SMART Yoga Mat

In this project, we proposed PYME, Pressure-based Yoga Motion Estimation, a system designed to predict yoga poses based on pressure values from mat sensor readings. The goal was to accurately classify specific motions, particularly yoga poses, by analyzing the pressure distribution when a user is on the mat.

Prototype

We designed a velostat-based pressure mat with a 12x6x2 resolution to capture pressure data during yoga poses. We conducted data collection with three participants, each performing distinct yoga poses. The collected data was processed to evaluate the capability of motion reconstruction based on pressure patterns.

This project demonstrated the potential of using pressure-sensitive mats for motion detection and classification, particularly in fitness and wellness applications. The custom prototype and model not only provided a cost-effective solution but also showcased the feasibility of integrating such technology into everyday fitness tools.

Datasets

References

[1] Shashank Tripathi, et al. MOYO: A dataset containing complex yoga poses, multi-view videos, SMPL-X meshes, pressure and body center of mass. CVPR. 2023.