基于阈值模型的行人违章从众穿越行为分析

根据行人违章调查数据,分析了从众心理对行人违章行为的影响。利用传播扩散和复杂网络科学理论与方法,基于阈值模型建立了从众心理在违章穿越中的影响分析模型,并根据观察数据进行了参数标定,定量分析了从众行为对行人违章的影响程度。结果证实,从众者对自身效用评价赋权越小,其发生从众违章行为的可能性就越大。     

成都市城市道路行人交通特性研究

本文通过对成都市路段、交叉口大量行人交通特性数据的采集,并进行了相关性分析,确定了性别、年龄、人数、出行目的、环境等因素对行人步行行为的影响。通过分析发现,男性行人的步行速度、步行随机性普遍大于女性;随着年龄的增大,行人的步行速度、步行随机性普遍降低;行人过街步行速度普遍低于路段步行速度、而过街谨慎性要高于路段;目的性强的行人步行速度和谨慎程度都要更高些;行人过街时往往表现出群体心理、从众心理和节省心理。据此,从硬件配置、管理和宣传教育三方面提出了相关改善措施。     

行人过街设施设置方法研究

首先分析目前我国行人过街存在的问题,接着对行人过街设施进行分类,并列举了三类特殊情况下的行人过街,最后提出行人过街配套设施的设置方法。     

高速公路异常事件检测中的目标检测和主体识别算法

针对高速公路监控中心需要轮询查看大量视频的繁琐任务及人员消耗,文章提出了基于人工智能计算机视觉的高速公路事件检测方法。该方法针对传统检测无法判断事件主体是否为工程养护车辆和工作人员的情况,制作了工程养护车辆和工作人员的数据集,采用yolox网络结构作为基础,在网络结构中增加目标识别头,同时对人和车辆进行检测和识别。经实际应用后表明,该方法检测效果优于对比组,可有效检测和识别社会车辆和工程养护车辆、普通行人和工作人员。     

我国行人过街绿闪信号的设置方式与路权分析

在行人过街交通信号中加入绿闪信号已经是国内较为常见的设置方式,但是绿闪信号究竟代表什么含义、其时长应该如何设置和计算,目前尚无统一定论。本文首先整理了绿闪信号在我国的设置现状,接着分析了国内涉及到绿闪信号的相关法规标准,然后对比了其他典型国家或地区的行人过街清空信号设置方式,总结出绿闪、红闪和持续红灯三种主要的设置类型,并对其进行了相应的优劣势分析。最后,从行人清空信号期间的人行横道路权争议入手,综合上述分析结果,提出了较为适宜我国现状的行人清空信号设置方法,并对健全完善我国行人清空信号设置规范提出了建议。     

让行人更加安全带全力自动刹车的行人探测系统

在日益拥堵的交通环境中,每天都有行人发生交通事故。在欧洲所有交通意外死亡人数中的14％是行人,美国的行人交通意外死亡率为11％．而中国的这一比率高至令人担忧的26％;     

工业制品仓储出库检测视频适用性研究

随着工业制品的不断发展和市场需求的增加,仓储出库检测对确保产品质量和安全性的重要性日益凸显。传统的人工检测方法存在效率低、误差大等问题,不适应大规模仓储出库需求的现状。视频技术可以实现非接触式的检测,具备快速、准确和可靠的优势,并且与自动化、智能化仓储管理相互融合,为提高仓储出库效率和质量管理提供新的解决方案。因此,本文对工业制品仓储出库检测视频的适用性进行研究,以期为相关行业人员提供参考。     

基于自适应滤波技术的管道泄漏检测方法

提出了一种基于小波变换和Kalman滤波相结合的自适应滤波方法,采用递推算法逐步修正滤波过程,即根据采样得到的压力信号实时地对滤波参数进行修正,使自适应滤波器能够有效地跟踪信号的变化,形成自适应降噪过程,通过自动寻优,选择最佳尺度,使之能在背景噪声较强或变化的情况下也能对管道压力信号进行有效的滤波处理,为准确检测管道泄漏和定位提供了良好基础.应用结果证明:该方法大大提高了信号处理的效率,在管道泄漏在线监测应用中效果较好.     

视频监控联网系统标准符合性检测平台研究

文章结合广西高速公路视频联网监控系统建设实际,阐述了视频监控联网系统标准符合性检测工作的任务及应用到的相关技术与工具软件,提出了开发一个实用性更强、更具推广性的标准符合性检测平台软件的新思路,并介绍了该平台的实现方法、应用技术及其推广效益。     

综合客运枢纽信息设置影响行人行为的调查分析

基于综合客运枢纽信息内涵及作用,根据不同的分类标准对综合客运枢纽信息进行了分类。枢纽内行人对信息有需求,枢纽信息的设置才会对行人有影响;因此,分别从不熟悉枢纽环境的进站行人、出站行人、换乘行人3个方面详细分析了枢纽内不同走行路径的行人对信息的不同需求。最后,通过对上海虹桥火车站实地调查,并对调查数据进行分析,得出在换乘过程中设置快速路径指示标识和实时信息都将影响枢纽内换乘行人的行为,并建议在地铁换乘高铁的A/B方向通道上,规范信息设置,凸显指路信息。     

Bridging the Gap in Planning Indoor Pedestrian Facilities

Abstract

Pedestrians are currently attracting the interest of various researchers and practitioners, particularly urban and transport planners. Analysis of the pedestrian behavior, environment and modeling has been carried out in diverse instances in the context of pedestrian planning. This paper seeks to identify the content of each of these three research areas and designate the linkages that connect their interests providing insights into planning indoor pedestrian facilities. To achieve this objective, a review of the literature on pedestrians walking indoors and indoor pedestrian environments was conducted. Understanding pedestrian behavior is fundamental in the pedestrian planning process. Principles of decision-making, cognition, wayfinding and flows were studied. When analyzing the pedestrian environment, Space Syntax and wayfinding analysis were found to be established methods that are an integral part of this field. Finally, the majority of the existing modeling approaches were identified. It was found that despite the dynamic evolution of each area, the integration of different research perspectives is weak. The paper concluded with the proposal of a mindmap which brings together all the concepts found in the literature and which should be explored for a more comprehensive planning of indoor pedestrian facilities.     

基于DSP的先进视频交通数据采集系统探讨

DSP是一种先进的视频交通数据采集系统,它操作简单,不仅能够有效的融入于道路交通数据采集系统,还能够与感应式十字路口信号灯控制系统、电子警察抓拍系统相结合,其双重功用被广泛应用于城市道路、高速公路交通数据采集,以及公路隧道、桥梁的意外事故监控系统中,并且可以适应各种天气,具有全天候检测的能力。文章从系统特点、检测数据精度、系统的多功能性及系统操作的方便性等方面介绍了该系统的先进性、实用性。     

Pedestrian gap acceptance for mid-block street crossing

Abstract

This paper investigates pedestrians' traffic gap acceptance for mid-block street crossing in urban areas. A field survey was carried out at an uncontrolled mid-block location in Athens, Greece. Pedestrians' decisions and traffic conditions were videotaped in terms of the size of traffic gaps rejected or accepted, waiting times and crossing attempts and vehicle speeds. A lognormal regression model was developed to examine pedestrian gap acceptance. It was found that gap acceptance was better explained by the distance from the incoming vehicle, rather than its speed. Other significant effects included illegal parking, presence of other pedestrians and incoming vehicles’ size. A binary logistic regression model was developed to examine the effect of traffic gaps and other parameters on pedestrians' decisions to cross the street or not. The results reveal that this decision is affected by the distance from the incoming vehicles and the waiting times of pedestrians.     

Detection Algorithms of Intentional Car Following on Smart Networks: A Primary Methodology

Abstract

This paper explores the possibility of detecting certain movements of vehicles that might provide useful information for crime investigations. It is known that existing car following models are interested in microscopic interactions between vehicles in randomly formed pairs. The present work, however, introduces the concept of macroscopic analysis of vehicle positions on a network and the idea of seeking if these movements exhibit any meaningful relationships. First of all detection algorithms are produced for two possible types of detection: (a) was a particular vehicle followed by any vehicle? and (b) did a particular vehicle follow any vehicle? These algorithms assume that every link in the network is equipped with some sort of vehicle identification or tracking device and the identities of all vehicles, such as their number plates, are fed into the program. Then a simulation program is developed to implement the first algorithm (Type (a)), as an example, to visualise the concept. Since the present paper is a preliminary and basic approach to the problem, a number of issues and details requiring further research, together with the directions which could be taken, are also identified and discussed.     

Evaluation of the Transferability of Incident Detection Algorithms Developed for Singapore Expressways

ABSTRACT

Two new detection algorithms, single-station DV (dual-variable) and dual-station CODE (COmbined Detector Evaluation) were developed earlier using 160 incidents collected along Singapore's Central Expressway (CTE). The transferability of these CTE-developed algorithms is assessed, as a case study, using 100 incidents collected from the Tullamarine Freeway and South Eastern Freeway in Melbourne, Australia. The investigation covers the differences in traffic detector systems (loop detectors versus video-based), road geometry and behaviour between drivers in Singapore and Australia. The re-calibrated application of these algorithms to freeways in Melbourne yielded a reasonably good detection performance as well as satisfying the average expected performances of seven traffic management centres surveyed in the USA. The results suggested that the detection logic of the algorithms developed for CTE possessed reasonably good transferability and are also suitable for receiving traffic inputs from video-based detectors as well as from loop detectors.     

The Influences of the Built Environment and Residential Self-Selection on Pedestrian Behavior: Evidence from Austin, TX

Pedestrian travel offers a wide range of benefits to both individuals and society. Planners and public health officials alike have been promoting policies that improve the quality of the built environment for pedestrians: mixed land uses, interconnected street networks, sidewalks and other facilities. Whether such policies will prove effective remains open to debate. Two issues in particular need further attention. First, the impact of the built environment on pedestrian behavior may depend on the purpose of the trip, whether for utilitarian or recreational purposes. Second, the connection between the built environment and pedestrian behavior may be more a matter of residential location choice than of travel choice. This study aims to provide new evidence on both questions. Using 1368 respondents to a 1995 survey conducted in six neighborhoods in Austin, TX, two separate negative binomial models were estimated for the frequencies of strolling trips and pedestrian shopping trips within neighborhoods. We found that although residential self-selection impacts both types of trips, it is the most important factor explaining walking to a destination (i.e. for shopping). After accounting for self-selection, neighborhood characteristics (especially perceptions of these characteristics) impact strolling frequency, while characteristics of local commercial areas are important in facilitating shopping trips.     

基于SR和LMD的埋地管道损伤谐波磁场检测方法

针对埋地钢质管道损伤不开挖检测问题,提出一种非接触式谐波磁场检测方法.利用调频载波原理将高频信号叠加到低频信号上构建谐波激励信号,通过聚焦阵列增强激励信号的空间辐射能量和靶向性;采用三维矢量隧道磁阻差分传感器阵列对磁场信号进行采集.采用双稳随机共振(SR)算法增强目标信号能量并采用局域均值分解(LMD)算法进行自适应时...     

Pedestrian detection for traffic safety based on Accumulate Binary Haar features and improved deep belief network algorithm

ABSTRACT

In order to improve traffic safety and protect pedestrians, an improved and efficient pedestrian detection method for auto driver assistance systems is proposed. Firstly, an improved Accumulate Binary Haar (ABH) feature extraction algorithm is proposed. In this novel feature, Haar features keep only the ordinal relationship named by binary Haar features. Then, the feature brings in the idea of a Local Binary Pattern (LBP), assembling several neighboring binary Haar features to improve discriminating power and reduce the effect of illumination. Next, a pedestrian classification method based on an improved deep belief network (DBN) classification algorithm is proposed. An improved method of input is constructed using a Restricted Bolzmann Machine (RBM) with T distribution function visible layer nodes, which can convert information on pedestrian features to a Bernoulli distribution, and the Bernoulli distribution can then be used for recognition. In addition, a middle layer of the RBM structure is created, which achieves data transfer between the hidden layer structure and keeps the key information. Finally, the cost-sensitive Support Vector Machine (SVM) classifier is used for the output of the classifier, which could address the class-imbalance problem. Extensive experiments show that the improved DBN pedestrian detection method is better than other shallow classic algorithms, and the proposed method is effective and sufficiently feasible for pedestrian detection in complex urban environments.     

Walking infrastructure design assessment by continuous space dynamic assignment modeling

For the planning and design of walking infrastructure, characterized by the fact that the pedestrians can choose their paths freely in two‐dimensional space, applicability of traditional discrete network models is limited. This contribution puts forward an approach for user‐optimal dynamic assignment in continuous time and space for analyzing for instance walking infrastructure in a two‐dimensional space. Contrary to network‐based approaches, the theory allows the traffic units to choose from an infinite non‐countable set of paths through the considered space. The approach first determines the continuous paths using a path choice model. Then, origin‐destination flows are assigned and traffic conditions are calculated. The approach to determine a user‐optimal assignment is heuristic and consists of a sequence of all‐or‐nothing assignments. An application example is presented, showing dynamic user equilibrium traffic flows through a realistic transfer station. The example is aimed at illustrating the dynamic aspects of the modeling approach, such as anticipation on expected flow conditions, and predicted behavior upon catching or missing a connection.     

Pedestrian crossing detection based on evidential fusion of video-sensors

This paper introduces an online pedestrian crossing detection system that uses pre-existing traffic-oriented video-sensors which, at regular intervals, provide coarse spatial measurements on areas along a crosswalk. Pedestrian crossing detection is based on the recognition of occupancy patterns induced by pedestrians when they move on the crosswalk. In order to improve the ability of non-dedicated sensors to detect pedestrians, we introduce an evidential-based data fusion process that exploits redundant information coming from one or two sensors: intra-sensor fusion uses spatiotemporal characteristics of the measurements and inter-sensor fusion uses redundancy between the two sensors. As part of the EU funded TRACKSS project on cooperative advanced sensors for road traffic applications, real data have been collected on an urban intersection equipped with two cameras. The results obtained show that the data fusion process enhances the quality of occupancy patterns obtained and leads to high detection rates of pedestrian crossings with multi-purpose sensors in operational conditions, especially when a secondary sensor is available.