Probabilistic Framework for Automated Analysis of Exposure to Road Collisions
The advent of powerful sensing technologies, especially video sensors and computer vision techniques, has allowed for the collection of large quantities of detailed traffic data. These technologies allow further advancement toward completely automated systems for road safety analysis. This paper presents a comprehensive probabilistic framework for automated road safety analysis. Building on traffic conflict techniques and the concept of the safety hierarchy, it provides computational definitions of the probability of collision for road users involved in an interaction. It proposes new definitions for aggregated measures over time. This framework allows the interpretation of traffic from a safety perspective, by studying all interactions and their relationship to safety. New and more relevant exposure measures can be derived from this work, and traffic conflicts can be detected. A complete vision-based system is implemented to demonstrate the approach, providing experimental results on real-world video data.
- Record URL:
- Summary URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/isbn/9780309125956
-
Authors:
- Saunier, Nicolas
- Sayed, Tarek A
- Publication Date: 2008
Language
- English
Media Info
- Media Type: Print
- Features: Figures; Photos; References;
- Pagination: pp 96-104
- Monograph Title: Safety Data, Analysis, and Modeling
-
Serial:
- Transportation Research Record: Journal of the Transportation Research Board
- Issue Number: 2083
- Publisher: Transportation Research Board
- ISSN: 0361-1981
Subject/Index Terms
- TRT Terms: Computer vision; Crash exposure; Traffic data; Traffic safety; Video cameras
- Uncontrolled Terms: Automated data analysis
- Subject Areas: Highways; Safety and Human Factors; I82: Accidents and Transport Infrastructure;
Filing Info
- Accession Number: 01099067
- Record Type: Publication
- ISBN: 9780309125956
- Files: TRIS, TRB, ATRI
- Created Date: May 21 2008 7:03AM