Adaptive multi-scale respiration monitoring method based on camera

Abstract

The invention discloses a self-adaptive multi-scale respiration monitoring method based on a camera, and relates to the technical field of video image signal recognition processing. The technical defect that a local optimal respiration signal and a global optimal respiration signal cannot be obtained by adopting a single image scale in the prior art is overcome. The method comprises the following steps: (1) collecting a respiration monitoring object in real time by adopting a camera; (2) performing multi-scale rule pre-segmentation on the video image acquired by the camera, and performing local respiration signal identification and extraction on each pre-segmented unit region under each scale; defining a unit region having a local respiratory signal output as a target region; and (3) comparing the local respiration signals extracted from the target area pre-segmented by each scale, determining an optimal segmentation scale according to the quality of the local respiration signals, and outputting the local respiration signals extracted from the target area under the optimal segmentation scale as monitoring respiration signals. The optimal segmentation scale is adaptively determined according to the quality of the respiration signals, so that the optimal respiration areas and the global optimal respiration signals under multiple scales are accurately obtained from the monitoring video of the respiration monitoring object, and the reliability of the camera for monitoring the respiration signals in a non-contact mode is improved.

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