| Issue |
ITM Web Conf.
Volume 45, 2022
2021 3rd International Conference on Computer Science Communication and Network Security (CSCNS2021)
|
|
|---|---|---|
| Article Number | 01027 | |
| Number of page(s) | 8 | |
| Section | Computer Technology and System Design | |
| DOI | https://doi.org/10.1051/itmconf/20224501027 | |
| Published online | 19 May 2022 | |
Real-time fall detection system based on deep learning and infrared array sensors
1
School of Information Science and Technology, Southwest Jiaotong University, China
2
School of Mechanical Engineering, Southwest Jiaotong University, China
3
School of Public Administration, Southwest Jiaotong University, China
4
National Interdisciplinary Institute on Aging, Southwest Jiaotong University, China
* Corresponding author: manchest@swjtu.edu.cn
In this paper, a novel fall detection algorithm based infrared image is proposed. Firstly, the RetinexNet algorithm is adopted for the infrared image pre-processing and enhancement, then the YOLOv3 algorithm is improved by adding three bounding boxes to achieve the task of falling posture detection and recognition, finally a fall data set collected by ourselves is utilized to train and test the algorithm. The experimental results shows that our proposed algorithm achieves excellent fall detection accuracy result and outperforms the traditional YOLOv3 algorithm, the average accuracy of our proposed algorithm is more than 90.86%, which meets the requirements of the fall detection task quite well.
© The Authors, published by EDP Sciences, 2022
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.