Human Fall Detection using Transfer Learning-based 3D CNN

TL;DR

This paper presents a vision-based fall detection system for seniors using transfer learning with a pre-trained 3D CNN to extract spatio-temporal features, combined with an SVM classifier, achieving efficient and accurate detection.

Contribution

It introduces a novel approach leveraging pre-trained 3D CNN features with SVM for fall detection, reducing training time and improving accuracy over traditional methods.

Findings

Effective detection on two datasets, GMDCSA and CAUCAFall.

Utilized transfer learning to reduce training time.

Achieved high accuracy with combined 3D CNN features and SVM.

Abstract

Unintentional or accidental falls are one of the significant health issues in senior persons. The population of senior persons is increasing steadily. So, there is a need for an automated fall detection monitoring system. This paper introduces a vision-based fall detection system using a pre-trained 3D CNN. Unlike 2D CNN, 3D CNN extracts not only spatial but also temporal features. The proposed model leverages the original learned weights of a 3D CNN model pre-trained on the Sports1M dataset to extract the spatio-temporal features. Only the SVM classifier was trained, which saves the time required to train the 3D CNN. Stratified shuffle five split cross-validation has been used to split the dataset into training and testing data. Extracted features from the proposed 3D CNN model were fed to an SVM classifier to classify the activity as fall or ADL. Two datasets, GMDCSA and CAUCAFall, were utilized to conduct the experiment. The source code for this work can be accessed via the following link: https://github.com/ekramalam/HFD_3DCNN.