Mixed Reality Medical First Aid Training System Based On Body Identification

Effective first aid training is helpful to improve the survival rate of the wounded in the face of natural disasters, emergencies and wars. While, traditional first aid training relies on the explanation and demonstration of experts, which has certain limitations. In this paper, we propose a novel type of first aid training system. The implementation of the system mainly includes three steps. First, medical body model images are collected to construct data sets. Second, key parts of the human body are identified and located based on a designed lightweight YOLO_v2 network. Finally, according to the results of the human identification, virtual guidance will be merged in the real environment by HoloLens glasses, and be uploaded to the server. With the Mixed Reality technology, we superimpose the corresponding virtual emergency instructions of cardiopulmonary resuscitation and artificial respiration in key parts of the body, and pass back to HoloLens glasses to realize first aid training. Experimental results show that the proposed medical first aid training system can make learners have a real touch and improve learning efficiency.