Optimal RWIS Sensor Density and Location – Phase IV
The primary objective of this project is to continue the previous research effort on developing highly transferrable and universally applicable methodologies, models, and tools for visualizing and inferring road surface conditions using data from road weather information systems (RWIS) and other road condition monitoring systems. More specifically, the research has the following five specific objectives: (1) Prepare and process a comprehensive training/testing dataset (e.g., RWIS and in-vehicle images) that covers a sufficiently large range of road, weather, and environmental conditions; (2) Test and improve the performance of alternative deep learning-based image classification models and determine the best model for real-time implementation; (3) Develop a system that can automate the process of updating the deep learning model as newly labelled data are received; (4) Generate LOS performance measures (e.g., BPRT, RSI) that can be used to quantitatively assess the efficiency of the existing maintenance program; and (5) Implement a web-based application for visualizing the spatial mapping and image recognition solutions and demonstrate the application with real world usage scenarios. This proposed continuation of the project will utilize datasets from the highways within the state of Iowa to take advantage of the substantial amount of archived stationary RWIS images, dash camera images (maintenance trucks), and geographic information system (GIS) data that were downloaded and processed in previous projects. Ultimately, this project will provide winter maintenance personnel with newfound knowledge and analytical tools, of which they can employ to make better use of available resources, resulting in better maintenance and improvements to their highway infrastructure thereby promoting improved winter mobility and safety.
Language
- English
Project
- Status: Active
- Funding: $154878
-
Contract Numbers:
TPF-5(435)
-
Sponsor Organizations:
Iowa Department of Transportation
800 Lincoln Way
Ames, IA United States 50010 -
Managing Organizations:
Iowa Department of Transportation
800 Lincoln Way
Ames, IA United States 50010 -
Project Managers:
Clute, Khyle
-
Performing Organizations:
University of Alberta, Edmonton
Department of Civil and Environmental Engineering
Edmonton, Alberta Canada -
Principal Investigators:
Kwon, Tae
- Start Date: 20211101
- Expected Completion Date: 20240831
- Actual Completion Date: 0
Subject/Index Terms
- TRT Terms: Image analysis; Location; Machine learning; Road weather information systems; Sensors
- Subject Areas: Data and Information Technology; Highways; Planning and Forecasting;
Filing Info
- Accession Number: 01910291
- Record Type: Research project
- Source Agency: Iowa Department of Transportation
- Contract Numbers: TPF-5(435)
- Files: RIP, STATEDOT
- Created Date: Feb 28 2024 11:59AM