The National Academies

NCHRP IDEA 20-30/IDEA 139 [Completed (IDEA)]

Development of Sensing Methodology for Intelligent and Reliable Work Zone Hazard Awareness
[ NCHRP 20-30 (NCHRP-IDEA) ]

  Project Data
Staff Responsibility: Dr. Inam Jawed

This project developed a methodology using vision-based object recognition algorithms to detect and track vehicles intruding into the work zone and to detect missing work zone channelization traffic control devices (such as barrels). Based on a literature review of work zone safety issues, driving behavior, and sensor technologies for improving work zone safety and discussions with Georgia DOT, work zone safety improvement needs were identified. These needs included (i) detecting vehicles intruding into work zone area and providing early warning to improve workers’ safety, and (ii) detecting missing work zone channelization traffic control devices (such as, barrels) to ensure the safety of drivers and workers and to prevent lawsuits against state DOTs. The vehicle detection and tracking algorithms were developed to provide accurate computation for minimizing false negative and false positive rates. In the second step, the threat level (safe, cautious, or dangerous) of each vehicle approaching work zone was analyzed based on each vehicle’s trajectory and its spatial proximity to a work zone taper. In the third step, a work zone hazard decision-support model was established based on the threat level of each approaching vehicle to determine adequate timing to trigger an alarm. Finally, with the aforementioned algorithms, a surveillance system including a 30-ft surveillance tower and cameras was developed and successfully tested on an actual pavement resurfacing work zone on Interstate I-95 near Savannah, Georgia. The contractor's final report is available.

To create a link to this page, use this URL: http://apps.trb.org/cmsfeed/TRBNetProjectDisplay.asp?ProjectID=2595