SmartMat
in Collab. with M. Sundholm and Sefar AG
Concept
The Smart Mat is built with pressure sensitive textiles designed and produced by Sefar AG for the EU FP7 project SimpleSkin. It has a spacial resolution of 128x64 over a 2-by-1 meter area with 40fps, driven by FPGAs and high-performance dedicated ADCs. It can be embedded under sports mats or carpets to detect workout or gait identification based on the body prints of the people.
It was show-cased on exhibitions such as Cebit, Berlin Government Open Door, etc. as live technical demos for exercise recognition and counting, with the software implemented in C++ with openCV and QML.
Publications
Transforming sensor data to the image domain for deep learning—An application to footstep detection , IJCNN, 2017
The carpet knows: Identifying people in a smart environment from a single step , Percom workshop, 2017
Smart-mat: Recognizing and counting gym exercises with low-cost resistive pressure sensing matrix, Ubicomp, 2014