CN115381444A - Rapid detection method for blood oxygen saturation - Google Patents
Rapid detection method for blood oxygen saturation Download PDFInfo
- Publication number
- CN115381444A CN115381444A CN202211076791.7A CN202211076791A CN115381444A CN 115381444 A CN115381444 A CN 115381444A CN 202211076791 A CN202211076791 A CN 202211076791A CN 115381444 A CN115381444 A CN 115381444A
- Authority
- CN
- China
- Prior art keywords
- oxygen saturation
- blood oxygen
- image
- model
- lip
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000008280 blood Substances 0.000 title claims abstract description 81
- 210000004369 blood Anatomy 0.000 title claims abstract description 81
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 title claims abstract description 79
- 239000001301 oxygen Substances 0.000 title claims abstract description 79
- 229910052760 oxygen Inorganic materials 0.000 title claims abstract description 79
- 238000001514 detection method Methods 0.000 title claims abstract description 21
- 238000012544 monitoring process Methods 0.000 claims abstract description 21
- 238000012937 correction Methods 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000009471 action Effects 0.000 claims description 3
- 230000006835 compression Effects 0.000 claims description 3
- 238000007906 compression Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 abstract 1
- 238000011084 recovery Methods 0.000 abstract 1
- 210000001525 retina Anatomy 0.000 abstract 1
- 206010011703 Cyanosis Diseases 0.000 description 3
- 108010054147 Hemoglobins Proteins 0.000 description 3
- 102000001554 Hemoglobins Human genes 0.000 description 3
- 206010021143 Hypoxia Diseases 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 210000004400 mucous membrane Anatomy 0.000 description 3
- BPYKTIZUTYGOLE-IFADSCNNSA-N Bilirubin Chemical compound N1C(=O)C(C)=C(C=C)\C1=C\C1=C(C)C(CCC(O)=O)=C(CC2=C(C(C)=C(\C=C/3C(=C(C=C)C(=O)N\3)C)N2)CCC(O)=O)N1 BPYKTIZUTYGOLE-IFADSCNNSA-N 0.000 description 2
- 208000002330 Congenital Heart Defects Diseases 0.000 description 2
- 108010064719 Oxyhemoglobins Proteins 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000007954 hypoxia Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000006545 Chronic Obstructive Pulmonary Disease Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010241 blood sampling Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 208000028831 congenital heart disease Diseases 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000004868 gas analysis Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 230000004768 organ dysfunction Effects 0.000 description 1
- 238000006213 oxygenation reaction Methods 0.000 description 1
- 239000000049 pigment Substances 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/14542—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring blood gases
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/7475—User input or interface means, e.g. keyboard, pointing device, joystick
- A61B5/748—Selection of a region of interest, e.g. using a graphics tablet
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- General Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Fuzzy Systems (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Optics & Photonics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to a rapid detection method of blood oxygen saturation, which comprises the steps that terminal equipment shoots lip images of a detector (without a whole face image), image preprocessing is carried out on the basis of a multi-scale retina enhancement (MSRCR) algorithm with color recovery, a built-in blood oxygen saturation model is sent into the terminal equipment, the lip color is identified by the blood oxygen saturation model, and the currently predicted blood oxygen saturation of the detector is output and is used for monitoring the home blood oxygen saturation in real time.
Description
Technical Field
The invention relates to a detection technology, in particular to a rapid detection method for blood oxygen saturation.
Background
The intelligent terminal is more and more widely applied to health monitoring. Compared with the existing clinical monitoring means, the intelligent terminal does not need additional detection equipment, and is more portable, real-time and efficient. Greatly meets the requirement of monitoring the health of people at home, and provides an effective method for early detection and early diagnosis of diseases.
The blood oxygen saturation is an important physiological parameter of the respiratory cycle of a human body, and can directly reflect the oxygenation of the lung and the oxygen carrying capacity of hemoglobin in blood. Hypoxia directly affects the aerobic metabolism of tissues, thereby causing organ dysfunction and even failure. Hypoxia is present in diseases such as chronic obstructive pulmonary disease and some congenital heart diseases. At present, the blood oxygen saturation is mainly monitored clinically through a pulse oxygen saturation instrument and blood gas analysis. Both require specialized instrumentation. The former is portable, but has 2-3% measuring error under the influence of factors such as skin pigment, bilirubin and the like; the latter is the 'gold standard' for monitoring the blood oxygen saturation, but needs invasive blood sampling, and applies a specific blood gas analyzer to analyze data, so that the latter cannot be widely applied to monitoring of people at home.
Disclosure of Invention
Aiming at the problem of monitoring the blood oxygen saturation in real time, a rapid detection method for the blood oxygen saturation is provided.
The technical scheme of the invention is as follows: a method for quickly detecting the blood oxygen saturation includes such steps as taking the image of lip of person to be detected by terminal, sending it to the internal blood oxygen saturation model, recognizing the lip color by said model, and outputting the current blood oxygen saturation value of person to be detected for real-time monitoring the blood oxygen saturation at home.
Further, the blood oxygen saturation model training method comprises the following steps:
1) Data acquisition: acquiring a lip image of a subject, and simultaneously monitoring the blood oxygen saturation of the subject by using an oximeter; the subject loads the lip image and the corresponding oximeter display blood oxygen saturation value as image data;
2) Data processing: performing brightness correction on the lip image of the collected subject, extracting a multi-channel color mean value of the image according to a preset ROI, and constructing an image data set;
3) Constructing a blood oxygen saturation model based on a multi-channel color space, facilitating the image data set in the step 2) and the blood oxygen saturation value corresponding to the image in the step 1), training the blood oxygen saturation model, and predicting the blood oxygen saturation value corresponding to the lip color;
4) In the model training process, a data set is divided into a 60% training set and a 40% testing set, and the trained blood oxygen saturation model is verified by the testing set to obtain the final trained blood oxygen saturation model.
Further, the loss function of the blood oxygen saturation model:
wherein n is the number of lip image features; y represents the vector of the monitoring result of the oximeter, X is a lip image feature matrix, and w is the weight vector of the feature matrix.
Further, lip image lightness correction in the data processing: the image brightness equalization correction is completed by adopting an MCRCR algorithm and designing a multi-scale Gaussian filter and an image overall brightness difference correction algorithm, wherein the Gaussian function is as follows:
x and y represent coordinates of each pixel point, C is a normalization constant, the width of the Gaussian filter is represented by a parameter sigma, the larger sigma is, the larger the filtering action range is, in order to give consideration to dynamic range compression and local feature detail extraction, the values of multi-scale Gaussian filter sigma are respectively 20, 72 and 250, and the filtering results corresponding to the sigma values under each scale are subjected to equal weight averaging to obtain the final correction result.
Further, the multichannel color mean in the data processing comprises RGB and HSV dual-color mean.
Further, the blood oxygen saturation model is described as follows:
SpO 2(result) =W 1 C 1 +W 2 C 2 +...+W n C n +β,
wherein, W 1 …W n Representing the trained blood oxygen saturation model weight, beta is the trained blood oxygen saturation model bias term, C 1 …C n For two-way image of lips of a subjectThe trace color data is combined to form a feature vector.
The invention has the beneficial effects that: the invention relates to a rapid detection method of blood oxygen saturation, which acquires a lip image instead of a whole face image. Under the condition of blood oxygen saturation change, particularly under the condition of oxygen deficiency, the color change of lips is more sensitive and remarkable; the operation method of machine learning is different from the RGB image algorithm of the prior patent, and can eliminate the difference of RGB colors of images under different light rays and different photographing environments, thereby realizing the accurate detection of the blood oxygen saturation; the method can be applied to all intelligent terminal equipment with cameras or with a picture reading function, and the rapid detection of the blood oxygen saturation can be realized through the APP.
Drawings
FIG. 1 is a flow chart of an implementation of the rapid detection method of blood oxygen saturation according to the present invention;
FIG. 2 is a comparison graph of the MCRCR algorithm for correcting the brightness of an image according to the method of the present invention;
FIG. 3 is an APP analysis interface diagram of the intelligent terminal of the present invention;
FIG. 4 is a comparison graph of the detection and oximeter of the instant invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
The color of the skin and mucous membranes changes with the color of the blood stream. When the reduced hemoglobin in the blood is >3mg/L, the skin and mucous membrane are changed in bluish purple, i.e. cyanosis. Cyanosis can occur in the whole skin and mucous membrane, but it is more pronounced in thin skin, less pigmented and capillary-rich areas such as lips and tongue.
A rapid detection method for blood oxygen saturation comprises the steps that terminal equipment shoots lip images of a detector, sends the lip images into a built-in blood oxygen saturation model of the detector, and outputs a current blood oxygen saturation value of the detector for monitoring the blood oxygen saturation of a house in real time. The blood oxygen saturation degree model training method specifically comprises the following steps:
1. data acquisition: acquiring lip images of a subject and simultaneously monitoring the blood oxygen saturation of the subject by using an oximeter; the lip image of the subject is obtained by a device with a photographing and shooting function, or the sample image data is transmitted by a medium and loaded in a local database. Oximeters are used to monitor the oxygen saturation of a subject's blood.
2. Algorithm (MSRCR) based image brightness correction; since home or clinical monitoring of blood oxygen saturation is usually performed in different environments, this will cause instability of the acquired lip image, thereby interfering with the monitoring result. Therefore, on the premise of keeping the image undistorted, based on the MCRCR algorithm, the image brightness equalization correction is completed by designing the multi-scale gaussian filter and the image overall brightness difference correction algorithm, as shown in the image brightness correction contrast diagram in fig. 2. The gaussian function used is as follows:
wherein x and y represent coordinates of each pixel point, C is a normalization constant, the width of the gaussian filter is represented by a parameter σ, and the larger σ is, the larger the filtering action range is, so that in order to give consideration to dynamic range compression and local feature detail extraction, the values of the multi-scale gaussian filter σ are respectively 20, 72 and 250, and the filtering results corresponding to the σ values under each scale are subjected to equal weight averaging, namely, the final correction result is obtained.
3. Extracting an image color mean value according to a preset ROI; the method supports the preset ROI size, and automatically extracts the multichannel color mean value (including RGB and HSV) by the program background based on the image after brightness correction.
4. Constructing a blood oxygen saturation degree model and a data set based on a multi-channel color space; because each channel of the RGB color space is related to the wavelength of reflected light of a substance, when the color of the lips changes due to oxygen saturation, the RGB channel color value of the lip image changes along with the color of the lips, and therefore the RGB channel color value has important significance as a training feature; in the HSV space, H visually defines the hue, so that the lip color change range can be better excavated and limited. Therefore, the RGB and HSV dual-color spaces are combined, and the data set and the blood oxygen saturation model are constructed based on the feature combination of the dual-color spaces and the detection value of the oximeter.
The machine learning algorithm integrated in the intelligent terminal is described as follows:
SpO 2(result) =W 1 C 1 +W 2 C 2 +...+W n C n +β,
wherein, W 1 …W n Representing the trained blood oxygen saturation model weight, beta is the trained blood oxygen saturation model bias term, C 1 …C n Is a feature vector composed of a two-channel color data combination of the lip images of the subject.
5. Training and applying the blood oxygen saturation model; in the model training process, the data set is divided into a 60% training set and a 40% testing set, and the blood oxygen saturation model is trained by optimizing the following loss function:
wherein n is the number of the lip image features; y represents the vector of the monitoring result of the oximeter, X is a lip image feature matrix, and w is the weight vector of the feature matrix.
After training, the model is deployed in the intelligent terminal APP to conveniently complete rapid oxyhemoglobin saturation monitoring. Therefore, after the lip image is shot, the background of the program automatically finishes brightness correction and extracts color signals, and finally, the feature vector is automatically reconstructed and input to the model to finish monitoring. The whole process can be automatically completed in the intelligent terminal APP. The APP analysis interface diagram of the intelligent terminal is shown in FIG. 3.
Blood oxygen saturation (SaO) 2 ) Is oxyhemoglobin (HbO) bound by oxygen in blood 2 ) The percentage of total bindable hemoglobin capacity. The method shown in fig. 4 is used for detecting blood oxygen saturation by comparing the color of lip or cyanosis with the oximeter detection chart obtained by trained machine learning modelThe consistency is very high when the comparison is carried out. The model trained by the invention is combined with the terminal to realize the home real-time monitoring of the blood oxygen saturation and effectively evaluate the state of illness of congenital heart disease.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that various changes and modifications can be made by those skilled in the art without departing from the spirit of the invention, and these changes and modifications are all within the scope of the invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (6)
1. A rapid detection method for blood oxygen saturation is characterized in that a terminal device shoots a lip image of a detector, the lip image is sent to a built-in blood oxygen saturation model of the detector, the blood oxygen saturation model identifies lip color, and a current blood oxygen saturation value of the detector is output and used for monitoring the blood oxygen saturation of a house in real time.
2. The rapid detection method of blood oxygen saturation according to claim 1, characterized in that the training method of blood oxygen saturation model is as follows:
1) Data acquisition: acquiring a lip image of a subject, and simultaneously monitoring the blood oxygen saturation of the subject by using an oximeter; the subject loads the lip image and the corresponding oximeter display blood oxygen saturation value as image data;
2) Data processing: performing brightness correction on the lip image of the collected subject, extracting a multi-channel color mean value of the image according to a preset ROI, and constructing an image data set;
3) Constructing a blood oxygen saturation model based on a multi-channel color space, facilitating the image data set in the step 2) and the blood oxygen saturation value corresponding to the image in the step 1), training the blood oxygen saturation model, and predicting the blood oxygen saturation value corresponding to the lip color;
4) In the model training process, a data set is divided into a 60% training set and a 40% testing set, and the trained blood oxygen saturation degree model is verified by the testing set to obtain the final trained blood oxygen saturation degree model.
3. The rapid detection method of blood oxygen saturation according to claim 2, characterized in that the loss function of the blood oxygen saturation model is:
wherein n is the number of lip image features; y represents the vector of the monitoring result of the oximeter, X is a lip image feature matrix, and w is the weight vector of the feature matrix.
4. The method of rapid detection of blood oxygen saturation according to claim 2 or 3, characterized in that lip image brightness correction in the data processing: the image brightness equalization correction is completed by adopting an MCRCR algorithm and designing a multi-scale Gaussian filter and an image overall brightness difference correction algorithm, wherein the Gaussian function is as follows:
wherein x and y represent the coordinates of each pixel point, C is a normalization constant, the width of the Gaussian filter is represented by a parameter sigma, the larger sigma is, the larger the filtering action range is, in order to give consideration to dynamic range compression and local feature detail extraction, the values of multi-scale Gaussian filter sigma are respectively 20, 72 and 250, and the filtering results corresponding to the sigma values under each scale are subjected to equal weight averaging, namely, the final correction result is obtained.
5. The method for rapidly detecting blood oxygen saturation degree based on machine learning according to claim 4, characterized in that the multichannel color mean value in data processing includes RGB and HSV two-color mean values.
6. The machine learning-based rapid detection method of blood oxygen saturation according to claim 5, characterized in that the blood oxygen saturation model is described as follows:
SpO 2(result) =W 1 C 1 +W 2 C 2 +...+W n C n +β,
wherein, W 1 …W n Representing the trained blood oxygen saturation model weight, beta is the trained blood oxygen saturation model bias term, C 1 …C n Is a feature vector formed by combining two channels of color data of the lip image of the subject.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211076791.7A CN115381444A (en) | 2022-09-05 | 2022-09-05 | Rapid detection method for blood oxygen saturation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211076791.7A CN115381444A (en) | 2022-09-05 | 2022-09-05 | Rapid detection method for blood oxygen saturation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115381444A true CN115381444A (en) | 2022-11-25 |
Family
ID=84123969
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211076791.7A Pending CN115381444A (en) | 2022-09-05 | 2022-09-05 | Rapid detection method for blood oxygen saturation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115381444A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116758069A (en) * | 2023-08-17 | 2023-09-15 | 济南宝林信息技术有限公司 | Medical image enhancement method for intestinal endoscope |
-
2022
- 2022-09-05 CN CN202211076791.7A patent/CN115381444A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116758069A (en) * | 2023-08-17 | 2023-09-15 | 济南宝林信息技术有限公司 | Medical image enhancement method for intestinal endoscope |
CN116758069B (en) * | 2023-08-17 | 2023-11-14 | 济南宝林信息技术有限公司 | Medical image enhancement method for intestinal endoscope |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wang et al. | Algorithmic principles of remote PPG | |
Guazzi et al. | Non-contact measurement of oxygen saturation with an RGB camera | |
US10004410B2 (en) | System and methods for measuring physiological parameters | |
US10398327B2 (en) | Non-contact assessment of cardiovascular function using a multi-camera array | |
RU2589389C2 (en) | Device and method of extracting information from characteristic signals | |
Trenta et al. | Advanced motion-tracking system with multi-layers deep learning framework for innovative car-driver drowsiness monitoring | |
Fan et al. | Non-contact remote estimation of cardiovascular parameters | |
CN111243739A (en) | Anti-interference physiological parameter telemetering method and system | |
CN111027485A (en) | Heart rate detection method based on face video detection and chrominance model | |
CN111387959A (en) | Non-contact physiological parameter detection method based on IPPG | |
WO2013046082A2 (en) | Distortion reduced signal detection | |
CN109009052A (en) | The embedded heart rate measurement system and its measurement method of view-based access control model | |
CN113361480B (en) | Human body pulse wave acquisition method based on face video | |
US11690543B2 (en) | System and method for camera-based quantification of blood biomarkers | |
CN115381444A (en) | Rapid detection method for blood oxygen saturation | |
Bai et al. | Real-time robust noncontact heart rate monitoring with a camera | |
TWI430776B (en) | Smart video skin test system and method of the same | |
CN112881303A (en) | Blood glucose concentration detection method based on hyperspectral imaging technology | |
CN110135357B (en) | Happiness real-time detection method based on remote sensing | |
Li et al. | Enhancement of remote PPG and heart rate estimation with optimal signal quality index | |
CN112597949B (en) | Psychological stress measuring method and system based on video | |
CN108090410A (en) | A kind of contactless facial rhythm of the heart Spinning and monitoring method | |
CN115376179A (en) | Non-contact heart rate measuring method and system | |
Sinhal et al. | Color intensity: a study of RPPG algorithm for heart rate estimation | |
CN113693573A (en) | Video-based non-contact multi-physiological-parameter monitoring system and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |