Microsoft Kinect Visual and Depth Sensors for Breathing and Heart Rate Analysis.

摘要: This paper is devoted to a new method of using Microsoft (MS) Kinect sensors for non-contact monitoring breathing and heart rate estimation detect possible medical neurological disorders. Video sequences facial features thorax movements are recorded by MS image, depth infrared enable their time analysis in selected regions interest. The proposed methodology includes the use computational methods functional transforms data selection, as well denoising, spectral visualization, order determine specific biomedical features. results that were obtained verify correspondence between evaluation frequency was from image mouth area movement sensor. Spectral evolution video frames also used estimation. Results estimated compared with those contact measurements Garmin (www.garmin.com). study proves simple can be efficiently record multidimensional sufficient accuracy intelligence. achieved detection 0.26% 1.47% following show how differentiate different kinds breathing. enables us obtain analyse diagnostic purposes home environment or during physical activities, enabling efficient human–machine interaction.