Physiological parameter monitoring method, device and hand-held device

Abstract

The invention discloses a physiological parameter monitoring method, a physiological parameter monitoring device and a hand-held device. The method includes the following steps that: a current face image is acquired; a cheek part image in the face image is extracted; the mean values of the green channels of the cheek part image are calculated, so that a mean value sequence can be obtained; sliding mean value filtering is performed on the mean value sequence, a physiological change curve is obtained by adjusting the filtering interval of the sliding mean value filtering; and feature extraction is performed on the physiological change curve, so that physiological parameters can be obtained. According to the physiological parameter monitoring method, different physiological parameter curves can be obtained through different filtering intervals; and the curves can be correspondingly processed, so that a plurality of physiological parameter values can be obtained. The invention also discloses a handheld device using the method. The method, device and the hand-held device of the invention have the advantages of low computation amount, high accuracy and low hardware requirements.

Description

technical field [0001] The invention relates to the field of physiological parameter monitoring research, in particular to a physiological parameter monitoring method, device and handheld device. Background technique [0002] The monitoring of human physiological parameters includes the monitoring of parameters such as ECG, blood pressure, heart rate, blood oxygen saturation, respiratory rate, body temperature, and carbon dioxide concentration in breathing. It is currently widely used in clinical medicine, wearable devices, mobile terminals and other fields. [0003] For example, currently mature non-invasive heart rate measurement methods include pulse measurement method, electrocardiographic signal method, and photoplethysmography (PhotoPlethysmoGraphy, PPG). in: [0004] 1. Pulse measurement method: This is actually the oldest method, which is pulse diagnosis in traditional Chinese medicine. On the wrist or on both sides of the neck, the pressure of the arteries can be ...

AI Technical Summary

Problems solved by technology

This solution is also the most immature for commercial use at present. The first reason is that the pressure sensor needs to semi-compress the wearer's artery for a long time, causing discomfort.

The second is that the pressure sensor is difficult to fix on the skin surface in a suitable way: if it is fixed too tightly, it will cause poor blood flow, and if it is too loose, it will not be able to measure

However, the current solutions generally have the following defects: 1. It will wear out the lens and affect the imaging effect of the camera lens; 2. Turn on the flash, which may burn your fingers; 3. When the weather is cold or the body is abnormal, the blood may not flow through 4. The permeability of the fingers must be good. If there are stains or coverings, the measurement results will be affected; 5. Devices without a flash or the flash is far away from the camera cannot collect heart rate (of which 3 and 4 are also one of the defects of the infrared sensor)

[0013] However, the above solution has the following problems: 1. It is necessary to shoot a video before analyzing the video. Generally, the length of the video taken is about 30 seconds, and the shooting process has high requirements on the ambient light; 2. It is necessary to analyze the video The ROI area is separated for each frame, and the measured personnel should try to avoid displacement so as not to affect the calculation results; 3. It is necessary to calculate the mean value of the Red / Green / Blue channel data at the same time; 4. It is necessary to use ICA to perform blind source separation of mixed signals. More computing time; 5. Spectrum analysis (DFT calculation) of the final signal is required, which is also time-consuming, and the converted spectrogram has higher requirements on the data source. If there is more interference, the calculated value will be directly inaccurate. correct

However, the effect is still not ideal

Images