Skip to Main Content
We introduce a new approach to analyzing the attentive state of a human subject, given cameras focused on the subject and their environment. In particular, the task of analyzing the focus of attention of a human driver is of primary concern. Up to 80% of automobile crashes are related to driver inattention; thus it is important for an Intelligent Driver Assistance System (IDAS) to be aware of the driver state. We present a new Bayesian paradigm for estimating human attention specifically addressing the problems arising in dynamic situations. The model incorporates vision-based gaze estimation, “top-down”- and “bottom-up”-based visual saliency maps, and cognitive considerations such as inhibition of return and center bias that affect the relationship between gaze and attention. Results demonstrate the validity on real driving data, showing quantitative improvements over systems using only gaze or only saliency, and elucidate the value of such a model for any human-machine interface.