DeepFall -- Non-invasive Fall Detection with Deep Spatio-Temporal Convolutional Autoencoders

TL;DR

DeepFall introduces a novel deep spatio-temporal autoencoder framework that detects falls as anomalies in non-invasive sensor data, effectively identifying unseen falls without requiring fall examples for training.

Contribution

The paper presents a new anomaly detection approach using deep autoencoders for fall detection, addressing data scarcity and class imbalance issues.

Findings

Outperforms traditional autoencoders in fall detection accuracy

Effective on thermal and depth camera datasets

Detects unseen falls with high reliability

Abstract

Human falls rarely occur; however, detecting falls is very important from the health and safety perspective. Due to the rarity of falls, it is difficult to employ supervised classification techniques to detect them. Moreover, in these highly skewed situations it is also difficult to extract domain specific features to identify falls. In this paper, we present a novel framework, \textit{DeepFall}, which formulates the fall detection problem as an anomaly detection problem. The \textit{DeepFall} framework presents the novel use of deep spatio-temporal convolutional autoencoders to learn spatial and temporal features from normal activities using non-invasive sensing modalities. We also present a new anomaly scoring method that combines the reconstruction score of frames across a temporal window to detect unseen falls. We tested the \textit{DeepFall} framework on three publicly available datasets collected through non-invasive sensing modalities, thermal camera and depth cameras and show superior results in comparison to traditional autoencoder methods to identify unseen falls.