MotionLab

A Computer Vision Biomechanics Prototype powered by Voyager Wingman and Axelera Metis

Hello Spanner, hello Axelera Team!

It is great to be back and to take part in another community challenge.

First of all, thank you for organizing this new initiative.

Due to our ongoing internal projects, we have not yet had the opportunity to work with Voyager Wingman. That is exactly why we see this challenge as the perfect opportunity to start using it on a real-world AI project and explore its capabilities.

Our proposal is called MotionLab.

The goal is to develop a first working prototype of a computer vision biomechanics system for sports training, athletic performance and rehabilitation.

Rather than trying to build a complete commercial product within one month, we want to demonstrate how Voyager Wingman can rapidly accelerate the creation of a practical AI pipeline running on Axelera Metis.

Our demonstration will focus on a simple but meaningful use case.

A camera will observe an athlete performing bodyweight squats.

The prototype will:

• automatically detect the athlete;
• recognize the squat exercise;
• estimate body pose;
• calculate a small set of key joint angles (hip, knee and trunk);
• count completed repetitions;
• display the exercise metrics in real time.

If successfully completed, this prototype will become the foundation for future developments, including posture assessment, gait analysis, movement analysis and recognition of additional exercises.

We selected this project because we believe it is a practical way to demonstrate both the capabilities of Axelera Metis and the development speed enabled by Voyager Wingman.

Thank you once again for this opportunity.

We are looking forward to taking part in the challenge, learning from the community and building something useful together.

Good luck to everyone!