Adaptive multi-scale respiration monitoring method based on camera

Abstract

A camera-based self-adaptive multi-scale respiration monitoring method relates to the technical field of video image signal recognition and processing. To solve the problem that the existing single image scale cannot obtain the local optimal respiratory signal and the global optimal respiratory signal, the steps are: (1), using the camera to collect the respiratory monitoring object in real time; (2), the video image collected by the camera Carry out multi-scale regular pre-segmentation, and perform local respiratory signal recognition and extraction on each pre-segmented unit area at each scale; define the unit area with local respiratory signal output as the target area; (3), pre-segmented each scale The local respiratory signals extracted from the target area are compared, the optimal segmentation scale is determined according to the quality of the local respiratory signal, and the partial respiratory signal extracted from the target area under the optimal segmentation scale is output as the monitoring respiratory signal. The optimal segmentation scale is adaptively determined according to the quality of the breathing signal, so as to accurately obtain the optimal breathing area and the global optimal breathing signal at multiple scales from the monitoring video of the breathing monitoring object, and improve the reliability of the camera's non-contact monitoring of the breathing signal.

Description

technical field [0001] The invention relates to the technical field of video image signal identification and processing. Background technique [0002] Respiratory frequency is a sensitive indicator of acute respiratory dysfunction, and it is also an important indicator to measure whether the human heart function is good or not and whether the gas exchange is normal. Normal adults breathe about 12-20 times per minute, and children breathe faster than adults, up to 20-30 times per minute; the breathing rate of newborns can reach 44 times per minute; the ratio of respiration to pulse is 1:4, that is With every breath, the pulse beats 4 times. At present, two basic monitoring methods of respiratory frequency are: direct monitoring method and indirect monitoring method. Direct monitoring methods include impedance method, temperature sensor method, pressure sensor method, carbon dioxide method, breath sound method, and ultrasound method; indirect monitoring methods include metho...

AI Technical Summary

Problems solved by technology

[0004] To sum up, the purpose of the present invention is to solve the existing technical deficiency that a single image scale cannot obtain a locally optimal respiratory signal and a globally optimal respiratory signal, and proposes an adaptive multi-scale respiratory monitoring method based on a camera

Images