Enhancing Bed Safety: Monitoring Sleeping Positions, Bed-Exits, and Falls Using Grid-EYE Infrared Array Sensors

Detecting bed-exit events, monitoring sleeping positions, and identifying potential falls can help ensure proper care for patients, elderly or individuals with disabilities, allowing caregivers or medical personnel to intervene promptly. This work presents a system for detecting such events employing two low-cost and low-resolution Infrared Array Grid-EYE sensors. The primary sensor, mounted on the ceiling, detects bed-exit events and identifies proper and critical sleeping positions using a neural network trained and validated on a dataset of 3000 images. The secondary sensor, positioned perpendicularly on a vertical wall, differentiates between proper bed-exit events and falls through a second neural network. The system achieved a success rate of up to 82% on a testing dataset with a total of 180 images under different conditions, demonstrating its potential for enhancing safety and well-being in smart living and healthcare settings.