Inspiration
Everyone in the team is a travelling enthusiast. Pair this with good programming skills and a strong interest in disruptive technologies such as AI and AR, we decided to prototype a mobile app the could elevate Montréal, our home hometown, as a leader in smart tourism.
What it does
Augmented Tourism suggests the best tourist attractions in Montréal based on user-defined interest and contextual data such as geolocations and then automatically builds an optimized itinerary.
On top of that, as travellers, we all know that the best memories are sometime the unexpected discoveries. Our app leverages this feeling by proposing an AR feature that recognize Montréal's landmark and displays cultural and scientific information in real time!
How we built it
We have decided to use the flutter framework to make it possible to build the application on all mobile platform(iOS, Android). This said we have a flutter mobile app that handle all the user experience part of the application. This app is using multiple API to make the full experience possible. From these API we have the google maps API to help us show the user his location and the landmarks around him. We also have the google vision landmark API to identify the landmark with the camera. Behind the curtain, we have a python django server that handles a REST API to send us the information we need. This server is connected to a noSQL firebase database and an authentication platform. All of these platform connect with each other to offer the full experience.
Challenges we ran into
All our challenges can be summarized with the following words: Discovering new technologies! We wanted our app to be accessible for everyone so we learned a language that was compatible for both Android and iOS on the fly.
Another challenge we had was to transfer the picture up to the google vision API with a bunny hop on our python server.
We also underestimated the time constraint of the project. We had to prioritize on our MVP functionalities because we couldn't fit all our designs and ideas in 24 hours
Accomplishments that we're proud of
Functionality-wise, we are thrilled by our landmark recognition. Users can expect our app to recognize landmarks with their phone camera in seconds! On top of that, our app overlays a description in real time.
We are also proud of the coordination we had as a team. We had a lot of dependencies between the client side and the server side that we had to plan for. Putting all those blocks together under 24h was both a challenge and an accomplishment.
What we learned
Since we always learn from the challenges we must face, you can expect that we discovered and learned Flutter. Flutter stable release was 38 days ago so we had to learn the basics while trying to develop complexed functionalities at the same time.
Another concrete learning was to embed google maps in a mobile app and push system defined parameters such as geolocation and then automatically building an itinerary.
What's next for Augmented Tourism
Unfortunately, we have design Ideas that we did not have the time to implement. In the future, we really want to leverage contextual data to refine our recommendation algorithm. i.e., if it is a rainy day, we would like to focus on indoor activities such has museums. We would also incorporate local events using Google Events API and recommendation systems. i.e, recommend the Jazz Festival if the user travel dates are matching with the event.
Bringing a community aspect and favouring sustainable activities is also an important feature we want to leverage. When the app will have a stable release and refined UI, we want to export the model to other cities as a white paper solution.
Log in or sign up for Devpost to join the conversation.