Search Results (210)

The growing popularity of Personal Light Electric Vehicles (PLEVs), such as e-scooters, has revolutionized urban mobility by offering compact, cost-effective, and environmentally friendly transportation solutions. However, safety concerns, including inadequate infrastructure, poor protective measures, and high accident rates, remain critical challenges. This paper presents the design and development of an innovative self-balancing microvehicle under the H2020 LEONARDO project, which aims to address these challenges through advanced engineering and user-centric design. The vehicle combines features of monowheels and e-scooters, integrating cutting-edge technologies to enhance safety, stability, and usability. The design adheres to European regulations, including Germany’s eKFV standards, and incorporates user preferences identified through representative online surveys of 1500 PLEV users. These preferences include improved handling on uneven surfaces, enhanced signaling capabilities, and reduced instability during maneuvers. The prototype features a lightweight composite structure reinforced with carbon fibers, a high-torque motorized front wheel, and multiple speed modes tailored to different conditions, such as travel in pedestrian areas, use by novice riders, and advanced users. Braking tests demonstrate deceleration values of up to 3.5 m/s², comparable to PLEV market standards and exceeding regulatory minimums, while smooth acceleration ramps ensure rider stability and safety. Additional features, such as identification plates and weight-dependent motor control, enhance compliance with local traffic rules and prevent misuse. The vehicle’s design also addresses common safety concerns, such as curb navigation and signaling, by incorporating large-diameter wheels, increased ground clearance, and electrically operated direction indicators. Future upgrades include the addition of a second rear wheel for enhanced stability, skateboard-like rear axle modifications for improved maneuverability, and hybrid supercapacitors to minimize fire risks and extend battery life. With its focus on safety, regulatory compliance, and rider-friendly innovations, this microvehicle represents a significant advancement in promoting safe and sustainable urban mobility. Full article

Occlusion remains a major challenge in person re-identification, as it often leads to incomplete or misleading visual cues. To address this issue, we propose a dual-branch occlusion-aware network (DOAN), which explicitly and implicitly enhances the model’s capability to perceive and handle occlusions. The proposed DOAN framework comprises two synergistic branches. In the first branch, we introduce an Occlusion-Aware Semantic Attention (OASA) module to extract semantic part features, incorporating a parallel channel and spatial attention (PCSA) block to precisely distinguish between pedestrian body regions and occlusion noise. We also generate occlusion-aware parsing labels by combining external human parsing annotations with occluder masks, providing structural supervision to guide the model in focusing on visible regions. In the second branch, we develop an occlusion-aware recovery (OAR) module that reconstructs occluded pedestrians to their original, unoccluded form, enabling the model to recover missing semantic information and enhance occlusion robustness. Extensive experiments on occluded, partial, and holistic benchmark datasets demonstrate that DOAN consistently outperforms existing state-of-the-art methods. Full article

Traditional 3D millimeter-wave radars lack target height information, leading to identification failures in complex scenarios. Upgrading to 4D millimeter-wave radars enables four-dimensional information perception, enhancing obstacle detection and improving the safety of autonomous driving. Given the high cost-sensitivity of in-vehicle radar systems, single-chip 4D millimeter-wave radar solutions, despite technical challenges in imaging, are of great research value. This study focuses on developing single-chip 4D automotive millimeter-wave radar, covering system architecture design, antenna optimization, signal processing algorithm creation, and performance validation. The maximum measurement error is approximately ±0.2° for azimuth angles within the range of ±30° and around ±0.4° for elevation angles within the range of ±13°. Extensive road testing has demonstrated that the designed radar is capable of reliably measuring dynamic targets such as vehicles, pedestrians, and bicycles, while also accurately detecting static infrastructure like overpasses and traffic signs. Full article

In computer vision, the performance of detectors trained under optimal lighting conditions is significantly impaired when applied to infrared domains due to the scarcity of labeled infrared target domain data and the inherent degradation in infrared image quality. Progress in cross-domain pedestrian re-identification is hindered by the lack of labeled infrared image data. To address the degradation of pedestrian recognition in infrared environments, we propose a framework for zero-shot infrared domain adaptation. This integrated approach is designed to mitigate the challenges of pedestrian recognition in infrared domains while enabling zero-shot domain adaptation. Specifically, an advanced reflectance representation learning module and an exchange–re-decomposition–coherence process are employed to learn illumination invariance and to enhance the model’s effectiveness, respectively. Additionally, the CLIP (Contrastive Language–Image Pretraining) image encoder and DINO (Distillation with No Labels) are fused for feature extraction, improving model performance under infrared conditions and enhancing its generalization capability. To further improve model performance, we introduce the Non-Local Attention (NLA) module, the Instance-based Weighted Part Attention (IWPA) module, and the Multi-head Self-Attention module. The NLA module captures global feature dependencies, particularly long-range feature relationships, effectively mitigating issues such as blurred or missing image information in feature degradation scenarios. The IWPA module focuses on localized regions to enhance model accuracy in complex backgrounds and unevenly lit scenes. Meanwhile, the Multi-head Self-Attention module captures long-range dependencies between cross-modal features, further strengthening environmental understanding and scene modeling. The key innovation of this work lies in the skillful combination and application of existing technologies to new domains, overcoming the challenges posed by vision in infrared environments. Experimental results on the SYSU-MM01 dataset show that, under the single-shot setting, Rank-1 Accuracy (Rank-1) andmean Average Precision (mAP) values of 37.97% and 37.25%, respectively, were achieved, while in the multi-shot setting, values of 34.96% and 34.14% were attained. Full article

Passengers often struggle to identify intended pickup locations when autonomous taxis (ATs) arrive, leading to confusion and delays. While prior external human–machine interface (eHMI) studies have focused on pedestrian crossings, few have systematically compared feedback modes and display positions for AT pickup guidance at varying distances. This study investigates the effectiveness of three eHMI feedback modes (Eye, Arrow, and Number) displayed at two positions (Body and Top) for communicating AT pickup locations. Through a controlled virtual reality experiment, we examined how these design variations impact user performance across key metrics including selection time, error rates, and decision confidence across varied parking distances. The results revealed distinct advantages for each feedback mode: Number feedback provided the fastest response times, particularly when displayed at the top position; Arrow feedback facilitated more confident decisions with lower error rates in close-range scenarios; and Eye feedback demonstrated superior performance in distant conditions by preventing severe identification errors. Body position displays consistently outperformed top-mounted ones, improving users’ understanding of the vehicle’s intended actions. These findings highlight the importance of context-aware eHMI systems that dynamically adapt to interaction distances and operational requirements. Based on our evidence, we propose practical design strategies for implementing these feedback modes in real-world AT services to optimize both system efficiency and user experience in urban mobility environments. Future work should address user learning challenges and validate these findings across diverse environmental conditions and implementation frameworks. Full article

To address the issues of missed detections and false detections of small target missed detections caused by dense occlusion in complex traffic environments, a non-maximum suppression method, Bot-NMS, is proposed to achieve accurate prediction and localization of occluded targets. In the backbone network of YOLOv7, the Ghost module, the ECA attention mechanism, and the multi-scale feature detection structure are introduced to enhance the network’s capacity to learn small target features. The SCSTD and KITTI datasets were used to train and test the improved YOLOv7 target detection network model. The results demonstrate that the improved YOLOv7 method significantly enhances the recall rate and detection accuracy of various targets. A multi-target tracking method based on target re-identification (ReID) is proposed. Utilizing deep learning theory, a ReID model for target identification is constructed to comprehensively capture global and foreground target features. By establishing the correlation cost matrix of the cosine distance and IoU overlap, the correlation between target detection objects, the tracking trajectory, and ReID feature similarity is realized. The VERI-776 vehicle re-identification dataset and MARKET1501 pedestrian re-identification dataset were used to train the proposed ReID model, and multi-target tracking performance comparison experiments were conducted on the MOT16 dataset. The results show that the multi-target tracking method by introducing the ReID model and improving the cost matrix can better deal with the dense occlusion of the target, and can effectively and accurately track the road target in the realistic complex traffic environment. Full article

The analysis of traffic crashes facilitates the identification of trends that can inform strategies to enhance road safety. This study aimed to detect high-risk zones and forecast collision patterns by integrating spatial analysis and predictive modeling. Traffic incidents along the Chone–Flavio Alfaro road segment in Manabí, Ecuador, were examined using Geographic Information Systems (GIS) and Kernel Density Estimation (KDE), based on official data from the National Traffic Agency (ANT) covering the period 2017–2023. Additionally, ARIMA, Prophet, and Long Short-Term Memory (LSTM) models were applied to predict crash occurrences. The most influential contributing factors were driver distraction, excessive speed, and adverse weather. Four main crash hotspots were identified: near Chone (PS 0–2.31), PS 2.31–7.10, PS 13.39–21.31, and PS 31.27–33.92, close to Flavio Alfaro. A total of 55 crashes were recorded, with side impacts (27.3%), pedestrian-related collisions (14.5%), and rear-end crashes (12.7%) being the most frequent types. The predictive models performed well, with Prophet achieving the highest estimated accuracy (90.8%), followed by LSTM (88.2%) and ARIMA (87.6%), based on MAE evaluations. These findings underscore the potential of intelligent transportation systems (ITSs) and predictive analytics to support proactive traffic management and resilient infrastructure development in rural regions. Full article

When natural disasters such as earthquakes occur, accurate navigation and positioning information may not be available, making a purely inertial pedestrian navigation system particularly important for rescuers. In this paper, researchers propose a zero-velocity update architecture for pedestrian navigation based on the Informer model, which is integrated into wearable devices. This architecture modifies the fully connected layer of the Informer model to be used for the binary classification task of the zero-velocity update method (ZUPT), allowing for accurate identification of gait information at each moment using only inertial measurement data. By wearing the device on the foot during natural disasters like earthquakes, the location of the pedestrian can be more accurately determined, facilitating rescue efforts. During the experimental process, a Kalman filter model was constructed to achieve zero-velocity updating of the pedestrian’s motion trajectory. A 2000 m walking experiment and a 210 m mixed-gait experiment were conducted to accurately identify gait information at each moment, thereby reducing the cumulative error of the inertial system. Subsequently, a convolutional neural network (CNN) model and a model combining CNN with a long short-term memory network (CNN + LSTM) were introduced as comparative experiments to verify the performance of the proposed architecture. The experimental results demonstrate that the proposed architecture enhances the adaptability of the zero-velocity update algorithm in underground or sheltered spaces, with all results outperforming the other two models. Full article

Due to the complexity of outdoor environments, we still face challenges in collecting up-to-date outdoor road network maps because of high data collection costs, resulting in a lack of navigation road network maps in outdoor scenarios. Existing road network extraction methods are mainly divided into trajectory data-based and remote sensing image-based methods. Due to factors such as tree occlusion, methods based on remote sensing images struggle to extract complete road information in outdoor environments. The methods based on trajectory data mainly use vehicle trajectories to extract two-dimensional roads, lacking three-dimensional (3D) road information such as elevation and slope, which are important for navigation path planning in outdoor scenarios. Given this, this paper proposes a hierarchical map construction method for extracting the three-dimensional outdoor pedestrian road network based on crowdsourced trajectory data. This method models the pedestrian road network as a graph composed of pedestrian areas, intersections, and road segments connecting these areas. Three-dimensional roads within and between the intersection areas are generated hierarchically. Experiments and comparative analyses were conducted using real-world outdoor trajectory datasets. Results show that the proposed method has higher accuracy in extracting 3D road information than existing methods. Full article

Vibration-based bridge modal identification is a crucial tool in monitoring and managing transportation infrastructure. Traditionally, this entails deploying a fixed array of sensors to measure bridge responses such as accelerations, determine dynamic characteristics, and subsequently infer bridge conditions that will facilitate prognosis and decision-making. However, such a paradigm is not scalable, possesses limited spatial resolution, and typically entails high effort and cost. Recently, mobile sensing-based paradigms have demonstrated promise in laboratory and field settings as an alternative. These methods can leverage big data from crowdsourcing vibration data acquired from smartphone devices belonging to pedestrians and passengers traveling over a bridge, constituting a significantly large data stream of indirectly sensed bridge response. Although the efficacy of such a paradigm has been demonstrated for a limited set of case studies, ubiquitous implementation requires analyzing the impact of vehicle dynamics and quantifying data sources that can be used for the purpose of bridge modal identification. This paper presents a road map for achieving this through dynamically diverse datastreams such as passenger cars, buses, bikes, and scooters. Existing datastreams point towards the implementation of crowdsourced mobile sensing paradigms in urban settings, which would facilitate effective decision-making for enhanced transportation infrastructure resilience. Full article

European cities are under pressure to be at the forefront of climate neutrality while providing inclusive, safe, and sustainable urban mobility. Street experiments are being adopted to accelerate this transition, yet assessing their impact remains challenging. This study addresses this gap by providing an evidence-based impact assessment of street experiments. The research builds on insights from 20 European cities, including 13 from the EU Cities Mission, regarding expected goals and current evaluation barriers. A preliminary quasi-experimental spatial and temporal approach is proposed and further enriched through the identification of the most relevant mobility domains and indicators addressed by cities. An exploration of data collection technologies is undertaken to meet the cities’ needs, culminating in the design of a portable and easy-to-install laboratory, the Labkit, for in situ and non-intrusive evaluation of public space interventions. The Labkit is tested and validated in an open area with a constant flow of pedestrians, cyclists, e-scooters, and vehicles. The results of this testing process, along with feedback from cities regarding the methodological approach and potential indicators, are analysed. The study concludes with a discussion of the opportunities and limitations of data-driven approaches for urban mobility impact assessment and the proposal of future research directions. Full article

Person re-identification (ReID) plays a crucial role in advancing UAV-based surveillance applications, enabling robust tracking and event analysis. However, existing methods in UAV scenarios primarily focus on individual pedestrians, requiring cumbersome annotation efforts and lacking seamless integration with ground-based surveillance systems. These limitations hinder the broader development of UAV-based monitoring. To address these challenges, this paper proposes an Unsupervised Aerial-Ground Re-identification from Pedestrian to Group (UAGRPG) framework. Specifically, we introduce a neighbor-aware collaborative learning (NCL) and gradual graph matching (GGC) strategy to uncover the implicit associations between cross-modality groups in an unsupervised manner. Furthermore, we develop a collaborative cross-modality association learning (CCAL) module to bridge feature disparities and achieve soft alignment across modalities. To quantify the optimal group similarity between aerial and ground domains, we design a minimum pedestrian distance transformation strategy. Additionally, we introduce a new AG-GReID dataset, and extensive experiments demonstrate that our approach achieves state-of-the-art performance on both pedestrian and group re-identification tasks in aerial-ground scenarios, validating its effectiveness in integrating ground and UAV-based surveillance. Full article

The rapid advancement of computer vision technology is transforming how transportation agencies collect roadway characteristics inventory (RCI) data, yielding substantial savings in resources and time. Traditionally, capturing roadway data through image processing was seen as both difficult and error-prone. However, considering the recent improvements in computational power and image recognition techniques, there are now reliable methods to identify and map various roadway elements from multiple imagery sources. Notably, comprehensive geospatial data for pedestrian and bicycle lanes are still lacking across many state and local roadways, including those in the State of Florida, despite the essential role this information plays in optimizing traffic efficiency and reducing crashes. Developing fast, efficient methods to gather this data are essential for transportation agencies as they also support objectives like identifying outdated or obscured markings, analyzing pedestrian and bicycle lane placements relative to crosswalks, turning lanes, and school zones, and assessing crash patterns in the associated areas. This study introduces an innovative approach using deep neural network models in image processing and computer vision to detect and extract pedestrian and bicycle lane features from very high-resolution aerial imagery, with a focus on public roadways in Florida. Using YOLOv5 and MTRE-based deep learning models, this study extracts and segments bicycle and pedestrian features from high-resolution aerial images, creating a geospatial inventory of these roadway features. Detected features were post-processed and compared with ground truth data to evaluate performance. When tested against ground truth data from Leon County, Florida, the models demonstrated accuracy rates of 73% for pedestrian lanes and 89% for bicycle lanes. This initiative is vital for transportation agencies, enhancing infrastructure management by enabling timely identification of aging or obscured lane markings, which are crucial for maintaining safe transportation networks. Full article

The primary aim of this study was to evaluate the spatial and temporal variation in human exposure to electromagnetic fields across different frequency bands within an urban area identified as the commercial zone of a medium-sized city. Central to this investigation was the use of an exposimeter, strategically positioned on the back of the operator and secured to the hip area via a belt, to ensure comprehensive and accurate field measurements. An initial analysis was conducted to determine the shielding coefficients of the human body, allowing for precise corrections of the electric field values used in the spatial assessment. To map power density across the study area for each frequency, kriging interpolation was applied. Furthermore, temporal variations in exposure levels were analyzed at three distinct times of day—morning business hours, afternoon business hours, and non-business hours—using robust statistical methods. The study’s innovative approach lies in the integration of GIS technology to uncover and visualize temporal patterns in exposure, particularly during periods of higher pedestrian density. This integration facilitated both the detection of temporal variations and the spatial representation of these changes, enabling rapid identification and assessment of exposure hotspots. Full article

Visible–infrared person re-identification (VI-ReID) aims to minimize the modality gaps of pedestrian images across different modalities. Existing methods primarily focus on extracting cross-modality features from the spatial domain, which often limits the comprehensive extraction of useful information. Compared with conventional approaches that either focus on single-frequency components or employ simple multi-branch fusion strategies, our method fundamentally addresses the modality discrepancy through systematic frequency-space co-learning. To address this limitation, we propose a novel bi-frequency feature fusion network (BiFFN) that effectively extracts and fuses features from both high- and low-frequency domains and spatial domain features to reduce modality gaps. The network introduces a frequency-spatial enhancement (FSE) module to enhance feature representation across both domains. Additionally, the deep frequency mining (DFM) module optimizes cross-modality information utilization by leveraging distinct features of high- and low-frequency features. The cross-frequency fusion (CFF) module further aligns low-frequency features and fuses them with high-frequency features to generate middle features that incorporate critical information from each modality. To refine the distribution of identity features in the common space, we develop a unified modality center (UMC) loss, which promotes a more balanced inter-modality distribution while preserving discriminative identity information. Extensive experiments demonstrate that the proposed BiFFN achieves state-of-the-art performance in VI-ReID. Specifically, our method achieved a Rank-1 accuracy of 77.5% and an mAP of 75.9% on the SYSU-MM01 dataset under the all-search mode. Additionally, it achieved a Rank-1 accuracy of 58.5% and an mAP of 63.7% on the LLCM dataset under the IR-VIS mode. These improvements verify that our model, with the integration of feature fusion and the incorporation of frequency domains, significantly reduces modality gaps and outperforms previous methods. Full article