We saw similar projects but none were fully functional, so we used the same APIS, to make our own version with a few more features. Our project works by using Open-CV and MediaPipe to detect every landmark of both your hands. We then use that data to do things like moving the cursor, changing the volume and switching windows. We had to consult StackOverflow and click many references in the API wrapper just to understand how to use the data, but when we did it was smooth sailing. We had to learn a lot about object-oriented programming with python in particular. It was also challenging as most of us have used MediaPipe before, but we were able to learn a lot about what it can do and now we are able to implement it in our future projects. We want to add more features such as the ability to scroll and type with your voice, and these are not too far away as we already have an idea of how to implement them. With only a day and a half to do this, I think our project turned out well. But it still has a long way to go.
Log in or sign up for Devpost to join the conversation.