Inspiration
For our project, we aimed to incorporate computer vision into a website that could assist individuals in recovering from injury and pain. We envisioned creating software that tracks patient movements during exercises and ensures they achieve the necessary range of motion for optimal recovery. This solution bridges the gap between technology and physical therapy, making recovery more accessible from the comfort of one’s home.
What it does
Our website offers a wide range of guided recovery exercises tailored to different types of injuries or mobility issues. Using AI-driven computer vision, GatorAid monitors the user's form and provides real-time feedback to help ensure proper technique and movement.
How we built it
We had a team of four people split into two groups: A front-end group and a back-end group. The front-end group worked on creating a website in React, but then eventually changed to using Streamlit in Python due to the simplicity of integration because the backend was in Python. The backend group utilized various Python libraries and an AI model in Python originally in Jupyter Notebook to create the movement tracker. They then programmed the different exercises and implemented a form checker based on the angles of the body using the AI model to track the body's pivot points, like the knees, hips, shoulders, etc.
Challenges we ran into
A challenge we ran into was integrating the front-end with the back-end. We had a Python file that would take the libraries needed to use computer vision and monitor the movement of the patient, but we needed to put it on the website that was using HTML. Unfortunately, HTML is incompatable with Python, so we needed to find a solution to access the Python file from the website.
Accomplishments that we're proud of
We are proud of our "clap to start" system, which significantly improves the user experience by making it more intuitive and accessible. Additionally, we gained valuable skills in computer vision and learned how to build websites using both React and Python.
What we learned
We learned a lot throughout the process of the project. We didn't have any experience with React, so we had to learn how to use React to create web applications. We also had to learn how to use computer vision to track a human's movements. We also learned how to make a cohesive software with both front-end and back-end.
What's next for GatorAID
Looking ahead, we plan to expand GatorAID by adding more exercises, especially targeting various muscle groups and injury types. We also aim to improve our tracking algorithms to handle more complex movements and introduce a more customizable experience for different levels of mobility. Eventually, we hope to collaborate with healthcare professionals to fine-tune the exercises and further enhance the accuracy of our AI feedback, making GatorAID a more comprehensive digital physical therapist.
Log in or sign up for Devpost to join the conversation.