A Framework For Fall Activity Detection and Classification using Deep Learning Method

Main Article Content

Pramod Kumar Soni Pramod Kumar Soni

Abstract

Detecting the fall of a person in indoor environment is a challenging issue especially for elderly and sick living alone. Cameras can continuously observes the scene and require little interaction with the user and therefore, are well suited for fall detection. In this paper, we propose a deep learning based framework for fall detection and classification. Further, we also apply different machine learning methods namely, Support Vector Machine (SVM) and decision tree after extracting important features to detect and classify the fall of a person. We compare our deep learning based framework with SVM and decision tree as well as other state-of-the-art methods. We have considered two different publicly available datasets for performing experiments. The experimental evaluation of our deep learning based proposed framework gives promising results and is comparable with other state-of-the-art methods.

Article Details

How to Cite
Pramod Kumar Soni, P. K. S., & Ayesha Choudhary. (2021). A Framework For Fall Activity Detection and Classification using Deep Learning Method. INFOCOMP Journal of Computer Science, 20(1). Retrieved from http://infocomp.dcc.ufla.br/index.php/infocomp/article/view/1327
Section
Human-Computer Interaction