Search

Given the dangers pedestrians are susceptible to when crossing the roadway, an investigation of motorists' yielding decisions at uncontrolled crossings should be prioritised. Some encounters between motorists and pedestrians turn into injuries or deaths due to excessive delay on the part of drivers, and pedestrians' impatience might lead them to opt for the rolling gap. Insights into drivers' yielding behaviour in developing countries are lacking. Meanwhile, developing countries contribute significantly to traffic deaths, particularly those in the African Region. Understanding drivers' yielding behaviour is necessary for effective interventions to safeguard pedestrians and encourage safe walking. Accordingly, by deploying a backward binary logit model, this study investigated drivers' yielding behaviour at marked uncontrolled pedestrian crossings through naturalistic observation. The results revealed that a small share of drivers, 258, were observed to yield to pedestrians, representing a 28% yielding rate in total. The model indicates that the chances of motorists yielding to pedestrians are enhanced by the following factors: pedestrian age, density, gender and traffic condition. Private car drivers had the lowest yielding rate of 18.2%, followed closely by public transport drivers. This research contributes to the discourse on drivers' yielding behaviour at pedestrian crossings with perspectives from a developing country. Further, it discusses policy implications for policymakers and enforcement agencies.

Abstract Visible‐infrared person re‐identification (VI‐ReID) aims to recognize images of the same person captured in different modalities. Existing methods mainly focus on learning single‐granularity representations, which have limited discriminability and weak robustness. This paper proposes a novel dual‐granularity feature fusion network for VI‐ReID. Specifically, a dual‐branch module that extracts global and local features and then fuses them to enhance the representative ability is adopted. Furthermore, an identity‐aware modal discrepancy loss that promotes modality alignment by reducing the gap between features from visible and infrared modalities is proposed. Finally, considering the influence of non‐discriminative information in the modal‐shared features of RGB‐IR, a greyscale conversion is introduced to extract modality‐irrelevant discriminative features better. Extensive experiments on the SYSU‐MM01 and RegDB datasets demonstrate the effectiveness of the framework and superiority over state‐of‐the‐art methods.

Background: Protective behavior is recommended to prevent COVID-19. However, the existing gap is no reliable evidence of protective behavior in southern urban areas in Iran. This study aims to estimate the prevalence of face mask usage and shield use among pedestrians in the Abadan, Khoramshahr, and Shadegan southern cities of Iran. Methods: This population-based cross-sectional study was conducted from June to August 2021 in the southwestern urban population of Iran. In this study, 7 425 pedestrians were selected from 85 neighborhoods. Sampling was conducted using a multi-stage method. The data were collected by observation passers on the street with a checklist and analyzed by SPSS software, version 26 statistical and WINPEPI software. The acceptable significance level was P

Accurately predicting the future trajectory of pedestrians is critical for tasks such as autonomous driving and robot navigation. Previous methods for pedestrian trajectory prediction dealt with social interaction and pedestrian movement factors either concurrently or sequentially, neglecting the link between them. Therefore, a spatial–temporal interaction-aware graph convolution network (STIGCN) is proposed for pedestrian trajectory prediction. STIGCN considers the correlation between social interaction and pedestrian movement factors to achieve more accurate interaction modeling. Specifically, we first constructed spatial and temporal graphs to model social interactions and movement factors. Then, we designed the spatial–temporal interaction-aware learning to utilize the spatial interaction features of each moment to assist the temporal interaction modeling and utilize the temporal interaction features of each pedestrian to assist the spatial interaction modeling, resulting in more accurate interaction modeling. Finally, a time-extrapolator pyramid convolution neural network (TEP-CNN) is designed to jointly estimate the two-dimensional Gaussian distribution parameters of future trajectories by combining the prediction features from multiple layers. Experimental results on two benchmark pedestrian trajectory prediction datasets show that our proposed method outperforms existing methods in terms of average displacement error and final displacement error and achieves more accurate predictions for pedestrian motions such as convergence and encounter. [ABSTRACT FROM AUTHOR]

Background: According to social-ecological models, the built and natural environment has the potential to facilitate or hinder physical activity (PA). While this potential is well researched in urban areas, a current systematic review of how the built and natural environment is related to PA in rural areas is lacking. Methods: We searched five databases and included studies for adults (18–65 years) living in rural areas. We included quantitative studies investigating the association between any self-reported or objectively measured characteristic of the built or natural environment and any type of self-reported or objectively measured PA, and qualitative studies that reported on features of the built or natural environment perceived as barriers to or facilitators of PA by the participants. Screening for eligibility and quality assessment (using the Standard Quality Assessment Criteria for Evaluating Primary Research Papers from a Variety of Fields) were done in duplicate. We used a narrative approach to synthesize the results. Results: Of 2432 non-duplicate records, 51 quantitative and 19 qualitative studies were included. Convincing positive relationships were found between the availability and accessibility of places for exercise and recreation and leisure-time PA as well as between the overall environment and leisure-time PA. Possible positive associations were found between the overall environment and total and transport-related PA, between greenness/natural environment and total PA, between cycling infrastructure and aesthetics and MVPA, and between pedestrian infrastructure and total walking. A possible negative relationship was found between safety and security and total walking. Qualitative studies complemented several environmental facilitators (facilities for exercise and recreation, sidewalks or streets with low traffic, attractive natural environment) and barriers (lack of facilities and destinations, lack of sidewalks, speeding traffic and high traffic volumes, lack of street lighting). Conclusions: Research investigating the relationship between the built and natural environment and PA behaviors of adults living in rural areas is still limited and there is a need for more high-quality and longitudinal studies. However, our most positive findings indicate that investing in places for exercise and recreation, a safe infrastructure for active transport, and nature-based activities are possible strategies that should be considered to address low levels of PA in rural adults. Trial registration: PROSPERO: CRD42021283508. [ABSTRACT FROM AUTHOR]

Intensive urban development has resulted in the degradation of the urban thermal environment in most regions. There is a growing consensus on the need to enhance urban thermal comfort through well-designed forms, especially in open spaces like urban canyons. To address this, our study focuses on Xi'an's commercial pedestrian streets, employing K-means clustering analysis to create 32 representative models based on actual scenes, capturing their textural characteristics. Simultaneously, 11 geometric indicators (2D/3D) were chosen to quantify the canyon's geometric form. We assessed the spatial and temporal distribution differences in the thermal environment across these models using Envi-met simulation. Finally, Spearman correlation analysis was employed to examine the correlation and significance of the two sets of indicators, culminating in formulating an ideal model. The findings reveal that (1) wind conditions are predominantly influenced by the canyon's geometric form, followed by solar radiation and temperature, with the lowest relative humidity change amplitude among the assessed thermal parameters. (2) Among the 11 geometric form indicators, 3D indicators correlate more significantly with thermal environment parameters than 2D indicators. Specifically, street orientation significantly impacts the thermal environment, Build-To-Line Rat holds greater significance than interface density, and both building shape coefficient and block surface ratio are significantly correlated with air temperature and wind speed, with a weaker correlation to solar radiation. (3) In the Xi'an region, courtyards oriented north-south demonstrate a more favorable trend in the thermal environment. [ABSTRACT FROM AUTHOR]

Several researchers have modified the original Social Force Model (SFM) for pedestrians by including vehicles and simulating interaction behaviors in shared space layouts. The present study is conducted at a signalized intersection where the performance and functionality are defined by spontaneous order. The SFM was modified, and two-wheelers were added along with cars and pedestrians to analyze their interactions. The Hybrid Calibration Method was adopted to calibrate the interaction parameters utilizing an optimization technique and real-time data from the study site. It can be concluded from the parameter values that the strength of interaction reduced as the range between the road agents increased. The findings can aid urban planners in visualizing the interaction behavior of pedestrians, cars, and two-wheelers. Moreover, the feasibility of introducing the shared space concept in India as an alternative to the conventional traffic planning system can also be determined during the designing phase. [ABSTRACT FROM AUTHOR]

Many enclosed public spaces with multiple destinations often feature obstacles, such as columns within the building space and dense crowds, which adversely affect the recognition and guidance of pedestrian sign. To mitigate this issue, enhancing traffic efficiency necessitates the implementation of auxiliary guidance signs. However, experience-based schemes for positioning these signs often require iterative adjustments to achieve the desired effect. Thus, this paper endeavors to address this challenge by analyzing the relationship between obstacles and pedestrians' visual blind areas. It establishes a mathematical model to describe pedestrian visual perception and its correlation with crowd density and individual visual field function. The model employs the effective aggregation area of the population exceeding a certain density threshold as its primary variable and enhances this variable's function. Subsequently, it formulates an effect function that yields a substantial improvement in various combinations and permutations of auxiliary guidance signs. To exemplify this research, a large subway transfer hall with multiple destinations serves as a simulation model. The study calculates the optimal combination of auxiliary guidance sign placements that align with the enhancement effect function. Based on this combination, an optimized layout plan is derived, resulting in a significant improvement. The results demonstrate that the auxiliary guidance sign layout scheme proposed in this study markedly enhances traffic efficiency in enclosed public spaces. This research serves as a valuable reference for decision-makers seeking to optimize traffic flow in such spaces. [ABSTRACT FROM AUTHOR]

Green spaces are important elements of cities due to their benefits to residents' physical health, mental health and development, and social connections. Residents are more likely to experience green space benefits when they use them frequently and usage increases when amenities are accessible. Because lower-income households often have less reliable access to automobiles, examining access solely on the road network is inadequate. Do households across the socioeconomic spectrum have access to green space on pedestrian and bicycle networks? After estimating residential locations (origins) from U.S. Census data and park and other green space locations (destinations) from the City of Albuquerque data, we connect the two using service area network analyses in a geographic information system (GIS). Findings suggest that overall green space access is a concern since less than 50% of Albuquerque residents have access to a green space within 400 m, indicating levels below those recommended by the World Health Organization. Park accessibility is relatively equally distributed for low-, middle-, and high-income households across both pedestrian and road networks. Access to other green space is a source of possible inequity with high-income households having more than five times the access to non-park green spaces than low-income households. The bike network presents another source of possible inequity as 39% of high-income households have access to the bike network versus only 30% of low-income households and an expansion of the bike network is a primary recommendation for increasing access in an equitable fashion. [ABSTRACT FROM AUTHOR]

This paper addresses the global optimal signal plan of a fixed time control for an isolated signalized intersection with central pedestrian refuges considering both vehicle delays and pedestrian delays. A signal phase plan, a pedestrian signal setting scheme, and a signal timing plan are all part of the signal plan presented here. Pedestrian delays are explicitly formulated with signal timing parameters considering signal phase plans and pedestrian signal setting schemes. Integer nonlinear combinatorial programming models are proposed to minimize average and total delays. Numerical experiments show that the proposed optimization models outperform the existing ones, especially when traffic demands between phases are unbalanced. The analysis of the results shows that separate pedestrian signalization settings, and adjacent (or nonadjacent) allowed crossing phases for pedestrians at central islands are superior signal plan options when the minimum phase time is insufficient (or sufficient) to accommodate the minimum green time for crosswalks. [ABSTRACT FROM AUTHOR]

Objective: This study used a virtual environment to examine how older and younger pedestrians responded to simulated augmented reality (AR) overlays that indicated the crossability of gaps in a continuous stream of traffic. Background: Older adults represent a vulnerable group of pedestrians. AR has the potential to make the task of street-crossing safer and easier for older adults. Method: We used an immersive virtual environment to conduct a study with age group and condition as between-subjects factors. In the control condition, older and younger participants crossed a continuous stream of traffic without simulated AR overlays. In the AR condition, older and younger participants crossed with simulated AR overlays signaling whether gaps between vehicles were safe or unsafe to cross. Participants were subsequently interviewed about their experience. Results: We found that participants were more selective in their crossing decisions and took safer gaps in the AR condition as compared to the control condition. Older adult participants also reported reduced mental and physical demand in the AR condition compared to the control condition. Conclusion: AR overlays that display the crossability of gaps between vehicles have the potential to make street-crossing safer and easier for older adults. Additional research is needed in more complex real-world scenarios to further examine how AR overlays impact pedestrian behavior. Application: With rapid advances in autonomous vehicle and vehicle-to-pedestrian communication technologies, it is critical to study how pedestrians can be better supported. Our research provides key insights for ways to improve pedestrian safety applications using emerging technologies like AR. [ABSTRACT FROM AUTHOR]

This exploratory study aimed to evaluate the preferences, expectations, and sense of safety of blind or visually impaired persons regarding three types of pedestrian phasing with audible pedestrian signals configurations that exist in Quebec City (Canada). These include: 1) exclusive phasing with non-directional audible pedestrian signals; 2) exclusive phasing with directional audible pedestrian signals; and 3) concurrent phasing with directional audible pedestrian signals. Thirty-two blind or visually impaired persons were asked to complete a survey. Their preferences and expectations regarding audible pedestrian signals were documented through a series of simulations. Their sense of safety regarding the three existing configurations were also documented. Subsequently, semi-directed, individual interviews with 11 of the individuals who had completed the survey were conducted to build off the collected information. No formal consensus regarding many of the issues discussed were established as participants' responses varied too significantly. However, findings suggest that the exclusive phasing with directional audible pedestrian signals configuration is perceived to be the safest option by the participants. This study may have practical implications on the design of intersections (e.g., selection of a type of pedestrian phasing with audible pedestrian signal) and the training of blind or visually impaired pedestrians. The addition of audible pedestrian signals to pedestrian signals heightens the sense of safety of blind or visually impaired persons. This study may have practical implications on the design of intersections with audible pedestrian signals and the selection of a type of audible pedestrian signals based on intersection characteristics. Since many participants reported a lower sense of safety when faced with concurrent phasing, it is recommended that more intensive orientation and mobility interventions be provided to blind or visually impaired pedestrians who use this type of traffic signals. Educating road users about blind or visually impaired pedestrians appears also essential. [ABSTRACT FROM AUTHOR]

Background: Active commuting to school can be a meaningful contributor to overall physical activity in children. To inform better micro-level urban design near schools that can support active commuting to school, there is a need for measures that capture these elements. This paper describes the adaptation of an observational instrument for use in assessing micro-scale environments around urban elementary schools in the United States. Methods: The Micro-scale Audit of Pedestrian Streetscapes for Safe Routes to School (MAPS-SRTS) was developed from existing audit instruments not designed for school travel environments and modifications for the MAPS-SRTS instrument include the structure of the audit tool sections, the content, the observation route, and addition of new subscales. Subscales were analyzed for inter-rater reliability in a sample of 36 schools in Austin, TX. To assess reliability for each subscale, one-way random effects single-measure intraclass correlation coefficients (ICC) were used. Results: Compared to the 30 original subscales, the adapted MAPS-SRTS included 26 (86.6%) subscales with revised scoring algorithms. Most MAPS-SRTS subscales had acceptable inter-rater reliability, with an ICC of 0.97 for the revised audit tool. Conclusions: The MAPS-SRTS audit tool is a reliable instrument for measuring the school travel environment for research and evaluation purposes, such as assessing human-scale determinants of active commuting to school behavior and documenting built environment changes from infrastructure interventions. [ABSTRACT FROM AUTHOR]

The article focuses on the accessibility challenges faced by visually impaired individuals, particularly at street intersections, and the role of Accessible Pedestrian Signals (APS) in addressing these challenges. It discusses the legal framework provided by the Americans with Disabilities Act (ADA) and related statutes, examines relevant court cases, and advocates for the implementation of APS as a solution to enhance the independent navigation of blind and low-vision pedestrians.

Point cloud object detection is gradually playing a key role in autonomous driving tasks. To address the issue of insensitivity to sparse objects in point cloud object detection, we have made improvements to the voxel encoding and 3D backbone network of the PVRCNN++. We have introduced adaptive pooling operations during voxel feature encoding to expand the point cloud information within each voxel, followed by the utilization of multi-layer perceptrons to extract richer point cloud features. On the 3D backbone network, we have employed adaptive sparse convolution operations to make the backbone network's channel count more flexible, allowing it to accommodate a wider range of input data types. Furthermore, we have integrated Focal Loss to tackle the issue of class imbalance in detection tasks. Experimental results on the public KITTI dataset demonstrate significant improvements over the PVRCNN++, particularly in pedestrian and bicycle detection tasks. Specifically, we have observed 1% increase in detection accuracy for pedestrians and 2.1% improvement for bicycles. Our detection performance also surpasses that of other comparative detection algorithms. [ABSTRACT FROM AUTHOR]

Ensuring real-time performance while leveraging pedestrian detection is a crucial prerequisite for intelligent driving technology. The development of lightweight models with good detection accuracy is also crucial. This work proposes a novel method, the Attention Digital Filter with Anchor-Free Feature Pyramid Learning Model (ADFAFPLM), to meet these needs. The suggested method consists of combining two networks: one is a digital filter based on an attention network that eliminates noise and other picture distortions. The attention-based residual network digital filters are chosen for their enhanced filtering performance, adaptability, efficient learning through residual connections, noise suppression, interpretability, and generalization capabilities. Next, from the input crowded and occluded photos, the pedestrian is identified using an anchor-free feature pyramid network. The Eurocity person dataset was used to train the model, and it was also tested on other datasets like CityPersons, INRIA, PennFudan, and Eurocity. The investigation was expanded to include images in hazy, noisy, and occlusion environments, among other environmental conditions. The image resolutions were also considered for analysis and it was observed that with increasing image resolution, the mAP increases. Based on the ablation study, the ADF-AFPLM adopted YOLOv8n with batch size 16, and image size 640 is considered for efficient result with different testing datasets. The model achieved a mean average precision (mAP) of approx. 87% and shows its efficacy over state-of-art models. [ABSTRACT FROM AUTHOR]

Person re-identification relies on discriminative features. However, most researches focus on extracting features from the high-layer of network while ignoring the middle-layer features, some important details are overlooked frequently. To address this issue, we propose a Multi-Scale and Multi-Patch Feature Fusion Network(MSPF). We employ modified OSFA to extract, align, and fuse the feature maps in the middle-layer of network, which can compensate for the lack of detailed information in the high-level network features. To obtain richer detailed global features of pedestrian, we construct a multi-patch feature fusion module(MPF). We concatenate the global features extracted from modified OSFA and MPF to obtain global features with richer detailed representations. Cross-entropy loss, triplet loss and center loss are combined to constrain our model. We evaluate the performance of our model on Market-1501, CUHK03_labeled and DukeMTMC. The results prove that our method is superior to the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Pedestrian trajectory prediction plays a crucial role in autonomous driving, as its accuracy directly affects the autonomous driving system's comprehension of the environment and subsequent decision-making processes. Current trajectory prediction methods tend to oversimplify pedestrians to mere point coordinates, utilizing positional information to infer interactions among individuals while overlooking the temporal correlations between them, thereby excessively simplifying pedestrian characteristics. To address the aforementioned issues, this paper proposes a trajectory prediction model for autonomous driving applications, that takes into account both pedestrian motion characteristics and scene interaction. The model optimizes the LSTM unit structure twice, serving to learn correlations among long trajectories of pedestrians and to integrate multiple forms of information into the neighborhood interaction module. Furthermore, our model introduces dual attention mechanisms for individuals and scenes, focusing on the key motion points of individual pedestrians and their interactive behavior with others in busy scenarios. The efficacy of the model was validated on the MOT16 pedestrian dataset and the Daimler pedestrian path prediction dataset, outperforming mainstream methods with 8% and 10% reductions in Average Displacement Error and Final Displacement Error respectively. [ABSTRACT FROM AUTHOR]

Pedestrian detection plays a crucial role in ensuring traffic safety within the domain of computer vision. However, accurately detecting pedestrians in complex environments proves to be a challenge due to issues such as occlusion. To address this issue, this paper presents an end-to-end pedestrian detection model founded on the DEtection TRansformer (DETR) architecture, effectively managing occlusion scenarios. The proposed model comprises a backbone Convolutional Neural Network (CNN) and a Transformer network. The backbone CNN incorporates variable convolution and U-Net design principles to enhance feature extraction capabilities, particularly for occluded pedestrians. Additionally, our innovative Adaptive Occlusion-Aware Attention Mechanism (AOAM) is embedded within the Transformer network, allowing the model to dynamically adjust attention weights and enhance the localization and identification of occluded pedestrians. Extensive experiments on the Caltech and ETH datasets demonstrate the superior performance of our model compared to state-of-the-art approaches across four key evaluation metrics. This study provides effective methodologies and theoretical foundations for pedestrian detection in complex environments. [ABSTRACT FROM AUTHOR]

Numerous technologies and systems, including autonomous vehicles, surveillance systems, and robotic applications, rely on the capability to accurately detect pedestrians to ensure their safety. As the demand for realtime object detection continues to rise, many researchers have dedicated their efforts to developing effective and trustworthy algorithms for pedestrian recognition. By integrating learning complexity-aware cascades with an enhanced you only look once (YOLO) algorithm, the paper presents a real-time system for identifying both items and pedestrians. The performance of the proposed approach is evaluated using the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) pedestrian dataset across both the v4 and v8 versions of the YOLO framework. Prioritizing both speed and accuracy, the enhanced YOLO algorithm outperforms its baseline counterpart. The demonstrated superiority of the suggested technique on the KITTI pedestrian dataset underscores its effectiveness in real-world contexts. Furthermore, the complexity-aware learning cascades contribute to a streamlined detection model without compromising performance. When applied to scenarios requiring real-time identification of objects and individuals, the proposed method consistently delivers promising outcomes. [ABSTRACT FROM AUTHOR]

We propose an extension of the anisotropic interaction model which allows for collision avoidance in pairwise interactions by a rotation of forces (Totzeck (2020) Kinet. Relat. Models 13 (6), 1219–1242.) by including the agents' body size. The influence of the body size on the self-organisation of the agents in channel and crossing scenarios as well as the fundamental diagram is studied. Since the model is stated as a coupled system of ordinary differential equations, we are able to give a rigorous well-posedness analysis. Then we state a parameter calibration problem that involves data from real experiments. We prove the existence of a minimiser and derive the corresponding first-order optimality conditions. With the help of these conditions, we propose a gradient descent algorithm based on mini-batches of the data set. We employ the proposed algorithm to fit the parameter of the collision avoidance and the strength parameters of the interaction forces to given real data from experiments. The results underpin the feasibility of the method. [ABSTRACT FROM AUTHOR]

Nowadays, with the rapid development of consumer Unmanned Aerial Vehicles (UAVs), utilizing UAV platforms for visual surveillance has become very attractive, and a key part of this is remote vision-based pedestrian attribute recognition. Pedestrian Attribute Recognition (PAR) is dedicated to predicting multiple attribute labels of a single pedestrian image extracted from surveillance videos and aerial imagery, which presents significant challenges in the computer vision community due to factors such as poor imaging quality and substantial pose variations. Despite recent studies demonstrating impressive advancements in utilizing complicated architectures and exploring relations, most of them may fail to fully and systematically consider the inter-region, inter-attribute, and region-attribute mapping relations simultaneously and be stuck in the dilemma of information redundancy, leading to the degradation of recognition accuracy. To address the issues, we construct a novel Mask-Relation-Guided Transformer (MRG-T) framework that consists of three relation modeling modules to fully exploit spatial and semantic relations in the model learning process. Specifically, we first propose a Masked Region Relation Module (MRRM) to focus on precise spatial attention regions to extract more robust features with masked random patch training. To explore the semantic association of attributes, we further present a Masked Attribute Relation Module (MARM) to extract intrinsic and semantic inter-attribute relations with an attribute label masking strategy. Based on the cross-attention mechanism, we finally design a Region and Attribute Mapping Module (RAMM) to learn the cross-modal alignment between spatial regions and semantic attributes. We conduct comprehensive experiments on three public benchmarks such as PETA, PA-100K, and RAPv1, and conduct inference on a large-scale airborne person dataset named PRAI-1581. The extensive experimental results demonstrate the superior performance of our method compared to state-of-the-art approaches and validate the effectiveness of mask-relation-guided modeling in the remote vision-based PAR task. [ABSTRACT FROM AUTHOR]

Predicting human trajectories poses a significant challenge due to the complex interplay of pedestrian behavior, which is influenced by environmental layout and interpersonal dynamics. This complexity is further compounded by variations in scene density. To address this, we introduce a novel dataset from the Festival of Lights in Lyon 2022, characterized by a wide range of densities (0.2–2.2 ped/ m 2 ). Our analysis demonstrates that density-based classification of data can significantly enhance the accuracy of predictive algorithms. We propose an innovative two-stage processing approach, surpassing current state-of-the-art methods in performance. Additionally, we utilize a collision-based error metric to better account for collisions in trajectory predictions. Our findings indicate that the effectiveness of this error metric is density-dependent, offering prediction insights. This study not only advances our understanding of human trajectory prediction in dense environments, but also presents a methodological framework for integrating density considerations into predictive modeling, thereby improving algorithmic performance and collision avoidance. [ABSTRACT FROM AUTHOR]

In the pedestrian navigation system, researchers have reduced measurement errors and improved system navigation performance by fusing measurements from multiple low-cost inertial measurement unit (IMU) arrays. Unfortunately, the current data fusion methods for inertial sensor arrays ignore the system error compensation of individual IMUs and the correction of position information in the zero-velocity interval. Therefore, these methods cannot effectively reduce errors and improve accuracy. An error compensation method for pedestrian navigation systems based on a low-cost array of IMUs is proposed in this paper. The calibration method for multiple location-free IMUs is improved by using a sliding variance detector to segment the angular velocity magnitude into stationary and motion intervals, and each IMU is calibrated independently. Compensation is then applied to the velocity residuals in the zero-velocity interval after zero-velocity update (ZUPT). The experimental results show a significant improvement in the average noise performance of the calibrated IMU array, with a 3.01-fold increase in static noise performance. In the closed-loop walking experiment, the average horizontal position error of a single calibrated IMU is reduced by 27.52% compared to the uncalibrated IMU, while the calibrated IMU array shows a 2.98-fold reduction in average horizontal position error compared to a single calibrated IMU. After compensating for residual velocity, the average horizontal position error of a single IMU is reduced by 0.73 m, while that of the IMU array is reduced by 64.52%. [ABSTRACT FROM AUTHOR]

• We examined the impact of peer presence on adolescent pedestrian risk-taking intentions whereby a traffic scenario-based experimental research. • Adolescents' behavioral intentions in traffic were safer when there were peers present than when there were no peers present. • Adolescents were less safe when crossing the street with familiar peer(s) than with unfamiliar peer(s). • Peer familiarity didn't effect adolescents' safety when walking on the sidewalk. • Adolescents' safety in traffic was higher with multiple familiar peers than with multiple unfamiliar peers. Adolescence is a high-risk period for traffic injury. One factor that may impact adolescent safety in traffic is the presence of peers. We conducted a quasi-experimental research study to examine the impact of peer presence, peer familiarity, and peer group size on adolescent pedestrian risk-taking intentions in both sidewalk and street-crossing settings. 607 students aged 12–18 years from Nantong city, China, completed a questionnaire that presented 20 traffic scenarios. The scenarios varied based on a 3 (peer group size: no peer vs. one peer vs. multiple peers) x 2 (peer familiarity: familiar vs. unfamiliar) x 2 (traffic setting: crossing the street vs. walking on the roadside) experimental design. Adolescents' responses indicated safer vs riskier intentions in each situation. (1) Adolescents were safer when walking on the sidewalk than when crossing the street; (2) Whether crossing the street or walking on the sidewalk, adolescents' behavioral intentions were safer when there were peers present than when there were no peers present; (3) Adolescents' safety tended to be higher overall with unfamiliar peers than with familiar peers; (4) Adolescents were less safe when crossing the street with familiar peer(s) than with unfamiliar peer(s), but no differences emerged when walking on the sidewalk. Adolescents report safer behavior when walking with a peer or peers compared with walking alone. Familiar peers reduce adolescents' safety of behavior intentions in traffic, especially when crossing the street. [ABSTRACT FROM AUTHOR]

• A virtual reality experiment exploring pedestrians' initial interactions with automated vehicles. • Investigates impacts of social context on pedestrians' understanding of and reaction to eHMIs. • Pedestrians' crossing decisions are influenced by other pedestrians next to them. • Behaviors of other pedestrians contribute to individual's difficulty in understanding eHMIs. Automated vehicles (AVs) are going to enter public roads in the near future and will inevitably encounter more than one pedestrian on roads. Very little is known about how multiple pedestrians will interact with AVs and their external human–machine interfaces (eHMIs). This study investigates the social influence of others on the pedestrian decision-making process during their initial encounters with AVs. In a virtual reality experiment, 26 male and 55 female participants in three experimental conditions made crossing decisions – either alone or next to other simulated pedestrians – in front of AVs equipped with abstract eHMIs showing yielding or non-yielding intentions. The results show that the behaviors of others significantly influenced pedestrian crossing decisions. While the appropriate behaviors of others contributed to faster crossing decision-making, misleading behaviors of others led to riskier crossing decisions and greater difficulty in understanding the eHMIs. However, the impacts from others on pedestrian crossing decisions disappeared once participants became more familiar with eHMIs. Qualitative data revealed that participants acquired knowledge about AVs and eHMIs through direct experience, observing others, and drawing from their past experiences. Additionally, there was a tendency among certain pedestrians to overly rely on and misuse eHMIs. To ensure the safe deployment of AVs, it is therefore essential to adequately educating the public about this novel technology and to optimize eHMI designs for effective communication with multiple pedestrians. [ABSTRACT FROM AUTHOR]

Pedestrian trajectory data, which can be used to mine pedestrian motion patterns or to model pedestrian dynamics, is crucial for indoor location‐based service studies and applications. However, researchers are faced with the challenges of data shortage and privacy restrictions when using pedestrian trajectory data. We present an Indoor Pedestrian Trajectory Generator (IPTG), which is a novel deep learning model to synthesize pedestrian trajectory data. IPTG first produces feature sequences that encode the spatial–temporal and semantic features of the walking process and then interpolates them into complete trajectories using A* and perturbation algorithms. IPTG has specially designed loss functions that preserve topological constraints and semantic characteristics. Incorporating the prior knowledge of environment constraints and pedestrian walking patterns, the IPTG model is capable of generating topologically and logically sound indoor pedestrian trajectories. We evaluated the synthesized trajectories based on multiple metrics and examined the generated trajectories qualitatively. The results show that IPTG outperforms several baselines, demonstrating its ability to generate semantically meaningful and spatiotemporally coherent trajectories. [ABSTRACT FROM AUTHOR]

For pedestrian detection in all weather conditions, multispectral imagery is the preferred solution for multimodal data acquisition. Due to the complementarity of multispectral data, the performance of pedestrian detection has been continuously improved. However, it is precise because of the diversity of data that the complexity of the model is increased. How to obtain a simple and lightweight high-performance network is the primary problem that the industry needs to solve. To solve this problem, this paper firstly proposes a lightweight high-performance network multi-receptive field and attention mechanism for multispectral pedestrian detection (MAPD). MAPD is a new scalable network based on multi-receptive field and attention mechanism. It cleverly combines multi-receptive field module and convolutional block attention module (CBAM) attention module to obtain multi-receptive field and attention module (MA). The module can be easily embedded into other network structures. After that, we analyze the proportion of pedestrian objects in the image to determine the receptive field range of the target, and use this range to design the multi-receptive field module of the network to obtain a network model suitable for detecting different object tasks. The MAPD network proposed in this paper has a very low parameter amount. Ablation studies on KAIST and CVC-14 datasets show that our method is effective and achieves state-of-the-art detection performance. [ABSTRACT FROM AUTHOR]

We propose a segmentation-based bounding box generation method for omnidirectional pedestrian detection that enables detectors to tightly fit bounding boxes to pedestrians without omnidirectional images for training. Due to the wide angle of view, omnidirectional cameras are more cost-effective than standard cameras and hence, suitable for large-scale monitoring. However, state-of-the-art pedestrian detectors cannot directly be applied to omnidirectional pedestrian detection because pedestrians' appearance in omnidirectional images may be rotated to any angle, which substantially degrades the performance of standard pedestrian detectors. Existing methods mitigate this issue by transforming images during inference, though the methods have limited detection accuracy and slow detection speed. A recently proposed method obviates the transformation at the cost of laborious annotation works and trains detectors with omnidirectional pedestrian detection datasets. We propose instead leveraging an existing large-scale object detection dataset to obviate both the transformation and annotation works. We train a detector with rotated images and tightly fitted bounding box annotations generated from the segmentation annotations in the object detection dataset, which enable detectors to detect pedestrians in omnidirectional images with tightly fitted bounding boxes. We also develop pseudo-fisheye distortion augmentation, which deforms images of perspective view to imitate the fisheye distortion and further enhances the performance. Extensive analysis shows that our detector successfully fits bounding boxes to pedestrians and demonstrates substantial performance improvement over existing methods. [ABSTRACT FROM AUTHOR]

Cross-modal visible-infrared person re-identification (VI-ReID) aims to retrieve images of the same pedestrians captured by visible (VIS) cameras and infrared (IR) cameras and it is a challenging task in intelligent security systems. The differences in imaging principles between visible and infrared images lead to large cross-modal differences and intra-class differences, and such cross-modal image differences can be considered as special image style differences, while several intra-class differences can be considered as differences in the form of content expression between visible and infrared images. Some state-of-the-art methods improve the performance of the VI-ReID model by using additional feature enhancement or feature generation modules, however, these methods also introduce additional parameters and increase the training cost. In this paper, to mitigate the differences in image style and content between VIS and IR images, we design two objective functions based on content and style, which are style loss and content loss for the VI-ReID task, respectively. Our model can effectively mitigate the differences between modes by optimizing the objective function to map VIS and IR features into the same feature space without additional auxiliary modules. After extensive experiments, our model achieves competitive performance on two challenging datasets. Notably, under the visible2infrared setting on the RegDB dataset, our model achieves the state-of-the-art (SOTA) Rank-1/mAP/mINP = 96.13%/91.35%/83.67%. [ABSTRACT FROM AUTHOR]

Person re-identification, as an essential research direction in intelligent security, has gained the focus of researchers and scholars. In practical scenarios, visible light cameras depend highly on lighting conditions and have limited detection capability in poor light. Therefore, many scholars have gradually shifted their research goals to cross-modality person re-identification. However, there are few relevant studies, and challenges remain in resolving the differences in the images of different modalities. In order to solve these problems, this paper will use the research method based on the attention mechanism to narrow the difference between the two modes and guide the network in a more appropriate direction to improve the recognition performance of the network. Aiming at the problem of using the attention mechanism method can improve training efficiency. However, it is easy to cause the model training instability. This paper proposes a cross-modal pedestrian re-recognition method based on the attention mechanism. A new attention mechanism module is designed to allow the network to use less time to focus on more critical features of a person. In addition, a cross-modality hard center triplet loss is designed to supervise the model training better. The paper has conducted extensive experiments on the above two methods on two publicly available datasets, which obtained better performance than similar current methods and verified the effectiveness and feasibility of the proposed methods in this paper. [ABSTRACT FROM AUTHOR]

The article describes how socioeconomic inequities contribute to discrepant unintentional injury risks and calls for an expansion of investment in innovative and targeted prevention strategies to narrow this disparity. Topics include the impact of poverty on injury, barriers and opportunities to implementation of injury prevention, and recommendations for advocacy groups, health care organizations, and community organizations.

Cross-view multi-object tracking aims to link objects between frames and camera views with substantial overlaps. Although cross-view multi-object tracking has received increased attention in recent years, existing datasets still have several issues, including (1) missing real-world scenarios, (2) lacking diverse scenes, (3) containing a limited number of tracks, (4) comprising only static cameras, and (5) lacking standard benchmarks, which hinder the investigation and comparison of cross-view tracking methods. To solve the aforementioned issues, we introduce DIVOTrack: a new cross-view multi-object tracking dataset for DIVerse Open scenes with dense tracking pedestrians in realistic and non-experimental environments. Our DIVOTrack has fifteen distinct scenarios and 953 cross-view tracks, surpassing all cross-view multi-object tracking datasets currently available. Furthermore, we provide a novel baseline cross-view tracking method with a unified joint detection and cross-view tracking framework named CrossMOT, which learns object detection, single-view association, and cross-view matching with an all-in-one embedding model. Finally, we present a summary of current methodologies and a set of standard benchmarks with our DIVOTrack to provide a fair comparison and conduct a comprehensive analysis of current approaches and our proposed CrossMOT. The dataset and code are available at https://github.com/shengyuhao/DIVOTrack. [ABSTRACT FROM AUTHOR]

This study aims to evaluate agreement among subjective thermal comfort, thermal sensation, thermal perception, and thermal tolerance indices, according to pedestrians in downtown Santa Maria, southern Brazil, which has a humid subtropical climate (Cfa). Between August 2015 and July 2016 (three periods), 1728 questionnaires were applied. Evaluation of the dependence of statistical variables was based on gender and age, at three periods of time: August 2015 (864 respondents), January 2016 (432 respondents), and July 2016 (432 respondents). Statistical evaluation was based on Pearson's chi-square test using RStudio software, and a significance level (α) of 5% for thermal comfort, thermal sensation, thermal preference, and thermal tolerance was used. Results indicated that age and gender affect the relationship between the variables. Thermal comfort and thermal tolerance presented the best correlation and coherence, regardless of age or gender. This study contributes to knowledge on the local microclimate and can contribute to urban planning to implement strategies that improve pedestrians' thermal comfort. [ABSTRACT FROM AUTHOR]

The emergence of Internet of things (IoT) technology has significantly influenced daily life and promoted the development of intelligent transportation systems and pilotless automobiles. In complex traffic environments such as curves and intersections, pilotless automobiles face some problems in pedestrian recognition, such as low detection distance accuracy and occlusion. To improve the timeliness of end-to-end information interaction and the early warning effect of anti-collision systems, a pedestrian target information fusion algorithm based on adaptive machine learning is proposed in the environment of Internet of vehicles (IoV). The pedestrian information acquired by roadside and on-board cameras is pretreated using a Kalman filter; then, the best position of the pedestrian target can be estimated and confirmed by integrating the time–space alignment, fuzzy association, and Kalman filtering results. Experiments show that both the maximum absolute error and the absolute mean error of the pedestrian trajectory are reduced significantly, i.e., by 45.0% and 58.5%, respectively, compared with those before trajectory fusion. Compared with S-LSTM and S-GAN methods, reasoning time is greatly reduced.Thus, the accuracy of pedestrian trajectory detection is improved by the fusion algorithm, and the warning accuracy of the system is enhanced. [ABSTRACT FROM AUTHOR]

Transportation databases have limited data regarding injury severity of pedestrian versus automobile patients. To identify opportunities to reduce injury severity, transportation and trauma databases were integrated to examine the differences in pedestrian injury severity at street crossings that were signalized crossings (SCs) versus nonsignalized crossings (NSCs). It was hypothesized that trauma database integration would enhance safety analysis and pedestrians struck at NSC would have greater injury severity. Single-center retrospective review of all pedestrian versus automobile patients treated at a level 1 trauma center from 2014 to 2018 was performed. Patients were matched to the transportation database by name, gender, and crash date. Google Earth Pro satellite imagery was used to identify SC versus NSC. Injury severity of pedestrians struck at SC was compared to NSC. A total of 512 patients were matched (median age = 41 y [Q1 = 26, Q3 = 55], 74% male). Pedestrians struck at SC (n = 206) had a lower injury severity score (ISS) (median = 9 [4, 14] versus 17 [9, 26], P < 0.001), hospital length of stay (median = 3 [0, 7] versus 6 [1, 15] days, P < 0.001), and mortality (21 [10%] versus 52 [17%], P = 0.04), as compared to those struck at NSC (n = 306). The transportation database had a sensitivity of 63.4% (55.8%-70.4%) and specificity of 63.4% (57.7%-68.9%) for classifying severe injuries (ISS >15). Pedestrians struck at SC were correlated with a lower ISS and mortality compared to those at NSC. Linkage with the trauma database could increase the transportation database's accuracy of injury severity assessment for nonfatal injuries. Database integration can be used for evidence-based action plans to reduce pedestrian morbidity, such as increasing the number of SC. [ABSTRACT FROM AUTHOR]

Background: The number of accidents due to distracted pedestrian is on the rise and many governments and institutions are enacting public policies which restrict texting while walking. However, pedestrians do more than just texting when they use their mobile devices on the go. Objective: Exploring pedestrian multitasking, this paper aims to examine the effects of mobile device task type on pedestrian performance outcomes. Method: We performed two studies in lab simulations where 78 participants were asked to perform different tasks on a mobile device (playing a game, reading, writing an email, texting one person, group texting) while performing a pedestrian visual discrimination task while either standing or walking on a treadmill. Behavioral performance as well as neurophysiological data are collected. Results: Results show that compared to a no-phone control, multitasking with any of the tasks on a mobile device leads to poor performance on a pedestrian visual discrimination task. Playing a game is the most cognitively demanding task and leads to the greatest performance degradation. Conclusion: Our studies show that multitasking with a mobile device has the potential to negatively impact pedestrian safety, regardless of task type. However, the impacts of different mobile device tasks are not all equivalent. More research is needed to tease out the different effects of these various tasks and to design mobile applications which effectively and safely capture pedestrians' attention. Application: Public policy, infrastructure, and smart technologies can be used to mitigate the negative effects of mobile multitasking. A more thorough understanding of mobile device task-specific factors at play can help tailor these counter-measures to better aid distracted pedestrians. [ABSTRACT FROM AUTHOR]

The location of curb ramps, crosswalk markings, and curb radius are important contributors to pedestrian safety at intersections, particularly for conflicts and crashes involving right turns. Drivers tend to have higher turning speeds at locations with larger curb radii, which also requires greater stopping sight distance. If the crosswalk is placed further away from the intersection corner (i.e., offset or setback from the intersection corner), it could potentially provide drivers better visibility of pedestrians and increase the available stopping distance. However, no study has previously been conducted to investigate the relationship between crosswalk location and curb radius. This paper presents the results of research that quantifies the relationship between the offset of crosswalks (setback crosswalk) and indirect safety measures (driver stopping, yielding, and speed selection) at intersections with the consideration of other characteristics during simulated driving. The study included field-based observations and driving simulator experiments. A driving simulator experiment with 50 participants was conducted to determine how setback distances, sharpness of curb radii, and presence of pedestrians affect driver stopping decision and position, and speed choice. Approximately 12 h of video (7:00 a.m.-7:00 p.m.) were collected at nine study sites that closely matched the designs tested in the driving simulator. Comparisons of drivers' speed in a similar scenario obtained from field and simulator data were performed to benchmark the observations from the driving simulator against field data. Stop line speeds were found to be consistent between experiments and turning speeds were found to be slightly higher in the driving simulator experiment. The research results suggest that curb radius should be smaller [less than 9 m (30 ft)] to control driver speed. Additionally, a setback distance of 6 m (20 ft) is a suitable upper bound for crosswalk placement when reconstructing intersections. [ABSTRACT FROM AUTHOR]

Traditional methods for investigating road safety mainly depend on crash data analysis, which is not always available, especially in developing countries. To overcome this shortage, new road safety tools/techniques have been introduced. This paper examined crowdsourcing data as a surrogate measure for accident data. This combined with users' internet-based surveys can be analyzed to provide indications of road safety situation. Two major neighborhoods in Cairo, Egypt, were selected for the study. Two sets of data were considered: crowdsourced crash data and an online questionnaire. Data analysis revealed a strong correlation between the two datasets in the case of road segment safety identification and road crash causes. According to both sets of data, speeding and random pedestrian crossing are the primary causes of traffic accidents. Multinomial logistic regression models were devised to identify the variables that significantly influenced (1) exceeding the speed limit by drivers and (2) unsafe pedestrian road crossing behavior. Lastly, this paper has introduced validation of applying the introduced crowdsourced data for investigating road safety and road users' behavior in Egypt and elsewhere when the traditional approach of using crash data is missing. Finally, policy recommendations are provided to improve drivers' and pedestrians' behaviors. [ABSTRACT FROM AUTHOR]

Visible‐infrared person re‐identification (VI‐ReID) aims to recognize images of the same person captured in different modalities. Existing methods mainly focus on learning single‐granularity representations, which have limited discriminability and weak robustness. This paper proposes a novel dual‐granularity feature fusion network for VI‐ReID. Specifically, a dual‐branch module that extracts global and local features and then fuses them to enhance the representative ability is adopted. Furthermore, an identity‐aware modal discrepancy loss that promotes modality alignment by reducing the gap between features from visible and infrared modalities is proposed. Finally, considering the influence of non‐discriminative information in the modal‐shared features of RGB‐IR, a greyscale conversion is introduced to extract modality‐irrelevant discriminative features better. Extensive experiments on the SYSU‐MM01 and RegDB datasets demonstrate the effectiveness of the framework and superiority over state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]

Modern experiments investigating human behaviour in emergencies are often implemented in virtual reality (VR), due to the increased experimental control and improved ethical viability over physical reality (PR). However, there remain questions regarding the validity of the results obtained from these environments, and no full validation of VR experiments has yet appeared. This study compares the results of two sets of experiments (in VR and PR paradigms) investigating behavioural responses to knife-based hostile aggressors. This study quantitatively analyses these results to ascertain whether the different paradigms generate different responses, thereby assessing the use of virtual reality as a data generating paradigm for emergencies. The results show that participants reported almost identical psychological responses. This study goes on to identify minimal differences in movement responses across a range of predictors, noting a difference in responses between genders. As a result, this study concludes that VR can produce similarly valid data as physical experiments when investigating human behaviour in hostile emergencies, and that it is therefore possible to conduct realistic experimentation through VR environments while retaining confidence in the resulting data. This has major implications for the future of this type of research, and furthermore suggests that VR experimentation should be performed for both existing and new critical infrastructure to understand human responses in hostile scenarios. [ABSTRACT FROM AUTHOR]