Covid-19 has presented society with many challenges, some of which include how education can be conducted in a socially-distanced world. Sportform was created to provide a solution to this challenge, primarily in physical education, by allowing technology to assist educators in providing the level of instruction required of them while embracing digital alternatives to physical classes. Sportform addresses key concerns of online physical education classes using web-conferencing, such that lack of accountability and supervision by using AI-powered tools to augment educators.
What it does
Sportform is a Multimedia Forum-based Web Application for users to upload and review fitness videos with a keen focus on improving one's form and competency in their respective exercises/sports. Sportform offers AI-assisted Form Analysis that uses Computer Vision and Pose Estimation to evaluate videos uploaded by users.
How we built it
Sportform comprises mainly of a Forum-based Web Application that was built using Next.js, and styled using Tailwind CSS formatting. User sign-ins were handled by Firebase, and implemented to interact with Google API to allow users to use their Google accounts to sign in to Sportform. Most excitingly, Sportform provides a platform for users to upload their videos for review using Computer Vision and Pose Estimation implemented by YOLOV8 Library.
Accomplishments that we're proud of
Sportform prides itself on its use of Computer Vision to provide accurate analysis of user forms.
What we learned
Our primary learning point was the integration of AI tools such as YOLOV8's object detection library with web application software. We needed to be able to responsively use computationally heavy API calls in a way that users are able to utilise the intended web features in a timely manner.
What's next for Sportform
Our team would love to expand the application to include other forms of exercise and sports. Some examples including Weightlifting, Indoor Climbing, and racket sports like Tennis. We plan to use cutting-edge pose estimation from YOLOv8 and custom-trained models to provide valuable feedback to athletes of all levels and body types.