Do you see what I see: towards a gaze-based surroundings query processing system

Abstract

A smart car can be defined in various dimensions. In this paper, we consider a gaze-based driver query processing system where the vehicle recognizes where the driver is looking at when she asks about roadside landmarks. By linking the tracked gaze of the driver with annotated maps and geo-location information, the system can let the vehicle provide immediate answers to the driver. We discuss the design and implementation of the system, along with the test results during real driving.