HOME MyTRB CONTACT US DIRECTORY E-NEWSLETTER FOLLOW US RSS


The National Academies

Transit IDEA J-04/IDEA 080 [Completed (IDEA)]

Enhancing Safety and Security of Transit Systems Using Computer Vision
[ TCRP J-04 (Innovations Deserving Exploratory Analysis--The Transit IDEA Program) ]

  Project Data
Funds: $100,000
Staff Responsibility: Jo Allen Gause
Research Agency: Rutgers University
Principal Investigator: Dimitris Metaxas
Effective Date: 12/4/2016
Fiscal Year: 2014

 This project will provide bus drivers the ability to detect distractions and fatigue during driving in order to prevent accidents. The system is based on a single camera aimed at the driver’s face and will provide a warning signal when the driver is distracted or fatigued. The Rutgers team developed the system and tested the method and advanced it to a prototype for application and potential commercialization. The testing took place on buses at Southern Pennsylvania Transportation Authority (SEPTA) and bus simulators provided by the Metropolitan Transportation Authority of NYC (MTA). The technology provides the operator with detailed information on detractions and fatigue during driving.

The three primary objectives of this research project were the following:
1) Develop a prototype of driver facial monitoring system via porting the software onto a portable processor to create a hardware system.
2) Initial prototype testing using existing or acquired videos to test the accuracy of the tracking ability of the prototype with a variety of facial features, including glasses, different skin tones, facial hair; with different levels of illumination; and with various degrees of facial movement.
3) Public beta testing of prototype on buses to evaluate the accuracy in terms of: (a.) validity – that the system accurately measures what it is supposed to measure, and (b.) sensitivity – that the system picks up distraction and fatigue with minimal false positives and negatives.
The final report is available.

To create a link to this page, use this URL: http://apps.trb.org/cmsfeed/TRBNetProjectDisplay.asp?ProjectID=4143