FACTS – A Computer Vision System for 3D Recovery and Semantic Mapping of Human Factors

The study of human attention in the frame of interaction studies has been relevant for usability engineering and ergonomics for decades. Today, with the advent of wearable eye-tracking and Google glasses, monitoring of human attention will soon become ubiquitous. This work describes a multi-component vision system that enables pervasive mapping of human attention. The key contribution is that our methodology enables full 3D recovery of the gaze pointer, human view frustum and associated human centered measurements directly into an automatically computed 3D model. We apply RGB-D SLAM and descriptor matching methodologies for the 3D modeling, localization and fully automated annotation of ROIs (regions of interest) within the acquired 3D model. This methodology brings new potential into automated processing of human factors, opening new avenues for attention studies.