Fixation data analysis for complex high-resolution satellite images*

Abstract

This paper reports an empirical study which inspects the human segmentation process for high-resolution satellite (HRS) images in the absence of target objects. The lack of standard guidelines for eye-tracking data analysis in the above-mentioned case motivates this study. Since a careful selection of area of interest (AOI) is necessary for meaningful interpretation of gaze data, this study represents a way to draw AOIs which metrics correlate with the human verbal response. This study formulates a hypothesis for AOI drawing and updates it until the metrics of the hypothesis based AOIs matches with the verbal response. The outputs of this study suggest the grouping of objects during AOI-based analysis of gaze data and provides some rules for the same. The AOIs drawing for hypothesis validation also highlights the dominance of perceptual grouping over the functional grouping of objects. Developing an autonomous system for segmentation and reference data creation are some possible future scopes of this study.