A GIS-based methodology for identifying pedestrians’ crossing patterns

A pedestrian trip is a spatiotemporal process going through different states and related to different decisions made at certain times and locations on the urban network. The analysis of pedestrian trips in terms of crossing patterns is a complex task, which is often further limited by a lack of appropriate and detailed data. The objective of this research is the development and testing of appropriate indicators of pedestrian crossing behavior along urban trips, and a methodology for collecting and processing the data required for the analysis of this behavior. First, a comprehensive set of indicators for the assessment of pedestrian behavior in urban areas is proposed (i.e. average trip length, number, type and location of crossings). Then, a GIS tool is developed for the storage and integration of information on pedestrian trips, and the crossings made during the trips, with other geographical information (e.g. road network function and geometry, traffic control and pedestrian facilities). The proposed approach is then tested at network level on a sample of pedestrian trips collected by a field survey. The results suggest specific patterns of pedestrian crossing behavior, such as the tendency to cross at the beginning of the trip and the tendency to cross at mid-block locations when signalized junctions are not available. The results are further discussed in terms of urban planning and management implications. It is concluded that the proposed approach is very efficient for the analysis of pedestrian crossing behavior in urban areas.     

Pedestrian detection and tracking at crossroads

This paper presents a system that can perform pedestrian detection and tracking using vision-based techniques. A very important issue in the field of intelligent transportation system is to prevent pedestrians from being hit by vehicles. Recently, a great number of vision-based techniques have been proposed for this purpose. In this paper, we propose a vision-based method, which combines the use of a pedestrian model as well as the walking rhythm of pedestrians to detect and track walking pedestrians. Through integrating some spatial and temporal information grabbed by a vision system, we are able to develop a reliable system that can be used to prevent traffic accidents happened at crossroads. In addition, the proposed system can deal with the occlusion problem. Experimental results obtained by executing some real world cases have demonstrated that the proposed system is indeed superb.     

Modeling vehicle–pedestrian interactions outside of crosswalks

Pedestrian and driver behaviors as well as their interactions, are essential in planning, designing and operating highway facilities. Pedestrian crossing outside of a marked or unmarked crosswalk (i.e. jaywalking), is one of those pedestrian behaviors that may highly affect safety and operations. Unlike permissible crossings at crosswalks, jaywalking events are not often anticipated by drivers, which may result in less driver reaction time and different vehicle operation dynamics. It is important to understand pedestrian crossing behavior outside of crosswalks, as well as driver yielding behavior towards them. To date, limited quantitative and behavioral research has been conducted to investigate this interaction or simulate it microscopically. This paper aims to explore both pedestrian jaywalking behavior (gap acceptance and speeds) and the corresponding driver reactions (yielding behavior) for modeling the vehicle–pedestrian interactions (VPI) outside the crosswalks in a micro-simulation environment. The study also quantifies the differences between vehicle–jaywalker and vehicle-permissible crossing. An observational study and an instrumented vehicle study were conducted on the campus of the University of Florida to collect data from pedestrian and driver perspectives, respectively.Crossing speed, yield acceptance and delay of jaywalking crossings and permissible crossings were observed in the study and these attributed can be used for replicating pedestrian operations in simulators. Moreover, behaviors of driver approaching jaywalkers versus pedestrians crossing at designated crosswalks were compared on the basis of yield rates, and vehicle speed profiles. Vehicle yield dynamics were analyzed to model the driver reactions towards jaywalkers. Lastly, it was found that the locations of jaywalking events are highly concentrated and influenced by the crossing environment, such as pedestrian and vehicular volume, bus stops presence and crossing distance.This paper establishes several quantitative relationships describing interactions between pedestrians crossing outside of crosswalks and approaching drivers, which provide the basis and assumptions for modeling such interactions in a micro-simulation environment for traffic operational analyses.     

无信号人行横道交通流特性的研究

考虑到行人穿越人行横道特点和心理因素,构建人行横道处机动车和行人相互干扰行为的元胞自动机模型。模型中重新制定行人和机动车的冲突干扰规则,引入临界安全间隙和临界决策间隙概念计算行人的通过概率,根据行人过街等待时间阈值定义了行人的冒险概率。模拟结果显示,临界决策间隙、行人忍耐时间阈值和行人的临界跟随间隙对机动车与行人流量均有不同程度的影响,其中行人的临界跟随间隙对交通流影响最大。     

基于行人安全的交通信号灯智能控制算法研究

提出了一种基于深度确定性策略梯度(DDPG, deep deterministic policy gradient)的行人安全智能交通信号控制算法;通过对交叉口数据的实时观测,综合考虑行人安全与车辆通行效率,智能地调控交通信号周期时长,相位顺序以及相位持续时间,实现交叉路口安全高效的智能控制;同时,采用优先经验回放提高采样效率,加速了算法收敛;由于行人安全与车辆通行效率存在相互矛盾,研究中通过精确地设计强化学习的奖励函数,折中考虑行人违规引起的与车辆的冲突量和车辆通行的速度,引导交通信号灯学习路口行人的行为,学习最佳的配时方案;仿真结果表明在动态环境下,该算法在行人与车辆冲突量,车辆的平均速度、等待时间和队列长度均优于现有的固定配时方案和其他的智能配时方案。     

Tracking Pedestrians Under Occlusion in Parking Space

Many traffic accidents occur in parking lots. One of the serious safety risks is vehicle-pedestrian conflict. Moreover, with the increasing development of automatic driving and parking technology, parking safety has received significant attention from vehicle safety analysts. However, pedestrian protection in parking lots still faces many challenges. For example, the physical structure of a parking lot may be complex, and dead corners would occur when the vehicle density is high. These lead to pedestrians’ sudden appearance in the vehicle’s path from an unexpected position, resulting in collision accidents in the parking lot. We advocate that besides vehicular sensing data, high-precision digital map of the parking lot, pedestrians’ smart device’s sensing data, and attribute information of pedestrians can be used to detect the position of pedestrians in the parking lot. However, this subject has not been studied and explored in existing studies. To fill this void, this paper proposes a pedestrian tracking framework integrating multiple information sources to provide pedestrian position and status information for vehicles and protect pedestrians in parking spaces. We also evaluate the proposed method through real-world experiments. The experimental results show that the proposed framework has its advantage in pedestrian attribute information extraction and positioning accuracy. It can also be used for pedestrian tracking in parking spaces.     

Simulating operational behaviors of pedestrian navigation

Navigation is an innate ability for humans, but simulating this capability in a virtual environment is no easy task and has been of interest to researchers for over a decade. This paper describes the development of ISAPT, an individual-based Intermodal Simulator for the Analysis of Pedestrian Traffic. ISAPT’s development is based on the observed behaviors of pedestrians reported from the literature and simulates the strategies employed by pedestrians for collision avoidance, including changes in speed and trajectory, passing strategies, and distance between objects. The implementation of these behaviors and strategies is described in the paper along with the results from a validation study. These results illustrate that the micro-level simulation of individual pedestrians gives ISAPT the ability to reproduce identified macro-level pedestrian behavior, as well as the capability to reproduce the operational statistics of an observed pedestrian corridor. Such functionality is necessary to support the use of simulation as a tool for designers and planners in the design and evaluation of intermodal facilities.     

Associated evolution of a support vector machine-based classifier for pedestrian detection

Support vector machine (SVM) has become a dominant classification technique used in pedestrian detection systems. In such systems, classifiers are used to detect pedestrians in some input frames. The performance of a SVM classifier is mainly influenced by two factors: the selected features and the parameters of the kernel function. These two factors are highly related and therefore, it is desirable that the two factors can be analyzed simultaneously, which are usually not the case in the previous work.In this paper, we propose an evolutionary method to simultaneously optimize the feature set and the parameters for the SVM classifier. Specifically, adaptive genetic operators were designed to be suitable for the feature selection and parameter tuning. The proposed method is used to train a SVM classifier for pedestrian detection. Experiments in real city traffic scenes show that the proposed approach leads to higher detection accuracy and shorter detection time.     

Modeling pedestrians’ interest in locations: A concept to improve simulations of pedestrian destination choice

Large environments that are designed for travel, leisure, and for everyday life – such as transport hubs, amusement parks, and shopping centers – feature different locations that are frequently visited by pedestrians. Each visit is evoked by one’s motivation to engage in some kind of activity at a certain location. By means of modeling the pedestrians’ interests in locations with the aid of computer simulations, it is possible to forecast the occupancy at locations by utilizing sophisticated pedestrian destination choice models. In the field of pedestrian dynamics research, location preference modeling is not common, but it is all the more rare to include a psychological grounding into such choice models. Here we show that our psychologically inspired and mathematically defined model to describe pedestrians’ interests in locations is able to improve the exactness of pedestrian destination choice models. The interest function model is based on the psychological concept of goal-related memory accessibility and on fundamental coherences found in pedestrian-related data that is measurable at locations. We validated the interest function model and our results provide evidence that our approach improves the simulation fidelity regarding occupancy forecasting. Because the interest concept is designed as a framework that can be coupled to existing microscopic pedestrian simulators, it can be used in most pedestrian destination choice models to describe pedestrian visiting preferences. Consequently, the reliability of the occupancy predictions of pedestrian simulations can be enhanced by integrating the interest function model into choices models.     

车辆辅助驾驶系统中基于计算机视觉的行人检测研究综述

基于计算机视觉的行人检测由于其在车辆辅助驾驶系统中的重要应用价值成为当前计算机视觉和智能车辆领域最为活跃的研究课题之一. 其核心是利用安装在运动车辆上的摄像机检测行人，从而估计出潜在的危险以便采取策略保护行人.本文在对这一问题存在的困难进行分析的基础上，对相关文献进行综述. 基于视觉的行人检测系统一般包括两个模块:感兴趣区分割和目标识别，本文介绍了这两个模块所采用的一些典型方法，分析了每种方法的原理和优缺点. 最后对性能评估和未来的研究方向等一系列关键问题给予了介绍.     

Pedestrian detection for intelligent transportation systems combining AdaBoost algorithm and support vector machine

Pedestrians are the vulnerable participants in transportation system when crashes happen. It is important to detect pedestrian efficiently and accurately in many computer vision applications, such as intelligent transportation systems (ITSs) and safety driving assistant systems (SDASs). This paper proposes a two-stage pedestrian detection method based on machine vision. In the first stage, AdaBoost algorithm and cascading method are adopted to segment pedestrian candidates from image. To confirm whether each candidate is pedestrian or not, a second stage is needed to eliminate some false positives. In this stage, a pedestrian recognizing classifier is trained with support vector machine (SVM). The input features used for SVM training are extracted from both the sample gray images and edge images. Finally, the performance of the proposed pedestrian detection method is tested with real-world data. Results show that the performance is better than conventional single-stage classifier, such as AdaBoost based or SVM based classifier.     

基于视野域机制的行人轨迹预测

为提高行人在复杂交通场景中交互的安全性,提出一种基于social-GAN（social-generative adversarial network）的行人轨迹预测算法SAN-GAN（social angle norm-GAN）。该算法首先以行人历史位置信息与头部信息为输入,通过轨迹生成器LSTM网络（long short term memory networks）获取行人隐藏特征信息,并基于行人视野域模块捕捉行人视野域动态变化,对所有行人建立扇形视野域并筛选有效信息,从而驱动神经网络模型预测行人未来轨迹变化。将SAN-GAN与LSTM、social-LSTM（social-long short term memory networks）、social-GAN等轨迹预测算法进行对比实验,结果表明SAN-GAN算法相较于其他算法,在预测3.2 s的行人轨迹时,ADE分别平均降低65.8%、51.2%、10.7%,FDE分别平均降低73.6%、60.9%、10.4%。SAN-GAN能够有效地预测行人在复杂交通环境中进行交互的未来轨迹。     

Recognition of pedestrian trajectories and attributes with computer vision and deep learning techniques

Analyzing the walking behavior of the public is vital for revealing the need for infrastructure design in a local neighborhood, supporting human-centric urban area development. Traditional walking behavior analysis practices relying on manual on-street surveys to collect pedestrian flow data are labor-intensive and tedious. On the contrary, automated video analytics using surveillance cameras based on computer vision and deep learning techniques appears more effective in generating pedestrian flow statistics. Nevertheless, most existing methods of pedestrian tracking and attribute recognition suffer from several challenging conditions, such as inter-person occlusion and appearance variations, which leads to ambiguous identities and hence inaccurate pedestrian flow statistics.Therefore, this paper proposes a more robust methodology of pedestrian tracking and attribute recognition, facilitating the analysis of pedestrian walking behavior. Specific limitations of a current state-of-the-art method are inferred, based on which several improvement strategies are proposed: 1) incorporating high-level pedestrian attributes to enhance pedestrian tracking, 2) a similarity measure integrating multiple cues for identity matching, and 3) a probation mechanism for more robust identity matching. From our evaluation using two public benchmark datasets, the developed strategies notably enhance the robustness of pedestrian tracking against the challenging conditions mentioned above. Subsequently, the outputs of trajectories and attributes are aggregated into fine-grained pedestrian flow statistics among different pedestrian groups. Overall, our developed framework can support a more comprehensive and reliable decision-making for human-centric planning and design in different urban areas. The framework is also applicable to exploiting pedestrian movement patterns in different scenes for analyses such as urban walkability evaluation. Moreover, the developed mechanisms are generalizable to future researches as a baseline, which provides generic insights of how to fundamentally enhance pedestrian tracking.     

Prediction of pedestrians routes within a built environment in normal conditions

Modelling and prediction of pedestrian routing behaviours within known built environments has recently attracted the attention of researchers across multiple disciplines, owing to the growing demand on urban resources and requirements for efficient use of public facilities. This study presents an investigation into pedestrians’ routing behaviours within an indoor environment under normal, non-panic situations. A network-based method using constrained Delaunay triangulation is adopted, and a utility-based model employing dynamic programming is developed. The main contribution of this study is the formulation of an appropriate utility function that allows an effective application of dynamic programming to predict a series of consecutive waypoints within a built environment. The aim is to generate accurate sequence waypoints for the pedestrian walking path using only structural definitions of the environment as defined in a standard CAD format. The simulation results are benchmarked against those from the A¹ algorithm, and the outcome positively indicates the usefulness of the proposed method in predicting pedestrians’ route selection activities.     

A genetic fuzzy system to model pedestrian walking path in a built environment

A study on the pedestrian’s steering behaviour through a built environment in normal circumstances is presented in this paper. The study focuses on the relationship between the environment and the pedestrian’s walking trajectory. Owing to the ambiguity and vagueness of the relationship between the pedestrians and the surrounding environment, a genetic fuzzy system is proposed for modelling and simulation of the pedestrian’s walking trajectory confronting the environmental stimuli. We apply the genetic algorithm to search for the optimum membership function parameters of the fuzzy model. The proposed system receives the pedestrian’s perceived stimuli from the environment as the inputs, and provides the angular change of direction in each step as the output. The environmental stimuli are quantified using the Helbing social force model. Attractive and repulsive forces within the environment represent various environmental stimuli that influence the pedestrian’s walking trajectory at each point of the space. To evaluate the effectiveness of the proposed model, three experiments are conducted. The first experimental results are validated against real walking trajectories of participants within a corridor. The second and third experimental results are validated against simulated walking trajectories collected from the AnyLogic® software. Analysis and statistical measurement of the results indicate that the genetic fuzzy system with optimised membership functions produces more accurate and stable prediction of heterogeneous pedestrians’ walking trajectories than those from the original fuzzy model.     

Automatic spatial analysis and pedestrian flow control for real-time crowd simulation in an urban environment

Distributing a collection of virtual humans throughout a large urban environment, where limited semantic information is available, poses a problem when attempting to create a visually realistic real-time environment. Randomly positioning agents within an urban environment will not cover the environment with virtual humans in a plausible way. For example, areas of the urban space that are more frequently used should have a higher population density both at the start and during the simulation. It is infeasible to manually identify all the areas in the urban environment which should be crowded or sparsely populated when considering a scalable method, suitable for large environments. Consequently, this paper combines and extends techniques from spatial analysis and virtual agent behaviour simulations to develop a system capable of automatically distributing pedestrians in an urban environment. In particular, it extends the Point-Based Space Syntax technique to enable the automatic analysis of a large urban environment in the presence of limited contextual information. This analysis specifies a set of population densities for areas in the environment and these values are used to initialise the locations of all the virtual humans in the environment. In addition to the initialisation stage the population densities in each area are consulted to ensure that the correct distribution of virtual humans is maintained throughout the simulation. The system is tested on an arbitrary section of a real city and comparisons of the characteristic parts of the test environment are correlated with the pedestrian movements.

Pedestrian navigation aids: information requirements and design implications

Recent years have seen an increased interest in navigational services for pedestrians. To ensure that these services are successful, it is necessary to understand the information requirements of pedestrians when navigating, and in particular, what information they need and how it is used. A requirements study was undertaken to identify these information requirements within an urban navigation context. Results show that landmarks were by far the most predominant navigation cue, that distance information and street names were infrequently used, and that information is used to enable navigation decisions, but also to enhance the pedestrians confidence and trust. The implications for the design of pedestrian navigation aids are highlighted.     

Control of swarm behavior in crossing pedestrians based on temporal/spatial frequencies

In the densely-populated urban areas, pedestrian flows often cross each other and congestion is caused. The congestion makes us feel uncomfortable and sometimes leads to pedestrian accidents. To reduce the congestion or the risk of accidents, it is required to control the swarm behavior of pedestrian flows. This paper proposes modeling and controlling method of the crossing pedestrian flows. In the social/urban engineering, it is well known that the swarm behavior with a diagonal stripe pattern emerges in the crossing area of the flows. This is a self-organized phenomenon caused by the local collision avoidance effect of the pedestrians. To control the macroscopic behavior of the flows, we utilize this self-organized phenomenon. Firstly, we propose the continuum model of the crossing pedestrian flows. In the continuum model, the dynamic change of the congestion in the diagonal stripe pattern is simulated as the density. Secondly, the novel control method to improve average flow velocity is proposed based on the model. The proposed method utilizes the dynamic interaction between the diagonal stripe pattern and guides, who are moving in the flows. The authors derive the control algorithm through an analysis on the temporal and spatial frequencies of the crossing flows. The validity is verified with simulations using the continuum model. Moreover, we apply the proposed method to the particle model, assuming the actual pedestrians.     

Information fusion to detect and classify pedestrians using invariant features

A novel approach to detect pedestrians and to classify them according to their moving direction and relative speed is presented in this paper. This work focuses on the recognition of pedestrian lateral movements, namely: walking and running in both directions, as well as no movement. The perception of the environment is performed through a lidar sensor and an infrared camera. Both sensor signals are fused to determine regions of interest in the video data. The classification of these regions is based on the extraction of 2D translation invariant features, which are constructed by integrating over the transformation group. Special polynomial kernel functions are defined in order to obtain a good separability between the classes. Support vector machine classifiers are used in different configurations to classify the invariants. The proposed approach was evaluated offline considering fixed sensors. Results obtained based on real traffic scenes demonstrate very good detection and classification rates.