Current at-home cardiopulmonary resuscitation (CPR) training systems are limited by the feedback they provide. Virtual trainers have the potential to enhance feedback in CPR training systems by providing real-time demonstrations. We developed CPRBuddy, a CPR training system that uses a virtual trainer to emulate a live trainer to automatically provide powerful feedback. CPRBuddy uses computer vision to track the user’s chest compressions and gives verbal and visual (in the form of demonstrative gestures) feedback.
Originally created as part of the Research Methods class, University of Florida, Spring 2017 in collaboration with Isaac D. Wang and Heng Yao.
Demo video: https://youtu.be/Pbn2tbakfy4
Source code
GitHub: https://github.com/smorrisonsmith/cpr
Citation
Sarah Morrison-Smith, Heng Yao, Isaac Wang, Benjamin Lok, and Jaime Ruiz. 2018. Staying Alive with Virtual Humans. In CHI ’18 Extended Abstracts on Human Factors in Computing Systems (CHI EA ’18). ACM, New York, NY, USA. PDF.