Enabling continuous object recognition in mobile augmented reality
Su, Xiang; Jiang, Ai; Cao, Jacky; Zhang, Wenxiao; Hui, Pan; Ye, Juan
Xiang Su, Ai Jiang, Jacky Cao, Wenxiao Zhang, Pan Hui, and Juan Ye. 2022. Enabling Continuous Object Recognition in Mobile Augmented Reality. In IUI ’22: 27th Annual Conference on Intelligent User Interfaces, March 22–25, 2022, Helsinki, Finland. ACM, New York, NY, USA, 4 pages. https://doi.org/10.1145/3490100.3516459
© Owner/Author 2022. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in IUI ’22: 27th Annual Conference on Intelligent User Interfaces, http://dx.doi.org/10.1145/3490100.3516459.
https://rightsstatements.org/vocab/InC/1.0/
https://urn.fi/URN:NBN:fi-fe2023041235994
Tiivistelmä
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.
Kokoelmat
- Avoin saatavuus [31941]