Abstract

Mobile Augmented Reality (MAR) applications enable users to interact with physical environments through overlaying digital information on top of camera views. Detecting and classifying complex objects in the real world presents a critical challenge to enable immersive user experiences in MAR applications. Aiming to provide continuous MAR experiences, we address a key challenge of continuous object recognition, which requires accommodating an increasing number of recognition requests on different types of images in MAR systems and possible new types of images in emerging applications. Inspired by the latest advance in continual learning approaches in computer vision, this paper presents a novel MAR system to enhance its scalability with continual learning in realistic scenarios. Our experiments demonstrate that 1) the system enables efficiently recognising objects without requiring retraining from scratch; and 2) edge computing further reduces latency for continual object recognition.