CN113892930B - Facial heart rate measuring method and device based on multi-scale heart rate signals - Google Patents
Facial heart rate measuring method and device based on multi-scale heart rate signals Download PDFInfo
- Publication number
- CN113892930B CN113892930B CN202111504748.1A CN202111504748A CN113892930B CN 113892930 B CN113892930 B CN 113892930B CN 202111504748 A CN202111504748 A CN 202111504748A CN 113892930 B CN113892930 B CN 113892930B
- Authority
- CN
- China
- Prior art keywords
- heart rate
- feature extraction
- extraction module
- facial
- video stream
- 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.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Abstract
The invention discloses a facial heart rate measuring method based on multi-scale heart rate signals. The method comprises the steps of carrying out skin segmentation on a video stream containing a face area frame by frame, training a feature extraction module, inputting the face video stream into the trained feature extraction module, outputting the face video stream into a plurality of heart rate values, and averaging all the output heart rate values to obtain a final heart rate predicted value. The method can obtain a high-precision heart rate estimation value and realize non-contact heart rate detection.
Description
Technical Field
The invention relates to the field of non-contact physiological signal detection, in particular to a method and a device for measuring a facial heart rate based on a multi-scale heart rate.
Background
The heart rate is one of important physiological parameters of a human body and can directly and effectively reflect the health state of the human body, so that the heart rate monitoring plays an irreplaceable role in monitoring the health of the human body. Cardiovascular diseases seriously jeopardize life and health, so how to prevent and detect cardiovascular diseases is a problem which is increasingly needed to be solved in China, wherein the long-term continuous monitoring of the heart rate fluctuation of a human body plays a crucial role in the fields of clinical medical treatment, health management and the like.
At present, heart rate detection methods are various, and contact type heart rate detection and non-contact type heart rate detection can be performed according to whether the heart rate detection method is in contact with a human body or not.
The contact heart rate detection mainly depends on a sensor, an electrode and the like which are in direct or indirect contact with a human body to acquire related information, and the use range of the contact heart rate detection has certain limitation due to the restriction and condition limitation of the contact heart rate detection on a detected object.
The non-contact mode does not need to contact with the human body when detecting the heart rate, so that the discomfort of the human body can not be caused in the detection process, and continuous and long-time non-invasive detection can be realized. At present, the mainstream heart rate monitoring mode is mainly contact type, but certain inconvenience and discomfort are caused to a measurer due to the fact that the heart rate monitoring mode is complex to operate and needs to be in contact with the skin of a human body for a long time in the detection process.
In recent years, the non-contact human cardiovascular system physiological parameter acquisition benefits from the development of integrated circuits, microelectronic technologies, imaging technologies and signal processing technologies in recent years, and has also been technically innovated. In particular, new modes based on video, which can more efficiently achieve contactless sensing, are receiving more extensive attention. Compared with the traditional measurement mode, the technology has the main advantages that the non-inductive measurement can be realized, the measurement cost is low, and the measurement can be carried out by using a common network camera or a mobile phone camera. The main principle of the method is based on the measurement of the PPG signal. The PPG signal is that the blood and other tissue components have different light absorption degrees in different frequency bands, and the volume of blood in blood vessels changes with the pulsation of the heart, so in the process of cardiac contraction and relaxation, the absorption amount of blood to light shows periodic pulse fluctuation with the cardiac contraction, and the fluctuation reflects the change of the signal received by the video sensor, namely the PPG signal. There are very few current methods and related applications for calculating facial heart rate values based on PPG signals.
Disclosure of Invention
The invention aims to provide a non-contact facial heart rate measuring method based on multi-scale heart rate signals by utilizing signal characteristics of facial skin, which helps people to prevent diseases and manage self health.
The purpose of the invention is realized by the following technical scheme: a facial heart rate measurement method based on a multi-scale heart rate signal comprises the following steps:
s11, respectively scaling each frame in the video stream containing the face region to 320 × 320-1080 × 1080 pixel size, performing skin segmentation frame by frame, and outputting a corresponding face skin image; arranging the output human face skin images according to the time sequence, and fusing the human face skin images into a video stream only containing the facial skin;
s12, converting the video stream only containing facial skin into a three-dimensional signal matrix set;
s13, training the feature extraction module by sequentially using a public data set CIFAR10, a three-dimensional signal matrix set and newly acquired human face video stream until a loss function MSE is less than 1 bpm;
s14, the human face video stream is collected again and input into the trained feature extraction module, a plurality of heart rate values are output, all the output heart rate values are averaged, and a final heart rate predicted value is obtained.
Further, step S12 includes the following sub-steps:
s121, dividing a video stream only containing facial skin into n non-overlapping time segments, and dividing each frame in the time segments into non-overlapping pixel small blocks;
s122, respectively converting the pixel small blocks from an RGB color gamut into a YUV color gamut; respectively calculating the average values of three components of all pixel points Y, U, V on the pixel small block to obtain a three-dimensional signal matrix;
s123 performs the operation of step S122 on each frame of the n time slices, respectively, to obtain a three-dimensional signal matrix set.
Furthermore, the feature extraction module comprises a multi-scale feature fusion part, an automatic coding and decoding part and an LSTM time fusion part which are sequentially connected.
Further, step S13 includes the following sub-steps:
s131, after each image of a public data set CIFAR10 is zoomed to 320 x 320-;
s132, inputting the three-dimensional signal matrix set obtained in the step S12 into the feature extraction module trained in the step S131, continuing to train the feature extraction module, minimizing a loss function MSE by using a gradient descent method, and storing the training result of the feature extraction module again;
s133, inputting the newly acquired human face video stream into the feature extraction module trained in the step S132, continuing to train the feature extraction module, and finishing the training of the feature extraction module when the loss function MSE is less than 1 bpm.
A facial heart rate measuring device based on multi-scale heart rate signals comprises one or more processors and is used for realizing the facial heart rate measuring method based on the multi-scale heart rate signals.
A computer readable storage medium having stored thereon a program for implementing the above-mentioned method of facial heart rate measurement based on multi-scale heart rate signals, when the program is executed by a processor.
Compared with the prior art, the invention has the following beneficial effects: firstly, the facial heart rate measuring method of the invention uses three different data to train the feature extraction module in the training stage, and the training on the CIFAR data set for the first time enables the model to have better generalization capability; training by using the three-dimensional signal matrix set for the second time, so that the feature extraction module can fully understand the input pulse wave signals; thirdly, a newly acquired human face video stream is used for training a feature extraction module, so that real data can be accurately understood; in addition, the feature extraction module extracts the input signal features from different scales, and guarantees the accuracy of the final heart rate calculation, so that the facial heart rate measurement method is high in measurement accuracy. Secondly, the deep learning-based feature extraction module is used, so that different environments such as illumination change and head movement can be adapted.
Drawings
Fig. 1 is a schematic flowchart of a method for measuring a facial heart rate based on a multi-scale heart rate signal according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a multi-scale feature fusion part of a heart rate calculation network according to the present invention;
FIG. 3 is a schematic diagram of a training process in the feature extraction module of the present invention;
fig. 4 is a block diagram of a facial heart rate measurement device based on a multi-scale heart rate signal according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
The following describes the method and apparatus for measuring facial heart rate based on multi-scale heart rate in detail with reference to the accompanying drawings. The features of the following examples and embodiments may be combined with each other without conflict.
The invention provides a facial heart rate measuring method based on multi-scale heart rate signals, which comprises the following steps as shown in figure 1:
s11, respectively scaling each frame in the video stream containing the face region to 320 × 320-1080 × 1080 pixel size, then performing skin segmentation frame by frame, and finally outputting a corresponding face skin image; arranging the output human face skin images according to the time sequence, and fusing the human face skin images into a video stream only containing the facial skin;
s12 converting a video stream containing only facial skin into a set of three-dimensional signal matrices, comprising the sub-steps of:
s121, dividing a video stream only containing facial skin into n non-overlapping time segments, and dividing each frame in the time segments into non-overlapping pixel small blocks;
s122, respectively converting the small pixel blocks from an RGB color gamut into a YUV color gamut; then, the average values of three components of Y, U, V pixel points on the pixel small blocks are respectively calculated, and a three-dimensional signal matrix is obtained;
s123, respectively carrying out the operation of the step S122 on each frame in the n time slices to obtain a three-dimensional signal matrix set; the three-dimensional signal matrix set is obtained by:
wherein the content of the first and second substances,t is a certain moment in time in the time period,
in order to simulate the heart rate frequency,
in order to simulate the breathing frequency of a patient,
，
to simulate the phase of the heart rate signal and the respiration signal,M 1 andM 2 respectively a simulated heart rate and a simulated breathing intensity,
in the form of a step-like signal,t 1 andt 2 respectively, the threshold value of the step signal,
the gaussian signals with different mean and standard deviation respectively are used as noise so as to enrich the diversity of the synthesized signal.
S13, training a feature extraction module, wherein the feature extraction module comprises a multi-scale feature fusion part, an automatic coding and decoding part and an LSTM time fusion part which are sequentially connected, and the training process comprises the following substeps:
s131, after each image of a public data set CIFAR10 is zoomed to 320 x 320-; the public data set CIFAR10 is used for training the feature extraction module mainly for training the classification capability of the feature extraction module.
S132, in order to enable the feature extraction module to have the function of distinguishing frequency domain information of different signals so as to find out a corresponding frequency band related to the heart rate; inputting the three-dimensional signal matrix set obtained in step S12 into the feature extraction module trained in step S131 for training, wherein the specific process is as shown in fig. 2-3, and in the multi-scale feature fusion part, based on the convolutional neural network, inputting the three-dimensional signal matrix into the multi-scale feature fusion part for multi-scale feature extraction through four convolution kernels with different sizes, namely 1 × 1, 1 × 2, 1 × 4 and 1 × 8, and respectively fusing the features under different scales into a feature map; the automatic coding and decoding part comprises a coder and a decoder based on a convolutional neural network, the fused feature maps are input into the automatic coding and decoding part, the feature maps are arranged according to a time sequence, the well-ordered feature maps are input into the LSTM time fusion part for LSTM time fusion, a plurality of heart rate values are output, simultaneously, a gradient descent method is utilized to minimize a loss function MSE, and the training result of the feature extraction module is stored again; after training, the convolutional neural network in the feature extraction module has the capability of identifying the frequency corresponding to the heart rate and can overcome the interference of the respiratory rate on the heart rate calculation.
S133, inputting the newly acquired human face video stream into the feature extraction module trained in the step S132, continuing to train the feature extraction module, and finishing the training of the feature extraction module when the loss function MSE is less than 1 bpm.
S14, the human face video stream is collected again and input into the trained feature extraction module, a plurality of heart rate values are output, all the output heart rate values are averaged, and a final heart rate predicted value is obtained.
The performance comparison of the facial heart rate measurement method of the invention and the existing heart rate measurement method is shown in table 1, the mean value and the root mean square error RMSE of the facial heart rate measurement method of the invention are 0.4 bpm and 4bpm respectively, which are obviously smaller than those of the other methods, and the measurement accuracy of the method is higher. In addition, the mean square error of the method is smaller than that of other methods, and the method is proved to have smaller dispersion degree.
Table 1: the performance of the facial heart rate measuring method is compared with that of the existing heart rate measuring method
Corresponding to the embodiment of the facial heart rate measuring method based on the multi-scale heart rate signal, the invention also provides an embodiment of a facial heart rate measuring device based on the multi-scale heart rate signal.
Referring to fig. 4, a facial heart rate measurement apparatus based on a multi-scale heart rate signal provided by an embodiment of the present invention includes one or more processors, and is configured to implement the facial heart rate measurement method based on a multi-scale heart rate signal in the foregoing embodiment.
Embodiments of the present facial heart rate measurement apparatus based on multi-scale heart rate signals may be applied to any data processing capable device, such as a computer or other like device or apparatus. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. The software implementation is taken as an example, and as a logical device, the device is formed by reading corresponding computer program instructions in the nonvolatile memory into the memory for running through the processor of any device with data processing capability. From a hardware aspect, as shown in fig. 4, the present invention is a hardware structure diagram of any device with data processing capability where the facial heart rate measurement apparatus based on multi-scale heart rate signals is located, except for the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 4, any device with data processing capability where the apparatus is located in the embodiment may also include other hardware according to the actual function of the any device with data processing capability, which is not described again.
The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the invention. One of ordinary skill in the art can understand and implement it without inventive effort.
Embodiments of the present invention further provide a computer-readable storage medium, on which a program is stored, and when the program is executed by a processor, the method for measuring a facial heart rate based on a multi-scale heart rate signal in the above embodiments is implemented.
The computer readable storage medium may be an internal storage unit, such as a hard disk or a memory, of any data processing capability device described in any of the foregoing embodiments. The computer readable storage medium can be any device with data processing capability, such as a plug-in hard disk, a Smart Media Card (SMC), an SD Card, a Flash memory Card (Flash Card), etc. provided on the device. Further, the computer readable storage medium may include both an internal storage unit and an external storage device of any data processing capable device. The computer-readable storage medium is used for storing the computer program and other programs and data required by the arbitrary data processing-capable device, and may also be used for temporarily storing data that has been output or is to be output.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (5)
1. A facial heart rate measurement method based on a multi-scale heart rate signal is characterized by comprising the following steps:
s11, respectively scaling each frame in the video stream containing the face region to 320 × 320-1080 × 1080 pixel size, performing skin segmentation frame by frame, and outputting a corresponding face skin image; arranging the output human face skin images according to the time sequence, and fusing the human face skin images into a video stream only containing the facial skin;
s12, converting the video stream only containing facial skin into a three-dimensional signal matrix set;
s13, training the feature extraction module by sequentially using a public data set CIFAR10, a three-dimensional signal matrix set and newly acquired human face video stream until a loss function MSE is less than 1 bpm;
the step S13 includes the following sub-steps:
s131, after each image of a public data set CIFAR10 is zoomed to 320 x 320-;
s132, inputting the three-dimensional signal matrix set obtained in the step S12 into the feature extraction module trained in the step S131, continuing to train the feature extraction module, minimizing a loss function MSE by using a gradient descent method, and storing the training result of the feature extraction module again;
s133, inputting the newly acquired human face video stream into the feature extraction module trained in the step S132, continuing to train the feature extraction module, and finishing training the feature extraction module when the loss function MSE is less than 1 bpm;
s14, the human face video stream is collected again and input into the trained feature extraction module, a plurality of heart rate values are output, all the output heart rate values are averaged, and a final heart rate predicted value is obtained.
2. The method for measuring facial heart rate based on multi-scale heart rate signals according to claim 1, wherein step S12 comprises the following sub-steps:
s121, dividing a video stream only containing facial skin into n non-overlapping time segments, and dividing each frame in the time segments into non-overlapping pixel small blocks;
s122, respectively converting the pixel small blocks from an RGB color gamut into a YUV color gamut; respectively calculating the average values of three components of all pixel points Y, U, V on the pixel small block to obtain a three-dimensional signal matrix;
s123 performs the operation of step S122 on each frame of the n time slices, respectively, to obtain a three-dimensional signal matrix set.
3. The method as claimed in claim 1, wherein the feature extraction module comprises a multi-scale feature fusion part, an automatic coding and decoding part and an LSTM time fusion part which are connected in sequence.
4. A facial heart rate measurement device based on multi-scale heart rate signals, characterized by comprising one or more processors for implementing the method of any one of claims 1-3.
5. A computer-readable storage medium, on which a program is stored which, when being executed by a processor, is adapted to carry out the method of multi-scale heart rate signal based facial heart rate measurement according to any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111504748.1A CN113892930B (en) | 2021-12-10 | 2021-12-10 | Facial heart rate measuring method and device based on multi-scale heart rate signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111504748.1A CN113892930B (en) | 2021-12-10 | 2021-12-10 | Facial heart rate measuring method and device based on multi-scale heart rate signals |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113892930A CN113892930A (en) | 2022-01-07 |
| CN113892930B true CN113892930B (en) | 2022-04-22 |
Family
ID=79025584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111504748.1A Active CN113892930B (en) | 2021-12-10 | 2021-12-10 | Facial heart rate measuring method and device based on multi-scale heart rate signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113892930B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105943013A (en) * | 2016-05-09 | 2016-09-21 | 安徽华米信息科技有限公司 | Heart rate detection method and device, and intelligent wearable device |
| CN105989357A (en) * | 2016-01-18 | 2016-10-05 | 合肥工业大学 | Human face video processing-based heart rate detection method |
| CN107692997A (en) * | 2017-11-08 | 2018-02-16 | 清华大学 | Heart rate detection method and device |
| CN108197595A (en) * | 2018-01-23 | 2018-06-22 | 京东方科技集团股份有限公司 | A kind of method, apparatus, storage medium and computer for obtaining evaluation information |
| CN110236514A (en) * | 2019-07-12 | 2019-09-17 | 华东师范大学 | The real-time heart rate detection method that mode based on video is extracted and median filtering combines |
| CN110269600A (en) * | 2019-08-06 | 2019-09-24 | 合肥工业大学 | Based on polynary empirical mode decomposition and the contactless video heart rate detection method for combining blind source separating |
| CN111597891A (en) * | 2020-04-13 | 2020-08-28 | 浙江工业大学 | Heart rate detection method based on multi-scale video |
| CN111839490A (en) * | 2020-05-26 | 2020-10-30 | 合肥工业大学 | Non-contact heart rate monitoring method and system |
| CN112200162A (en) * | 2020-12-03 | 2021-01-08 | 中国科学院自动化研究所 | Non-contact heart rate measuring method, system and device based on end-to-end network |
| CN112806977A (en) * | 2021-02-05 | 2021-05-18 | 复旦大学 | Physiological parameter measuring method based on multi-scale fusion network |
| CN113573627A (en) * | 2019-01-14 | 2021-10-29 | 运动数据试验室有限公司 | System for measuring heart rate |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170332917A1 (en) * | 2016-05-19 | 2017-11-23 | The Regents Of The University Of California | Non-intrusive portable sleep apnea assessment system |
| CN111626182B (en) * | 2020-05-25 | 2021-03-26 | 浙江大学 | Method and system for accurately detecting human heart rate and facial blood volume based on video |
| CN113688985A (en) * | 2021-07-26 | 2021-11-23 | 浙江大华技术股份有限公司 | Training method of heart rate estimation model, heart rate estimation method and device |
-
2021
- 2021-12-10 CN CN202111504748.1A patent/CN113892930B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105989357A (en) * | 2016-01-18 | 2016-10-05 | 合肥工业大学 | Human face video processing-based heart rate detection method |
| CN105943013A (en) * | 2016-05-09 | 2016-09-21 | 安徽华米信息科技有限公司 | Heart rate detection method and device, and intelligent wearable device |
| CN107692997A (en) * | 2017-11-08 | 2018-02-16 | 清华大学 | Heart rate detection method and device |
| CN108197595A (en) * | 2018-01-23 | 2018-06-22 | 京东方科技集团股份有限公司 | A kind of method, apparatus, storage medium and computer for obtaining evaluation information |
| CN113573627A (en) * | 2019-01-14 | 2021-10-29 | 运动数据试验室有限公司 | System for measuring heart rate |
| CN110236514A (en) * | 2019-07-12 | 2019-09-17 | 华东师范大学 | The real-time heart rate detection method that mode based on video is extracted and median filtering combines |
| CN110269600A (en) * | 2019-08-06 | 2019-09-24 | 合肥工业大学 | Based on polynary empirical mode decomposition and the contactless video heart rate detection method for combining blind source separating |
| CN111597891A (en) * | 2020-04-13 | 2020-08-28 | 浙江工业大学 | Heart rate detection method based on multi-scale video |
| CN111839490A (en) * | 2020-05-26 | 2020-10-30 | 合肥工业大学 | Non-contact heart rate monitoring method and system |
| CN112200162A (en) * | 2020-12-03 | 2021-01-08 | 中国科学院自动化研究所 | Non-contact heart rate measuring method, system and device based on end-to-end network |
| CN112806977A (en) * | 2021-02-05 | 2021-05-18 | 复旦大学 | Physiological parameter measuring method based on multi-scale fusion network |
Non-Patent Citations (3)
| Title |
|---|
| Video-Based Physiological Measurement Using 3D Central Difference Convolution Attention Network;Yu Zhao et al;《2021 IEEE Internatioanl Joint Conference on Biometrics》;20210407;全文 * |
| 基于卷积神经网络的非接触式视频心率测量方法研究;张森乐;《中国优秀硕士学位论文全文数据库》;20210215;全文 * |
| 基于面部视频的非接触式心率检测研究;万青;《中国优秀硕士学位论文全文数据库》;20200715;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113892930A (en) | 2022-01-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| McDuff et al. | iphys: An open non-contact imaging-based physiological measurement toolbox | |
| Bobbia et al. | Unsupervised skin tissue segmentation for remote photoplethysmography | |
| Gideon et al. | The way to my heart is through contrastive learning: Remote photoplethysmography from unlabelled video | |
| CN109480808A (en) | A kind of heart rate detection method based on PPG, system, equipment and storage medium | |
| Luo et al. | Micro-vessel image segmentation based on the AD-UNet model | |
| CN111728602A (en) | Non-contact blood pressure measuring device based on PPG | |
| US20150092983A1 (en) | Method for calibration free gaze tracking using low cost camera | |
| CN109977858A (en) | A kind of heart rate detection method and device based on image analysis | |
| CN105701331A (en) | Computer-aided diagnosis apparatus and computer-aided diagnosis method | |
| CN110517780A (en) | A kind of aneurysm rupture methods of risk assessment and system | |
| Li et al. | Non-contact ppg signal and heart rate estimation with multi-hierarchical convolutional network | |
| CN111588353A (en) | Body temperature measuring method | |
| Santra et al. | A non-invasive approach for estimation of hemoglobin analyzing blood flow in palm | |
| Zheng et al. | Heart rate prediction from facial video with masks using eye location and corrected by convolutional neural networks | |
| Wang et al. | Accurate face alignment and adaptive patch selection for heart rate estimation from videos under realistic scenarios | |
| Szankin et al. | Long distance vital signs monitoring with person identification for smart home solutions | |
| Alnaggar et al. | Video-based real-time monitoring for heart rate and respiration rate | |
| Wei et al. | Remote photoplethysmography and heart rate estimation by dynamic region of interest tracking | |
| Yang et al. | Graph-based denoising for respiration and heart rate estimation during sleep in thermal video | |
| CN108814543B (en) | High-speed video eye shakes appearance system | |
| Wu et al. | Anti-jamming heart rate estimation using a spatial–temporal fusion network | |
| CN113892930B (en) | Facial heart rate measuring method and device based on multi-scale heart rate signals | |
| Liu et al. | Contactless respiratory rate monitoring for icu patients based on unsupervised learning | |
| Deligianni et al. | Patient-specific bronchoscope simulation with pq-space-based 2D/3D registration | |
| CN108903956A (en) | It detects a lie device and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |