Inspiration
The inspiration for this project came when I saw my dad setting up ring cameras, while also throwing out old phones we had for years. I wondered if by any chance the two could've been combined, solving both issues at once. The DubHacks track and introduction to YNA from Tmobile came at the perfect time, giving me a new look into how I could combine all three into a working solution.
What it does
This project enables any browser-capable device to be a security camera. With built-in facial recognition and immediate calls to the home owner that streams live audio, AnyCam represents the next generation of sustainable security.
How we built it
We built it by hacking together pieces from across different realms. Our previous experience with computer vision, web development, and webRTC protocols enabled us to build a functioning product on JavaScript and React. By scrapping together various libraries and picking apart the TMobile API, we were able to arrive at a solution that fit our needs and vision.
Challenges we ran into
The largest challenge we ran into was integration with the TMobile API. It was difficult to fit together due to the nature of the data we were handling, as frame refreshes and entire page refreshes caused many calls to be made in quick succession. Additionally, we ran into many problems connecting the phone numbers, which made it difficult to test out key features.
Accomplishments that we're proud of
The biggest accomplishment that we're proud of is the live audio streaming and seamlessness of connectivity. The app perfectly balances between speed and accuracy, providing fine tuning capabilities to adjust settings to the user's wishes. The ability for this app to scale and add new features in an additional plus, as the app is built in React which is highly flexible to change.
What we learned
We learned a lot about API calls, debugging network issues, and connecting with third party services. We also gained insights into dependency mangement and how to ensure that build integrity is maintained in a fast-paced environment.
What's next for AnyCam
We hope to add database capabilities to store and retrieve "familiar faces", preventing unnecessary calls for when a family member or trusted person is detected by the security camera. When available, we intend to add video streaming functionality as well through the YNA API. We hope to build out the code into React Native, allowing it to truly be deployed on any device, even without a browser. By creating a mobile application, we circumvent the need to have a browser host, speeding up processing and creating a better customer experience.
Log in or sign up for Devpost to join the conversation.