Creating a 3D representation from a pressure signal with Kingston University

‍What was the purpose of the study? The Pressure and Posture Inference Technology (PPIT) project, in partnership with Kingston University, aims to convert signals from a 2-dimensional pressure mat into a 3-dimensional posture. Using a machine learning algorithm, that data can then be used to predict the movement of the human body, in relation to the pressure recorded by the mat itself. 

‍

Context: A previous research study by the Massachusetts Institute of Technology (MIT) in the US found pressure sensors could be incorporated with shoes and mats, and paired with a machine-learning system to measure and predict a person’s movements. A mat used during yoga practice for example, could detect postures based on the pressure distribution sensed on the textile surface. TG0 researchers hope to take this concept further. 

‍

TG0’s role in the study: TG0 is using an infra-red camera system at Kingston University to track the coordinates of the body as it moves. A diverse group of 10 volunteers, each with a different age, height, weight will be monitored, and the data will then be used to build the algorithm. There are hundreds of signals and hundreds of movements to be tracked and categorised. 

‍

Results and conclusion: The study is ongoing

‍

Next steps: In the future, it’s hoped this can be developed further, so that the algorithm can adapt to a specific user, and for the technology in the pressure mat itself to be scalable and suitable for mass production.