The Viability of Image Analysis Measures of Visual Clutter in the AR UI Space as a Predictive Measures of User Performance
Jonathan Flittner, John Luksas, Joseph L. Gabbard · 2020 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) · 2020
This study determines if existing image analysis measures of visual clutter are viable in the AR UI space, as they have only been established and tested for traditional displays. Image analysis measures of clutter were specifically chosen as they can be applied to complex and naturalistic images as is common to experience while using an AR UI. The end goal of this research is to use this study as the beginning of a clutter score algorithm, that is capable of predicting user performance for a given AR UI. In this experiment, twelve participants performed a visual search task of locating a target image in an array of images where some images were virtual and some were real. Participants completed this task under three different clutter levels (low, medium, high) against five different levels of virtual object percentage and two types of targets (real, virtual) with repetition. We measured task performance through response time. Our results show significant differences in response time between clutter levels. Participants consistently had more difficulty finding objects in more cluttered scenes, where clutter was determined through image analysis methods. Furthermore, response time was correlated to image analysis measures of clutter for combined (virtual and real) arrays but not for measures of clutter taken of the individual array components (virtual or real).