DEVELOPING A MOBILE APP FOR AI-BASED COMPARATIVE TRAINING PLATFORM FOR ATHLETES
BeONE Sports is an AI-based platform for athletes that provides users with workout analysis, focusing on specific and isolated actions to enhance athletic performance.
BeONE Sports is an AI-based platform for athletes that provides users with workout analysis, focusing on specific and isolated actions to enhance athletic performance.
Country
USA
Industry
Sports
Cooperation period
December 2022 - now
Cooperation type
Consulting, dedicated development team of 5-8 experts
Country
USA
Industry
Sports
Cooperation period
December 2022 - now
Cooperation type
Consulting, dedicated development team of 5-8 experts
MobiDev is clearly an impressive organization. Everything from communications, UI/UX, mobile app development, and management skills to strategy and understanding the zeitgeist of technology development…MobiDev has it all.
MobiDev has super capable, young, and energetic people working to make the best product possible, and they treat the client’s project like it is their own – which is truly rare.
It’s been a great start to a long relationship.
After two decades of design experience across multiple industries and building a career that included working in nanotechnology and AI, former Division 1 athlete Scott Deans decided to start his sports technology startup, BeONE Sports in 2022, aimed to support athletes’ specialized training regardless of their location worldwide. Empowering an advanced training methodology with computer vision, BeONE Sports provides data-driven training programs for athletes and coaches.
MobiDev covers a full cycle iOS app development, which in particular, includes processing data received from the existing BeONE Sports ML models, video rendering, and in-app purchases.
When it comes to developing software for the demanding SportsTech industry, it is particularly important to provide a high application performance and stability in terms of high user load. The app must be extremely flexible in terms of the range of smartphone models it supports in order to reach a larger audience of aspiring athletes.
Following the thoughts of Scott Deans, which he shared in his Medium interview, BeONE sports is designed to overcome key stigmas in SportsTech. These include the perception that SportsTech is designed exclusively for the 1%, seen as a niche industry, not focused on serving the larger customer base with limited resources, and that it prioritizes science over customer needs.
Before the development began, we went through a consulting stage, covering both business and technical analysis. The dedicated experts identified and finalized project requirements, updated the client's design assets and explored the optimal options for the applied technologies and architecture. This stage provided valuable insights and guidance, ensuring that the project started off on the right track.
Considering the optimal technology for data processing, the MobiDev team confirmed MediaPipe to fit optimally into key project requirements, like operating on multiple platforms, offline video processing, and high data processing speed. Covering an iOS app for the MVP stage, BeONE sports is expected to also be available for Android and the web in the future. MediaPipe allows the deployment of a single codebase across different operating systems, significantly reducing the development timeline and ensuring consistent functionality across platforms. Offline video processing is one of BeONe sports key features which MobiDev also enabled through MediaPipe. It effectively optimizes resource utilization for processing high-dimensional data, which also ensures smooth performance on resource-constrained devices. Another significant achievement with the implementation of MediaPipe is high data processing speed which takes half the time of the video’s duration. Thus users usually get video analysis results within a few seconds, enhancing the app’s overall responsiveness and user experience.
Among the key challenges we needed to deal with was the delivery of the system’s stable functioning in terms of high and variable workloads from over 10,000 athletes and coaches. We chose Kubernetes, since it gives the advantage of horizontal scalability, enabling us to handle the surge in user demand. As the user base grows, Kubernetes will automatically scale the app by adding more containers to match the increasing workload, ensuring a responsive and high-performing app even during peak usage. Furthermore, Kubernetes intelligently manages container placement and resource allocation, optimizing resource utilization. This not only helps reduce operational costs, it also ensures the best performance.
After processing data from ML models and evaluating performance accuracy, the app accomplishes video rendering to provide athletes with easy-to-understand analysis. During this stage, BeONE Sports splits a video into segments, adds scores for each attempt, and adds a “skeleton” with key points of the user’s body. Users can add an overlay with a “ghost” figure chosen from the library of professional athletes’ videos or the user’s performance history. Along with these features, users get personalized recommendations to enhance their performance.
After MobiDev deployed and launched the BeONE Sports app in 2023, Scott Deans and his team focused on expanding the library of professional athletes. In particular, they engaged Stacy Sykora, Mike Hollis, Michelle Focam, Cash Peterman, Cheyenne Parker, and Zack Granite to share their professional performance with BeONE sports users so that young athletes could learn from the pros.
The app actively covers various sports, including volleyball. With its five significant Volleyball AI Actions, BeONE Sports has announced a partnership with the Lone Star Classic Tournament in Dallas, which hosts 20,000 athletes, coaches, and parents competing over three weekends.