6.13 Evaluating Image-Derived Estimates of Road Weather Conditions

Wednesday, 15 July 2020: 11:35 AM
Virtual Meeting Room
Brittany Welch, Univ. of Utah, Salt Lake City, UT; and J. Horel

Handout (1.7 MB)

Winter weather creates hazardous driving conditions nationwide that create the need for real-time assessments of road weather conditions. In regions of complex terrain such as the Wasatch Front of Utah or the Front Range of the Rockies in Wyoming and Colorado, state transportation departments (DOTs) spend millions of dollars for winter maintenance operations. Road Weather Information Systems (RWIS) are one automated approach to monitor weather and pavement conditions continuously. Although there are hundreds of RWIS across Utah, Wyoming, and Colorado, those observing sites are insufficient by themselves to monitor the conditions along the extensive roadways in those states.

DOTs invest heavily in cameras installed along roadways to monitor traffic flow and road state. There are so many cameras that it can be difficult for DOT staff to be aware of adverse conditions at all times at all places. Commercial products, such as the Helios® Real-time Ground Weather Intelligence System of the Harris Corporation, are available to help monitor weather and pavement conditions obtained from camera networks. Helios relies on image processing to provide transportation staff with web services to monitor road weather information throughout their area of responsibility.

The accuracy of the camera-based estimates of pavement state, visibility, and precipitation available from Helios is being compared to observations of those and other weather and road-state parameters at nearby RWIS sites during the 2018-2019 and 2019-2020 winters in Utah and Wyoming. The ability of the Helios output to correctly identify road surfaces that are fully or partially covered by snow is examined.

- Indicates paper has been withdrawn from meeting
- Indicates an Award Winner