Computer Vision Embedded Based Model for Human Fall Detection

DOI

10.2991/978-94-6463-831-8_50How to use a DOI?

Keywords

Computer Vision; Convolutional Neural Networks; Fall Detection

Abstract

The majority of old people who live unaccompanied in their own home typically do not get any attention. They are susceptible to falls and are often unconscious in emergencies after the fall. This leads to both fatal and nonfatal emergencies. Therefore, alert or immediate medical help can reduce the adversity that comes with the impact. Most methods include usage of technologies like wearable sensors, ambient sensors and many more, but they are often invasive, inaccessible, and expensive. These factors are taken into consideration, and a solution to the problem of cost and comfort is addressed. The system here is designed using computer vision techniques to detect fall to accurately classify falls and non-falls. Efforts are to lower the overall cost of the entire system compared to other systems available in the market. Moreover, it is taken into consideration that there is absolutely no requirement for any hardware that must be worn. This ensures comfort and avoids any distraction due to it. As most of the other systems used a multi-camera or complex camera system, here a single simple portable camera was used. This model can be installed in the room to detect falls and report them to provide quick medical attention through an Internet of Things-based notification system. Furthermore, the results recorded for self-made video inputs showed an accuracy of 96.2% to 98.93%.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Abin Abraham
AU  - Manisha Dudhedia
AU  - Neeraj Ghate
AU  - Siddhant Kulkarni
AU  - Swati Deshmukh
AU  - Purshottam Chilveri
PY  - 2025
DA  - 2025/08/31
TI  - Computer Vision Embedded Based Model for Human Fall Detection
BT  - Proceeding of the 1st International Conference on Lifespan Innovation (ICLI 2025)
PB  - Atlantis Press
SP  - 412
EP  - 419
SN  - 2468-5739
UR  - https://doi.org/10.2991/978-94-6463-831-8_50
DO  - 10.2991/978-94-6463-831-8_50
ID  - Abraham2025
ER  -