On March 7, 2016 Dr. Barmpoutis of the Digital Worlds Institute at the University of Florida hosted a webinar to demonstrate how to use the Driver’s Motion Depth Database (DMDDB) that he and his team of collaborators from the University of Kansas and the University of Alabama at Birmingham developed from a STRIDE-funded project titled “Investigating the Effect of Drivers’ Body Motion on Traffic Safety”. The webinar was attended by graduate students, faculty, consultants and state DOT representatives. During the webinar, Barmpoutis discussed the technologies that were employed in making this database, demonstrated how the database can be used as a resource in future research projects, and discussed the results of the STRIDE-funded study that utilized this dataset for performing statistical analysis of the drivers’ body motion patterns.

Barmpoutis’ team of researchers on the STRIDE-funded project included Dr. Alexandra Kondyli, University of Kansas, and Dr. Virginia Sisiopiku, University of Alabama at Birmingham.  STRIDE is the 2012 U.S. Department of Transportation grant-funded, regional (Region 4 – Southeast) University Transportation Center (UTC) housed at the University of Florida Transportation Institute (UFTI).

What is the DMDDB?

The DMDDB is an open-access database that contains depth video sequences of drivers performing merges and lane changes in freeway and rural segments in the area of Gainesville, Fla. The 3D motion of drivers has been captured in the database in more than 300,000 depth frames that can be browsed and analyzed using a simple programming interface. Dr. Barmpoutis’ research proposed a novel approach for studying the actual movements of drivers inside the vehicle when they were performing a specific maneuver type or while engaging in secondary tasks that require a certain body movement. With the use of two low-cost infrared depth sensors, the 3D shape of selected participants were constructed as they were performing various driving maneuvers and as they were engaged in secondary tasks while driving. His team investigated the relationship between potentially unsafe driving events and the actual driver body posture and movements when performing a driving maneuver (e.g., lane changing, merging) under different traffic and geometric configurations and when engaging with a secondary task.

Project Website: http://research.dwi.ufl.edu/dmddb/

Recorded Webinar Link: https://mctrans.adobeconnect.com/r9ekkduo4v5/