On the Design of Edge-Assisted Mobile IoT Augmented and Mixed Reality Applications

Abstract

Mobile IoT-based augmented and mixed reality (AR/MR) applications are gained increased attention by providing immersive experiences for applications in different domains. In such applications, live video streaming will be processed in a real-time manner for object detection, identification, and tracking, as well as to render virtual overlays on the user's field of view. However, mobile IoT AR/MR applications have a high demand for processing and storage resources that can not be supplied by resource-constrained IoT devices. Hence, edge computing will be fundamental to support mobile IoT AR/MR applications by deploying resources in the proximity of IoT devices. Thus, heavy computation tasks are offloaded to and executed at remote edge servers. In this paper, we discuss the recent solutions designed to enable edge computing for mobile IoT AR/MR applications. We shed light on the limitations of current task offloading approaches designed for edge-assisted IoT applications, and present recent works to support edge-assisted IoT AR/MR applications. We highlight the main challenges and discuss the advantages and limitations of current approaches designed for local and remote object detection in mobile AR/MR applications. Finally, we point out some future research directions in need of further investigation.