HOME MyTRB CONTACT US DIRECTORY E-NEWSLETTER FOLLOW US RSS


The National Academies

NCHRP IDEA 20-30/IDEA 217 [Active (IDEA)]

A Real-Time Proactive Intersection Safety Monitoring and Visualization System Based on Radar Sensor Data

  Project Data
Funds: $137,000
Staff Responsibility: Inam Jwed
Research Agency: University of Louisville
Principal Investigator: Zhixia (Richard) Li
Fiscal Year: 2019

This project will develop and test a real-time intersection proactive safety visualization system (IPSV) based on vehicle and pedestrian trajectory data collected by radar sensors. Work in Stage 1 will focus on developing the IPSV algorithm from automated data collection of radar sensor data. An algorithm of automated data preprocessing will be developed and implemented in the IPSV. The algorithm will integrate trajectory data from the four radar sensors used at the intersection. The coordinate transformation algorithm will be implemented and noise reduction algorithm will be developed to remove the trajectory noise from the analysis. A second algorithm that automatically classifies different traffic and pedestrian movements will be developed to allow automatic computing of time to different types of collision. Based on predefined threshold of time to collision (TTC), traffic conflicts of different types will be automatically identified and their severity measured. Work in the second and final stage will involve developing a user interface to configure IPSV parameters as well as testing and validating the IPSV.  A configuration tool will be developed to provide interface for users to configure the TTC thresholds and traffic conflict types through a user-friendly interface.  The IPSV will be tested at an intersection in Louisville, KY. Trajectory data will be collected along with TTC, traffic conflicts, and traffic conflict severity data. All functions of IPSV will be tested to make sure that they work as intended and validated based on field collected data. The accuracy of TTC, traffic conflicts, and traffic conflicts severity will be evaluated using trajectory data collected from a video camera. The safety performance accuracy will also be compared to the historical crash data to ascertain whether there is a consistent trend. The final report will provide all relevant data, findings, and conclusions along with recommendations on how to use the technology to monitor and assess intersection safety.

To create a link to this page, use this URL: http://apps.trb.org/cmsfeed/TRBNetProjectDisplay.asp?ProjectID=4878