The elderly population is increasing rapidly around the world. There are no
enough caretakers for them. Use of AI-based in-home medical care systems is
gaining momentum due to this. Human fall detection is one of the most important
tasks of medical care system for the aged people. Human fall is a common
problem among elderly people. Detection of a fall and providing medical help as
early as possible is very important to reduce any further complexity. The
chances of death and other medical complications can be reduced by detecting
and providing medical help as early as possible after the fall. There are many
state-of-the-art fall detection techniques available these days, but the
majority of them need very high computing power. In this paper, we proposed a
lightweight and fast human fall detection system using pose estimation. We used
`Movenet' for human joins key-points extraction. Our proposed method can work
in real-time on any low-computing device with any basic camera. All computation
can be processed locally, so there is no problem of privacy of the subject. We
used two datasets `GMDCSA' and `URFD' for the experiment. We got the
sensitivity value of 0.9375 and 0.9167 for the dataset `GMDCSA' and `URFD'
respectively. The source code and the dataset GMDCSA of our work are available
online to access.

使用姿势估计提出了一种轻量级快速的人体摔倒检测系统，可以在低计算设备上实时工作，对于老年人的医疗护理系统非常重要。