Automated Analysis of Pedestrian–Vehicle Conflicts Using Video Data

Abstract

Pedestrians are vulnerable road users, and despite their limited representation in traffic events, pedestrian-involved injuries and fatalities are overrepresented in traffic collisions. However, little is known about pedestrian exposure to the risk of collision, especially when compared with the amount of knowledge available for motorized traffic. More data and analysis are therefore required to understand the processes that involve pedestrians in collisions. Collision statistics alone are inadequate for the study of pedestrian–vehicle collisions because of data quantity and quality issues. Surrogate safety measures, as provided by the collection and study of traffic conflicts, were developed as a proactive complementary approach to offer more in-depth safety analysis. However, high costs and reliability issues have inhibited the extensive application of traffic conflict analysis. An automated video analysis system is presented that can (a) detect and track road users in a traffic scene and classify them as pedestrians or motorized road users, (b) identify important events that may lead to collisions, and (c) calculate several severity conflict indicators. The system seeks to classify important events and conflicts automatically but can also be used to summarize large amounts of data that can be further reviewed by safety experts. The functionality of the system is demonstrated on a video data set collected over 2 days at an intersection in downtown Vancouver, British Columbia, Canada. Four conflict indicators are automatically computed for all pedestrian–vehicle events and provide detailed insight into the conflict process. Simple detection rules on the indicators are tested to classify traffic events. This study is unique in its attempt to extract conflict indicators from video sequences in a fully automated way.

Analysis of Pedestrian–Vehicle Traffic Conflicts in Street Designs with Elements of Shared Space

“…However, some examples of work on conflicts between vehicles and other road users can be found in the literature, mostly for the purpose of assessing the safety of pedestrian crossings and the interactions within mixed traffic flows. These include: (24), where a method categorising vehicle-pedestrian conflicts at crossings into one of 13 types was derived with a view of identifying potential safety hazards; (25), where pedestrianvehicle conflicts along with traffic characteristics data were used to perform automated assessment of the safety of Pelican crossings in the UK; and (26)(27), in which an automated video analysis system to classify road users as vehicles or pedestrians, identify conflict situations between them and categorise them according to their severity was developed. Also, there are several instances of methods adapted from well-established vehicle-vehicle methods to monitor pedestrian-vehicle conflicts, such as: the application of the STCT in (28) and (29); the use of the USDoTCT in (30); and the adaptation of the CIHTCT in (12) and in (31).…”

Automated Analysis and Validation of Right-Turn Merging Behavior

“…The analysis of traffic conflicts and the measurement of conflicts indicators have often been conducted through manual observations. Recent work addressed the opportunity for the automation of traffic-conflicts data collection (Saunier & Sayed, 2007) and provided a guideline for the objective measurements of conflicts indicators (Ismail et al, 2009;Laureshyn et al, 2009;Sayed et al, 2012). Large-scale application validation of this line of research was demonstrated in Autey et al (2012) and Ismail et al (2010)).…”

“…The automated approach solves many shortcomings in manual data collection and provides a more practical and efficient way to capture, store, and analyze elements of the traffic information for largescale data. Automated video analysis was used before in extracting conflict data in Ismail et al, 2009;Sayed et al, 2013) and the detection of violations in (Ismail et al, 2011;Zaki et al, 2012). Automated video data analysis for traffic movements is a practical computer vision application, where road users are detected and their travel trajectories tracked in an automated manner.…”

Microssimulação da travessia de pedestres: coleta de dados para calibração de modelos

“…No processo de coleta de dados, em travessias nos acessos a rotatórias, o autor identificou limitações que tornam necessário rastrear manualmente alguns objetos. Recentemente, Ismail et al (2009) desenvolveram uma ferramenta automática para rastrear pedestres e veículos e detectar eventos que possam conduzir a colisões, calculando indicadores de severidade dos conflitos. Os autores destacam que para utilizar a ferramenta em ambientes com fluxos maiores, no entanto, são necessários aperfeiçoamentos.…”