Paper Details

TRB 91st Annual Meeting (January 22-26, 2012)

Event Number:	432
Event Title:	Research for the Sake of Safety
Event Date:	Jan 23 2012 7:30PM- 9:30PM
Event Location:	Marriott, Virginia A
Event Description:
Event Agenda:

Feasibility of Computer Vision-Based Safety Evaluations: Case of Signalized Right-Turn Safety Treatment (12-0448)

Traditional road safety analysis has often been undertaken using historical collision records. However, limitations on the quality and completeness of collisions data gave rise to surrogate safety measures especially the traffic conflict technique (TCT). Traditionally, TCT's have relied on in-field observation, which has some reliability and repeatability problems. Therefore, successful automation of extracting conflicts from video sensors data can have considerable benefits for traffic safety studies. One safety application that could greatly benefit from automated traffic conflicts analysis is before-and-after (BA) evaluation of safety treatments. There are several advantages that support the adoption of traffic conflict techniques in BA safety studies. Traffic conflicts are more frequent than road collisions and are of marginal social cost. Traffic conflicts provide insight into the failure mechanism that leads to road collisions. BA studies based on traffic conflicts can be conducted over shorter periods. The main objective of this paper is to demonstrate the use of automated traffic conflicts analysis for a before-and-after safety evaluation. A right-turn safety improvement was implemented at an intersection in the City of Edmonton in 2009 to mitigate high occurrence of rear-end and merging collisions. The right-turn ramp was closed and all right-turning vehicles were brought to the right-turn lane at the intersection where a “no right turn on red” sign was installed. Video sensors are selected in this study as the primary source of conflicts data. The analysis of video data to measure traffic conflicts is undertaken using an automated traffic safety tool. The distributions of the calculated conflict indicators before-and-after the treatment show a considerable reduction in the frequency and severity of traffic conflicts which suggests a significant positive change in safety for rear-end, merging and total conflicts. It is hoped that the results of this study will show the potential for the adoption of automated conflict analysis to conduct BA safety studies.

Authors
     Sayed, Tarek , University of British Columbia, Canada
     Ismail, Karim , Carleton University, Canada
     Zaki, Mohamed H., University of British Columbia, Canada
     Autey, Jarvis , University of British Columbia, Canada