CN111797794A - Facial dynamic blood flow distribution detection method - Google Patents
Facial dynamic blood flow distribution detection method Download PDFInfo
- Publication number
- CN111797794A CN111797794A CN202010666893.9A CN202010666893A CN111797794A CN 111797794 A CN111797794 A CN 111797794A CN 202010666893 A CN202010666893 A CN 202010666893A CN 111797794 A CN111797794 A CN 111797794A
- Authority
- CN
- China
- Prior art keywords
- blood flow
- pulse wave
- roi
- channel
- sub
- 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
- 230000017531 blood circulation Effects 0.000 title claims abstract description 60
- 230000001815 facial effect Effects 0.000 title claims abstract description 32
- 238000001514 detection method Methods 0.000 title claims abstract description 13
- 238000013186 photoplethysmography Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 25
- 238000001228 spectrum Methods 0.000 claims description 18
- 238000012880 independent component analysis Methods 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 9
- 238000012935 Averaging Methods 0.000 claims description 8
- 238000012847 principal component analysis method Methods 0.000 claims description 8
- 238000000513 principal component analysis Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008451 emotion Effects 0.000 description 2
- 230000008338 local blood flow Effects 0.000 description 2
- 230000035479 physiological effects, processes and functions Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000001931 thermography Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000006397 emotional response Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 210000000653 nervous system Anatomy 0.000 description 1
- 210000001002 parasympathetic nervous system Anatomy 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000002889 sympathetic effect Effects 0.000 description 1
- 210000002820 sympathetic nervous system Anatomy 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
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
- A61B5/02416—Detecting, measuring or recording pulse rate or heart rate using photoplethysmograph signals, e.g. generated by infrared radiation
-
- 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
- A61B5/026—Measuring blood flow
-
- 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
-
- 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
- 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
- G06V40/14—Vascular patterns
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Cardiology (AREA)
- Physiology (AREA)
- Molecular Biology (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Hematology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The invention relates to a facial dynamic blood flow distribution detection method, which comprises the following steps: acquiring a face area video of a person to be detected in a set time window, wherein the face area video comprises a plurality of frames of color mode RGB images; preprocessing each frame of color mode RGB image to obtain a plurality of frames of face images; determining an ROI in a certain frame of face image, tracking in each frame of face image, and determining the standard heart rate of the ROI through remote photoplethysmography; correspondingly segmenting a plurality of sub-regions in each frame of face image; determining standard pulse wave signals of each sub-area by using remote photoplethysmography; obtaining a blood flow intensity characteristic value of each sub-area according to the standard pulse wave signals of each sub-area; obtaining facial blood flow distribution according to the blood flow intensity characteristic value of each subregion; and sliding a set time window by a set sliding length, and repeating the steps to obtain the facial dynamic blood flow distribution. The invention does not need to contact with the person to be tested, does not cause damage, and is convenient and quick and has high precision.
Description
Technical Field
The invention relates to the technical field of image detection, in particular to a method for detecting dynamic blood flow distribution of a face.
Background
The non-contact extraction of the blood flow distribution has very important significance for the researches on human physiology, emotional response mechanism and the like. The distribution state of facial blood flow is controlled by sympathetic and parasympathetic nervous systems, and the change of emotion and physiological information enables the nervous systems to control and regulate the blood flow distribution.
The local blood flow distribution detection has wide application prospect in the fields of clinical medicine, emotion calculation and the like. At present, the blood flow distribution detection mainly takes the principles of Doppler, ultrasound, thermal imaging and the like, has the advantages of safety, no wound, real-time performance and the like, and can detect the physicochemical characteristics of local blood flow distribution and change. Although these methods can achieve more accurate measurement of blood flow distribution, there are many disadvantages in practical applications: 1. the detection process needs to be in contact with limbs, and the patient is continuously monitored for a long time to be bound to a certain degree; 2. the device is in a high-frequency microwave environment for a long time, so that the physiology and the tissue of a human body are damaged to a certain extent, the temperature of the tissue of the human body is influenced by various factors, and the detection result of the thermal imaging equipment has no judgment significance; 3. the operation process is complicated.
Disclosure of Invention
The invention aims to provide a non-contact, convenient and quick facial dynamic blood flow distribution detection method.
In order to achieve the purpose, the invention provides the following scheme:
a facial dynamic blood flow distribution detection method includes:
s1, acquiring a facial area video of the person to be detected in the set time window; the face region video includes a plurality of frames of color mode RGB images;
s2, preprocessing each frame of the color mode RGB image to obtain a plurality of frames of face images;
s3, determining ROI in a certain frame of the face image, tracking in each frame of the face image, and determining the standard heart rate of the ROI through remote photoplethysmography;
s4, correspondingly segmenting a plurality of sub-regions in each frame of the face image; determining a standard pulse wave signal of each sub-area by using remote photoplethysmography;
s5, obtaining a blood flow intensity characteristic value of each sub-area according to the standard pulse wave signals of each sub-area;
s6, obtaining facial blood flow distribution according to the blood flow intensity characteristic value of each sub-region; sliding the set time window by a set sliding length, and returning to S1 to obtain the dynamic blood flow distribution of the face; the set sliding length is less than the length of the set time window.
Preferably, the S2 specifically includes:
s21, carrying out binarization processing on the color mode RGB image of the ith frame to obtain a binary image corresponding to the color mode RGB image of the ith frame; wherein i belongs to n, and n is the total frame number of the color mode RGB image;
s22, performing expansion processing on the binary image to obtain an expanded image;
and S23, taking the expansion image as a mask template, and performing mask operation on the expansion image and the corresponding color mode RGB image of the ith frame to obtain the face image.
Preferably, the S3 specifically includes:
s31, determining ROI in the face image of the mth frame, and tracking in each frame of the face image to obtain pixel values of each channel in the ROI; wherein m belongs to n, and n is the total frame number of the color mode RGB image;
s32, averaging the pixel values of each channel in the ROI to obtain a first pixel average value;
s33, determining a first initial pulse wave signal of each channel according to the first pixel average value of each channel;
s34, filtering the first initial pulse wave signals of each channel to obtain first filtered pulse wave signals of each channel;
s35, selecting data corresponding to a certain channel as a standard pulse wave signal of the ROI according to a principal component analysis method or an independent component analysis method; the data is data of each first filtered pulse wave signal corresponding to the ROI after principal component analysis or independent component analysis.
S36, performing fast Fourier transform on the standard pulse wave signal of the ROI to obtain a first power spectrum amplitude and a frequency corresponding to the first power spectrum amplitude;
and S37, selecting the frequency corresponding to the maximum first power spectrum amplitude as the standard heart rate of the ROI.
Preferably, the S4 specifically includes:
s41, correspondingly dividing a plurality of sub-regions in each frame of the face image according to the set dividing side length;
s42, comparing the pixel value of each sub-area with a set pixel threshold value, wherein the sub-area which is larger than or equal to the pixel threshold value is defined as an active detector, and the sub-area which is smaller than the pixel threshold value is defined as an inactive detector; the standard pulse wave signal and the blood flow intensity characteristic value corresponding to the invalid detector are both defined as 0;
s43, averaging the pixel values of each channel in the ith effective detector to obtain a second pixel average value; wherein l belongs to h, and h is the total number of effective detectors;
s44, determining a second initial pulse wave signal of each channel according to the second pixel average value of each channel;
s45, filtering the second initial pulse wave signals of each channel to obtain second filtered pulse wave signals of each channel;
s46, selecting data corresponding to a certain channel as a standard pulse wave signal of the effective detector according to a principal component analysis method or an independent component analysis method; the data is obtained after the second filtered pulse wave signals corresponding to the effective detector are subjected to principal component analysis or independent component analysis.
Preferably, the S5 specifically includes:
s51, carrying out fast Fourier transform on the standard pulse wave signal of the q-th effective detector to obtain a second power spectrum amplitude; wherein q is the t, and t is the total number of effective detectors;
s52, selecting the second power spectrum amplitude corresponding to the standard heart rate as an initial characteristic value;
and S53, averaging the initial characteristic value and the second power spectrum amplitude values on both sides of the initial characteristic value to be used as the blood flow intensity characteristic value of the effective detector.
Preferably, the S6 specifically includes:
s61, restoring the blood flow intensity characteristic value corresponding to each sub-region according to the space position before segmentation;
s62, smoothing each restored blood flow intensity characteristic value to obtain the facial blood flow distribution;
and S63, sliding the set time window by the set sliding length, and returning to S1 to obtain the dynamic blood flow distribution of the face.
Preferably, the S35 specifically includes:
s35, selecting data of a channel corresponding to the maximum characteristic value as a standard pulse wave signal of the ROI by adopting the principal component analysis method; the data is data of each first filtering pulse wave signal corresponding to the ROI after principal component analysis;
or S35, selecting the data of the channel with the maximum data correlation with the green channel as the standard pulse wave signal of the ROI by adopting the independent component analysis method; the data is obtained by analyzing independent components of each first filtered pulse wave signal corresponding to the ROI.
Preferably, the facial region video is acquired by a mobile phone camera or a high-speed acquisition device.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention relates to a facial dynamic blood flow distribution detection method, which comprises the following steps: acquiring a face area video of a person to be detected in a set time window, wherein the face area video comprises a plurality of frames of color mode RGB images; preprocessing each frame of color mode RGB image to obtain a plurality of frames of face images; determining an ROI in a certain frame of face image, tracking in each frame of face image, and determining a standard heart rate of the ROI through photoplethysmography; correspondingly segmenting a plurality of sub-regions in each frame of face image; determining standard pulse wave signals of each sub-area by utilizing the photoplethysmography; obtaining a blood flow intensity characteristic value of each sub-area according to the standard pulse wave signals of each sub-area; obtaining facial blood flow distribution according to the blood flow intensity characteristic value of each subregion; and sliding a set time window by a set sliding length, and repeating the steps to obtain the facial dynamic blood flow distribution. The invention does not need to contact with the person to be tested, does not cause damage, and is convenient and quick and has high precision.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a method for detecting facial dynamic blood flow distribution according to the present invention;
FIG. 2 is a diagram illustrating the effect of segmenting sub-regions according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a non-contact, convenient and quick facial dynamic blood flow distribution detection method.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a flowchart of a method for detecting facial dynamic blood flow distribution according to the present invention, and as shown in fig. 1, the present invention discloses a method for detecting facial dynamic blood flow distribution, including:
s1, acquiring a facial area video of the person to be detected in the set time window; the face region video includes a plurality of frames of color mode RGB images; the face area video is acquired through a mobile phone camera or high-speed acquisition equipment. The high-speed acquisition equipment is a Charge Coupled Device (CCD) or a Complementary Metal Oxide Semiconductor (CMOS).
And S2, preprocessing each frame of the color mode RGB image to obtain a plurality of frames of face images.
Specifically, the S2 includes:
s21, carrying out binarization processing on the color mode RGB image of the ith frame to obtain a binary image corresponding to the color mode RGB image of the ith frame; wherein i ∈ n, n is the total frame number of the color mode RGB image.
S22, performing expansion processing on the binary image using circular structural elements having a size of 30 × 30 pixels to obtain an expanded image.
And S23, taking the expansion image as a mask template, performing mask operation with the color mode RGB image of the ith frame, and removing a background area to obtain the face image.
S3, determining a Region of interest (ROI) in a certain frame of the face image, tracking in each frame of the face image, and determining the standard heart rate of the ROI through remote photoplethysmography;
as an alternative embodiment, the S3 of the present invention includes:
s31, determining ROI in the face image of the mth frame, and tracking in each frame of the face image to obtain pixel values of each channel in the ROI; where m is equal to n, and n is the total frame number of the color mode RGB image.
Specifically, in this embodiment, 68 face key points are detected for the face image of the mth frame, eyebrow, eye, nose, mouth, and cheek contours are located, and the 68 key points are numbered; taking the 29 th key point as the central point of the ROI; taking half of the distance between the 1 st and 15 th keypoints as the width of the ROI; taking the distance between the 28 th key point and the 29 th key point as the height of the ROI; determining the starting coordinate and the ending coordinate of the ROI according to the central point, the width and the height of the ROI so as to position the ROI; and performing the ROI positioning on each frame of the face image so as to track the ROI.
And S32, averaging the pixel values of each channel in the ROI to obtain a pixel average value.
And S33, determining the initial pulse wave signal of each channel according to the pixel average value of each channel.
And S34, filtering the initial pulse wave signals of each channel to obtain filtered pulse wave signals of each channel. Specifically, a band-pass filter of 0.75-4Hz is selected to carry out filtering processing on the initial pulse wave signal; so as to remove the baseline drift phenomenon caused by factors such as respiratory respiration and the like.
And S35, selecting data corresponding to a certain channel as a standard pulse wave signal of the ROI according to a principal component analysis method or an independent component analysis method.
In this embodiment, when the principal component analysis method is adopted, data of a channel corresponding to a maximum eigenvalue is selected as a standard pulse wave signal of the ROI; when the independent component analysis method is adopted, the data of the channel with the maximum data correlation with the green channel is selected as the standard pulse wave signal of the ROI.
The data is data of each first filtered pulse wave signal corresponding to the ROI after principal component analysis or independent component analysis.
And S36, performing fast Fourier transform on the standard pulse wave signal of the ROI to obtain a power spectrum amplitude and a frequency corresponding to the power spectrum amplitude.
And S37, selecting the frequency corresponding to the maximum power spectrum amplitude as the standard heart rate of the ROI.
S4, correspondingly segmenting a plurality of sub-regions in each frame of the face image; and determining standard pulse wave signals of each sub-area by using remote photoplethysmography.
As an alternative embodiment, the S4 of the present invention includes:
and S41, correspondingly dividing a plurality of sub-regions in each frame of the face image according to the set dividing side length. In this embodiment, a size of 30 × 30 is selected for segmentation, and the segmentation result is shown in fig. 2.
S42, comparing the pixel value of each sub-area with a set pixel threshold value, wherein the sub-area which is larger than or equal to the pixel threshold value is defined as an active detector, and the sub-area which is smaller than the pixel threshold value is defined as an inactive detector; and the standard pulse wave signal and the blood flow intensity characteristic value corresponding to the invalid detector are both defined as 0. In this embodiment, the set pixel threshold value is 25.
The method for obtaining the standard pulse wave signal of each effective detector is the same as the method for obtaining the standard pulse wave signal of the ROI, and is not described in detail herein.
And S5, obtaining the blood flow intensity characteristic value of each sub-area according to the standard pulse wave signal of each sub-area.
Specifically, the S5 specifically includes:
s51, carrying out fast Fourier transform on the standard pulse wave signal of the q-th effective detector to obtain a power spectrum amplitude; where q ∈ t, t is the total number of active detectors.
And S52, selecting the power spectrum amplitude corresponding to the standard heart rate as an initial characteristic value.
And S53, averaging the initial characteristic value and the power spectrum amplitude values on both sides of the initial characteristic value to be used as the blood flow intensity characteristic value of the effective detector.
S6, obtaining facial blood flow distribution according to the blood flow intensity characteristic value of each sub-region; sliding the set time window by a set sliding length, and returning to S1 to obtain the dynamic blood flow distribution of the face; the set sliding length is less than the length of the set time window.
Preferably, the S6 specifically includes:
s61, restoring the blood flow intensity feature values corresponding to the sub-regions according to the spatial positions before the segmentation.
And S62, performing smoothing operation on each restored blood flow intensity characteristic value to obtain the facial blood flow distribution.
And S63, sliding the set time window by the set sliding length, and returning to S1 to obtain the dynamic blood flow distribution of the face.
In this embodiment, the length of the set time window is 30s, and the sliding length is 1 s.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (8)
1. A facial dynamic blood flow distribution detection method is characterized by comprising the following steps:
s1, acquiring a facial area video of the person to be detected in the set time window; the face region video includes a plurality of frames of color mode RGB images;
s2, preprocessing each frame of the color mode RGB image to obtain a plurality of frames of face images;
s3, determining ROI in a certain frame of the face image, tracking in each frame of the face image, and determining the standard heart rate of the ROI through remote photoplethysmography;
s4, correspondingly segmenting a plurality of sub-regions in each frame of the face image; determining a standard pulse wave signal of each sub-area by using remote photoplethysmography;
s5, obtaining a blood flow intensity characteristic value of each sub-area according to the standard pulse wave signals of each sub-area;
s6, obtaining facial blood flow distribution according to the blood flow intensity characteristic value of each sub-region; sliding the set time window by a set sliding length, and returning to S1 to obtain the dynamic blood flow distribution of the face; the set sliding length is less than the length of the set time window.
2. The method according to claim 1, wherein the step S2 specifically includes:
s21, carrying out binarization processing on the color mode RGB image of the ith frame to obtain a binary image corresponding to the color mode RGB image of the ith frame; wherein i belongs to n, and n is the total frame number of the color mode RGB image;
s22, performing expansion processing on the binary image to obtain an expanded image;
and S23, taking the expansion image as a mask template, and performing mask operation on the expansion image and the corresponding color mode RGB image of the ith frame to obtain the face image.
3. The method for detecting facial dynamic blood flow distribution according to claim 1 or 2, wherein the step S3 specifically includes:
s31, determining ROI in the face image of the mth frame, and tracking in each frame of the face image to obtain pixel values of each channel in the ROI; wherein m belongs to n, and n is the total frame number of the color mode RGB image;
s32, averaging the pixel values of each channel in the ROI to obtain a first pixel average value;
s33, determining a first initial pulse wave signal of each channel according to the first pixel average value of each channel;
s34, filtering the first initial pulse wave signals of each channel to obtain first filtered pulse wave signals of each channel;
s35, selecting data corresponding to a certain channel as a standard pulse wave signal of the ROI according to a principal component analysis method or an independent component analysis method; the data is data of each first filtering pulse wave signal corresponding to the ROI after principal component analysis or independent component analysis;
s36, performing fast Fourier transform on the standard pulse wave signal of the ROI to obtain a first power spectrum amplitude and a frequency corresponding to the first power spectrum amplitude;
and S37, selecting the frequency corresponding to the maximum first power spectrum amplitude as the standard heart rate of the ROI.
4. The method for detecting facial dynamic blood flow distribution according to claim 1 or 2, wherein the step S4 specifically includes:
s41, correspondingly dividing a plurality of sub-regions in each frame of the face image according to the set dividing side length;
s42, comparing the pixel value of each sub-area with a set pixel threshold value, wherein the sub-area which is larger than or equal to the pixel threshold value is defined as an active detector, and the sub-area which is smaller than the pixel threshold value is defined as an inactive detector; the standard pulse wave signal and the blood flow intensity characteristic value corresponding to the invalid detector are both defined as 0;
s43, averaging the pixel values of each channel in the ith effective detector to obtain a second pixel average value; wherein l belongs to h, and h is the total number of effective detectors;
s44, determining a second initial pulse wave signal of each channel according to the second pixel average value of each channel;
s45, filtering the second initial pulse wave signals of each channel to obtain second filtered pulse wave signals of each channel;
s46, selecting data corresponding to a certain channel as a standard pulse wave signal of the effective detector according to a principal component analysis method or an independent component analysis method; the data is obtained after the second filtered pulse wave signals corresponding to the effective detector are subjected to principal component analysis or independent component analysis.
5. The method for detecting facial dynamic blood flow distribution according to claim 4, wherein the step S5 specifically comprises:
s51, carrying out fast Fourier transform on the standard pulse wave signal of the q-th effective detector to obtain a second power spectrum amplitude; wherein q is the t, and t is the total number of effective detectors;
s52, selecting the second power spectrum amplitude corresponding to the standard heart rate as an initial characteristic value;
and S53, averaging the initial characteristic value and the second power spectrum amplitude values on both sides of the initial characteristic value to be used as the blood flow intensity characteristic value of the effective detector.
6. The method for detecting facial dynamic blood flow distribution according to claim 4, wherein the step S6 specifically comprises:
s61, restoring the blood flow intensity characteristic value corresponding to each sub-region according to the space position before segmentation;
s62, smoothing each restored blood flow intensity characteristic value to obtain the facial blood flow distribution;
and S63, sliding the set time window by the set sliding length, and returning to S1 to obtain the dynamic blood flow distribution of the face.
7. The method for detecting facial dynamic blood flow distribution according to claim 3, wherein the step S35 specifically comprises:
s35, selecting data of a channel corresponding to the maximum characteristic value as a standard pulse wave signal of the ROI by adopting the principal component analysis method; the data is data of each first filtering pulse wave signal corresponding to the ROI after principal component analysis;
or S35, selecting the data of the channel with the maximum data correlation with the green channel as the standard pulse wave signal of the ROI by adopting the independent component analysis method; the data is obtained by analyzing independent components of each first filtered pulse wave signal corresponding to the ROI.
8. The method according to claim 1, wherein the facial region video is obtained by a mobile phone camera or a high-speed acquisition device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010666893.9A CN111797794A (en) | 2020-07-13 | 2020-07-13 | Facial dynamic blood flow distribution detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010666893.9A CN111797794A (en) | 2020-07-13 | 2020-07-13 | Facial dynamic blood flow distribution detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111797794A true CN111797794A (en) | 2020-10-20 |
Family
ID=72808286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010666893.9A Pending CN111797794A (en) | 2020-07-13 | 2020-07-13 | Facial dynamic blood flow distribution detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111797794A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113143264A (en) * | 2021-04-16 | 2021-07-23 | 北京理工大学 | Blood glucose detection area selection device and method based on blood perfusion imaging |
| CN114403837A (en) * | 2022-01-24 | 2022-04-29 | 佛山科学技术学院 | Handheld heart rate detection device and method based on skin microscopic image |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101789078A (en) * | 2010-03-01 | 2010-07-28 | 江西财经大学 | Robust infrared face recognition technology |
| CN103702014A (en) * | 2013-12-31 | 2014-04-02 | 中国科学院深圳先进技术研究院 | Non-contact physiological parameter detection method, system and device |
| CN103793690A (en) * | 2014-01-27 | 2014-05-14 | 天津科技大学 | Human body biotic living body detection method based on subcutaneous bloodstream detection and application |
| CN104138254A (en) * | 2013-05-10 | 2014-11-12 | 天津点康科技有限公司 | Non-contact type automatic heart rate measurement system and measurement method |
| KR20150093036A (en) * | 2014-02-06 | 2015-08-17 | 한국전자통신연구원 | Apparatus for measuring Biometric Information and Method thereof |
| CN105989357A (en) * | 2016-01-18 | 2016-10-05 | 合肥工业大学 | Human face video processing-based heart rate detection method |
| CN106127707A (en) * | 2016-06-23 | 2016-11-16 | 南京大学金陵学院 | A kind of processing method of supersonic blood image |
| CN106491114A (en) * | 2016-10-25 | 2017-03-15 | Tcl集团股份有限公司 | A kind of heart rate detection method and device |
| CN107692997A (en) * | 2017-11-08 | 2018-02-16 | 清华大学 | Heart rate detection method and device |
| CN108968920A (en) * | 2018-07-12 | 2018-12-11 | 维沃移动通信有限公司 | A kind of data detection method and electronic equipment |
| CN109389806A (en) * | 2018-11-08 | 2019-02-26 | 山东大学 | Fatigue driving detection method for early warning, system and medium based on multi-information fusion |
| US20190125197A1 (en) * | 2017-10-31 | 2019-05-02 | Hitachi, Ltd. | Biological Information Detection Apparatus and Biological Information Detection Method |
| CN109700449A (en) * | 2018-08-09 | 2019-05-03 | 阳光学院 | It is a kind of can anti-head proper motion effective heart rate measurement system |
| CN109977930A (en) * | 2019-04-29 | 2019-07-05 | 中国电子信息产业集团有限公司第六研究所 | Method for detecting fatigue driving and device |
| CN110163126A (en) * | 2019-05-06 | 2019-08-23 | 北京华捷艾米科技有限公司 | A kind of biopsy method based on face, device and equipment |
| CN110367950A (en) * | 2019-07-22 | 2019-10-25 | 西安爱特眼动信息科技有限公司 | Contactless physiologic information detection method and system |
| CN110384491A (en) * | 2019-08-21 | 2019-10-29 | 河南科技大学 | A kind of heart rate detection method based on common camera |
| CN111166313A (en) * | 2019-12-26 | 2020-05-19 | 中国电子科技集团公司电子科学研究院 | Heart rate measuring method and device and readable storage medium |
| CN111259895A (en) * | 2020-02-21 | 2020-06-09 | 天津工业大学 | Emotion classification method and system based on facial blood flow distribution |
| CN111260634A (en) * | 2020-01-17 | 2020-06-09 | 天津工业大学 | Facial blood flow distribution extraction method and system |
| US20200214614A1 (en) * | 2019-01-07 | 2020-07-09 | Stmicroelectronics S.R.L. | Image processing method and corresponding system |
-
2020
- 2020-07-13 CN CN202010666893.9A patent/CN111797794A/en active Pending
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101789078A (en) * | 2010-03-01 | 2010-07-28 | 江西财经大学 | Robust infrared face recognition technology |
| CN104138254A (en) * | 2013-05-10 | 2014-11-12 | 天津点康科技有限公司 | Non-contact type automatic heart rate measurement system and measurement method |
| CN103702014A (en) * | 2013-12-31 | 2014-04-02 | 中国科学院深圳先进技术研究院 | Non-contact physiological parameter detection method, system and device |
| CN103793690A (en) * | 2014-01-27 | 2014-05-14 | 天津科技大学 | Human body biotic living body detection method based on subcutaneous bloodstream detection and application |
| KR20150093036A (en) * | 2014-02-06 | 2015-08-17 | 한국전자통신연구원 | Apparatus for measuring Biometric Information and Method thereof |
| CN105989357A (en) * | 2016-01-18 | 2016-10-05 | 合肥工业大学 | Human face video processing-based heart rate detection method |
| CN106127707A (en) * | 2016-06-23 | 2016-11-16 | 南京大学金陵学院 | A kind of processing method of supersonic blood image |
| CN106491114A (en) * | 2016-10-25 | 2017-03-15 | Tcl集团股份有限公司 | A kind of heart rate detection method and device |
| US20190125197A1 (en) * | 2017-10-31 | 2019-05-02 | Hitachi, Ltd. | Biological Information Detection Apparatus and Biological Information Detection Method |
| CN107692997A (en) * | 2017-11-08 | 2018-02-16 | 清华大学 | Heart rate detection method and device |
| CN108968920A (en) * | 2018-07-12 | 2018-12-11 | 维沃移动通信有限公司 | A kind of data detection method and electronic equipment |
| CN109700449A (en) * | 2018-08-09 | 2019-05-03 | 阳光学院 | It is a kind of can anti-head proper motion effective heart rate measurement system |
| CN109389806A (en) * | 2018-11-08 | 2019-02-26 | 山东大学 | Fatigue driving detection method for early warning, system and medium based on multi-information fusion |
| US20200214614A1 (en) * | 2019-01-07 | 2020-07-09 | Stmicroelectronics S.R.L. | Image processing method and corresponding system |
| CN109977930A (en) * | 2019-04-29 | 2019-07-05 | 中国电子信息产业集团有限公司第六研究所 | Method for detecting fatigue driving and device |
| CN110163126A (en) * | 2019-05-06 | 2019-08-23 | 北京华捷艾米科技有限公司 | A kind of biopsy method based on face, device and equipment |
| CN110367950A (en) * | 2019-07-22 | 2019-10-25 | 西安爱特眼动信息科技有限公司 | Contactless physiologic information detection method and system |
| CN110384491A (en) * | 2019-08-21 | 2019-10-29 | 河南科技大学 | A kind of heart rate detection method based on common camera |
| CN111166313A (en) * | 2019-12-26 | 2020-05-19 | 中国电子科技集团公司电子科学研究院 | Heart rate measuring method and device and readable storage medium |
| CN111260634A (en) * | 2020-01-17 | 2020-06-09 | 天津工业大学 | Facial blood flow distribution extraction method and system |
| CN111259895A (en) * | 2020-02-21 | 2020-06-09 | 天津工业大学 | Emotion classification method and system based on facial blood flow distribution |
Non-Patent Citations (3)
| Title |
|---|
| BENJAMIN KOSSACK 等: "Local blood flow analysis and visualization from RGB-video sequences", 《CURRENT DIRECTIONS IN BIOMEDICAL ENGINEERING》, vol. 5, no. 1, pages 373 - 376 * |
| 刘 祎 等: "基于人脸视频的非接触式心率测量方法", 《纳米技术与精密工程》, vol. 14, no. 1, pages 76 - 79 * |
| 汤春明 等: "基于交叉滑动窗口模型算法的非接触心率测量方法", 《天津工业大学学报》, vol. 39, no. 2, pages 54 - 60 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113143264A (en) * | 2021-04-16 | 2021-07-23 | 北京理工大学 | Blood glucose detection area selection device and method based on blood perfusion imaging |
| CN113143264B (en) * | 2021-04-16 | 2023-08-01 | 北京理工大学 | Blood glucose detection area selection method based on blood perfusion imaging |
| CN114403837A (en) * | 2022-01-24 | 2022-04-29 | 佛山科学技术学院 | Handheld heart rate detection device and method based on skin microscopic image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bobbia et al. | Unsupervised skin tissue segmentation for remote photoplethysmography | |
| US9025826B2 (en) | Formation of a time-varying signal representative of at least variations in a value based on pixel values | |
| KR102285999B1 (en) | Heart rate estimation based on facial color variance and micro-movement | |
| CN105989357A (en) | Human face video processing-based heart rate detection method | |
| Bobbia et al. | Remote photoplethysmography based on implicit living skin tissue segmentation | |
| KR102358325B1 (en) | Method and apparatus for measuring robust pulse rate and respiratory rate using face images | |
| Zhao et al. | Performance evaluation of visual object detection and tracking algorithms used in remote photoplethysmography | |
| CN111797794A (en) | Facial dynamic blood flow distribution detection method | |
| CN111938622B (en) | Heart rate detection method, device and system and readable storage medium | |
| Zhu et al. | Fitness heart rate measurement using face videos | |
| Alzahrani et al. | Preprocessing realistic video for contactless heart rate monitoring using video magnification | |
| Kumar et al. | Total variation denoising based approach for R-peak detection in ECG signals | |
| Al-Naji et al. | Contactless cardiac activity detection based on head motion magnification | |
| KR102150635B1 (en) | Method for measuring heart rate based on Vision System | |
| Gupta et al. | Accurate heart-rate estimation from face videos using quality-based fusion | |
| Gwak et al. | Motion-based respiratory rate estimation with motion artifact removal using video of face and upper body | |
| Li et al. | Comparison of region of interest segmentation methods for video-based heart rate measurements | |
| Nikolic-Popovic et al. | Impact of motion artifacts on video-based non-intrusive heart rate measurement | |
| CN114557685B (en) | Non-contact type exercise robust heart rate measurement method and measurement device | |
| Zhao et al. | Remote estimation of heart rate based on multi-scale facial rois | |
| Lin et al. | Step count and pulse rate detection based on the contactless image measurement method | |
| Wang et al. | Camera-based respiration monitoring: Motion and PPG-based measurement | |
| Han et al. | Exploration of the optimal skin-camera distance for facial photoplethysmographic imaging measurement using cameras of different types | |
| Murashov et al. | Detecting events in video sequence of video-EEG monitoring | |
| Ben Salah et al. | Contactless heart rate estimation from facial video using skin detection and multi-resolution analysis |
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 |