Leveraging Artificial Intelligence on Things for Real-time Safety Notifications in High-Risk Regions of Collision

Each year, 90% of the roughly 36,000 traffic-related deaths in the U.S. are the result of human errors according to the Automobile Association of America. Keeping drivers alert with early safety notifications on potential risks is important to reduce human errors and improve public safety. Currently, navigation Apps can provide pre-announced construction locations, traffic delays, accidental cites, and weather alarming. However, there is a complete lack of real-time risk notifications. Existing databases such as Crash Reporting Information System (CRIS), and Pavement Management Information System (PMIS) have documented locations, time, road geometrics, weather conditions, and causes of accidents, allowing identifications of high-risk regions of collision. Further, the current Video Imaging Vehicle Detection System (VIVDS) of the Texas Department of Transportation (TxDOT) can take, store, and transmit traffic images and video to their data center in low frequency or on-demand real-time monitoring. However, the post-collection process from VIVDS is performed at the data center, imposing challenges on real-time traffic flow monitoring due to the limitations on storage, computational capability, communication bandwidth, energy consumption, and cost. There is also an urgent demand to enhance the VIVDS under visual limited scenarios such as nighttime and foggy weather leading to frequent human errors. Therefore, the research team proposes to generate low-cost real-time early safety notifications by implementing artificial intelligence (AI) on existing road devices in all weather and light conditions. The framework developed in this project will be compatible with existing infrastructure and specifications from VIVDS of TxDOT. Upon achievement, the framework, development details, and operation manuals will be shared with TxDOT, allowing easy transformable implementation to the current infrastructure. The proposed project will integrate the research activities with educational training by developing new course modules for AI and risk analysis, advising senior designs for undergraduates and thesis/dissertation projects for graduate students, and supporting undergraduate research experiences in collaboration with the NSF Research Experiences for Undergraduates (REU) program at the University of Texas at San Antonio (UTSA). The team will actively recruit minority, female, and disabled students into our research teams and outreach activities. An annual open house and demonstration to local middle and high school students will be scheduled with the Northside Independent School District in San Antonio.

• Supplemental Notes:
  • 22SAUTSA49

Language

• English

Project

• Status: Active
• Funding: $100000
• Contract Numbers:

  69A3551747106

• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Managing Organizations:

  Transportation Consortium of South-Central States (Tran-SET)

  Louisiana State University
  Baton Rouge, LA  United States  70803
• Project Managers:

  Mousa, Momen

• Performing Organizations:

  University of Texas at San Antonio

  One UTSA Circle
  San Antonio, TX  United States  78249
• Principal Investigators:

  Jin, Yufang

• Start Date: 20220401
• Expected Completion Date: 0
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers Program

Subject/Index Terms

• TRT Terms: Artificial intelligence; Information processing; Real time information; Traffic safety; Vehicle detectors
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management; Safety and Human Factors;

Filing Info

• Accession Number: 01844945
• Record Type: Research project
• Source Agency: Transportation Consortium of South-Central States (Tran-SET)
• Contract Numbers: 69A3551747106
• Files: UTC, RIP
• Created Date: May 9 2022 6:04AM