, 4.1%, 5%, 5%, and 5.8% in terms of mAP@0.5, mAP@0.5:0.95, F1-Score, precision, and recall, respectively. This algorithm achieved significant performance improvement in the task of detecting surface defects on magnetic tiles. Full article