Augmented Reality for Location-Based Adaptive Mobile Learning

Abstract

Augmented Reality (AR) has become a popular interactive technique in the last few years. One of the critical challenges is to identify the real-life objects. Further, how to fully exert the advantages of the AR technique under the limited resources available on the mobile devices is another critical challenge. To resolve the above issue, firstly this thesis reviewed the real-life object tagging and identification techniques. Secondly this thesis studied the Human Computer Interaction (HCI) Interface and the environmental sensors on the mobile phones. Lastly this thesis implemented a Multiple Real-life Object Identification Algorithm along with the development of the Multi Object Identification Augmented Reality (MOIAR) application. Subsequently, the MOIAR application has been implemented in the location-based mobile learning environment, where the Legislative Assembly of Alberta is included as an example real-life learning object. This MOIAR implementation has applied the tagging and identification technique review as well as the HCI and sensors study, to prove the usability and practicability of the MOIAR application.