A new approach to create 3D fixation density maps for stereoscopic images

An approach to create fixation density maps(FDM) for stereoscopic images is proposed in this paper, overcoming the shortages of current methods. A new representation of stereoscopic images like Computed Tomography (CT) is used, which can show more information such as depth and discomfort zone. Apart from this, we follow the protogenetic 2D calibration of eyetracker by a 3D offline calibration to gain accuracy of 3D gaze points, tuned to a particular user. We combine these two parts through classifying eyetracking data to several depth planes which are segmented in the procedure of the representation method like CT, and obtain the fixation distribution in different depth levels for a stereoscopic image.