Non-touch-type real-time measurement method and system for human respiratory parameters

Abstract

The invention provides a non-touch-type real-time measurement method for human respiratory parameters. The method comprises following steps: (1)generating Wi-Fi signals near a human body, collecting channel state signal CSI of the Wi-Fi signals; (2) de-nosing the channel state signals CSI collected; (3) dividing the CSI signals into different periods such that features of each signal are the same in the same time period; (4) extracting frequencies, periodicities and amplitude values of sub-carriers from multiple sub-carriers in each section of CSI signals such that central frequencies and respiratory amplitude values of each section of CSI signals are obtained by weighted average calculations. The invention provides a system achieving the above method. The method has following beneficial effects: by monitoring channel state information of Wi-Fi signals near the human body, feature value showing respiration of the human body can be extracted and real-time respiration frequencies can be calculated. Without installing intrusive sensors on the human body, the method does not expose privacy of the human body.

Description

technical field [0001] The invention belongs to the technical field of computer vision detection, and more specifically relates to a non-contact real-time measurement method and system for human breathing parameters. Background technique [0002] With the continuous progress of society and the development of computer technology, it has always been the goal of artificial intelligence researchers to make machines have a human way of thinking. At present, biological indicators, action recognition and behavior understanding of the human body have gradually become research hotspots in the field of computer vision detection. These studies can help people understand some characteristics, such as the other party's heart rate, behavior, posture, etc., through which the target's attitude, emotion, etc. can be reflected. Real-time detection of human respiratory parameters is one of many human biological indicator recognition and behavior understanding, and is an important part of comp...

AI Technical Summary

Problems solved by technology

[0004] Most of the traditional real-time measurement methods for monitoring human respiratory parameters require installing sensors on relevant parts of the human body, such as wrists, throats or chest respiratory parts, which are invasive monitoring and will cause inconvenience to the monitored person

Non-invasive sleep posture monitoring often uses infrared cameras, causing hidden dangers of privacy leakage

Images