121. MONITORING DRIVER BEHAVIOR AND GENERATING DRIVE-QUALITY REPORTS ON EMBEDDED COMPUTING PLATFORMS

Department: Electrical & Computer Engineering
Research Institute Affiliation: California Institute for Telecommunications and Information Technology (Calit2)
Faculty Advisor(s): Mohan M. Trivedi

Primary Student
Name: Frankie Lu
Email: frlu@ucsd.edu
Phone: 626-872-5553
Grad Year: 2016

Abstract
Studying driver behaviors can be useful in finding and correcting patterns that make them more likely to be involved in accidents on the road. We present a two-camera based embedded system that analyzes the dynamics of other vehicles to the front and rear of a host vehicle during a drive. The system monitors maneuvers that the driver makes with respect to his/her proximity to these surrounding vehicles. It records periods of the drive with moderate to high levels of risky driving. At the end of a trip, a drive-quality assessment report is sent to the driver's phone and stored locally so they can identify risky behaviors in their driving and learn to drive safer over time. Our embedded system setup uses minimal processing resources, operates at real-time frame rates (10-15 fps), has been tested in natural driving conditions, and is scalable to additional sensing modalities that can monitor more variables of driver activity.

Industry Application Area(s)
intelligent systems, computer vision, driver assistance, embedded electronics

« Back to Posters or Search Results


Contact:   researchexpo@soe.ucsd.edu   (858) 534-6068