Inspiration

This past year, the highschool that my partner (Aiden) and I (Kevin) went to had 2 bomb threats. Additionally, I had transferred school districts prior to going to my current highschool, and the highschool that I was supposed to go had a few knife stabbings that were on the news. Many of my friends felt unsafe and actually chose to go to a different highschool because of it. Overall, we believe safety should never interfere with education.

What it does

Aegis inputs a video and returns an annotated video with gun and knife detections along with a depth map video. It also has a dashboard so the user can track statistics.

How we built it

We trained a custom YOLOv8 model and used the Depth Anything V2 model for our machine learning needs. We used docker to deploy to a cloud Gpu on Paperspace. We used a Python Flask REST API to hook everything up. We used React, Tailwind CSS and a few CSS libraries in the frontend to deploy to DigitalOcean. We used Firebase for authentication.

Challenges we ran into

While trying to set up our website on DigitalOcean, our website wasn’t correctly rendering with the necessary JS and CSS, which was due to our website only partially using React Router.The main reason why only some of our website was because we weren’t sure how to implement React Routing with our flask backend authorization. Eventually, after a couple hours searching online, and some troubleshooting, we were able to fully implement React Routing into our website.

Accomplishments that we're proud of

We are very proud of hosting this as a public website on DigitalOcean. We are also very proud of finishing this project in time. A few other accomplishments in no particular order are: Setting up Firebase authentication, using Docker, deploying API to a cloud GPU.

What we learned

We learned a lot from this project, including React Routing, Firebase authentication, docker, and the general process for deploying a website.

What's next for Aegis

We want to expand this technology to make it more efficient. Currently, our cloud GPU is very costly so we hope to migrate to a lower-cost solution, making the software more inclusive. Additionally, we hope to partner with nonprofits and startups to enable this solution in the real world.

Built With

Share this project:

Updates