Context-Aware Recommender Systems in Augmented Reality for Tourism

Duration

12 months

Status

Completed

MTC Team

Dr. Saikishore Kalloori, Ribin Chalumattu, Dr. Severin Klingler


The rapid advances of augmented reality (AR) technologies in recent years have enabled more and more stable, immersive and accessible AR experiences for consumers. In tourism, points of interest (POIs) can be enhanced with virtual elements and tourists can be provided with additional information about the places they are visiting. Furthermore, the use of recommender systems allows a personalized experience for each user.

Goals

In this project, we create various AR experiences to demonstrate the use of AR in tourism. A major goal is to create recommender systems that show only relevant information based on user preferences and contextual information. We also explore different technologies to enable location-aware AR experiences and conduct user studies to evaluate the usability and usefulness of our systems.

Outcomes

Personalized facts for tourist attractions. We created an AR experience where users can visit various attractions in the city of Zurich and learn some interesting facts about them. Once a POI is recognized by our prototype, icons appear next to the POI that can be clicked on to reveal some images and facts. We developed a simple recommender system that retrieves and shows facts based on the interests of the user and the preferences of similar users.

By playing the video you accept the privacy policy of YouTube.Learn more OK
ETH Media Technology Center

Personalized POI recommendations. We developed a tourist experience for the Niederdorf old town in Zurich that shows useful information about restaurants and shops to the user in AR. Once our system is able to localize the user within the old town, rotating icons appear in front of the buildings. If users are interested in learning more about a particular POI, they can simply click on the corresponding icon to reveal an additional window that shows details about the POI such as its name, description, rating and some user reviews.
The core feature of our AR experience is a recommender system that generates personalized POI recommendations for each user. For that, we designed a virtual 3D signpost where each POI suggestion is visualized by a signboard that displays the name and distance and points towards the location of the recommended POI. If users like any of the recommendations, they can simply click on the corresponding signboard to reveal a navigation line which shows the entire path to the suggested POI.
Finally, we also experimented with cartoon animations to visualize the POI information in an engaging way.

By playing the video you accept the privacy policy of YouTube.Learn more OK
ETH Media Technology Center
By playing the video you accept the privacy policy of YouTube.Learn more OK
ETH Media Technology Center

Publications

Download

JavaScript has been disabled in your browser