Where is the driver looking: Analysis of head, eye and iris for robust gaze zone estimation

Driver´s gaze direction is a critical information in understanding driver state. In this paper, we present a distributed camera framework to estimate driver´s coarse gaze direction using both head and eye cues. Coarse gaze direction is often sufficient in a number of applications, however, the challenge is to estimate gaze direction robustly in naturalistic real-world driving. Towards this end, we propose gaze-surrogate features estimated from eye region via eyelid and iris analysis. We present a novel iris detection computational framework. We are able to extract proposed features robustly and determine driver´s gaze zone effectively. We evaluated the proposed system on a dataset, collected from naturalistic on-road driving in urban streets and freeways. A human expert annotated driver´s gaze zone ground truth using information from the driver´s eyes and the surrounding context. We conducted two experiments to compare the performance of the gaze zone estimation with and without eye cues. The head-alone experiment has a reasonably good result for most of the gaze zones with an overall 79.8% of weighted accuracy. By adding eye cues, the experimental result shows that the overall weighted accuracy is boosted to 94.9%, and all the individual gaze zones have a better true detection rate especially between the adjacent zones. Therefore, our experimental evaluations show efficacy of the proposed features and very promising results for robust gaze zone estimation.