Search Results (357)

Previous research has primarily focused on the restorative effects of environments on the general population, often overlooking the specific restorative capacity of urban settings for the disabled population. There is a lack of comprehensive investigation into the interaction between accessibility elements and urban restorativeness. This study, conducted in Shenzhen, Guangdong Province, China, categorizes streetscape accessibility elements for the disabled population and develops a recognition system based on an enhanced DeeplabV3+ framework. Semantic segmentation of streetscape accessibility elements was performed using 201,860 sampling points and 807,440 street view images. This study employed a combination of TrueSkill scoring, sentiment semantic analysis, LDA topic modeling, and LAB color clustering to quantify and visualize urban restorativeness. The impact of accessibility elements on urban restorativeness was explored using the XGBoost-SHAP model. Results indicate significant effects of architectural space constraints and high-density motor vehicle distribution on the safety of the disabled population’s mobility. The low pixel ratio of accessibility facilities and signs indicates insufficient infrastructure, while high landscape recognition rates exhibit significant spatial coverage heterogeneity. Detection rates for the disabled population in street views are nearly zero, highlighting a severe lack of inclusivity in pedestrian environments. Urban restorativeness exhibited a pattern of being higher in the south and east, and lower in the north and west. Among the accessibility elements, public green spaces (PGS) contributed the most to urban restorativeness, accounting for 25% of the impact, and the study elucidates the mechanisms through which various elements affect urban restorativeness. This absence stems from spatial competition, missing co-design, threshold effect conflicts, and color interference mechanisms. This research breaks away from traditional linear analytical frameworks and reveals the complex non-linear relationship between accessibility elements and urban restorativeness through the XGBoost-SHAP model, providing a quantitative decision-making tool for planning accessible environments in high-density cities. Full article

Urban traffic congestion remains a persistent global challenge, contributing to significant economic inefficiencies, elevated greenhouse gas emissions, and diminished quality of life. This paper presents a real-world video-based traffic monitoring study combined with a proposed adaptive signal control framework. In the monitoring component, YOLOv11 object detection was applied directly to footage recorded from an overhead bridge position on a 40 km/h road. The model successfully detected and tracked multiple road-user categories, including cars, trucks, buses, motorcycles, cyclists, and pedestrians, yielding 1041 vehicle detections across 25 unique tracked objects. Vehicle speeds were estimated from inter-frame centroid displacement, and a Region of Interest (ROI) occupancy model was used to classify congestion states as High, Medium, or Free Flow using thresholds grounded in Highway Capacity Manual (HCM) level-of-service criteria. The system detected 11 high-congestion frames (3.8%), 184 medium-congestion frames (63.9%), and 93 free-flow frames (32.3%), consistent with moderate congestion observed during the recording period. In the proposed control component, a Proximal Policy Optimisation (PPO)-based reinforcement learning signal controller is designed around the YOLOv11 detection outputs as its state representation. Based on comparable adaptive traffic signal control studies in the literature, the proposed framework is projected to achieve approximately 25% higher peak-hour throughput, 35% shorter queue lengths, and 32% lower average waiting times relative to a fixed-time signal baseline. The detection accuracy (mAP@0.5 = 93.2%) and inference speed (32 FPS) cited are published YOLOv11 benchmarks used as indicative performance references. This work bridges real-world perception and proposed intelligent control, providing a transparent and reproducible methodology for next-generation smart city traffic management. Full article

Road network extraction and updating are crucial for urban development, map updating, and mobility applications. Existing trajectory-based methods often underutilize grid-level semantic information and neighborhood context, thereby limiting their robustness to noisy, heterogeneous, and cross-city trajectory conditions. This study proposes a supervised framework for trajectory-driven road network extraction by coupling intra-grid movement semantics with inter-grid neighborhood context. Multi-level features, including convex-hull shape descriptors, directional clustering, DTW-based (Dynamic Time Warping) heterogeneity, and neighborhood density differences, are used to train a Random Forest classifier for key-grid detection. The detected key grids are further processed through morphology-aware thinning and Kalman smoothing to generate a topology-preserving and vectorization-ready road skeleton. The model is trained on pedestrian trajectories from Shenzhen and directly transferred to vehicle trajectories in Wuhan and Changsha under a zero-shot setting. Experimental results show that the proposed method achieves longer correctly extracted road length and competitive length-based precision compared with raster-based reference methods, while feature-importance and ablation analyses confirm the complementary role of neighborhood context. The proposed pipeline is scalable, interpretable, and transferable, supporting trajectory-based road map updating and urban network analysis. Full article

While Low Emission Zone (LEZ) enforcement cameras provide a constant stream of traffic data, such resources remain significantly underexploited for urban mobility planning, as their current application is restricted to enforcing vehicle access regulations and issuing fines. This paper presents MobiCugat, a framework demonstrating that Automatic Number Plate Recognition (ANPR) camera data from a municipal LEZ network can serve as the calibration backbone for high-fidelity, city-scale traffic simulations for a policy-testing Digital Twin. The case study is Sant Cugat del Vallès (Barcelona), where the local council sought to evaluate new scenarios for the area using an evidence-based, data-driven approach. Vehicle detection records from 102 LEZ ANPR cameras were processed into 15-min traffic intensity time series through a General Data Protection Regulation (GDPR)-compliant pipeline. The Realistic Urban Traffic Generator (RUTGe), a Deep Reinforcement Learning-based tool, was used to generate SUMO-compatible traffic demand whose simulated detector counts reproduce the observed camera-based intensities. The resulting simulations reproduced the observed detector-level traffic intensities with ${\mathrm{MARE}}_{\%}$ values between $2.29\%$ and $2.90\%$ across representative morning peak, midday off-peak, and evening peak traffic conditions. Additionally, camera analysis of over $470,000$ vehicle records revealed that resident traffic ($37.4\%$) dominates over through-traffic ($3.8\%$), significantly refining prior survey-based estimates. Our high-fidelity simulation tool based on SUMO, features realistic traffic patterns calibrated through AI-driven techniques, enabling the evaluation of diverse ’what-if’ scenarios—such as road closures, pedestrianization, changes in traffic direction, or relocation of bus stops. By quantifying the impact of these interventions, our tool facilitates informed decision-making prior to physical implementation. The proposed pipeline is cost-effective, privacy-preserving, and directly replicable for any municipality operating an LEZ camera network, offering a scalable template for evidence-based urban mobility planning, aligned with the European Strategy for Data and the EU Green Deal goals for sustainable mobility. Full article

Electric vehicles introduce new considerations for pedestrian safety because their lower operating noise at low speeds may reduce pedestrian detectability in urban traffic environments. This study proposes a simulation-based integrated active–passive pedestrian protection framework for electric vehicles by linking automatic emergency braking, active hood deployment, and post-crash head injury assessment. A total of 688 valid pedestrian–vehicle crash records from the National Highway Traffic Safety Administration database were analyzed, and 5 representative pedestrian crash scenarios were constructed through clustering-informed scenario screening and a benchmark pedestrian AEB scenario. The scenarios were reconstructed in a PreScan–Simulink co-simulation environment to evaluate a time-to-collision-based AEB strategy, while the active hood system was assessed using multi-body dynamics simulation and finite element head impact analysis. The AEB results showed that three scenarios were avoided before pedestrian contact, whereas two remained unavoidable, with residual impact speeds of approximately 31.5 km/h and 46 km/h. The hood reached a stable deployed posture within approximately 0.1 s under the modeled conditions. The HIC₁₅ results at eight selected impact points showed that speed reduction and hood deployment generally reduced head injury metrics, but full compliance with the reference HIC₁₅ threshold of 1000 was not achieved at all points. These findings suggest that the proposed strategy can improve simulated pedestrian head protection performance under selected electric vehicle crash scenarios, while further structural optimization, experimental validation, and cost–benefit assessments are still required. Full article

In open environments, lightweight pedestrian and vehicle detection models deployed on edge platforms of Unmanned Ground Vehicles (UGVs) often struggle to balance detection accuracy and inference efficiency when facing complex backgrounds, distant small targets, and occluded objects. To address this, we propose a lightweight object detection model based on YOLO11n, named UGV-Net. This model enhances feature interaction and global context modeling capabilities by introducing the C3k2_PS module, employs Dysample dynamic upsampling to achieve content-aware feature reconstruction, and designs an LSDECD detection head to reduce multi-scale prediction redundancy and computational overhead, thereby balancing detection accuracy and inference efficiency. Compared with the baseline model YOLO11n, UGV-Net improves F1 score, mAP50, and mAP50:95 by 2.19%, 2.26%, and 2.10%, respectively, on the KITTI dataset, while reducing GFLOPs from 6.3 to 4.9 and the number of parameters from 2.58M to 2.41M. Similarly, on the SODA10M and FLIR datasets, the F1 score improves by 1.71% and 1.41%, and mAP50 improves by 1.67% and 2.39%, respectively, demonstrating excellent detection accuracy and generalization ability. Furthermore, experiments on the Jetson Orin Nano platform verify that UGV-Net achieves robust real-time detection performance, making it an efficient, reliable, and lightweight solution for UGV perception in open environments. Full article

Reliable pedestrian perception in autonomous driving depends not only on detecting the target, but also on how completely and consistently its three-dimensional geometry is captured from different sensor viewpoints. This study presents a LiDAR-based observability framework for evaluating pedestrian representation on the ANTA compact autonomous vehicle platform using a roof-mounted Top LiDAR (TL), a Front-Right LiDAR (FRL), and their fused configuration. The pedestrian was analyzed in a canonical local frame using geometric extent ratios, projected surface occupancy, voxel-based volumetric occupancy, and statistical descriptors of the local point distribution, integrated into a global observability score, $S_{3D}$. A Distance-Robustness Index (DRI), an overlap-based complementarity analysis, and a lightweight temporal centroid-sensitivity check over 20 consecutive frames were used to characterize performance across distance. Using ROS 2 bag data processed offline in MATLAB R2025b the fused configuration achieved the highest mean global score (0.563), compared with 0.504 for FRL and 0.432 for TL, and the highest robustness ($\mathrm{DRI}=0.5628$, $CV=10.7\%$). The results show that 1 m maximizes local density, 2–3 m maximize projected and volumetric completeness, and 7 m provides the best balanced observability. Within the evaluated platform and under the controlled benchmark conditions, complementary multi-LiDAR fusion provided the strongest overall geometry-aware pedestrian representation. Full article

Many place recognition approaches, which identify previously visited places or locations by matching current sensory data, such as 2D RGB images and 3D point clouds, have been proposed to achieve accurate and robust localization and loop closure detection in global positioning system (GPS)-denied environments. Since visual place recognition (VPR) methods that rely on images captured by camera sensors are highly sensitive to variations in appearance, including changes in lighting, surface color, and shadows, they can lead to poor place recognition accuracy. In contrast, light detection and ranging (LiDAR)-based place recognition (LPR) approaches based on 3D point cloud data that captures the shape and geometric structure of the environment are robust to changes in place appearance and can therefore provide more reliable place recognition results than VPR methods. This work presents an indoor LPR method called PointNetVLAD-based indoor pedestrian localization (PIPL). PIPL is a deep network model that uses PointNetVLAD to learn to extract global descriptors from 3D LiDAR point cloud data. PIPL can recognize places previously visited by a pedestrian using point clouds captured by a low-cost LiDAR sensor on a smartphone in small-scale indoor environments, while PointNetVLAD performs place recognition for vehicles using high-cost LiDAR, GPS, and inertial measurement unit (IMU) sensors in large-scale outdoor areas. For place recognition on 3D point cloud reference maps generated from LiDAR scans, PointNetVLAD exploits the universal transverse mercator (UTM) coordinate system based on GPS and IMU measurements, whereas PIPL uses a virtual coordinate system designed in this study due to the unavailability of GPS indoors. In experiments conducted in campus buildings, PIPL shows significant advantages over NetVLAD (known as a convolutional neural network (CNN)-based VPR method). Particularly in indoor environments with repetitive scenes where geometric structures are preserved and image-based appearance features are sparse or unclear, PIPL achieved $39\%$ higher top-1 accuracy and $10\%$ higher top-3 accuracy compared to NetVLAD. Furthermore, PIPL achieved place recognition accuracy comparable to NetVLAD even with a small number of points in a 3D point cloud and outperformed NetVLAD even with a smaller model training dataset. The experimental results also indicate that PIPL requires over $76\%$ less place retrieval time than NetVLAD while maintaining robust place classification performance. Full article

Pulse-width-modulated (PWM) automotive headlights enhance nighttime event-based camera detection, yet systematic parameter optimization for vulnerable road user detection remains unexplored. This study evaluates PWM frequency, duty cycle, light distribution, ego-vehicle speed, and ambient lighting under European New Car Assessment Programme-inspired crossing scenarios for cyclist and pedestrian detection. Results establish performance ranging from substantial improvements to severe degradation relative to continuous illumination. Cyclist detection achieves robust performance with high-frequency modulation across light distributions, while low-frequency operation with low beam produces severe degradation through background noise accumulation. Pedestrian detection requires high beam with street lighting enabled; low beam universally fails regardless of modulation parameters. Limited parameter combinations achieve simultaneous improvements for both targets. Detection performs optimally on retroreflective surfaces, while low-reflectivity clothing limits capability, requiring target-specific optimization. Full article

This paper evaluates the feasibility of real-time traffic data analysis on resource-constrained edge devices using a hybrid processing approach. The proposed architecture integrates an LF Edge eKuiper complex event processing engine, deployed within Docker containers, with a native YOLO deep learning model for pedestrian detection. The model processes video frames at 480 × 240 resolution on CPU-only Raspberry Pi devices, achieving up to 30 FPS. The research specifically investigates the performance limits of Raspberry Pi 3 and Raspberry Pi 4 platforms when simultaneously processing high-throughput simulated traffic data from the SUMO simulator (Belgrade scenario, with vehicle distributions and densities adjusted for small, medium, and large traffic volumes) and live video streams, respectively. Experimental results indicate that while both platforms can process up to 2600 messages per second in the settings without image processing, the introduction of a camera sensor reveals a significant hardware bottleneck. The Raspberry Pi 4 maintains robust real-time performance with an average complex event detection latency of less than 500 ms. In contrast, the Raspberry Pi 3 exhibits severe performance degradation, with image processing delays exceeding 8 s, rendering it unsuitable for real-time safety alerts. The findings demonstrate that with appropriate hardware selection, edge-based complex event processing can successfully detect critical safety events, such as sudden vehicle acceleration near pedestrians, without relying on cloud infrastructure. Full article

In the context of urban renewal, the spatial interface of historic commercial districts functions as both a carrier of historical character and a key setting for commercial activity, public life, and local cultural expression. To address the limitations of conventional studies that rely heavily on field observation and qualitative description, this study takes Xiaohe Zhijie in Hangzhou as a case and develops a multi-level street-view recognition framework for the quantitative analysis of spatial interface characteristics. Based on street-view image collection and standardized preprocessing, a sample database was established at the sampling-point scale. Semantic segmentation, automated commercial object detection, and manual interpretation were combined to identify interface elements, including buildings, sky, greenery, pavement, vehicles, pedestrians, and commercial objects, while commercial content was assessed in terms of locality and homogenization. The results show that Xiaohe Zhijie exhibits a building-dominated and relatively enclosed interface pattern, with greenery and pavement forming the basic environmental ground, weak vehicle interference, and localized enhancement of vitality through commercial objects and pedestrian activities. Significant differences were found among street segments in openness, commercial coverage, and local expression. Three interface types were identified: commercial–cultural composite, local life-oriented, and waterfront landscape–cultural composite. The main challenge lies not in commercialization itself, but in stronger visual locality than content locality and increasing homogenization, resulting in a pattern of “localized form but homogenized content.” Full article

This paper presents ANAID (Autonomous Naturalistic obstacle-Avoidance Interaction Dataset), a new multimodal dataset designed to support research on autonomous driving, particularly with regard to obstacle avoidance and naturalistic driver–vehicle interaction. Data were collected using a Hyundai Tucson Hybrid equipped with a Comma-3X autonomous-driving development kit, combining high-resolution front-facing video with detailed CAN-bus telemetry. The dataset comprises four data collection campaigns, each corresponding to a single continuous driving session, yielding a total of 208 videos and 240,014 synchronized frames. In addition to the video data, the dataset provides vehicle state measurements (speed, acceleration, steering, pedal positions, turn signals, etc.) and an additional annotation layer identifying evasive maneuvers derived from steering-related signals. Data were recorded across four driving campaigns on an urban circuit at Universidad Europea de Madrid, capturing diverse real-world scenarios such as roundabouts, intersections, pedestrian areas, and segments requiring obstacle avoidance. A multi-stage processing pipeline aligns telemetry and visual data, extracts frames at 20 FPS, and detects evasive maneuvers using threshold-based time-series analysis. ANAID provides a fully aligned and non-destructive representation of naturalistic driving behavior, enabling research on control prediction, driver modeling, anomaly detection, and human–autonomy interaction in realistic traffic conditions. Full article

As autonomous driving technology progresses, efficient and accurate object detectors are able to detect pedestrians, vehicles, road signs, and obstacles in real time, thereby enhancing driving safety and serving as a part of autonomous driving. However, the performance of such object detectors is limited and cannot be leveraged to satisfy modern autonomous driving systems. To address this issue, we develop an object detection network for autonomous driving scenarios, SST-YOLO, which is based on YOLOv8. First, we propose a Sobel Convolution & Convolution (SCC) module to enhance the backbone, which incorporates a SobelConv branch to explicitly model gradient-based edge information and improve structural feature representation. In addition, we replace the original path aggregation feature pyramid network (PAFPN) with a Small Object Augmentation Pyramid Network (SOAPN), which integrates SPDConv and CSP-OmniKernel modules to strengthen multi-scale feature fusion and enhance small object representation. Finally, a Task-Adaptive Decomposition & Alignment Head (TADAHead) is designed, which employs task decomposition, dynamic deformable convolution, and classification-aware modulation to decouple tasks and achieve adaptive spatial alignment, thereby improving detection accuracy and robustness in complex scenarios. Experiments on the public autonomous driving dataset KITTI show that our proposed method outperforms the baseline YOLOv8 model. Compared with the baseline results, mAP@0.5:0.95 ranges from 65.1% to 69.2%, which indicates that the proposed SST-YOLO network can achieve object detection for autonomous cars. Full article

Near-miss events, defined as hazardous traffic interactions without actual collisions, provide valuable indicators for proactive traffic safety assessment. However, existing studies mainly focus on collision detection or object-level perception, while near-miss interactions and their severity remain insufficiently explored. This study proposes a video-based framework for real-time near-miss detection and risk evaluation in complex urban intersections. The framework integrates an enhanced YOLOv11 detector with a small-object detection head, BoT-SORT multi-object tracking, and bird’s-eye-view (BEV) transformation to accurately extract trajectories and motion features of heterogeneous road users. A Near-Miss Risk Index (RI) is developed by jointly considering spatial proximity, time-to-collision, and motion intensity to quantify near-miss severity levels. Experimental results on real-world CCTV data demonstrate that the proposed method effectively identifies high-risk interactions among vehicles, motorcycles, and pedestrians, providing interpretable severity assessment and supporting proactive traffic safety analysis for intelligent transportation systems. Full article

Effective traffic control using Artificial Intelligence (AI) is essential to ensure safe passage for all road users. AI-based collision detection systems offer advanced mechanisms to prevent accidents and improve highway safety. This research investigates two distinct collision scenarios: vehicle–pedestrian and vehicle–motorcyclist interactions. The proposed method in this research involves the bidirectional Long Short Term Memory (LSTM), Convolutional Neural Network with LSTM (CNN–LSTM), and transformer models. The model is furthermore tuned using random or grid search. For the pedestrian–vehicle scenario, the CNN–LSTM model achieved 99.76% accuracy, 99.77% precision, and 99.76% recall, highlighting its strong classification performance. In the vehicle–motorcyclist scenario, the bidirectional LSTM reached 99.73% accuracy with precision and recall of 99.15%, demonstrating its effectiveness in detecting imminent crashes. The optimized CNN-LSTM by random search has focused on decreasing the false-positive rate and increasing the positive rate. It has achieved superior results compared to previous research. These results suggest that the system could be effectively implemented as an early collision warning solution on edge devices. Full article