CN117557506A - Device and method for detecting infant heart rate with high video precision - Google Patents
Device and method for detecting infant heart rate with high video precision Download PDFInfo
- Publication number
- CN117557506A CN117557506A CN202311401234.2A CN202311401234A CN117557506A CN 117557506 A CN117557506 A CN 117557506A CN 202311401234 A CN202311401234 A CN 202311401234A CN 117557506 A CN117557506 A CN 117557506A
- Authority
- CN
- China
- Prior art keywords
- infant
- heart rate
- detecting
- identified
- module
- 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
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000004297 night vision Effects 0.000 claims abstract description 9
- 238000012935 Averaging Methods 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000003287 optical effect Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 8
- 239000008280 blood Substances 0.000 abstract description 4
- 210000004369 blood Anatomy 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 4
- 238000005070 sampling Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 8
- 230000009471 action Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000000862 absorption spectrum Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- INGWEZCOABYORO-UHFFFAOYSA-N 2-(furan-2-yl)-7-methyl-1h-1,8-naphthyridin-4-one Chemical compound N=1C2=NC(C)=CC=C2C(O)=CC=1C1=CC=CO1 INGWEZCOABYORO-UHFFFAOYSA-N 0.000 description 1
- 108010054147 Hemoglobins Proteins 0.000 description 1
- 102000001554 Hemoglobins Human genes 0.000 description 1
- 108010064719 Oxyhemoglobins Proteins 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 108010002255 deoxyhemoglobin Proteins 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
Classifications
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/143—Sensing or illuminating at different wavelengths
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
-
- 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
- G06V40/168—Feature extraction; Face representation
-
- 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
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Medical Informatics (AREA)
- Human Computer Interaction (AREA)
- Cardiology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The invention discloses a device and a method for detecting infant heart rate with high precision by video, comprising the following steps: s1: carrying out feature point identification on the face of the infant by using a dl ib algorithm, and selecting 16 feature points with larger centers; s2: after the 16 special selection areas are identified, ensuring that parts which cannot be completely identified are removed within a period of time; s3: the time between every two peaks is a heartbeat time, and the heart rate value of the infant can be obtained by averaging a plurality of continuous heartbeats. According to the invention, the multi-point security feature matching sampling is carried out on the human face, so that the overlarge color change caused by shooting a non-skin area when the size of the human face changes is avoided; the night vision function is added, but the flow of the real blood can be realized only by the infrared ray of 960nm instead of the infrared ray of 850nm in the traditional sense; the filter of the special camera is added to accurately match the infrared effect; multiple fault tolerance judgment is added, and an interference part is eliminated; and can accurately measure the partial face when the partial face is identified.
Description
Technical Field
The invention relates to the technical field of infant heart rate detection, in particular to equipment and a method for detecting infant heart rate with high video precision.
Background
Heart rate is a very important physiological parameter of the human body and can reflect the health level of the human body in time. The most direct way to obtain heart rate is mainly by means of contact sensors, such as electrocardiographs and pulse wave detectors, which can monitor the heart rate and pulse information of the human body very accurately, however they require external hardware devices and direct contact with the skin of the human body to obtain the measured information. These devices are expensive and not easy to carry, and the form of contact detection often brings great burden to the testee, so the detection cost is high, and the real-time detection of the physiological information of the user is not facilitated.
The non-contact heart rate detection device and method based on the face video disclosed by publication No. CN114722869A accurately extracts heart rate signals contained in the face video through methods such as manual data synthesis, deep neural network, face area detection, waveform analysis and the like, combines a coding decoder model with related detection and data analysis technologies, builds a complete detection framework based on deep learning and aiming at non-contact heart rate pulse waves of the face, and develops an algorithm of data synthesis to solve the problem of shortage of face data and labels containing biological characteristics at present, thereby realizing non-contact heart rate pulse wave detection based on the face video and being applicable to clinical diagnosis.
In the prior art, the human face is coarsely processed, and the size change caused by the human face movement can directly influence the result; the existing algorithm cannot measure at night; the characteristics of the software and the hardware are not precisely matched, and the effect is to be improved.
Disclosure of Invention
The invention aims to provide equipment and a method for detecting the heart rate of an infant with high video precision, which are used for solving the problems in the prior art.
In order to achieve the above purpose, the present invention provides the following technical solutions: a device and a method for detecting the heart rate of an infant with high video precision comprise the following steps:
s1: carrying out feature point identification on the face of the infant by using a dl ib algorithm, and selecting 16 feature points with larger centers;
s2: after the 16 special selection areas are identified, ensuring that parts which cannot be completely identified are removed within a period of time;
s3: the time between every two peaks is a heartbeat time, and the heart rate value of the infant can be obtained by averaging a plurality of continuous heartbeats.
Preferably, the time guaranteed in S2 is 30S.
Preferably, in the step S2, a part with the AC/DC smaller than 1/1000 is removed, and a part with the AC/DC larger than 1/10 is removed.
Preferably, in S2, when the number of the special selection areas is less than 3, no calculation is performed.
The device for detecting the heart rate of the infant by using the video with high precision comprises an acquisition module, a night vision module, a characteristic matching module and a fault tolerance module;
the acquisition module is used for acquiring the video of the person;
the night vision module is used for providing assistance for the acquisition module to clearly acquire video in an environment with dark light;
the feature matching module performs feature point identification, and selects 16 feature points with larger centers;
the fault-tolerant module is used for eliminating an interference part; and the partial face can be accurately measured after being identified.
Preferably, the acquisition module comprises a camera and an optical filter.
Compared with the prior art, the invention has the beneficial effects that:
1. the feature point recognition is carried out on the face of the baby by using a dl ib algorithm, 68 (0-67) edge recognition points of different original algorithms are adopted, and 16 (A-P) feature points with larger centers are selected to avoid the use of different interference items for expression or action;
2. the multi-point security feature matching sampling is carried out on the human face, so that the situation that the color change is overlarge due to the fact that a non-skin area is shot when the size of the human face changes is avoided;
3. the night vision function is added, but the flow of the real blood can be realized only by the infrared ray of 960nm instead of the infrared ray of 850nm in the traditional sense;
4. the filter of the special camera is added to accurately match the infrared effect;
5. multiple fault tolerance judgment is added, and an interference part is eliminated; and can accurately measure the partial face when the partial face is identified.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is an absorption spectrum of the present invention;
FIG. 2 is a filter band diagram of the present invention;
FIG. 3 is a feature point identification map of the present invention;
FIG. 4 is a graph of the total luminance change of the selected area according to the present invention;
fig. 5 is a flow chart of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention.
Referring to fig. 1-5, in an embodiment of the present invention, a device and a method for detecting a heart rate of an infant with high video accuracy, including the following steps:
s1: carrying out feature point identification on the face of the infant by using a dl ib algorithm, and selecting 16 feature points with larger centers;
s2: after the 16 special selection areas are identified, ensuring that parts which cannot be completely identified are removed within a period of time;
s3: the time between every two peaks is a heartbeat time, and the heart rate value of the infant can be obtained by averaging a plurality of continuous heartbeats.
Preferably, the time guaranteed in S2 is 30S.
Preferably, in the step S2, a part with the AC/DC smaller than 1/1000 is removed, and a part with the AC/DC larger than 1/10 is removed.
Preferably, in S2, when the number of the special selection areas is less than 3, no calculation is performed.
The device for detecting the heart rate of the infant by using the video with high precision comprises an acquisition module, a night vision module, a characteristic matching module and a fault tolerance module;
the acquisition module is used for acquiring the video of the person;
the night vision module is used for providing assistance for the acquisition module to clearly acquire video in an environment with dark light;
the feature matching module performs feature point identification, and selects 16 feature points with larger centers;
the fault-tolerant module is used for eliminating an interference part; and the partial face can be accurately measured after being identified.
Preferably, the acquisition module comprises a camera and an optical filter.
The multi-point security feature matching sampling is carried out on the human face, so that the situation that the color change is overlarge due to the fact that a non-skin area is shot when the size of the human face changes is avoided; the night vision function is added, but the flow of the real blood can be realized only by the infrared ray of 960nm instead of the infrared ray of 850nm in the traditional sense; the filter of the special camera is added to accurately match the infrared effect; multiple fault tolerance judgment is added, and an interference part is eliminated; and can accurately measure the partial face when the partial face is identified.
Variations in the hemoglobin content of blood during the human cardiac cycle can result in minor changes in skin color, and by analyzing this feature, the human heart rate is analyzed. The color change is mainly caused by Hb (deoxyhemoglobin absorbs much light at 950nm and less light at 700 nm) and HbO 2 (oxyhemoglobin absorbs much more red light at 700nm, forInfrared 950nm absorption is less); their absorption spectra are shown in FIG. 1.
The 700nm is just in the red light sensitive area in the visible light RGB, which is suitable for color photographing when the light is strong in daytime; and obtaining 950nm graph is suitable for photographing at night or when light is weak, the 850nm LED commonly used in the market is changed into 950nm LED, and the filtering curve of the filter is changed from the common filter to the filtering band of FIG. 2. The filter is optional, the picture is not colored by the filter, the perception of a person is only influenced, and the algorithm identification is not greatly influenced.
The dl ib algorithm is used for identifying feature points of the face of the baby, but 68 (0-67) edge identification points of the original algorithm are different, and 16 (A-P) feature points with larger centers are selected to avoid using different interference items for expression or action, as shown in figure 3.
After the 16 special selection areas are identified, ensuring that the parts which cannot be completely identified are removed within a period of time (preferably 30 s); removing the part with the AC/DC less than 1/1000 (obtained according to the neural network test), removing the part with the AC/DC more than 1/10 (obtained according to the neural network test), wherein the error caused by excessive action or excessive light change is removed, and when the number of the specially selected areas is less than 3, no calculation is performed; the total brightness change of each special selection area is shown in fig. 4, wherein the time between every two peaks is one heartbeat time, and the average value of a plurality of continuous heartbeats is calculated, so that the heart rate value of the infant can be obtained; (wherein Red represents 700nm Red light, and IR represents 950nm infrared light).
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. A method for detecting the heart rate of an infant with high video precision, which is characterized by comprising the following steps of: the method comprises the following steps:
s1: the method comprises the steps of performing feature point identification on the face of an infant by using a dlib algorithm, and selecting 16 feature points with larger centers;
s2: after the 16 special selection areas are identified, ensuring that parts which cannot be completely identified are removed within a period of time;
s3: the time between every two peaks is a heartbeat time, and the heart rate value of the infant can be obtained by averaging a plurality of continuous heartbeats.
2. The method for detecting the heart rate of the infant with high video precision according to claim 1, wherein the method comprises the following steps of: the guaranteed time in the step S2 is 30S.
3. The method for detecting the heart rate of the infant with high video precision according to claim 1, wherein the method comprises the following steps of: and removing the part with the AC/DC smaller than 1/1000 in the step S2, and removing the part with the AC/DC larger than 1/10.
4. The method for detecting the heart rate of the infant with high video precision according to claim 1, wherein the method comprises the following steps of: and in the step S2, when the number of the special selection areas is less than 3, no calculation is performed.
5. A device for detecting the heart rate of an infant with high video precision, which is characterized in that: the device comprises an acquisition module, a night vision module, a characteristic matching module and a fault tolerance module;
the acquisition module is used for acquiring the video of the person;
the night vision module is used for providing assistance for the acquisition module to clearly acquire video in an environment with dark light;
the feature matching module performs feature point identification, and selects 16 feature points with larger centers;
the fault-tolerant module is used for eliminating an interference part; and the partial face can be accurately measured after being identified.
6. The apparatus and method for detecting infant heart rate with high accuracy by video according to claim 5, wherein: the acquisition module comprises a camera and an optical filter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311401234.2A CN117557506A (en) | 2023-10-26 | 2023-10-26 | Device and method for detecting infant heart rate with high video precision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311401234.2A CN117557506A (en) | 2023-10-26 | 2023-10-26 | Device and method for detecting infant heart rate with high video precision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117557506A true CN117557506A (en) | 2024-02-13 |
Family
ID=89817563
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311401234.2A Pending CN117557506A (en) | 2023-10-26 | 2023-10-26 | Device and method for detecting infant heart rate with high video precision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117557506A (en) |
-
2023
- 2023-10-26 CN CN202311401234.2A patent/CN117557506A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sanyal et al. | Algorithms for monitoring heart rate and respiratory rate from the video of a user’s face | |
| CN106580301B (en) | A kind of monitoring method of physiological parameter, device and handheld device | |
| US10004410B2 (en) | System and methods for measuring physiological parameters | |
| RU2675036C2 (en) | Device and method for obtaining information about vital signs of subject | |
| EP2973394B1 (en) | Device and method for determining the blood oxygen saturation of a subject | |
| EP3052008B1 (en) | Improved signal selection for obtaining a remote photoplethysmographic waveform | |
| McDuff et al. | Fusing partial camera signals for noncontact pulse rate variability measurement | |
| CN105813564A (en) | Device and method for determining vital signs of a subject | |
| CN106236049A (en) | Blood pressure measuring method based on video image | |
| Fan et al. | Non-contact remote estimation of cardiovascular parameters | |
| CN106456071A (en) | Device, system and method for determining the concentration of a substance in the blood of a subject | |
| US20220039678A1 (en) | Device, system and method for obtaining a vital signal of a subject | |
| CN112890792A (en) | Cloud computing cardiovascular health monitoring system and method based on network camera | |
| CN112233813A (en) | Non-contact non-invasive heart rate and respiration measurement method and system based on PPG | |
| Sahindrakar et al. | Improving motion robustness of contact-less monitoring of heart rate using video analysis | |
| CN112294282A (en) | Self-calibration method of emotion detection device based on RPPG | |
| Zeng et al. | Infrared video based non-invasive heart rate measurement | |
| Nikolaiev et al. | Non-contact video-based remote photoplethysmography for human stress detection | |
| CN113576475B (en) | Deep learning-based contactless blood glucose measurement method | |
| Sahin et al. | Non-contact heart rate monitoring from face video utilizing color intensity | |
| JP7132568B2 (en) | Biological information measuring device and biological information measuring method | |
| CN114271800B (en) | Non-invasive continuous blood pressure monitoring method and application in office environment | |
| Zhu et al. | Non-contact detection of cardiac rate based on visible light imaging device | |
| CN117557506A (en) | Device and method for detecting infant heart rate with high video precision | |
| 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 |