A Comparative Evaluation of Augmented Reality Frameworks: A Plane Mapping and Resource Utilisation Perspective

Augmented reality (AR) plane detection is an important application in several areas such as advertising, training, and supporting visually impaired people. This work compared the capabilities of ARCore and ARKit, which are two major AR frameworks, in plane detection using several Android and Apple mobile devices. The test examined plane detection and mapping under different lighting conditions as well as runtime, overall system efficiency and optimization across the different frameworks. Findings within the context of the study show that ARKit was on average more reliable and accurate at plane detection and mapping in comparison to ARCore. ARKit had a 14.84% computational optimization lead over ARCore, while ARCore was more efficient in RAM utilisation than ARKit within the parameters that were tested in this study. The result of this study could guide future prototyping and mobile AR plane detection application development.