Research Article
A generic interpretable fall detection framework based on low-resolution thermal images
@INPROCEEDINGS{10.4108/eai.11-11-2021.2317972, author={Yannick Wend Kuni Zoetgnande and Jean-Louis Dillenseger}, title={A generic interpretable fall detection framework based on low-resolution thermal images}, proceedings={Proceedings of the 4th edition of the Computer Science Research Days, JRI 2021, 11-13 November 2021, Bobo-Dioulasso, Burkina Faso}, publisher={EAI}, proceedings_a={JRI}, year={2022}, month={5}, keywords={thermal images fall detection stereo vision deep learning}, doi={10.4108/eai.11-11-2021.2317972} }- Yannick Wend Kuni Zoetgnande
Jean-Louis Dillenseger
Year: 2022
A generic interpretable fall detection framework based on low-resolution thermal images
JRI
EAI
DOI: 10.4108/eai.11-11-2021.2317972
Abstract
In this paper, we addressed the problem of fall detection using low-resolution thermal images. We proposed a new method for fall detection only based on the reconstructed matches and a determined threshold. By classifying a pair of matched points on the ground or not on the ground, we could easily determine how many percent of the shape of a person is on the ground. Thus, we could determine if there is a fall or not. The experiments show that the method is able to classify features of the human silhouette as one the ground or not on the ground
Copyright © 2021–2025 EAI
