A Two-stage Human Fall Detection Model Based on Rule-Based Algorithm and CNN-LSTM

DOI

10.2991/978-94-6239-707-1_24How to use a DOI?

Keywords

Fall detection; CNN-LSTM; Healthcare

Abstract

Human fall detection is an important area of concern in the context of healthcare monitoring systems and is a significant issue. Automatic fall detection systems help in the prevention of fatal injuries and rapid medical care for senior citizens living alone, children left alone, as well as in various other such instances. Fall detection models regardless of their precisions are struggling with fall detection in uncontrolled environments with respect to pose variations, lighting variations, fall instances with pose occlusions, and fall instances with high similarities among activities. In this paper, we propose a two-stage fall detection model that combines a rule-based fall detection approach with a CNN–LSTM model. A public fall detection dataset called Le2i is used for training of the fall detection model that contains information about fall instances, fall instances with their boundary box values, as well as instances with their time fall boxes. Experimental results indicate that the proposed fall detection model would significantly reduce the computational cost while providing comparable performance to existing fall detection models.

Copyright

© 2026 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  - Aman Kumar Patel
AU  - Sneha Barmaiya
AU  - Megha Patidar
AU  - Anand Singh Jalal
PY  - 2026
DA  - 2026/06/18
TI  - A Two-stage Human Fall Detection Model Based on Rule-Based Algorithm and CNN-LSTM
BT  - Proceedings of the International Conference on Recent Advances in Intelligent and Sustainable Technologies (RAIST 2026)
PB  - Atlantis Press
SP  - 278
EP  - 287
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-707-1_24
DO  - 10.2991/978-94-6239-707-1_24
ID  - Patel2026
ER  -