Many car accidents are caused by driver's deviation from normal condition like carelessness. We aim to construct a driving assist system that is able to detect driver's deviation signal from normal condition. The system detects the deviation signal using driver's time-series head motion information. In this paper, we analyze driving movies taken by monocular in-vehicle camera, and examine driver's head position category in safety verification at intersections for quantification of head motion information. Moreover, we propose a quantifiable categorizing algorithm of head motion using two kinds of unsupervised neural networks, and it provides a possibility of quantification of the head position.