Algoritmo para la detección de posiciones corporales durante el sueño a partir de imágenes térmicas en niños menores a un año

Abstract

Sudden infant death syndrome (SIDS) is one of the leading causes of death for children under one year of age around the world. Although its causes are unknown, it has been determined that one of the factors that can lead to the occurrence of the syndrome is that the infant sleeps in a prone or side position. In this work, an algorithm is proposed that allows determine from the processing of thermal images and without the constant need by human supervision, if the child has acquired a risky position for their health during sleep. This algorithm has been developed using basic image processing tools such as morphology, thresholding and histogram equalization, together with a clustering algorithm. The algorithm was implemented in the Python programming language and this document shows the results and the evaluation of its performance.