Highway Design and Safety

Automated Traffic Sign Recognition Using Computer Vision and Deep Learning

The importance of traffic signs for traffic operations and safety requires transportation agencies to maintain an inventory of them and their condition. To conduct such an inventory, WSDOT staff must physically visit locations for sign verification and data collection. Given the huge number of posted traffic signs, this means that traditional sign asset management is time-consuming and costly.  New, automated solutions are needed to collect traffic sign data and manage them in a timely and cost-effective manner. To address this issue, this study is developing a traffic sign data collection system from open street images, an algorithm for detecting and recognizing traffic signs in those images, and an expandable sample data inventory of traffic signs in a designated region in Washington, including both freeways and local streets. The final products will provide an automated solution to reduce manual labor and will significantly contribute to traffic sign asset management.  

Principal Investigator: Yinhai Wang, Civil and Environmental Engineering, UW
Sponsor: WSDOT
WSDOT Technical Monitor: Dina Swires 
WSDOT Project Manager: Doug Brodin 
Scheduled completion: September 2024

Extending the SR 522 SPaT Challenge to Active Transportation Users

This project will give researchers hands-on experience with the connected transportation environment and interactions among pedestrians, bicycles, vehicles, and traffic signals. Specifically, this project will integrate data from traffic control system signal phase and timing (SPaT) broadcasts along SR 522 north of Seattle within an application (app) that pedestrians and bicyclists will use on their mobile devices. Pedestrians will be able to use the app to request right of way and receive information on the status of the pedestrian signal. Bicycle users will be able to indicate their presence to actuate the traffic signal. All users will also be able to send/receive better quality information on their location within a crosswalk, bicycle lane, pathway, or vehicle travel lane. The project not only has the potential to improve intersection operations but has clear implications for helping increase the safety of all non-motorized road users, particularly those with vision impairments and other disabilities.

Principal Investigator: Yinhai Wang, Civil and Environmental Engineering, UW
Sponsor: WSDOT
WSDOT Technical Monitor: Justin Belk
WSDOT Project Manager: Doug Brodin
Scheduled completion: June 2023

Field Analysis of Wood Guardrail Post Decay

This project is investigating the integrity of wood guardrail posts in strategic locations of Washington state. Guardrail systems protect motorists involved in a crash by dissipating energy and keeping them from leaving the roadway. The guardrail post is an important part of the system. Unfortunately, wood guardrail posts are susceptible to failing during a crash event because of a loss of strength from wood decay.  Wood decay may be due to fungal growth or insect intrusion and is difficult to detect by visual inspection alone because decay commonly occurs inside the post.  Phase I of this research proposed utilizing a stress wave timing (SWT) device for non-destructive field testing of wood posts.  This Phase II study is focusing on quantifying the factors that affect wood post service life in the Northwest, including the post’s age, location, and physical properties such as wood species, treatment method, and lumber grade.  WSDOT will be able to use the information provided to consider the need to revise wood treatment specifications and/or design guidance for wood guardrail posts.

Principal Investigator: Adam Phillips, Civil and Environmental Engineering, WSU
Sponsor: WSDOT
WSDOT Technical M0nitor: Brad Manchas
WSDOT Project Monitor: Doug Brodin
Scheduled completion: June 2018