Search Results (76)

Automated vehicular traffic management in Latin American cities requires solutions capable of capturing, processing, and visualizing events through measurable operational update intervals. Conventional automatic number plate recognition (ANPR) pipelines can return plate text while leaving the visual adequacy of the associated crop unassessed and disconnected from downstream cloud persistence, alerts, and monitoring. Because this separation can propagate visually unreliable evidence into operational records, a unified workflow is needed to evaluate plate-crop legibility before the event is exposed to operators. This work presents a three-phase methodology, applied to the SAVH system (Sistema de Aforo Vehicular, Vehicle Counting System), which integrates a Dahua ANPR camera (Zhejiang Dahua Vision Technology Co., Ltd., Hangzhou, China) with a cloud architecture on Amazon Web Services (AWS). The camera captures the vehicle and performs textual reading of the license plate, sending vehicle notifications directly to the FastAPI service deployed on Amazon EC2. This service extracts the visual evidence and runs the YOLOv8n classification variant (YOLOv8n–CLS), which classifies the legibility of the plate crop into two classes: legible plate and non-legible plate. Structured events and visual evidence are persisted in managed storage services, and a serverless function serves the web dashboard queries through an application programming interface (API) managed by Amazon API Gateway. The model was trained on a relabeled dataset derived from the public LPLCv2 collection, split into training, validation, and test subsets. Evaluation on 720 independent images from the test set achieved 97.78% overall accuracy, with 97.75% macro precision, 97.82% macro recall, 97.78% macro F1-score, and an AUC of 0.9981. External validation on 2000 real Guayaquil images achieved 86.10% accuracy, 85.84% macro F1-score, and an AUC of 0.9742. The external results show a performance gap consistent with domain shift and motivate cautious interpretation of deployment results. The contribution is the integration and evaluation methodology rather than a new neural architecture: YOLOv8n–CLS, FastAPI, and the AWS services are existing components assembled into a documented operational workflow. Full article

Automatic License Plate Recognition (LPR) is an essential technology in modern intelligent transportation systems, facilitating the identification of vehicles without manual intervention. It supports a wide range of applications, including traffic monitoring, electronic toll payment, parking automation, secure access management, and law enforcement operations, thereby improving transportation efficiency, security, and operational effectiveness. However, real-world license plate images are frequently affected by motion blur, noise, illumination variations, adverse weather conditions, and low resolution, which significantly degrade recognition performance. To address these challenges, this study proposes an Adaptive Hybrid CNN–Mamba–Multi-Head Attention Network with Northern Goshawk Optimization (AHCMM-Net-NGO) for robust LPR. The proposed framework combines license plate detection, progressive image restoration and enhancement, hierarchical multi-scale feature learning, efficient contextual modeling using Vision Mamba, adaptive attention refinement, and automatic hyperparameter optimization within a unified end-to-end architecture. The framework was evaluated on the UFPR-ALPR dataset containing 4500 fully annotated vehicle images captured under real-world driving conditions. Experimental outcomes demonstrate superior recognition performance, achieving 98.96% accuracy, 98.89% precision, 98.81% recall, and a 98.85% F1-score. Comprehensive experimental evaluations, including ablation studies, hyperparameter sensitivity analysis, cross-validation, and comparative performance analysis, further demonstrate the efficacy, robustness, and generalization capability of the proposed framework. Overall, the proposed AHCMM-Net-NGO framework provides an accurate, reliable, and robust solution for license plate recognition under challenging imaging conditions and demonstrates strong potential for intelligent transportation systems, although practical deployment should consider the computational requirements of the integrated deep learning framework. Full article

Urban environments are saturated with imaging sensors deployed for purposes unrelated to vehicle identification, from ATM and dashboard cameras to pole-mounted CCTV and smartphones. We term the use of such non-purpose-built sensors for secondary inference “opportunistic sensing”; its central question is where, under uncontrolled capture conditions, AI-enabled restoration remains reliable. This paper introduces recoverability maps, a task-agnostic methodology for quantifying that boundary, and applies it to oblique-view license plate recognition (LPR). It pairs a full-grid synthetic sweep of the degradation space with two summary measures: a boundary area-under-curve for coverage and a reliability score $F$ for the frequency and depth of interior unrecovered pockets. For LPR, the space is the oblique-angle grid $[0°,89°{]}^2$ sampled by Scrambled Sobol sequences, and the utility is plate-level optical character recognition (OCR) accuracy. Within this synthetic benchmark, approximately $90$–$92\%$ of the angle grid is recoverable (best single model to union of restoration arms), recovery degrades sharply beyond roughly $80°$ in both axes, and lateral rotations are harder to reconstruct than elevational ones. Five restoration architectures cluster within a narrow AUC band of $0.89$–$0.93$, and share the same $\alpha /\beta$ asymmetry, so the recoverable region is set primarily by sensing geometry, with architecture affecting efficiency and interior consistency; discriminative architectures outperform generative models. The methodology is validated on real plates: on CCPD and the Brazilian legacy and Mercosur layouts of RodoSol-ALPR, restoration raises held-out extreme-angle recognition by $+15$ to $+38$ exact-match points under plate-specialized recognizers, and the discriminative-over-generative ordering reproduces on real data. Full article

To address the joint requirements of illegal parking detection and license plate recognition under complex traffic scenarios and limited edge-device resources, this study proposes RKF-YOLO, a lightweight dual-task model based on improved YOLOv11n that integrates Rep-CSP structural optimization, knowledge-transfer-enhanced training (KTET), and Focal-CIoU loss. Compared with YOLOv11n, RKF-YOLO reduces parameters and FLOPs by 38.2% and 38.1%, respectively, while improving $\mathrm{mAP}@0.5$ and $\mathrm{mAP}@0.5:0.95$ by 0.6 and 1.1 percentage points for parking detection; for plate detection, Focal-CIoU improves $\mathrm{mAP}@0.5:0.95$ by 1.3 percentage points and contributes to a recognition accuracy of 95.7%. The unified framework uses a shared backbone and task-oriented detection heads to support vehicle-level illegal parking detection and license-plate-oriented localization. Rep-CSP enhances multi-scale feature representation, asymmetric channel reduction with feature compensation reduces redundant computation, and KTET improves convergence through optimizer and learning-rate migration. Deployment on RK3588 achieves 59.5 FPS for parking detection and 95.1% recognition accuracy, demonstrating real-time performance and practical applicability on resource-constrained edge devices. Full article

We present a modular multi-attribute vehicle analysis pipeline that integrates YOLO-based models and an OCR engine into a single workflow. The system detects vehicles, classifies color, recognizes make and sub-model, detects license plates, and extracts plate characters to generate a structured vehicle record. Vehicle detection is reported with standard metrics (precision, recall, and mAP@0.5), while license plate detection is reported at IoU = 0.3 to reflect the small-object nature of plates and downstream OCR usability. Among the evaluated versions, YOLOv8 provides the most balanced overall performance across modules, while maintaining real-time-equivalent throughput of approximately 18–22 FPS for the full pipeline on recorded traffic videos, depending on scene complexity. We emphasize module-level evaluation and runtime benchmarking; instance-level end-to-end identification across unique vehicles is defined as future work once track-based ground truth becomes available. Full article

In urban traffic systems, traditional signal control can no longer meet the increasing traffic demand, and local congestion is severe during peak hours. Fixed detector data is characterized by high deployment density, full sample detection and restorable vehicle paths, providing new data support for coordinated signal control. We propose an optimization method for regional coordinated control, with the Changsha road network as the study area. Firstly, based on License Plate Recognition (LPR) data, the road network is divided into sub-networks and combined with the boundary control for regional coordinated control. Then, the critical path is taken as the control object, and the phase coordination rate is introduced as the optimization objective. The particle swarm optimization algorithm improved by the logistic chaotic map is used as the global searcher, and sequential quadratic programming is adopted as the local searcher to solve the optimization strategy for the objective function. Finally, a simulated road network is constructed in VISSIM 6.0 simulation software to verify the effectiveness of the strategy. The results show that the optimization strategy reduces intersection delay and saturation by 20.3% and 19.3% in the critical path coverage area. Road travel time and the average number of vehicle stops are reduced by 21% and 22.1%. This indicates that the regional coordinated control based on the improved particle swarm algorithm can better alleviate the peak hour traffic congestion. Full article

Motor vehicle encroachment into non-motorized lanes is a common but hard-to-verify violation in urban intersections, especially when monitored from unmanned aerial vehicles (UAVs) or high-mounted overhead views. Existing rule-based solutions built on horizontal bounding boxes and center-point/line-crossing criteria are sensitive to perspective distortion, occlusion, and frame-to-frame jitter, resulting in unstable decisions and low evidential value. This paper presents a cascaded UAV-view system that closes the loop from perception to evidence output through detection–segmentation–recognition–decision. First, we adopt a two-stage detection cascade: a lightweight vehicle detector localizes vehicles using axis-aligned bounding boxes, and a dedicated YOLOv5n-based oriented bounding box (OBB) license plate detector, constructed via architecture grafting and weight transfer, is then applied within each vehicle region of interest (ROI) to localize rotated license plates under large pose variation and small-target conditions. Second, a U-Net lane region segmentation module provides pixel-level spatial constraints to define an enforceable lane occupancy region. Third, a perspective rectification step is integrated with the PP-OCRv4 optical character recognition (OCR) framework to improve license plate recognition reliability for tilted plates. Finally, an area ratio criterion and an N-frame temporal counter are used to suppress transient misdetections and stabilize alarms. On a representative 100-sample controlled encroachment benchmark, the proposed system improves detection accuracy from 67.0% to 92.0% and reduces the false positive rate from 32.35% to 5.88% compared with a baseline horizontal bounding box (HBB)-based rule. The system outputs both violation alarms and license plate evidence, supporting practical deployment for multi-view traffic governance. Full article

Port areas are core hubs for national logistics and high-risk security zones that require constant vehicle access control. However, ensuring the reliability of automatic license plate recognition (ALPR) systems in port environments is severely challenged by complex image degradations, such as dense haze, low light, and motion blur. In this study, we propose a stage-wise degradation-aware restoration network (SDR-Net), which effectively addresses harsh port conditions by sequentially restoring photometric and structural degradations. Particularly, SDR-Net first secures visual cues lost to haze and low light through a photometric restoration module involving a dark-channel-prior-based dehazing and adaptive brightness adjustment. Next, a structural restoration module based on a generative adversarial network featuring edge-guided structural feature blocks and edge-aware refinement blocks is employed to precisely reconstruct character strokes and outlines damaged by motion blur, stably restoring license plate legibility even under complex degradation conditions. Experiments across various intensities of complex degradation demonstrate that SDR-Net maintains high character recognition accuracies of over 97.35% under mild motion blur and low-concentration haze conditions, indicating its superiority over state-of-the-art models. Notably, the performance gap between SDR-Net and comparison models widened as the degradation intensity increased, and SDR-Net achieved the highest multiscale structural similarity index scores across all intervals. Full article

The escalating global rates of traffic accidents in urban areas and the growing demands of smart cities underscore the urgent need for advanced real-time monitoring solutions. This paper presents an EdgeML-based system for vehicle tracking that performs real-time speed and distance analysis and traffic violation detection. This is achieved by deploying a YOLOv8 object detection model on a Raspberry Pi 5 with a Coral USB Edge TPU accelerator. The system integrates computer vision and IoT technologies to enable real-time processing. It utilizes the Message Queuing Telemetry Transport (MQTT) protocol to allow scalable communication between distributed edge devices and a central MongoDB database, facilitating real-time storage and analysis of traffic data. A synthetic dataset generated via the Blender 3D modeling tool validates the system’s accuracy, demonstrating average speed and distance measurement errors of ±2.11 km/h and ±0.58 m, respectively. These findings are further supported by preliminary practical experiments in a real-world environment, where speed estimation errors remained within 0–2 km/h and distance errors stayed below 0.11 m. Key innovations of this work include license plate recognition, speeding and collision detection, and context analysis using Google’s Gemini-2.5-Flash API. A Streamlit dashboard provides real-time visualization of traffic metrics, violations, and aggregated data. A comparative evaluation of YOLOv5n, YOLOv8n, YOLOv11n, and YOLOv12n identifies YOLOv8n as the most suitable model for embedded deployment, achieving 91.07 ± 0.61% mAP@0.5 without quantization, 88.77 ± 3.31% mAP@0.5 with quantization, while maintaining real-time performance of 30–43 frames per second (FPS) on the Edge TPU. The system’s modular architecture, low latency, and robust performance highlight its suitability for smart city applications, enhancing traffic safety and enabling data-driven urban mobility management. Full article

Intelligent transportation systems (ITSs) are crucial for modern traffic management and law enforcement. This paper addresses the challenge of monitoring and managing extensive vehicle traffic in large cities like Lahore, Pakistan. We propose a deep learning based ITS utilizing Vision Transformers combined with convolutional feature extraction to accurately identify vehicle type, color, make/model, and license plates. Experiments were conducted on a comprehensive dataset collected from multiple checkpoints across Lahore under varying environmental conditions. Our proposed model achieved high accuracy rates: 98.0% for vehicle type classification, 96.0% for color detection, 95.0% for make/model identification, and 89.0% for license plate recognition. These results demonstrate the system’s potential to significantly enhance traffic management and road safety and support law enforcement operations in developing urban environments. Full article

Background: Automatic vehicle recognition has recently become an area of great interest, providing substantial support for multiple use cases, including law enforcement and surveillance applications. In real traffic conditions, where for various reasons license plate recognition is impossible or license plates are forged, alternative solutions are required to support human personnel in identifying vehicles used for illegal activities. In such cases, appearance-based approaches relying on vehicle make and model recognition (VMMR) and vehicle color recognition (VCR) can successfully complement license plate recognition. Methods: This research addresses appearance-based vehicle identification, in which VMMR and VCR rely on inherent visual cues such as body contours, stylistic details, and exterior color. In the first stage, vehicles passing through an intersection are detected, and essential visual characteristics are extracted for the two recognition tasks. The proposed system employs deep learning with semantic segmentation and data augmentation for color recognition, while histogram of oriented gradients (HOG) feature extraction combined with a support vector machine (SVM) classifier is used for make-model recognition. For the VCR task, five different neural network architectures are evaluated to identify the most effective solution. Results: The proposed system achieves an overall accuracy of 94.89% for vehicle make and model recognition. For vehicle color recognition, the best-performing models obtain a Top-1 accuracy of 94.17% and a Top-2 accuracy of 98.41%, demonstrating strong robustness under real-world traffic conditions. Conclusions: The experimental results show that the proposed automatic vehicle recognition system provides an efficient and reliable solution for appearance-based vehicle identification. By combining region-tailored data, segmentation-guided processing, and complementary recognition strategies, the system effectively supports real-world surveillance and law-enforcement scenarios where license plate recognition alone is insufficient. Full article

This study develops an automatic dispatch system for quadrotor UAVs that integrates air-writing gesture recognition with a graphical user interface (GUI). The DJI RoboMaster quadrotor UAV (DJI, Shenzhen, China) was employed as the experimental platform, combined with an ESP32 microcontroller (Espressif Systems, Shanghai, China) and the RoboMaster SDK (version 3.0). On the Python (version 3.12.7) platform, a GUI was implemented using Tkinter (version 8.6), allowing users to input addresses or landmarks, which were then automatically converted into geographic coordinates and imported into Google Maps for route planning. The generated flight commands were transmitted to the UAV via a UDP socket, enabling remote autonomous flight. For gesture recognition, a Raspberry Pi integrated with the MediaPipe Hands module was used to capture 16 types of air-written flight commands in real time through a camera. The training samples were categorized into one-dimensional coordinates and two-dimensional images. In the one-dimensional case, X/Y axis coordinates were concatenated after data augmentation, interpolation, and normalization. In the two-dimensional case, three types of images were generated, namely font trajectory plots (T-plots), coordinate-axis plots (XY-plots), and composite plots combining the two (XYT-plots). To evaluate classification performance, several machine learning and deep learning architectures were employed, including a multi-layer perceptron (MLP), support vector machine (SVM), one-dimensional convolutional neural network (1D-CNN), and two-dimensional convolutional neural network (2D-CNN). The results demonstrated effective recognition accuracy across different models and sample formats, verifying the feasibility of the proposed air-writing trajectory framework for non-contact gesture-based UAV control. Furthermore, by combining gesture recognition with a GUI-based map planning interface, the system enhances the intuitiveness and convenience of UAV operation. Future extensions, such as incorporating aerial image object recognition, could extend the framework’s applications to scenarios including forest disaster management, vehicle license plate recognition, and air pollution monitoring. Full article

In today’s fast-paced world, secure and efficient access control is crucial for places like schools, gated communities, and corporate campuses. The system must overcome the issues of manual checking and record maintenance of traditional methods like RFID cards or license plate recognition. Our work introduces a budget-friendly, automated solution. A prototype was developed for a vehicle sticker recognition system to control and monitor gate access at NFC IET University as a case study. The automated system design will replace manual checking by detecting the car stickers issued to each vehicle by the university administration. An optimized lightweight YOLOv8 model is trained to identify three categories: IET stickers (authorized for access), non-IET stickers (unauthorized), and no sticker (denied access). A webcam connected to the Raspberry Pi 4 scans approaching vehicles. Authorized vehicles are allowed when the relevant class is detected, which signals a servo motor to open the gate. Otherwise, access to the gate is denied, and infrared (IR) sensors close the gates. A second set of IR sensors and a servo motor was also added to manage the exit side, preventing unauthorized tailgating. The system’s modular design makes it adaptable for different environments, and its use of affordable hardware and open-source tools keeps costs low, which is ideal for smaller institutions or communities. The prototype model is tested and trained on self-collected datasets comprising 506 images. Full article

Accurate prediction of downstream vehicle arrivals is pivotal for intelligent signal control, yet many advanced controllers depend on high-resolution trajectories that are rarely available outside connected-vehicle settings. We present a deployable alternative that converts ubiquitous Automatic License Plate Recognition (ALPR) timestamps into the predictive inputs required by modern controllers. The method couples a Hidden Markov Model (HMM) for separating free-flow samples from signal-induced delays with a dynamic platoon-dispersion model that is re-estimated online in a rolling window to forecast downstream arrival profiles in real time. In a Simulation of Urban Mobility (SUMO) corridor testbed, the proposed framework consistently outperforms fixed-kernel dispersion and fixed-travel-time baselines, reducing RMSE by 57–75% and MAE by 53–73% across demand levels; ablation results confirm that HMM-based filtering is the dominant contributor to the gains. Robustness experiments further show stable parameter estimation under low ALPR matching rates, indicating suitability for real-world conditions where data quality fluctuates. Because it operates with existing roadside cameras and lightweight inference, the framework is readily integrable into adaptive signal strategies and broader smart-city traffic management. By turning discrete ALPR events into reliable arrival predictions, it bridges the gap between advanced signal control and today’s sensing infrastructure, enabling cost-effective real-time signal optimization in data-constrained urban networks. Full article

Parking space shortages are attributed to an increased density of vehicle presence in the urban context, necessitating the implementation of effective parking management strategies, especially in areas where facility expansion is constrained by limited land availability. Many parking facilities remain operationally inefficient and underutilized due to manual VP methods and having little access to parking resource utilization data. This study develops a DT-based SPMS integrating machine vision, data modeling, and DT technology to automate facility management operations. The system uses YOLOv7 for vehicle and License Plate Detection (LPD), and Deep Text Recognition–Scene Text Recognition (DTR-STR) for license plate recognition (LPR). The findings indicate an 89.89% accuracy for VP- and LPR-based occupancy tracking tasks, and 94.86% for vehicle detection or VD-based occupancy tracking. The system in the built environment comprises three features: (1) automated VP at parking entry and exit points, (2) occupancy monitoring through LPR, (3) Object Detection (OD) for occupancy tracking. The 3D BIM DT model in Autodesk Revit processes inference data from machine vision models to visualize parking activity. Full article