A Device with Artificial Vision for the Analysis of Movements in Geriatric Patients

This article describes the design of a device that uses Deep learning and computer vision libraries to allow the analysis of postures in geriatric patients. The objective of the study was to evaluate the relationship between posture analysis in geriatric patients and the effect of distance, lighting, and speed in posture recognition with the two devices used for motion capture in Short Physical Performance Battery tests. This is an experimental type of research that contributes to a novel proposal to improve the living conditions of the elderly population and the search for healthy aging. It was possible to prove that the variables illumination, distance, and speed have a direct relationship with the posture analysis obtained with a Raspberry device and a core i7 computer, of which the core i7 computer had a better performance compared to the Raspberry.