Dynamic Tracking and Real-Time Fall Detection Based on Intelligent Image Analysis with Convolutional Neural Network
Ching-Bang Yao, Cheng-Tai Lu, Zhe-Ming Lu · 2024
Read Dynamic Tracking and Real-Time Fall Detection Based on Intelligent Image Analysis with Convolutional Neural Network by Ching-Bang Yao, Cheng-Tai Lu, Zhe-Ming Lu (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11644254.txt.
Description
Yao, Lu, and Lu build a system to track care recipients and detect falls in twenty twenty-four. Many countries face rapid aging and a shortage of care workers. A system that follows a person and flags a fall at once could help a lot. The team combines a drone with image analysis tools for this task.
A face and body detection method tracks the person as the drone moves. An improved pose analysis tool judges fall posture in near real time. The team tested detection for falls in four directions. Their system beat a Google training tool on all four directions. Backward fall accuracy rose from about seventy percent to ninety-five percent. Forward and leftward falls also improved by near fourteen points. All four directions exceeded ninety-five percent in their tests.
Catalog record
| CREATOR | Ching-Bang Yao, Cheng-Tai Lu, Zhe-Ming Lu |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 70 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |