Showing papers in "Accident Analysis & Prevention in 2021"

TL;DR: In this paper, the authors provide a comprehensive and systematic review of significant SSM studies, identify limitations and opportunities for future SSM and CAV research, and assist researchers and practitioners with choosing the most appropriate SSM for safety studies.

TL;DR: In this paper, a real-time monitoring framework is proposed for traffic accident detection and condition analysis using ontology and latent Dirichlet allocation (OLDA) and bidirectional long short-term memory (Bi-LSTM).

TL;DR: A review of naturalistic driving studies carried out by collecting vehicle performance data and driver behavior data during normal, impaired, and safety-critical situations suggests driver behavior is a major cause in the majority of road accidents.

TL;DR: A comprehensive and up-to-date summary of surrogate safety assessment methodologies and conflict measures and metrics can be found in this article, where a total of 549 studies were meticulously reviewed to achieve this aim.

TL;DR: In this paper, the effects of key crash contributing factors on total crashes and crashes of different collision types are analyzed separately and compared, and significant risk factors are identified, including speed limits, area type, number of lanes, roadway functional class, shoulder width and shoulder type.

TL;DR: In this article, the authors explore the relationship between built environment factors and the spatial distribution of freight truck-related crashes using XGBoost and SHAP methods and show that variables related to the built environment, in particular demographics, land uses and road network, are highly correlated to freight truck related crashes of all three injury types.

TL;DR: In this paper, a mobile sensing system has been developed to collect data for quantifying the surrogate safety metrics in terms of experienced vibrations, speed changes, and proximity to surrounding objects.

TL;DR: In this article, the authors used variational autoencoder to encode all the crash and non-crash events into a latent space and then sampled from the latent space containing crash data.

TL;DR: In this paper, a novel deep learning-based approach with a customized f1-loss function was proposed to predict the severity of traffic crashes in work zones in Louisiana from 2014 to 2018.

TL;DR: A timely comparative review of existing driving strategies of autonomous vehicles is provided and three characteristic dimensions that are important to measure driving strategies are proposed: preferred objective, risk appetite, and collaborative manner.

TL;DR: In this paper, the effect of inappropriate speed adjustment to adverse conditions on crash-injury severities, and how this effect might vary across male and female drivers, and over time, is not well understood.

TL;DR: Findings indicate that better design and planning of built environments are necessary for safe and efficient access for pedestrians and for the long-term improvement of walkability in a high-density city such as Hong Kong.

TL;DR: In this article, the authors evaluated the Waymo Driver's performance within real-world fatal collision scenarios that occurred in a specific operational design domain (ODD) to address the rare nature of high-severity collisions.

TL;DR: The findings of this study support the influence of gender in the statistical explanation of both deliberate and undeliberate walking risky road behaviors, also depicting the differential role of certain demographic and psychosocial factors when the authors compare male and female pedestrians.

TL;DR: In this article, the authors investigated the effects of AVs on the behavior of a following human-driver in mixed traffic streams and found that a driver that follows an AV exhibits lower driving volatility in terms of speed and acceleration, which represents more stable traffic flow behavior and lower crash risk.

TL;DR: In this article, the authors analyzed the factors affecting the injury severity of three-wheeled motorized vehicles (3W-MR) using various machine learning-based identification algorithms, i.e., Decision jungle (DJ), Random Forest (RF), and Decision Tree (DT).

TL;DR: It was revealed that the probability of critical crashes varies at any given value of real-time traffic-related predictors according to different combinations of longitudinal grade and road surface conditions, indicating an essential need for Active Traffic Management to timely apply interventions not only based on real- time traffic- related predictors but also according to various combinations of environmental conditions.

TL;DR: In this paper, the authors identify the AV safety quantification studies, evaluate the quantification approaches used in the literature, and uncover the gaps and challenges in AV safety evaluation, and identify the most appropriate quantification method based on their goals and study limitations.

TL;DR: In this paper, the authors investigated the impact of the COVID-19 pandemic on road traffic collisions, fatalities, and injuries using time series analyses, and concluded that a worse performance was identified in terms of road safety.

TL;DR: In this article, the influence of gender, age group, group-crossing, technological devices and carrying items on pedestrians crossing behaviors at signalized and unsignalized crosswalks simultaneously was examined.

TL;DR: In this article, the authors evaluated the impact of various AV Market Penetration Rates (MPR) on the safety and operation of urban arterials in proximity of a driveway under different traffic levels of service (LOS).

TL;DR: Age and driving style were found to have a significant effect on older adults' acceptance of FAVs, with older age and greater dissimilarity of an individual's manual driving style from the FAV's driving style being associated with lower acceptance.

TL;DR: In this article, the authors compare the threshold determination approaches for DRAC-based crash estimation applying Bayesian hierarchical extreme value modeling, and show that the use of multisite Bayesian Hierarchical models outperforms the at-site models.

TL;DR: In this article, a random parameters (RP) Bayesian hierarchical extreme value modeling approach was proposed to account for the unobserved heterogeneity among different conflict observation sites and road user behaviors.

TL;DR: In this article, a study was conducted in downtown Brisbane, Australia, where e-scooters must be ridden on the footpath, bicycles are allowed on the road and the feetpath, and helmet use is mandatory for bicycle and e scooter riders of all ages.

TL;DR: It is suggested that single-bicycle crashes on road sections result in more severe injuries than single-bike crashes on bicycle lanes, and crashes on low volume roads with few bicyclists are also related to an increased probability of severe injury.

TL;DR: In this article, a scenario-based AV safety testing framework was proposed with sequence of events embedded as a core component, based on the findings of crash sequences are useful for developing AV test scenarios, and cluster analysis characterized AV crash sequences into seven groups with distinctive crash dynamic features.

TL;DR: In this article, the authors investigated contributing factors to potential collision risks during lane-changing processes from the perspective of vehicle groups and explore the unobserved heterogeneity of individual lane changing maneuvers.

TL;DR: Crash modification functions (CMFs) of pavement surface and geometric design indicators for different crash types, pavement conditions, and lighting conditions based on data from two-lane rural highways in Italy allow to effectively integrate pavement management systems and safety management systems.

TL;DR: Wang et al. as mentioned in this paper proposed a new safety performance measure-Risk Status (RS), by fusing crash data and surrogate safety measure (SSMs) based approach that can assess traffic safety by capturing the more frequent "near-crash" situations, but it is criticized for the potential sampling and measurement errors.