122. THE RHYTHMS OF HEAD, EYES AND HANDS AT STOP CONTROLLED INTERSECTIONS

Department: Electrical & Computer Engineering
Faculty Advisor(s): Mohan M. Trivedi

Primary Student
Name: Sujitha Catherine Martin
Email: scmartin@ucsd.edu
Phone: 858-822-0002
Grad Year: 2016

Abstract
In this work, we study the complex coordination of head, eyes and hands as the driver approaches a stop-controlled intersection; in particular how, if at all, the coordination varies depending on what maneuver (e.g. go straight, turn right, turn left) the driver intends to make at the intersection. The framework is made up of three major parts. The first part is the naturalistic driving dataset collection: synchronized capture of sensors looking-in and looking-out, multiple drivers driving in urban environment, and segmenting events at stop-controlled intersections. The second part is extracting reliable features from purely vision sensors looking in at the driver: eye movements, head pose and hand location respective to the wheel. The third part is in the construction of features using temporal pyramids and using the random forest algorithm to extract optimal feature subset; these optimal features reflect which of the cues (i.e. head, eyes, hands) are relevant and at what time period they are relevant. Using 24 different events (from 5 drivers resulting in 12200 frames analyzed) of three different maneuvers at stop controlled intersections, we found that preparatory motions range in the order of a few seconds to a few milliseconds, depending on the modality (i.e. eyes, head, hand), before the event occurs.

Industry Application Area(s)
Intelligent Vehicles

« Back to Posters or Search Results


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