United States Department of Transportation
i
A Real-time Proactive Intersection Safety Monitoring System Based on Video Data
-
2022-04-01
-
[PDF-3.53 MB]
Details:
-
Creators:
-
Corporate Creators:
-
Corporate Contributors:Rutgers University. Center for Advanced Infrastructure and Transportation ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology ; United States. Department of Transportation. University Transportation Centers (UTC) Program ; New Jersey. Division of Highway Traffic Safety ; United States. Department of Transportation. Federal Highway Administration
-
Subject/TRT Terms:
-
Publication/ Report Number:
-
Resource Type:
-
Geographical Coverage:
-
Edition:Final Report 03/31/2021 - 02/28/2022
-
Corporate Publisher:
-
Abstract:In recent years, identifying road users' behavior and conflicts at intersections have become an essential data source for evaluating traffic safety. According to the Federal Highway Administration (FHWA), in 2020, more than 50% of fatal and injury crashes occurred at or near the intersections, necessitating further investigation. This study developed an innovative artificial intelligence (AI)-based video analytic tool to assess intersection safety using surrogate safety measures. Surrogate safety measures (e.g., Post-encroachment Time (PET) and Time-to-Collision (TTC)) are extensively used to identify future threats, such as rear-end and left-turning collisions due to vehicle and road users' interactions. To extract the trajectory data, this project integrates a real-time AI detection model - YOLO-v5 with a tracking framework based on the DeepSORT algorithm. 54 hours of high-resolution video data were collected at six signalized intersections (including three3-leg intersections and three 4-leg intersections) in Glassboro, New Jersey. Non-compliance behaviors, such as red-light running and pedestrian jaywalking, are captured to better understand the risky behaviors at these locations. The proposed approach achieved an accuracy of 92% to 98% for detecting and tracking the road users' trajectories. Additionally, a user-friendly web-based application was developed that provides directional traffic volumes, pedestrian volumes, vehicles running a red light, pedestrian jaywalking events, and PET and TTC for crossing conflicts between two road users. In addition, an extreme value theory (EVT) was used to estimate the number of crashes at each intersection utilizing the frequency of PETs and TTCs. Finally, the intersections were ranked based on the calculated score considering the severity of crashes. Overall, the developed tool as well as the crash estimation model and ranking method, can provide valuable information for engineers and policymakers to assess the safety of intersections and implement effective countermeasures to mitigate the intersection-involved crashes.
-
Format:
-
Funding:
-
Collection(s):
-
Main Document Checksum:
-
Download URL:
-
File Type:
