Non-contact respiratory rate detection method based on depth image

Abstract

The invention discloses a non-contact respiratory rate detection method based on a depth image. The method comprises the following steps: acquiring an original depth image, acquiring a figure position and acquiring depth information; by utilizing a maximum distance limiting method and a maximum outer contour extraction algorithm, respectively eliminating influences of void noise and close-range interferents in the original depth image, creating a human body mask image and obtaining a human body depth image; positioning a breathing area by utilizing the correlation between a human chest area and human skeleton joint points; extracting respiratory signal data contained in the depth image of the thoracic cavity region by using a principal component analysis algorithm; and obtaining the human respiratory rate through a peak value detection method. The influence of void noise and interference objects is eliminated when the human body depth image is obtained, so that the human body breathing frequency with accurate data is obtained, the equipment used in the method is convenient to carry, and the price can reach the wide application level.

Description

technical field [0001] The invention relates to the field of respiratory frequency monitoring, in particular to a non-contact respiratory frequency detection method based on a depth image. Background technique [0002] With the rapid development of modern industrial society and the improvement of people's living standards, the degree of environmental pollution has gradually increased, and people are paying more and more attention to their own health. Breathing is the most basic and important vital sign signal of the human body. The rhythm, intensity and frequency information contained in the breathing physiological signal can effectively reflect the lesions of the respiratory system organs, heart and brain system organs and other parts. As an important parameter of respiratory physiological signals, respiratory frequency is an important physiological indicator for the diagnosis of various chronic diseases such as pneumonia, asthma, and cardiac arrest. Through the detection ...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the disadvantages of low accuracy of the collected data due to the influence of hollow noise and close-range interference objects in the large-scale application of respiratory frequency detection in the prior art, and to provide a depth image-based non-invasive The contact breathing frequency detection method avoids the influence of contact detection equipment by acquiring the depth image of the human body, and eliminates the influence of hollow noise and interfering objects at close range on the acquired depth image of the human body, and more effectively extracts the required breathing Information, so as to obtain accurate data of human respiratory rate

Images