CN111027485A - Heart rate detection method based on face video detection and chrominance model - Google Patents
Heart rate detection method based on face video detection and chrominance model Download PDFInfo
- Publication number
- CN111027485A CN111027485A CN201911265288.4A CN201911265288A CN111027485A CN 111027485 A CN111027485 A CN 111027485A CN 201911265288 A CN201911265288 A CN 201911265288A CN 111027485 A CN111027485 A CN 111027485A
- Authority
- CN
- China
- Prior art keywords
- heart rate
- skin
- chrominance
- detection
- face video
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Abstract
The invention discloses a heart rate detection method based on face video detection and a chrominance model, which comprises the following steps: acquiring a face video and extracting an interested area to obtain a component data set; skin detection is carried out on the region of interest to obtain the number of skin pixel points; extracting chrominance signals of the component data set according to the number of the skin pixel points and filtering; extracting pulse wave signals of the filtered chrominance signals; the invention utilizes skin detection to eliminate the interference of human facial skin artifacts, overcomes the influence of facial shaking and illumination transformation through a chromaticity model and Butterworth filtering, extracts stable and clean pulse wave signals, and then carries out spectrum analysis to estimate the heart rate, thereby improving the accuracy of heart rate detection and having higher robustness.
Description
Technical Field
The invention relates to the technical field of video image processing, in particular to a heart rate detection method based on face video detection and a chrominance model.
Background art:
with the development of computer vision technology, visual image processing technology is beginning to be applied to the medical fields of clinical diagnosis, operation implementation, health monitoring and the like. The heart rate is one of important physiological parameters of life activities, is mainly used for judging whether the metabolism of a human body is normal or not, judging the medicine intake condition, preventing heart diseases and the like, and has important significance for clinical diagnosis and evaluation of the health condition of the human body. The traditional clinical heart rate detection method needs to be in contact with a human body, is complex in equipment operation, low in automation degree, easy to cause discomfort of the human body and not suitable for long-time heart rate detection. Compared with the prior art, the non-contact heart rate detection only needs the camera to monitor the heart rate of the human body in real time, and has low cost and convenience.
Disclosure of Invention
The invention aims to provide a heart rate detection method based on face video detection and a chrominance model, and aims to overcome the defects that the heart rate detection operation of general equipment is complicated, the automation degree is low, and human bodies are prone to generating uncomfortable feeling in the prior art.
A heart rate detection method based on face video detection and a chrominance model comprises the following steps:
acquiring a face video and extracting an interested area to obtain a component data set;
skin detection is carried out on the region of interest to obtain the number of skin pixel points;
extracting chrominance signals of the component data set according to the number of the skin pixel points and filtering;
extracting pulse wave signals of the filtered chrominance signals;
and carrying out spectrum analysis on the pulse wave signal to obtain a heart rate value.
Further, the method for acquiring the face video and extracting the region of interest to obtain the component data set comprises the following steps:
acquiring a face video by adopting a camera to acquire a plurality of frames of video images;
carrying out face detection on each frame of video image and extracting an interested region;
and integrating the extracted regions of interest to obtain a component data set.
Further, the method for performing skin detection on the region of interest in the component data set to obtain the number of skin pixel points comprises the following steps:
converting the color space of the interested region of each frame of video image from RGB to HSL;
skin artifacts of all pixel points of the video image are obtained through skin detection;
filtering all skin artifacts to obtain RGB component sequences of all skin pixels of the region of interest;
and counting the number of the skin pixel points after the artifact is filtered.
Further, the method for extracting the chrominance signals of the component data set according to the number of the skin pixel points and filtering the chrominance signals comprises the following steps:
respectively averaging the component data sets according to the number of the skin pixel points to obtain a skin pixel sequence;
solving through the component data set to obtain a skin pixel component mean value;
carrying out standardization processing on the skin pixel sequence according to the skin pixel component average value;
calculating the processed skin pixel sequence to obtain a chrominance signal sequence;
and filtering the chrominance signal sequence to obtain a filtered chrominance signal.
Further, the method for extracting the pulse wave signal of the filtered chrominance signal comprises the following steps:
calculating the filtered chrominance signal X ', Y' to obtain the pulse wave signal s ═ s1，s2，...，sn，...，sNThe calculation formula is as follows:
S＝X′-αY′；
in the formula, σ (·) represents a standard deviation of the signal.
Further, the method for obtaining the heart rate value by performing the spectrum analysis on the pulse wave signal comprises the following steps:
performing discrete Fourier transform on the pulse wave signal S to obtain a frequency domain signal
F＝{f1，f2，...，fn，...，fN}；
The calculation formula is as follows:
wherein, k is 1, 2.... cndot.n;
the frequency domain signal F is subjected to spectral analysis to calculate a heart rate value, and the formula is as follows:
HR＝60*fH(10)；
wherein f isHIndicating the peak to frequency.
Further, the region of interest includes one or more of the forehead, the left cheek, and the right cheek.
Further, the filtering method comprises Butterworth band-pass filtering, wherein the pass band is 1.00-2.16 HZ, the corresponding heart rate is 60-130 bpm, and the stop band bandwidth is 0.5-3.33 HZ.
The invention has the advantages that: according to the heart rate detection method based on the face video detection and the chromaticity model, the heart rate detection is realized through the common RGB camera, the sensor is not required to be in contact with a human body for detection, the limitation of time and space is avoided, the comfort level of the human body is improved, and meanwhile, the problems of shaking of the head of the human body, noise and the like are effectively solved in the realization process.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention.
FIG. 2 is a graph showing the results of the test examples of the present invention.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific embodiments.
As shown in fig. 1 to 2, a heart rate detection method based on human face video detection and a chrominance model includes the following steps:
the method comprises the following steps: collecting a face video and extracting an interested area to obtain a component data set:
acquiring a face video by adopting a camera to acquire a plurality of frames of video images;
carrying out face detection on each frame of video image and extracting an interested region;
integrating the extracted regions of interest to obtain a component data set;
the specific implementation steps are as follows:
acquiring 150 continuous face video images by using an RGB camera, detecting a rectangular face frame of each frame of video image by a haar-like face detector in OpenCV, positioning three regions of interest (ROI) of the forehead and two cheeks at the same time, and acquiring an RGB component data set of the face ROI of the 150 frames of video images:
Reds＝{red1，red2，...，redn，...，red150}；
Greens＝{green1，green2，...，greenn，...，green150}；
blues＝{blue1，blue2，...，bluen，...，blue150}；
wherein redn，greenn，bluenRGB color component sequences respectively representing face ROIs of the nth frame video image;
and, the RGB color component sequence of the face ROI of the n-th frame video image
redn＝{r1，r2，...，ri，...，rT}；greenn＝{g1，g2，...，gi，...，gT}；
bluen＝{b1，b2，…，bi，...，bT}；
Wherein r isi，gi，biRGB components corresponding to the ith pixel point in the frame image ROI respectively, wherein T is the number of the pixel points of the frame image ROI;
step two: skin detection is carried out on the region of interest to obtain the number of skin pixel points:
converting the color space of the interested region of each frame of video image from RGB to HSL;
skin artifacts of all pixel points of the video image are obtained through skin detection;
filtering all skin artifacts to obtain RGB component sequences of all skin pixels of the region of interest;
counting the number of skin pixel points after filtering the artifacts;
the specific implementation steps are as follows:
since the ROI region of the face detected from the video image contains skin pixel artifacts, skin detection is required to extract skin pixels in the ROI region;
the method comprises the following specific steps:
①, taking the nth frame video image as an example, the color space of the nth frame video image ROI is converted from RGB to HSL, where n is 1, 2.
Wherein, Vmax＝max(ri，gi，bi)，Vmin＝min(ri，gi，bi). Obtaining H after color space conversioni，Si，LiRespectively corresponding to HSL components of the ith pixel point in the ROI of the nth frame of video image;
② detecting skin artifact of all pixel points of the n-th frame video image through skin, and filtering to remove the artifact to obtain RGB component sequence of all skin pixels of ROI of the n-th frame video image
red′n＝{r1，r2，...，ri，...，rM}；green′n＝{g1，g2，...，gi，...，gM}；
blue′n＝{b1，b2，...，bi，...，bMM represents the number of skin pixel points of the n frame of video image ROI after artifact is filtered;
step three: extracting the chrominance signals of the component data set according to the number of the skin pixel points and filtering:
respectively averaging the component data sets according to the number of the skin pixel points to obtain a skin pixel sequence;
solving through the component data set to obtain a skin pixel component mean value;
carrying out standardization processing on the skin pixel sequence according to the skin pixel component average value;
calculating the processed skin pixel sequence to obtain a chrominance signal sequence;
filtering the chrominance signal sequence to obtain a filtered chrominance signal;
the specific implementation steps are as follows:
averaging RGB component data sets of ROI skin pixels of 150 frames of video images respectively to obtain a skin pixel sequence RedAvg ═ rds1，reds2，...，redsn，...，reds150}；
GreenAvg＝{greens1，greens2，...，greensn，...，greens150}；
BlueAvg＝{blues1，blues2，...，bluesn，...，blues150}；
Wherein
Respectively the mean values of RGB components of all skin pixels of the ROI of the nth frame video image; butterworth filtering is carried out on chrominance signals extracted from sequences RedAvg, GreenAvg and BlueAvg based on chrominance model(ii) a The method comprises the following specific steps:
① assuming that the illumination intensity of the camera in the chromaticity model is constant in the video acquisition time, the sequences RedAvg, GreenAvg and BlueAvg are standardized to eliminate the influence of the illumination intensity of the camera in the video acquisition time.
Wherein
Average value of the red component, Avgr, representing skin pixels of ROI of 150 frames of video imagenThe normalized red color component of the skin pixels of the ROI of the n-th frame of video image is shown. The sequences RedAvg, GreenAvg and BlueAvg are processed to obtain:
AvgR＝{Avgr1，Avgr2，...，Avgrn，...，Avgr150}；
AvgG＝{Avgg1，Avgg2，...，Avggn，...，Avgg150}；
AvgB＝{Avgb1，Avgb2，...，Avgbn，...，Avgb150}；
② calculating a chrominance signal sequence X ═ X from the sequence AvgR, AvgG and AvgB1，x2，...，xn，...，x150Y ═ Y1，y2，...，yn，...，y150}；
The chrominance signal calculation formula is as follows:
xn＝3Avgrn-2Avggn(5)；
yn＝1.5Avgrn+Avggn-Avgbn(6)；
③, performing Butterworth band-pass filtering on the chrominance signals X and Y to obtain filtered chrominance signals X 'and Y' so as to eliminate noise interference, wherein the passband is 1.00-2.16 HZ, the corresponding heart rate is 60-130 bpm, and the stopband bandwidth is 0.5-3.33 HZ;
step four: extracting the pulse wave signal of the filtered chrominance signal:
calculating the filtered chrominance signal X ', Y' to obtain the pulse wave signal S ═ { S }1，s2，...，sn，...，sN}; the calculation formula is as follows:
S＝X′-αY′；
in the formula, σ (·) represents a standard deviation of the signal;
step five: carrying out spectrum analysis on the pulse wave signal to obtain a heart rate value:
performing discrete Fourier transform on the pulse wave signal S to obtain a frequency domain signal
F＝{f1，f2，...，fn，...，fN}；
The calculation formula is as follows:
wherein, k is 1, 2.... cndot.n;
the frequency domain signal F is subjected to spectral analysis to calculate a heart rate value, and the formula is as follows:
HR＝60*fH(10)；
wherein f isHIndicating the peak to frequency.
In this embodiment, the region of interest includes one or more of the forehead, the left cheek, and the right cheek.
It will be appreciated by those skilled in the art that the invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The embodiments disclosed above are therefore to be considered in all respects as illustrative and not restrictive. All changes which come within the scope of or equivalence to the invention are intended to be embraced therein.
Claims (8)
1. A heart rate detection method based on face video detection and a chrominance model is characterized by comprising the following steps:
acquiring a face video and extracting an interested area to obtain a component data set;
skin detection is carried out on the region of interest to obtain the number of skin pixel points;
extracting chrominance signals of the component data set according to the number of the skin pixel points and filtering;
extracting pulse wave signals of the filtered chrominance signals;
and carrying out spectrum analysis on the pulse wave signal to obtain a heart rate value.
2. The heart rate detection method based on the face video detection and the chrominance model according to claim 1, wherein: the method for acquiring the face video and extracting the region of interest to obtain the component data set comprises the following steps:
acquiring a face video by adopting a camera to acquire a plurality of frames of video images;
carrying out face detection on each frame of video image and extracting an interested region;
and integrating the extracted regions of interest to obtain a component data set.
3. The heart rate detection method based on the face video detection and the chrominance model according to claim 1, wherein: the method for carrying out skin detection on the region of interest in the component data set to obtain the number of skin pixel points comprises the following steps:
converting the color space of the interested region of each frame of video image from RGB to HSL;
skin artifacts of all pixel points of the video image are obtained through skin detection;
filtering all skin artifacts to obtain RGB component sequences of all skin pixels of the region of interest;
and counting the number of the skin pixel points after the artifact is filtered.
4. The heart rate detection method based on the face video detection and the chrominance model according to claim 1, wherein: the method for extracting the chrominance signals of the component data set according to the number of the skin pixel points and filtering comprises the following steps:
respectively averaging the component data sets according to the number of the skin pixel points to obtain a skin pixel sequence;
solving through the component data set to obtain a skin pixel component mean value;
carrying out standardization processing on the skin pixel sequence according to the skin pixel component average value;
calculating the processed skin pixel sequence to obtain a chrominance signal sequence;
and filtering the chrominance signal sequence to obtain a filtered chrominance signal.
5. The heart rate detection method based on the face video detection and the chrominance model according to claim 1, wherein: the method for extracting the pulse wave signal of the filtered chrominance signal comprises the following steps:
calculating the filtered chrominance signal X ', Y' to obtain the pulse wave signal S ═ { S }1，s2，...，sn，...，sNThe calculation formula is as follows:
S＝X′-αY′；
in the formula, σ (·) represents a standard deviation of the signal.
6. The heart rate detection method based on the face video detection and the chrominance model according to claim 1, wherein: the method for obtaining the heart rate value by carrying out the spectrum analysis on the pulse wave signal comprises the following steps:
performing discrete Fourier transform on the pulse wave signal S to obtain a frequency domain signal
F＝{f1，f2，...，fn，...，fN}；
The calculation formula is as follows:
wherein k is 1,2, … …, N;
the frequency domain signal F is subjected to spectral analysis to calculate a heart rate value, and the formula is as follows:
HR＝60*fH(10)；
wherein f isHIndicating the peak to frequency.
7. The heart rate detection method based on the face video detection and the chrominance model according to claim 1, wherein: the region of interest includes one or more of the forehead, the left cheek, and the right cheek.
8. The heart rate detection method based on the face video detection and the chrominance model according to claim 4 or 6, wherein: the filtering method comprises Butterworth band-pass filtering, wherein a pass frequency band is 1.00-2.16 HZ, a corresponding heart rate is 60-130 bpm, and a stop band bandwidth is 0.5-3.33 HZ.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911265288.4A CN111027485A (en) | 2019-12-11 | 2019-12-11 | Heart rate detection method based on face video detection and chrominance model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911265288.4A CN111027485A (en) | 2019-12-11 | 2019-12-11 | Heart rate detection method based on face video detection and chrominance model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111027485A true CN111027485A (en) | 2020-04-17 |
Family
ID=70205797
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911265288.4A Pending CN111027485A (en) | 2019-12-11 | 2019-12-11 | Heart rate detection method based on face video detection and chrominance model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111027485A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112507930A (en) * | 2020-12-16 | 2021-03-16 | 华南理工大学 | Method for improving human face video heart rate detection by using illumination balancing method |
| CN112507877A (en) * | 2020-12-08 | 2021-03-16 | 北京工业大学 | System and method for detecting heart rate under condition of partial video information loss |
| CN112890792A (en) * | 2020-11-25 | 2021-06-04 | 合肥工业大学 | Cloud computing cardiovascular health monitoring system and method based on network camera |
| CN113780100A (en) * | 2021-08-20 | 2021-12-10 | 北京工业大学 | Facial physiological information shielding method without changing video effect |
| CN116109818A (en) * | 2023-04-11 | 2023-05-12 | 成都中医药大学 | Traditional Chinese medicine pulse condition distinguishing system, method and device based on facial video |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009123737A2 (en) * | 2008-04-03 | 2009-10-08 | Becton, Dickinson And Company | Advanced detection of sepsis |
| CN101959458A (en) * | 2008-03-06 | 2011-01-26 | 摩托罗拉公司 | Visible images easy to use is measured the method and apparatus of heart rate |
| CN105188520A (en) * | 2013-03-14 | 2015-12-23 | 皇家飞利浦有限公司 | Device and method for determining vital signs of a subject |
| CN105989357A (en) * | 2016-01-18 | 2016-10-05 | 合肥工业大学 | Human face video processing-based heart rate detection method |
| CN106725411A (en) * | 2017-02-15 | 2017-05-31 | 成都皓图智能科技有限责任公司 | A kind of contactless heartbeat detecting method accelerated based on GPU |
| CN107529646A (en) * | 2017-05-02 | 2018-01-02 | 广东工业大学 | A kind of non-contact type method for measuring heart rate and device based on Euler's image zoom |
| CN108771539A (en) * | 2018-03-21 | 2018-11-09 | 上海师范大学 | A kind of detection method and its device of the contactless heart rate based on camera shooting |
| CN109480808A (en) * | 2018-09-27 | 2019-03-19 | 深圳市君利信达科技有限公司 | A kind of heart rate detection method based on PPG, system, equipment and storage medium |
-
2019
- 2019-12-11 CN CN201911265288.4A patent/CN111027485A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101959458A (en) * | 2008-03-06 | 2011-01-26 | 摩托罗拉公司 | Visible images easy to use is measured the method and apparatus of heart rate |
| WO2009123737A2 (en) * | 2008-04-03 | 2009-10-08 | Becton, Dickinson And Company | Advanced detection of sepsis |
| CN105188520A (en) * | 2013-03-14 | 2015-12-23 | 皇家飞利浦有限公司 | Device and method for determining vital signs of a subject |
| CN105989357A (en) * | 2016-01-18 | 2016-10-05 | 合肥工业大学 | Human face video processing-based heart rate detection method |
| CN106725411A (en) * | 2017-02-15 | 2017-05-31 | 成都皓图智能科技有限责任公司 | A kind of contactless heartbeat detecting method accelerated based on GPU |
| CN107529646A (en) * | 2017-05-02 | 2018-01-02 | 广东工业大学 | A kind of non-contact type method for measuring heart rate and device based on Euler's image zoom |
| CN108771539A (en) * | 2018-03-21 | 2018-11-09 | 上海师范大学 | A kind of detection method and its device of the contactless heart rate based on camera shooting |
| CN109480808A (en) * | 2018-09-27 | 2019-03-19 | 深圳市君利信达科技有限公司 | A kind of heart rate detection method based on PPG, system, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 万铮结: "基于人脸视频图像的心率检测研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112890792A (en) * | 2020-11-25 | 2021-06-04 | 合肥工业大学 | Cloud computing cardiovascular health monitoring system and method based on network camera |
| CN112507877A (en) * | 2020-12-08 | 2021-03-16 | 北京工业大学 | System and method for detecting heart rate under condition of partial video information loss |
| CN112507930A (en) * | 2020-12-16 | 2021-03-16 | 华南理工大学 | Method for improving human face video heart rate detection by using illumination balancing method |
| CN112507930B (en) * | 2020-12-16 | 2023-06-20 | 华南理工大学 | Method for improving human face video heart rate detection by utilizing illumination equalization method |
| CN113780100A (en) * | 2021-08-20 | 2021-12-10 | 北京工业大学 | Facial physiological information shielding method without changing video effect |
| CN113780100B (en) * | 2021-08-20 | 2024-03-01 | 北京工业大学 | Facial physiological information shielding method without changing video effect |
| CN116109818A (en) * | 2023-04-11 | 2023-05-12 | 成都中医药大学 | Traditional Chinese medicine pulse condition distinguishing system, method and device based on facial video |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111027485A (en) | Heart rate detection method based on face video detection and chrominance model | |
| CN110269600B (en) | Non-contact video heart rate detection method based on multivariate empirical mode decomposition and combined blind source separation | |
| CN104173051A (en) | Automatic noncontact respiration assessing system and assessing method | |
| Feng et al. | Motion artifacts suppression for remote imaging photoplethysmography | |
| CN110236511A (en) | A kind of noninvasive method for measuring heart rate based on video | |
| McDuff et al. | Fusing partial camera signals for noncontact pulse rate variability measurement | |
| CN110647815A (en) | Non-contact heart rate measurement method and system based on face video image | |
| Fallet et al. | Imaging photoplethysmography: What are the best locations on the face to estimate heart rate? | |
| Yu et al. | Noncontact monitoring of heart rate and heart rate variability in geriatric patients using photoplethysmography imaging | |
| CN111714105A (en) | Human vital sign perception system based on IPPG | |
| CN203290905U (en) | Non-contact automatic respiration measuring system | |
| CN111839492B (en) | Heart rate non-contact type measuring method based on face video sequence | |
| Wedekind et al. | Automated identification of cardiac signals after blind source separation for camera-based photoplethysmography | |
| CN111281367A (en) | Anti-interference non-contact heart rate detection method based on face video | |
| CN111444797A (en) | Non-contact heart rate detection method | |
| Mitsuhashi et al. | Video-based stress level measurement using imaging photoplethysmography | |
| Wu et al. | Camera-based heart rate measurement using continuous wavelet transform | |
| CN113591769B (en) | Non-contact heart rate detection method based on photoplethysmography | |
| US20180122066A1 (en) | System and method for extracting a periodic signal from video | |
| Panigrahi et al. | Non-contact HR extraction from different color spaces using RGB camera | |
| Nikolaiev et al. | Non-contact video-based remote photoplethysmography for human stress detection | |
| Suriani et al. | Non-contact Facial based Vital Sign Estimation using Convolutional Neural Network Approach | |
| CN116509359A (en) | Multi-target heart rate monitoring method and device for construction site operation | |
| Sarkar et al. | Evaluation of video magnification for nonintrusive heart rate measurement | |
| CN115381444A (en) | Rapid detection method for blood oxygen saturation |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200417 |