Understanding pedestrian behavior and spatial relations:A pedestrianized area in Besiktas,Istanbul

This research provides a mixed method of investigating and analyzing pedestrian behavior in pedestrianized areas,which is one of the human-based urban development practices.The relationship between pedestrian behavior and perception of the city is discussed through a combination of architect and urban planner Gordon Cullen’s theory and Space Syntax methodology.This study examines the development and implementation of the methodology to understand the relationship between pedestrian behavior and space in Besiktas Koyici settlement,Istanbul.The methodology,integrated with on-site observations(observing 10 min at five different observation points in the settlement at predetermined times on weekdays and weekends),surveys(determining pedestrian movement and perception in terms of Cullen’s theory)and spatial configuration(Space Syntax analysis(connectivity,integrity)done with DepthMapX software),aims to analyze pedestrian behavior patterns.The concepts of sense of place and content,as well as the effects of their sub-concepts on their behaviors,were revealed because of a survey conducted with students and architects of variety of educational levels who are daily users of the field.Pedestrian counting and observations were used to create density,activity,and mobility maps of the area.It has been found that pedestrianized areas have a significant impact on pedestrian behavior through influencing vitality and appeal and that Cullen’s theory may be used to analyze pedestrian behavior and perceptions of the city.The study showed that spatial configuration and Cullen’s theory effect pedestrian movement by complementing each other.

Simulation study on cooperation behaviors and crowd dynamics in pedestrian evacuation

Pedestrian evacuation is actually a process of behavioral evolution. Interaction behaviors between pedestrians affect not only the evolution of their cooperation strategy, but also their evacuation paths-scheduling and dynamics features. The existence of interaction behaviors and cooperation evolution is therefore critical for pedestrian evacuation. To address this issue, an extended cellular automaton(CA) evacuation model considering the effects of interaction behaviors and cooperation evolution is proposed here. The influence mechanism of the environment factor and interaction behaviors between neighbors on the decision-making of one pedestrian to path scheduling is focused. Average payoffs interacting with neighbors are used to represent the competitive ability of one pedestrian, aiming to solve the conflicts when more than one pedestrian competes for the same position based on a new method. Influences of interaction behaviors, the panic degree and the conflict cost on the evacuation dynamics and cooperation evolution of pedestrians are discussed. Simulation results of the room evacuation show that the interaction behaviors between pedestrians to a certain extent are beneficial to the evacuation efficiency and the formation of cooperation behaviors as well. The increase of conflict cost prolongs the evacuation time. Panic emotions of pedestrians are bad for cooperation behaviors of the crowd and have complex effects on evacuation time. A new self-organization effect is also presented.

Research on Open Block's Pedestrian System Based on the EnvironmentBehavior Theory: A Case Study of Shenzhen Oct-loft

In the context of banning gated communities, blocks returning to the human-oriented scale become the new normal, and pedestrian system design will be paid more attention in the urban planning field. Oct-Loft Creative Park is a template for open blocks in Shenzhen, with a convenient and humanized pedestrian system. This paper selects the creative park's pedestrian system as the research object, using the environment-behavior theory for analysis. Finally, optimization strategies of pedestrian system will be put forward.

Pedestrian choice behavior analysis and simulation of vertical walking facilities in transfer station

Considering the interlayer height, luggage, the difference between queuing pedestrians, and walking speed, the pedestrian choice model of vertical walking facilities is established based on a support vector machine. This model is verified with the pedestrian flow data of Changchun light-rail transfer station and Beijing Xizhimen transfer station. Adding the pedestrian choice model of vertical walking facilities into the pedestrian simulation model which is based on cellular automata, the pedestrian choice behavior is simulated. In the simulation, the effects of the dynamic influence factors are analyzed. To reduce the conflicts between pedestrians in opposite directions, the layout of vertical walking facilities is improved. The simulations indicate that the improved layout of vertical walking facilities can improve the efficiency of pedestrians passing.

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.

Model and application of bidirectional pedestrian flows at signalized crosswalks

This research of bidirectional pedestrian flows at signalized crosswalks is divided into two parts： model and applica- tion. In the model part, a mixed survey including the questionnaire investigation and tracking investigation is conducted to gain the basic data about walking tendentiousness of a pedestrian crossing. Then, the forward, right-hand, outstripping, and influential coefficients are outlined to quantize walking tendentiousness of pedestrian crossing and estimate transition probabilities of pedestrians. At last, an improved cellular automation model is proposed to describe walking tendentious- ness and crossing behaviors of pedestrians. In the application part, channelization research of bidirectional pedestrian flows is presented for real signalized crosswalk. In this process, the effects of right-side-walking and conformity behaviors on the efficiency of pedestrian crossing are thoroughly analyzed based on simulations and experiments to obtain a final channelization method to raise the efficiency of a pedestrian crossing at the crosswalk.

公共场所行人异常行为识别方法综述

为明确公共场所行人异常行为识别理论与技术研究进展,首先,借助中国知网(CNKI)和Web版引文数据库(WOS),给出公共场所行人异常行为广义定义与泛在特征,将常见异常行为划分为危害行为、不合群行为和违规行为3类;其次,从数据和技术基础视域,将现有异常行为识别方法划分为人工设计法、人体骨架法、红绿蓝(RGB)图像法和可穿戴传感器法4类;然后,梳理国内外主流人群异常行为数据集,分析相关算法在数据集上的性能表现;最后,从可用数据集和数据融合检测等方面总结现有研究方法局限性,给出未来研究方向与优化建议。研究结果表明:4类异常行为识别方法各有其优缺点;异常行为识别领域缺乏行为种类丰富、定义清晰、高质量的人群异常行为数据集;未来研究应聚焦稳健性强、准确率高的异常行为识别方法、模型及算法;探索多维数据融合互补检测方法,提升异常行为识别理论成果的应用场景的自洽性和自适应性,提高公共场所人群安全治理水平。

基于图像处理的行人过街安全警示系统设计与研究

为了提高行人过街的安全性和效率,避免安全事故的发生,设计一种可以实时检测行人过街行为以及车辆往来的行人过街安全警示系统。该系统采用图像处理技术和嵌入式系统技术,能够实时监测行人、车辆和交通信号灯状态,能准确快速地提醒过街行人注意出行及安全,提高城市交通秩序,有助于推进智慧城市建设和交通安全领域的技术创新,具有一定的理论和实践价值。

基于行人轨迹数据的城市轨道交通车站单向通道行人跟随行为特性研究

[目的]提升乘客服务水平、保障安全是城市轨道交通车站设施布局及运营管理的核心,车站设施的科学设计需研究行人跟随行为的基本特性及其规律。[方法]结合行人轨迹提出行人跟随行为描述模型及其表征参数,设计可控试验模拟城市轨道交通车站单向通道行人跟随行为,采集视频数据提取行人跟随轨迹,深入分析跟随行为发生时行人跟随速度差、跟随时距、横纵向间距等表征参数的特征和规律,研究行人密度、通道宽度、性别和熟悉环境四个因素对单向通道行人跟随行为特性的影响。[结果及结论]行人流密度越低,平均跟随速度差与平均跟随时距均越小;通道宽度对跟随行为表征参数无显著影响;异性间跟随比同性间跟随的表征参数值均较大;不熟悉环境者相对熟悉环境者表征参数值离散程度较大。

基于微观行为分析的城市轨道交通车站内行人步行速度影响分析

城市轨道交通的建设和运营推动城市交通系统的完善和社会经济的发展,但随着客流量的日益增长,行人在城市轨道交通车站内的步行需求与站内引导行人流的设施设备之间产生矛盾,导致乘客步行时间增加。文章选取重庆市轨道交通3号线上的重庆交通大学站进行数据调研,将行人按年龄分为3个不同群体,并设定23组自变量。为探究自变量对行人步行速度的具体影响,建立基于行人微观行为的回归分析模型,将行人步行速度设为因变量。最后根据回归结果筛选出10组对站内行人步行速度影响显著的变量参数,以此帮助城市轨道交通车站提升服务水平,提高站内行人通行效率。

考虑跨越行为和障碍物类型的人员疏散模型

为研究区分障碍物类型的跨越行为对疏散的影响,基于元胞自动机建立跨越行为模型,采用Dijkstra算法改进障碍物场景下的静态场值,根据跨越障碍物时的难易程度将可跨越障碍物划分为可轻松跨越型(Ⅰ类)和不易跨越型(Ⅱ类),提出体力值的概念,用体力值的大小来区分行人是否具有跨越能力,提出障碍物占有率的概念,通过改变其取值来表示疏散空间中Ⅰ类障碍物数量的不同;分析跨越比例、障碍物占有率、障碍物类型等因素对疏散的影响。研究结果表明:区分障碍物类型的跨越行为更能提高疏散效率,同时也更符合实际;不同跨越比例下跨越障碍物行为对疏散的促进效果不同;障碍物占有率不同时,按障碍物类型跨越行为并不总能使疏散时间降至最低。研究结果可为提高行人疏散效率、制定疏散策略提供参考。

基于人体运动识别约束的室内定位方法

针对传统的行人航迹推算(Pedestrian Dead Reckoning,PDR)方法无法满足多运动状态下的定位问题,提出了一种基于神经网络运动识别辅助室内定位的方法。构建出卷积神经网络(Convolutional Neural Network,CNN)和门控循环单元(Gated Recurrent Unit,GRU)组合的神经网络模型,用于识别人体的运动状态并完成分类。根据运动分类的结果应用到行人航迹推算中,分析和筛选运动参数特征作为算法的阈值约束条件来提高定位精度。在算法中运动步数由合加速度计数据波形检测得到,步长由运动状态的特征自适应调整步长模型。通过实验验证,CNN-GRU模型在自建数据集上的准确率达到99.6%。将识别结果应用到PDR中,在112 m 4种动作的矩形路线中定位误差为1.8 m,误差远低于传统PDR定位的19.9 m。实验结果验证了该方法的可行性。

地铁车站步行障碍行人避让行为建模与进出站仿真

为向步行障碍人群提供更精细化的出行服务,本文研究步行障碍行人微观出行行为,解析不同个体属性行人间的冲突避让行为机理。从行人的生理差异角度出发,扩展传统元胞自动机模型场域,同时改进场强模型和模型更新规则,建立步行障碍行人运动及避让行为的元胞自动机模型。通过构建行人运动场地实验,提取普通行人和步行障碍行人轨迹,分析其运动速度、运动偏移角度和横向移动距离等冲突避让特征参数,标定元胞自动机模型中的相关参数。场地实验结果表明,步行障碍行人的运动能力较差,自由度较低,其在冲突避让过程中的偏移角度和偏移距离均明显小于普通行人,主要通过降低行走速度进行被动避让。仿真结果显示,行人速度及普通行人、轮椅行人和婴儿车行人的横向偏移距离与实测数据的误差分别为2.74%、3.35%、6.71%、6.16%。最后,基于改进模型对上海地铁迪士尼站站台层乘客出站场景进行仿真,进一步验证了模型的有效性,并提出无障碍电梯布设的优化方案。步行障碍行人仿真模型的有效建立,可为地铁无障碍电梯等无障碍设施的规划和设计提供理论支持。

基于行为轨迹的中庭式酒店COVID-19感染概率研究

中庭式酒店建筑因中庭空间人员密集、气流波动大,属呼吸道传染疾病高感染概率区域,建筑高大公共空间的传染概率有待研究.以某中庭式酒店为研究对象,基于该酒店人流状况、行为轨迹的实测,通过回归分析,得到该酒店人流密度的分布规律;运用Anylogic软件,结合Wells-Riley感染概率计算模型,对不同类型人员感染后的酒店人群感染概率进行模拟.通过模拟可知,住宿人群、就餐人群、商务会议三类人群中单一人群感染时,感染概率分别为29.3%,17.9%,36.4%;当三类人员及后勤人员共同耦合感染时,感染概率增加至42.6%.通过对污染物颗粒的时空分布规律的分析发现三层、标准层污染物颗粒较多;人员交叉与感染概率呈正相关;流线交叉较多的就餐空间、滞留时间较长休闲空间、竖向交通空间等应重点考虑设计措施以降低其感染概率;该研究为人员行为轨迹下的酒店空间的布局优化提供研究思路,为疫情背景下寒冷地区中庭式酒店平疫结合酒店空间布局设计研究提供理论依据.

城市道路中间路段人车冲突中网联预警信息对驾驶行为的影响

本文旨在研究网联预警信息对城市道路人车冲突中驾驶人行为的影响。利用驾驶模拟器设计城市道路驾驶场景与网联预警信息系统,考虑不同类型的视觉盲区,构建了6个典型的行人与机动车冲突场景。将招募的70名驾驶人划分为实验组和对照组,进行驾驶模拟器实验,采集实验过程中的驾驶人行为和车辆轨迹数据。利用生存分析法研究了不同因素对冲突过程中驾驶人避让反应时间与制动持续时间的影响,并建立面向冲突过程的人车事故风险预测模型,评估网联预警信息对驾驶行为的影响。结果表明:由公交车、路侧停车及树木与车辆等导致的视觉盲区会降低驾驶绩效,增加冲突过程中驾驶人的避让反应时间,降低制动持续时间;人行横道的存在使平均避让反应时间减少0.90 s,使平均制动持续时间增加0.41 s,并降低人车事故风险;网联预警信息可使驾驶人的平均避让反应时间减少0.52 s,平均制动持续时间增加0.40 s,使制动过程更加平稳,显著降低冲突过程中的事故风险,保障行人安全。

城市交通枢纽行人异常行为分析研究综述

城市交通枢纽是居民出行的重要支撑节点,普遍具有客流密集、空间封闭、多方式客流复杂交织等特征,也承担了巨大的安全组织与运维的压力。因此,对枢纽内行人异常行为的管控是保证其安全运维的重要关注点之一。目前,对枢纽行人异常行为的辨识主要是依托计算机视觉技术来实现,即:一种是主要关注客流轨迹和密度差异,利用目标检测技术提取枢纽内行人目标并进行轨迹预测,以分析个体或小群体的异常轨迹数据来判断行人的异常行为;另外一种是利用姿势估计技术提取行人的微观动作数据,通过分析行人的骨骼关节点数据来判断其异常动作和行为意图。故梳理了枢纽内行人行为的研究成果,概括分析了基于模型驱动和数据驱动的行人异常行为研究与应用成果,并解析行人异常行为的致因机理,总结了枢纽面对行人异常行为的管理措施,最后进行了枢纽行人异常行为研究的分析和展望。该综述可以加深对交通枢纽行人异常行为的理解,为枢纽内行人的安全运维提供参考和支持。

基于VR试验的地下综合体人员疏散决策

为了探究人员在疏散过程中的出口选择等决策行为规律,预测疏散人员对疏散出口的选择情况,应用虚拟现实(VR)技术搭建地下空间综合体场景,并开展人员疏散试验。首先,借助SPSS软件对试验结果进行统计分析,构建无序多分类Logistic回归模型,识别主要影响因素;然后,计算各类影响因素的贡献并建立相关性分析模型;最后,基于支持向量机(support vector machine,SVM)算法,建立人员疏散决策模型。结果表明:疏散人员倾向于选择初始朝向的出口进行疏散;当面对的多个出口距离相近时,人员与出口的距离对疏散人员出口选择的影响较小;基于SVM的疏散决策模型的预测准确率为93%。

基于多传感器融合的行人异常行为识别方法

常规的行人异常行为识别方法无法针对行人行为特征进行识别,导致识别准确性较低,因此,设计了一种基于多传感器融合的行人异常行为识别方法。在多传感器融合中,通过摄像头得到人体不同行为的最小外接矩形框,并计算出人的宽高比,以反映行人的运行特征;然后根据平行式双目视觉测量原理,获取行人位置信息,并利用空间对齐的方式,获得行人位置信息,实现行人异常行为点云信息与图像信息一致的目标,从而提高信息融合的精准度;最后结合行人的步长、速度、方向等轨迹数据对行人异常行为进行分类,并通过奖励或惩罚机制优化分类识别结果,完成行人异常行为识别。实验结果表明,使用该方法进行行人异常行为识别时,行人异常行为识别的平均精确度在0.98~1.00的范围内变化,行人异常行为识别的均值平均精度在0.97~1.00的范围内变化。由此表明,该方法的识别准确性更高,能够应用于实际生活中。

公共建筑环境下行人行为特性及拥挤机理研究综述

介绍国内外对于公共建筑环境下行人行为特性及拥挤机理方面的研究成果,主要包括:自由流情况下的行人运动速度,人群运动的最佳密度,行人的年龄、文化、性别、退让距离、温度、旅行目的、运动方向和建筑设施类型对行人流速度和流量的影响,以及行人流的密度和速度关系。成果显示:各国学者在人群的速度、密度和流量之间的相互关系方面研究较多,所得的结论趋于一致;但对于影响行人流速度和流量的各种因素并没有进行深入的研究,尤其是拥挤情况下行人的心理状态和拥挤事故的相互关系。

北京市道路信号交叉口自行车和行人的行为研究

对北京市信号交叉口的自行车和行人在混和交通流中的微观行为进行研究分析.研究中使用视频采集技术和数据分析技术来收集和分析自行车和行人在交叉口的行为.论文的主要研究结果是信号交叉口自行车和行人的各种微观行为特征和基础行为模型,这些结果有助于理解信号交叉口混和交通流的行为,并为城市混和交通流的微观交通模拟模型提供基础数据和理论依据.