Fall Detector Adapted to Nursing Home Needs through an Optical-Flow based CNN

TL;DR

This paper presents a vision-based fall detection system for nursing homes using a CNN trained with a custom sensitivity metric, emphasizing the importance of temporal data to improve detection accuracy and reduce false alarms.

Contribution

It introduces a CNN-based fall detection method tailored to medical needs, incorporating a custom metric and decision process for better clinical relevance.

Findings

Detects 86.2% of falls

Produces 11.6% false alarms

Highlights importance of temporal data

Abstract

Fall detection in specialized homes for the elderly is challenging. Vision-based fall detection solutions have a significant advantage over sensor-based ones as they do not instrument the resident who can suffer from mental diseases. This work is part of a project intended to deploy fall detection solutions in nursing homes. The proposed solution, based on Deep Learning, is built on a Convolutional Neural Network (CNN) trained to maximize a sensitivity-based metric. This work presents the requirements from the medical side and how it impacts the tuning of a CNN. Results highlight the importance of the temporal aspect of a fall. Therefore, a custom metric adapted to this use case and an implementation of a decision-making process are proposed in order to best meet the medical teams requirements. Clinical relevance This work presents a fall detection solution enabled to detect 86.2% of falls while producing only 11.6% of false alarms in average on the considered databases.