Abstract
An Improved Feature-Based Method for Fall Detection
Highlights
According to the report of the World Health Organization, approximately 28~35% of people aged 65 and over fall each year and 32~42% of those over 70 years of age
The results show that our approach achieves an accuracy of 93.56%, which is better than other typical methods
We systematically evaluate the effectiveness of the proposed method and compare it with other classic fall detection methods on a publicly available datasets: TST V2 [27]
Summary
According to the report of the World Health Organization, approximately 28~35% of people aged 65 and over fall each year and 32~42% of those over 70 years of age. In [6], fall detection methods were classified into two major categories: handcrafted action representations and learning-based action representations. When the shape of the 3D bounding box exceeds a thread value, a fall can be detected These shape-based methods perform poorly in fall-like activity discrimination. Different from handcrafted features, deep learning method is designed to mimic the way of how humans observe the world from a biological perspective. These kinds of method always contain hierarchical layers and much more trainable parameters than shallow architectures. It cannot be denied that RNN-based methods achieve great performance in action recognition Most of this kind of methods is end-to-end contracture which tends to overstress the temporal information [18].
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have