Recognition of occluded pedestrians from the driver's perspective for extending sight distance and ensuring driving safety at signal-free intersections

Urban intersections without traffic signals are prone to accidents involving motor vehicles and pedestrians.Utilizing computer vision technology to detect pedestrians crossing the street can effectively mitigate the occurrence of such accidents.Faced with the complex issue of pedestrian occlusion at signal-free intersections,this paper proposes a target detection model called Head feature And ENMS fusion Residual connection For CNN(HAERC).Specifically,the model includes a head feature module that detects occluded pedestrians by integrating their head features with the overall target.Additionally,to address the misselection caused by overlapping candidate boxes in two-stage target detection models,an Extended Non-Maximum Suppression classifier(ENMS)with expanded IoU thresholds is proposed.Finally,leveraging the CityPersons dataset and categorizing it into four classes based on occlusion levels(heavy,reasonable,partial,bare),the HAERC model is experimented on these classes and compared with baseline models.Experimental results demonstrate that HAERC achieves superior False Positives Per Image(FPPI)values of 46.64%,9.59%,9.43%,and 6.78%respectively for the four classes,outperforming all baseline models.The study concludes that the HAERC model effectively identifies occluded pedestrians in the complex environment of urban intersections without traffic signals,thereby enhancing safety for long-range driving at such intersections.

Safety analysis of pedestrian and roadway dimensional-dividing buildings

The safety performance of pedestrian and roadway dimensional-dividing buildings under seismic excitations are analysed. Considering the large displacement of the isolator bearing during earthquake, the gravity force becomes the dominant forces because of the accumulated permanent deformations in the building, which results in the structure collapse due to lateral instability. A mod- el is established based on an inelastic time history analysis to consider P - z~ effects in multi-degree- of-freedom. A safety criterion of the system is defined. The influence of the stiffness of an independ- ent column is revealed and compared with the influence of the shear force of the independent column to analyze the safety of the structures. Numerical results show that the special structure of pedestrian and roadway dimensional-dividing buildings can reduce the risk of the building in earthquake. The suitable section and height of the independent column greatly affect the building safety.

Transit Bus and Pedestrian Safety Analysis in the Context of Operator Improvements and Traffic Volume Assessment

Pedestrian safety related to public bus transit is an integral part of promoting sustainability especially in the urban setting. This concept has received significant attention within the last decade as transit agencies strive to make their systems more sustainable and safer at the same time. This study examined pedestrian collisions related to public transit buses in Philadelphia over a three-year study period from 2008 to 2011. The objective is to perform a detailed analysis on crash records, which provides the foundation on statistics for bus-pedestrian collision to allow for future studies in modeling work in this field. Results of this research provided insights on bus-pedestrian collisions in terms of bus maneuver, cause of crash, impact point of bus, and relation to hourly traffic volume. A strong correlation was found between traffic volume and bus-pedestrian collision rate in terms of hours of the day. For any given hour, an increase in collision frequency was found if the traffic volume exceeds a threshold of 5% of its average annual daily traffic. This serves as an indicator of locations that pedestrians are vulnerable at. Analyses were conducted to the fullest extent allowable by the limited dataset. This study presents findings that can be future developed and investigated in future studies. Additionally, countermeasures are recommended in each section that presents a critical area to address.

Self-Perception and General Perception of the Safety Impact of Autonomous Vehicles on Pedestrians, Bicyclists, and People with Ambulatory Disability

For autonomous vehicles (AVs) to receive general acceptance, society must have a positive perception about their safety impact on vulnerable road users. Using data from a statewide random-digit-dialing telephone survey of 1001 adults, this paper examines how New Jersey residents perceive the safety impact of AVs on pedestrians, bicyclists, and people with ambulatory disability. It uses a combination of confirmatory factor analysis and ordered probit models. Confirmatory factor analysis is used to create latent variables on socioeconomic status and built environment. Three ordered probit models are used to examine people’s perception of AV safety impact on each of the three population groups. The models also examine how frequent walkers, bicyclists, and people with ambulatory disability perceive their own safety as well as the safety of the other two groups. All three models examine the effect of familiarity with AV, gender, age, income, education, race, ethnicity, number of vehicles in household, political party affiliation, as well as built environment and socioeconomic status of the municipalities where the survey respondents live. The analysis showed that men, people with familiarity with the AV concept, Democrats, bicyclists, and people with high household income generally have a positive perception about the safety impact of AVs. While frequent walkers are ambivalent about their own safety as pedestrians, bicyclists have a positive perception about their own safety and the safety of pedestrians, whereas people with ambulatory disability have a strong negative perception about their own safety. The models did not show statistically significant effects of socioeconomic status or built environment of municipalities on AV safety perception.

Technical Analysis and Improvement of the Pedestrian Safety Protection of a Car Hood

The pedestrian protection technology must be used in automotive design if China-made automotives want to compete and grow strong in the world in the future. In this paper, a CAE simulation analysis is made for a domestic sedan car hood to check whether it meet the pedestrian safety protection laws and regulations. Results show that the original car cannot meet the demands of the rules. In order to meet the standards of the pedustrian protection rules, the car hood should undergo structural improvements. Tested again by CAE simulation analysis, the car after a series of improved design can reached the 3-star class EuroNCAP（ Euro New Car Assessment Program）standard of the car pedestrian safety protection laws and regulations.

IR-YOLO: Real-Time Infrared Vehicle and Pedestrian Detection

Road traffic safety can decrease when drivers drive in a low-visibility environment.The application of visual perception technology to detect vehicles and pedestrians in infrared images proves to be an effective means of reducing the risk of accidents.To tackle the challenges posed by the low recognition accuracy and the substan-tial computational burden associated with current infrared pedestrian-vehicle detection methods,an infrared pedestrian-vehicle detection method A proposal is presented,based on an enhanced version of You Only Look Once version 5(YOLOv5).First,A head specifically designed for detecting small targets has been integrated into the model to make full use of shallow feature information to enhance the accuracy in detecting small targets.Second,the Focal Generalized Intersection over Union(GIoU)is employed as an alternative to the original loss function to address issues related to target overlap and category imbalance.Third,the distribution shift convolution optimization feature extraction operator is used to alleviate the computational burden of the model without significantly compromising detection accuracy.The test results of the improved algorithm show that its average accuracy(mAP)reaches 90.1%.Specifically,the Giga Floating Point Operations Per second(GFLOPs)of the improved algorithm is only 9.1.In contrast,the improved algorithms outperformed the other algorithms on similar GFLOPs,such as YOLOv6n(11.9),YOLOv8n(8.7),YOLOv7t(13.2)and YOLOv5s(16.0).The mAPs that are 4.4%,3%,3.5%,and 1.7%greater than those of these algorithms show that the improved algorithm achieves higher accuracy in target detection tasks under similar computational resource overhead.On the other hand,compared with other algorithms such as YOLOv8l(91.1%),YOLOv6l(89.5%),YOLOv7(90.8%),and YOLOv3(90.1%),the improved algorithm needs only 5.5%,2.3%,8.6%,and 2.3%,respectively,of the GFLOPs.The improved algorithm has shown significant advancements in balancing accuracy and computational efficiency,making it promising for practical use in resource-limited scenarios.

Measuring Pedestrian Stress Response (MPSR) Using Wearable Technologies

Walkability is an essential aspect of urban transportation systems. Properly designed walking paths can enhance transportation safety, encourage pedestrian activity, and improve community quality of life. This, in turn, can help achieve sustainable development goals in urban areas. This pilot study uses wearable technology data to present a new method for measuring pedestrian stress in urban environments and the results were presented as an interactive geographic information system map to support risk-informed decision-making. The approach involves analyzing data from wearable devices using heart rate variability (RMSSD and slope analysis) to identify high-stress locations. This data-driven approach can help urban planners and safety experts identify and address pedestrian stressors, ultimately creating safer, more walkable cities. The study addresses a significant challenge in pedestrian safety by providing insights into factors and locations that trigger stress in pedestrians. During the pilot study, high-stress pedestrian experiences were identified due to issues like pedestrian-scooter interaction on pedestrian paths, pedestrian behavior around high foot traffic areas, and poor visibility at pedestrian crossings due to inadequate lighting.

A Workable Solution for Reducing the Large Number of Vehicle and Pedestrian Accidents Occurring on a Yellow Light

Traffic intersections are incredibly dangerous for drivers and pedestrians. Statistics from both Canada and the U.S. show a high number of fatalities and serious injuries related to crashes at intersections. In Canada, during 2019, the National Collision Database shows that 28% of traffic fatalities and 42% of serious injuries occurred at intersections. Likewise, the U.S. National Highway Traffic Administration (NHTSA) found that about 40% of the estimated 5,811,000 accidents in the U.S. during the year studied were intersection-related crashes. In fact, a major survey by the car insurance industry found that nearly 85% of drivers could not identify the correct action to take when approaching a yellow traffic light at an intersection. One major reason for these accidents is the “yellow light dilemma,” the ambiguous situation where a driver should stop or proceed forward when unexpectedly faced with a yellow light. This situation is even further exacerbated by the tendency of aggressive drivers to inappropriately speed up on the yellow just to get through the traffic light. A survey of Canadian drivers conducted by the Traffic Injury Research Foundation found that 9% of drivers admitted to speeding up to get through a traffic light. Another reason for these accidents is the increased danger of making a left-hand turn on yellow. According to the National Highway Traffic Safety Association (NHTSA), left turns occur in approximately 22.2% of collisions—as opposed to just 1.2% for right turns. Moreover, a study by CNN found left turns are three times as likely to kill pedestrians than right turns. The reason left turns are so much more likely to cause an accident is because they take a driver against traffic and in the path of oncoming cars. Additionally, most of these left turns occur at the driver’s discretion—as opposed to the distressingly brief left-hand arrow at busy intersections. Drive Safe Now proposes a workable solution for reducing the number of accidents occurring during a yellow light at intersections. We believe this fairly simple solution will save lives, prevent injuries, reduce damage to public and private property, and decrease insurance costs.

城市步行安全及其环境影响要素研究综述与展望

【目的】步行空间作为城市公共空间的重要组成部分,其安全品质是构建宜步行城市的重要基础,直接影响居民出行意愿和步行体验。【方法】以Web of Science和CNKI数据库1975—2022年步行安全相关文献为研究对象,通过计量分析与人工检阅相结合的方式,分析当前与步行安全及其环境影响要素研究相关文献的分布特征,梳理研究脉络,分析研究热点。【结果】1)步行环境安全性与行人安全感知主导步行安全研究发展方向,建成环境对行人安全事故以及行人安全感知的影响成为研究者关注的重点,新数据和新技术为分析步行安全环境核心影响要素提供支持。2)在城市建成环境中,街区、街道和交叉口等不同层级的环境要素,从活动安全、交通安全和防卫安全3个维度,对行人步行安全产生重要影响。3)研究对象从客观的建成环境拓展到主观的心理感知,研究内容从个案的安全事故分析拓展到综合的城市环境建设,研究方法方面多维度集成研究逐步替代单专业技术分析。【结论】揭示了步行安全与环境影响要素研究的发展方向、主要脉络以及关注重点,凸显多层级建成环境要素对步行安全事故和行人安全感知的重要影响,为开展步行安全环境实证研究提供理论支持。未来研究中,需对步行安全性和行人安全感知进行协同思考,推进相关研究技术的适用性,关注新兴交通技术发展对步行环境安全品质的影响。

突发攻击行为教室人群疏散最佳出口布局研究

为了研究突发攻击行为下的多障碍物教室人群疏散动态,并设计最佳出口布局,基于势函数元胞自动机模型构建了突发攻击行为教室人群疏散模型,考虑到攻击行为对疏散的影响,重构行人更新规则。模拟单侧两出口、三出口布局下,所有出口宽度分别为0.8 m、1.2 m、1.6 m时,一名攻击者位于教室前方、中部、后方的高密度人群疏散动态。结果表明:在相同出口布局下,攻击者位于教室后方时,人群不能兼顾向前逃生与向后观察攻击者,而导致疏散时间耗费最多;在两出口情况下,出口宽度的增加使行人可选目标位置变多,攻击者可选目标位置同样变多,使场景内伤亡人数呈现先增加后减少的趋势;在三出口情况下,出口宽度为1.6 m时,疏散时间为所有情形下最短,比两出口情况缩短29.2%。

Analysis of conflict factors between pedestrians and right-turning vehicles at signalized intersections

Due to the fact that there is no protected signal phase for right turns at most signalized intersections, the conflict between pedestrians and right-turning vehicles is one of the most common conflict types for pedestrians. A pedestrian safety analysis of the common right-turn mode at four-phase signalized intersections is presented. Relative risk is used as a measure of the effect of behaviors. The analysis mainly includes five pedestrian factors that affect the conflict process between pedestrians and right-turning vehicles. Pedestrians tend to have a higher risk of being involved in conflicts in the following six situations: crossing with others, running over the crossing, entering the intersection, being near the exit lane, crossing in the middle or at the end of a green light when the right-turn lane is shared, crossing at the beginning of a green light or red period when the right-turn lane is exclusive. It is easier for pedestrians to get priority when crossing the street in the following situations: running over a crossing, entering the intersection, being near the entrance lane, and not using the crosswalk. However, pedestrians are more inclined to yield to right-turning vehicles when pedestrians are crossing in the middle of the green light time. Some measures to alleviate the conflict are put forward according to the conclusion. Video observations also indicate that a clear pedestrian waiting area must be marked for both pedestrian safety and right-turning vehicle efficiency at major flat intersections, particularly when the arms cover the lateral dividing strips.

Spatial Regression Analysis of Pedestrian Crashes Based on Point-of-Interest Data

Pedestrian safety has recently been considered as one of the most serious issues in the research of traffic safety. This study aims at analyzing the spatial correlation between the frequency of pedestrian crashes and various predictor variables based on open source point-of-interest (POI) data which can provide specific land use features and user characteristics. Spatial regression models were developed at Traffic Analysis Zone (TAZ) level using 10,333 pedestrian crash records within the Fifth Ring of Beijing in 2015. Several spatial econometrics approaches were used to examine the spatial autocorrelation in crash count per TAZ, and the spatial heterogeneity was investigated by a geographically weighted regression model. The results showed that spatial error model performed better than other two spatial models and a traditional ordinary least squares model. Specifically, bus stops, hospitals, pharmacies, restaurants, and office buildings had positive impacts on pedestrian crashes, while hotels were negatively associated with the occurrence of pedestrian crashes. In addition, it was proven that there was a significant sign of localization effects for different POIs. Depending on these findings, lots of recommendations and countermeasures can be proposed to better improve the traffic safety for pedestrians.

Simulation of High Density Pedestrian Flow: A Microscopic Model

In recent years, modelling crowd and evacuation dynamics has become very important, with increasing huge numbers of people gathering around the world for many reasons and events. The fact that our global population grows dramatically every year and the current public transport systems are able to transport large amounts of people heightens the risk of crowd panic or crush. Pedestrian models are based on macroscopic or microscopic behaviour. In this paper, we are interested in developing models that can be used for evacuation control strategies. This model will be based on microscopic pedestrian simulation models, and its evolution and design requires a lot of information and data. The people stream will be simulated, based on mathematical models derived from empirical data about pedestrian flows. This model is developed from image data bases, so called empirical data, taken from a video camera or data obtained using human detectors. We consider the individuals as autonomous particles interacting through social and physical forces, which is an approach that has been used to simulate crowd behaviour. The target of this work is to describe a comprehensive approach to model a huge number of pedestrians and to simulate high density crowd behaviour in overcrowding places, e.g. sport, concert and pilgrimage places, and to assist engineering in the resolution of complicated problems through integrating a number of models from different research domains.

Pedestrian Countdown Signals: What Impact on Safe Crossing?

This paper examines safety impacts of a Pedestrian Countdown Signal (PCS) installed on a busy downtown intersection in San Diego, California. Crossing episodes of over 5000 pedestrians were videotaped and analyzed using multivariate statistical methods. Details of timing of pedestrian crossing as well as information about vehicular traffic and signal timing were carefully coded for each pedestrian. Significant safety benefits of the PCS system were found on the long crossings over a street with high vehicular volumes: most pedestrians were able to effectively increase their walking speed to complete their crossing without committing the exit violation—even if they have already committed the entry violation. However, on the short crossing with light vehicular traffic, PCS was generally ineffective in preventing the entry violations from becoming exit violations. Over there, many pedestrians felt safe enough to walk over a short crossing with no apparent vehicular traffic in sight instead of waiting for a green signal. The length of crossing and volume of interfering vehicular traffic were consistently found the most significant variables affecting the crossing violation rates of different categories of pedestrians. Crossing violation rates were the highest for runners, bicyclists and older males. Crossing violation characteristics were found to be consistent over time.

Investigation of Braking Timing of Drivers for Design of Pedestrian Collision Avoidance System

The braking behavior of drivers when a pedestrian comes out from the sidewalk to the road was analyzed using a driving simulator. Based on drivers＇ braking behavior, the braking control timing of the system for avoiding the collision with pedestrians was proposed. In this study, the subject drivers started braking at almost the same time in terms of TTC （Time to Collision）, regardless of the velocity of a subject vehicle and crossing velocity of pedestrians. This experimental result showed that brake timing of the system which can minimize the interference for braking between drivers and the system is 1.3 s of TTC. Next, the drivers＇ braking behavior was investigated when the system controlled braking to avoid collision at this timing. As a result, drivers did not show any change of braking behavior with no excessive interference between braking control by the system and braking operation by drivers for avoiding collisions with pedestrians which is equivalent to the excessive dependence on the system.

Safety Performance Functions for Traffic Signals:Phasing and Geometry

A significant proportion of urban crashes,especially serious and fatal crashes,occur at traffic signals.Many of the black-spots in both Australia and New Zealand cities occur at high volume and/or high-speed traffic signals.Given this,crash reduction studies often focus on the major signalised intersections.However,there is limited information that links the phasing configuration,degree of saturation and overall cycle time to crashes.While a number of analysis tools are available for assessing the efficiency of intersections,there are very few tools that can assist engineers in assessing the safety effects of intersection upgrades and new intersections.Safety performance functions have been developed to help quantify the safety impact of various traffic signal phasing configurations and level of intersection congestion at low and high-speed traffic signals in New Zealand and Australia.Data from 238 signalised intersection sites in Auckland,Wellington,Christchurch,Hamilton,Dunedin and Melbourne was used to develop crash prediction models for key crash-causing movements at traffic signals.Different variables(road features)effect each crash type.The models indicate that the safety of intersections can be improved by longer cycle times and longer lost inter-green times,especially all-red time,using fully protected right turns and by extending the length of right turn bays.The exception is at intersections with lots of pedestrians where shorter cycle times are preferred as pedestrian crashes increase with longer wait times.A number of factors have a negative impact on safety including,free left turns,more approach lanes,intersection arms operating near or over capacity in peak periods and higher speed limits.

行人过街行为分析与建模

行人过街违章行为的影响因素及过街行为建模对行人过街安全和行人违章特性研究具有重要的理论意义。通过多层次交叉联列表方法分析了影响行人过马路违章行为的因素,并建立了多元Logistic模型。检验结果表明,模型存在共线性问题,通过逐步回归方法筛选出10个显著影响行人违章行为的因素。通过模型分析发现,影响行人违章过马路的多种因素中,年龄、是否携带东西、结伴情况、受教育程度、等待过街人数、信号灯了解程度、视力情况、路口类型、有无机非护栏和过街位置都对违章行为有显著影响。年轻人和结伴行人更可能违章,而受过高等教育的人违章概率较低;对信号灯和路况了解不足、视力不佳的行人违章概率较高;路口类型和是否有护栏也会影响违章行为,远离车辆过街的行人违章概率更大。

车辆视角下的行人穿行意图识别与行为预测

预测行人穿行马路的行为一直是智能驾驶汽车研究领域的重点方向,对于行人安全保护至关重要。现有研究通常使用轨迹或姿势对行人的行为进行建模,但是行人行为复杂多变,需对其进行更加深层的语义解读。将行人的穿行意图与行为相结合,设计多任务网络来识别行人意图并预测行人行为。行人的穿行意图会影响其行为,故使用行人未来的行为作为先验来检测行人目前的意图和行为,同时考虑到行人周围的交通目标与自车运动对于行人的影响,设计特征融合模块来融合行人特征与交通目标特征。在自动驾驶数据集(PIE和JAAD)上验证实验模型,结果表明,该模型展现了其在行人意图与行为建模方面的优势。

群组感知的行人轨迹预测方法研究

自动驾驶场景下,大多数方法没有对行人群体进行建模,这样会对道路交通的安全造成影响。因此,提出了一种针对群组感知的行人轨迹预测网络(GPCNet)。具体来说,在组内,从个体层面学习行人之间的交互,考虑不同行人的偏好问题。在组间,从群体层面学习行人组间的交互,使用社会力模型考虑行人轨迹的碰撞问题。仿真结果表明,与常用的轨迹预测方法相比,GPCNet在ETH和UCY数据集上的性能提高了约75.4%。

不同姿态人群的火场疏散模型研究

在火灾疏散中,火场高温烟气带来的物理威胁和心理压力会对人员疏散产生影响。为了量化火灾环境下人员可能采用的弯腰、爬行等疏散姿态及其与火源间的交互对疏散过程的影响,采用椭圆表征行人不同的运动姿态,考虑火源产生的物理和心理影响,基于社会力模型建立了一种混合姿态火场疏散模型。本模型能够再现试验中观测到的行人绕行及避让火源行为,可根据火源状态提前规划疏散路径避开高温区域。研究发现,当人员采用爬行、蹲行和弯腰行走三种姿态疏散时,人群的疏散时间随密度和火源温度升高而延长。随着路径风险差异增大和行人危险敏感度提高,选择安全路径的行人比例逐渐增大。研究可以为火灾环境下人员的安全应急疏散管理提供技术支持。