Dynamics of Driver's Gaze: Explorations in Behavior Modeling & Maneuver Prediction
This work addresses driver assistance and automation by improving gaze-based behavior modeling, but it is incremental as it builds on existing gaze analysis methods.
The paper tackled the problem of modeling driver gaze dynamics to understand monitoring behavior, developing a machine vision framework to classify gaze into zones and represent dynamics via accumulation, duration, and frequency. It showed that these patterns can predict maneuvers like lane changes up to a few hundred milliseconds in advance.
The study and modeling of driver's gaze dynamics is important because, if and how the driver is monitoring the driving environment is vital for driver assistance in manual mode, for take-over requests in highly automated mode and for semantic perception of the surround in fully autonomous mode. We developed a machine vision based framework to classify driver's gaze into context rich zones of interest and model driver's gaze behavior by representing gaze dynamics over a time period using gaze accumulation, glance duration and glance frequencies. As a use case, we explore the driver's gaze dynamic patterns during maneuvers executed in freeway driving, namely, left lane change maneuver, right lane change maneuver and lane keeping. It is shown that condensing gaze dynamics into durations and frequencies leads to recurring patterns based on driver activities. Furthermore, modeling these patterns show predictive powers in maneuver detection up to a few hundred milliseconds a priori.