Technical Evaluation of HoloLens for Multimedia: A First Look

Abstract

Augmented-reality (AR) technology has been developing rapidly for decades. A recently released cutting-edge AR device, Microsoft HoloLens, has attracted considerable attention with its advanced capabilities. In this paper, we report the design and execution of a series of experiments to quantitatively evaluate HoloLens’ performance in head localization, real environment reconstruction, spatial mapping, hologram visualization, and speech recognition. The results show that HoloLens is able to estimate head posture more correctly at low movement speeds, reconstruct the environment most precisely for a flat surface under bright conditions, anchor augmented contents at desired locations most accurately at distances of 1.5 m and 2.5 m, display objects with an average size error of 6.64%, and recognize speech commands with correctness rates of 74.47% and 66.87% for userdefined and system-defined commands, respectively. Discussions are also provided to further explain our work and the limitations of the experiments.