A smart vision sensor for detecting risk factors of a toddler's fall in a home environment

Abstract

This paper presents a smart vision sensor for detecting risk factors of a toddler's fall in an indoor home environment assisting parents' supervision to prevent fall injuries. We identified the risk factors by analyzing real fall injury stories and referring to a related organization's suggestions to prevent falls. In order to detect the risk factors using computer vision, two major image processing methods, clutter detection and toddler tracking, were studied with using only one commercial web-camera. For practical purposes, there is no need for a toddler to wear any sensors or markers. The algorithms for detection have been developed, implemented and tested.