AthleteAI

Democratizing Elite Sports Coaching through the use of AI

Comment 4

Inspiration

Institutions that lack resources and representation might not have the means to access elite sports coaching. Our team holds the view that important knowledge about sports techniques can be curated and presented as a reference for those who cannot afford coaching for their teams. Our aim is to organize information about correct techniques and make it universally available.

What it does

A user will upload a brief video showcasing their form and technique. Our specialized algorithm, utilizing computer vision, will assess their posture and movements. By contrasting this with our established models, the system will produce an analytical breakdown of how their form measures up to the ideal standard for that movement. Based on this data, users will receive recommendations to enhance their form and a visual representation of their wireframe during the action.

How we built it

AthleteAI was built with using a combination of new technologies, deep learning algorithms, and cloud infrastructure. On the Next.js and ChakraUI front-end, the user begins by first selecting the sport and movement of their choice. Then they will upload a video of themselves performing that movement. After, using our custom algorithm in the backend with Flask, their movements will be analyzed with OpenCV then with a combination of NumPy, SciPy, and Matplotlib data analysis results will then be shown with tips on how to improve their form based on the data results.

Challenges we ran into

A major challenge we have encountered was attempting to host both the Flask back-end, containing our custom algorithm and deep learning infrastructure, along with our Next.js front-end, containing our UI/UX. Another challenge was serializing the mp4 file as it was passed along from the front-end to the back-end.

Accomplishments that we're proud of

Our state of the art algorithm is capable of truly impacting underprivileged communities in regards to their access towards elite sports coaching. Our team at AthleteAI is also proud of the UI/UX design of our website, along with the interactive data analytics that showcases the user's strengths and weaknesses for the particular movement.

What we learned

Our team has learned the multi-facets of Azure deployment that would be useful for future projects. In addition, we learned how to develop engaging user interfaces that are both functional and beautiful. Lastly, we've learned how to properly clean our data to make it process efficiently and reliably on our custom algorithm.

What's next for AthleteAI

The forthcoming plans for AthleteAI involve broadening its reach to cater to all individuals seeking sports coaching. Additionally, we aim to enhance our internal infrastructure to accommodate a vast number of users on the platform.

Team

Anthony Yao - https://www.linkedin.com/in/anthonyjyao/ Sanjay Taylor - https://www.linkedin.com/in/sanjaytaylor/ Vincent Lin - https://www.linkedin.com/in/vincent-lin-uf/ Andrew Tang - https://www.linkedin.com/in/andrtang/

Built With

+ 15 more
Share this project:

Updates