NaviGaze (NaviGlass)

Inspiration

Now more than ever, AI has dominated our world. We were originally inspired by the usage of Chat GPT by biomedical technology companies to develop medical analysis technology and we wondered, how can AI revolutionize accessibility for everyone? We we're determined to use AI to make the world more equal for everyone- and with that we developed NaviGaze.

What it does

At NaviGaze our mission is to empower and enhance the lives of visually impaired individuals by providing innovative, accessible, and reliable smart glasses. The glasses take a photo of the surroundings, use google cloud AI to interpret the image, then use google cloud text-to-speech to speak the image contents, which is played to the wearer of the glasses. Additionally, the general public can download the app and upload photos of locations to develop the database and map the world in 3D.

WHat we learned ##

AI Image recognition Python Arduino Libraries Circuits Teamwork (:

How we built it

We built this using google cloud API integrated into Python. We did back end development using visual studio code and front end with Adobe Illustrator and XD.

Challenges we ran into

Technical Challenges: Integrating Google Cloud to depict image contents Creating an ergonomic and cost effective product design Designing a beautiful and accessible front end Dividing image into sections to analyze Arduino camera integration

Accomplishments that we're proud of

Integrating Arduino camera module as a cost effective camera Implementing Google Cloud text to speech API for a natural sounding voice Using artificial intelligence to depict image contents Gamification of the app to incentivize users to contribute

What's next for NaviGaze (NaviGlass)

For the future, we want to optimize the Arduino camera module to take and upload photos faster. We also want to develop a better design that fits all the equipment onto the glasses efficiently.

Built With

Submitted to

HackaBull 2023

Created by

I worked on the front end development of this project. My biggest challenge was using Adobe XD to design the app. I wanted to have a sleek, IOS inspired look that also ran smoothly and logically. I did some research on IOS design styles and downloaded IOS templates provided by Apple to do this. I also was in charge of making the powerpoint, and rendering the images. I helped with the CAD design using Solidworks and rendered everything using Adobe Dimension. Overall it was fun working on this project and I learned a lot about the importance of teamwork when doing front-end as you want to be working hand in hand with back end to ensure everything works smoothly together

Zeki Sert
I worked as the hardware lead (Arduino and arducam).This was my first time exploring the different arducam libraries.

Urvi Jain
I worked on the back end image and voice recognition through the use of google cloud AI and python. Additionally, through the use of Solidworks, I made the CAD file and render of the product.

César Briones
I worked on the back-end trying to get the Google Cloud Vision AI to give relevant information from an image like labels and objects.

Aditya Mathur

Updates

Zeki Sert started this project — Mar 26, 2023 12:54 PM EDT

Leave feedback in the comments!

Log in or sign up for Devpost to join the conversation.