CN112716468A - Non-contact heart rate measuring method and device based on three-dimensional convolution network - Google Patents
Non-contact heart rate measuring method and device based on three-dimensional convolution network Download PDFInfo
- Publication number
- CN112716468A CN112716468A CN202011466448.4A CN202011466448A CN112716468A CN 112716468 A CN112716468 A CN 112716468A CN 202011466448 A CN202011466448 A CN 202011466448A CN 112716468 A CN112716468 A CN 112716468A
- Authority
- CN
- China
- Prior art keywords
- heart rate
- face
- region
- determining
- sample
- 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 44
- 238000009532 heart rate measurement Methods 0.000 claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 230000001815 facial effect Effects 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 230000003595 spectral effect Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 abstract description 3
- 230000008921 facial expression Effects 0.000 abstract description 3
- 238000005286 illumination Methods 0.000 abstract description 3
- 238000013186 photoplethysmography Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000002565 electrocardiography Methods 0.000 description 1
- 230000004886 head movement Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002106 pulse oximetry Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—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
- A61B5/02—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
- A61B5/02444—Details of sensor
-
- 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
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
-
- 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
- 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
- G06V40/15—Biometric patterns based on physiological signals, e.g. heartbeat, blood flow
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Animal Behavior & Ethology (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Public Health (AREA)
- Cardiology (AREA)
- Physiology (AREA)
- Veterinary Medicine (AREA)
- Pathology (AREA)
- Data Mining & Analysis (AREA)
- Heart & Thoracic Surgery (AREA)
- General Engineering & Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Psychiatry (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Power Engineering (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Fuzzy Systems (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The invention discloses a non-contact heart rate measuring method and a non-contact heart rate measuring device based on a three-dimensional convolutional network, wherein the method comprises the steps of determining a face region-of-interest sample according to a target video after the target video is received; and determining corresponding heart rate information through a preset algorithm based on the face region of interest sample. The embodiment of the invention determines the area of interest of the face by using the target video, realizes the expansion of data samples, reduces the interference of factors such as illumination, movement, facial expression change and the like, and improves the accuracy of heart rate measurement.
Description
Technical Field
The invention relates to the technical field of heart rate detection, in particular to a non-contact heart rate measuring method and device based on a three-dimensional convolution network.
Background
Heart rate is a key vital sign and can be widely used to assess physical condition, mental stress, etc. of a subject. The heart rate measurement has great application value in many fields, such as health tracking, medical diagnosis, safety inspection, anti-counterfeiting video identification and the like.
Currently reliable high-precision heart rate measurement methods are Electrocardiography (ECG), pulse oximetry, photoplethysmography (PPG), etc. However, these measurement modalities all rely on direct skin contact, limiting the use of the subject in relevant settings. In addition, there are some non-contact heart rate measurement methods such as ultra-wideband radar and laser doppler vibrometry, but these measurement methods are usually costly and expensive.
The non-contact heart rate measurement algorithm of the traditional method is easily interfered by ambient light and movement, so that the robustness is not enough in practical use, and when the ambient light of a tested person changes randomly or periodically, the heart rate measured by the traditional method is not accurate any more. In addition, the performance of the conventional method is greatly affected by the movement of the tested person, such as head movement, speaking and the like.
Disclosure of Invention
The embodiment of the invention provides a non-contact heart rate measuring method and device based on a three-dimensional convolution network, which are used for determining a facial region-of-interest sample by using a target video, realizing expansion of a data sample and solving the problem that the heart rate cannot be accurately measured in a complex environment.
In a first aspect, an embodiment of the present invention provides a non-contact heart rate measurement method based on a three-dimensional convolutional network, including:
after receiving a target video, determining a face interesting area sample according to the target video;
and determining corresponding heart rate information through a preset algorithm based on the face region of interest sample.
Optionally, determining a facial region-of-interest sample according to the target video includes:
carrying out face detection on the image frame of the target video to determine a corresponding face area image;
adjusting the face region image according to preset image parameters to obtain a face region-of-interest image;
and selecting a specified number of face interesting region images from the face interesting region images corresponding to the target video according to a preset rule so as to obtain the face interesting region sample.
Optionally, determining, by a preset algorithm, corresponding heart rate information based on the facial region of interest sample includes:
and determining corresponding heart rate information according to the facial region of interest sample through a preset three-dimensional convolution network and a residual error network.
Optionally, determining, by using a preset three-dimensional convolution and a residual error network, corresponding heart rate information according to the facial region of interest sample includes:
and tracking the PPG peak time of the electrocardio PPG signal output by the three-dimensional convolution through a preset loss function.
Optionally, determining, by using a preset three-dimensional convolution and a residual error network, corresponding heart rate information according to the facial region of interest sample, further includes:
and carrying out identity mapping on the redundant layer corresponding to the residual error network so as to keep the corresponding heart rate characteristic information.
Optionally, after determining corresponding heart rate information through a preset algorithm based on the facial region of interest sample, the method further includes:
and carrying out filtering processing on the heart rate information through a specified filter.
Optionally, after performing filtering processing on the heart rate information by using a specified filter, the method further includes:
and determining a corresponding heart rate value according to the heart rate information after the filtering processing by a power spectral density method.
In a second aspect, an embodiment of the present invention provides a non-contact heart rate measuring apparatus, including:
the face extraction module is used for determining a face interesting region sample according to a target video after the target video is received;
and the data processing module is used for determining corresponding heart rate information through a preset algorithm based on the face interesting region sample.
In a third aspect, the present invention provides a computer readable storage medium storing one or more computer programs, which are executable by one or more processors to implement the aforementioned steps of the non-contact heart rate measurement method based on a three-dimensional convolutional network.
According to the embodiment of the invention, the target video is utilized to determine the facial interesting area sample, so that the data sample is expanded, the interference of factors such as illumination, movement and facial expression change is reduced, and the accuracy of heart rate measurement is improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a basic flow diagram of a first embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an apparatus according to a second embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Example one
A first embodiment of the present invention provides a non-contact heart rate measurement method based on a three-dimensional convolutional network, as shown in fig. 1, including:
s101, receiving a target video;
s102, determining a face region-of-interest sample according to the target video;
s103, determining corresponding heart rate information through a preset algorithm based on the face interesting area sample.
Specifically, the target video referred to in this embodiment may be a front video of a real-time person or a crowd captured by using a camera. Of course, the server may implement the video transmitted remotely, including the front of the person. The specific video capturing or transmitting manner is not limited herein. Extracting a face interesting region sample from the target video, and calculating corresponding heart rate information through a preset algorithm according to the face interesting region sample corresponding to the target video. Therefore, the embodiment of the invention expands the data samples, reduces the interference of factors such as illumination, movement, facial expression change and the like, and improves the accuracy of heart rate measurement.
Optionally, determining a facial region-of-interest sample according to the target video includes:
carrying out face detection on the image frame of the target video to determine a corresponding face area image;
adjusting the face region image according to preset image parameters to obtain a face region-of-interest image;
and selecting a specified number of face interesting region images from the face interesting region images corresponding to the target video according to a preset rule so as to obtain the face interesting region sample.
Specifically, in this embodiment, after acquiring a target video from an image capturing apparatus, preprocessing the target video includes:
in this embodiment, face detection may be performed on each frame of the target video by using an open source kit openface, a specified number of facial feature points of each frame may be reserved, for example, 68 facial feature points may be reserved, and then facial feature point regions below eyes and above a mouth are extracted, so as to determine a corresponding face region image.
Then, the face region image is adjusted according to preset image parameters, in this embodiment, the face region image corresponding to the image frame may be adjusted to be a face region-of-interest image that can be input as a subsequent network model, for example, the face region image may be adjusted to have an image size of 64 × 64, and then when getitem is rewritten in a pytorch, the face region image with the size of 64 × 64 is horizontally flipped.
Then, after the target video is processed, a specified number of face interesting area images are selected from the face interesting area images corresponding to the target video according to a preset rule, so that a face interesting area sample is obtained. For example, in a specific implementation, 128 consecutive frames of all 64 × 64 video frames may be taken as a facial region sample, so as to obtain a sample set size of (1,3,128,64, 64).
Optionally, determining, by a preset algorithm, corresponding heart rate information based on the facial region of interest sample includes:
and determining corresponding heart rate information according to the facial region of interest sample through a preset three-dimensional convolution network and a residual error network.
Specifically, in the present embodiment, a face region-of-interest sample obtained after the preprocessing is subjected to recognition training.
In a specific implementation, a rPPG signal with heart rate information can be extracted from a facial region of interest image of a facial region of interest sample using a three-dimensional convolution and residual network. Since the heart rate can only reflect the characteristics in one time period, the method of the present embodiment uses the facial region-of-interest samples (including 128 frames of facial region-of-interest images) across time as input, thereby including the temporal characteristics and spatial characteristics of the heart rate of the tested person or group of persons.
Optionally, determining, by using a preset three-dimensional convolution and a residual error network, corresponding heart rate information according to the facial region of interest sample includes:
and tracking the PPG peak time of the electrocardio PPG signal output by the three-dimensional convolution through a preset loss function.
Unlike the commonly used loss functions MSE and Cross control, the loss function-pearson correlation coefficient defined by the method of this embodiment can track the occurrence time of each peak of the PPG rather than completely fitting the peak size, thereby reducing the complexity of the non-contact heart rate estimation.
Optionally, determining, by using a preset three-dimensional convolution and a residual error network, corresponding heart rate information according to the facial region of interest sample includes:
and carrying out identity mapping on the redundant layer corresponding to the residual error network so as to keep the corresponding heart rate characteristic information.
In this embodiment, the residual network is used based on the assumption that there are layers containing the most heart rate signals in the network, and many network layers in the deep network are redundant layers. In the embodiment, identity mapping is completed by utilizing the redundant layers, so that the input and the output of the redundant layers passing through the identity layers keep the same characteristics. Thereby ensuring that the residual network does not lose heart rate characteristic information related to heart rate.
Optionally, after determining corresponding heart rate information through a preset algorithm based on the facial region of interest sample, the method further includes:
and carrying out filtering processing on the heart rate information through a specified filter.
Optionally, after performing filtering processing on the heart rate information by using a specified filter, the method further includes:
and determining a corresponding heart rate value according to the heart rate information after the filtering processing by a power spectral density method.
Specifically, in this embodiment, the rPPG signal obtained as described above may be filtered by using a third-order butterworth band pass filter. And then analyzing the filtered rPPG signal by a power spectral density method (PSD) to finally obtain a heart rate value.
In summary, the embodiment of the invention can detect the heart rate of the human body in real time, acquire the facial video of the crowd through the camera equipment, train by using the residual error structure and the three-dimensional convolution model, and extract a plurality of facial feature points by adopting the openface face detection algorithm, thereby expanding the data size and solving the problem that the heart rate cannot be accurately and remotely measured in a complex environment. Meanwhile, the method of the embodiment is also the first method for realizing heart rate detection and analysis by using three-dimensional convolution.
Example two
A second embodiment of the present invention provides a non-contact heart rate measuring device, as shown in fig. 2, including:
the face extraction module is used for determining a face interesting region sample according to a target video after the target video is received;
and the data processing module is used for determining corresponding heart rate information through a preset algorithm based on the face interesting region sample.
Specifically, in this embodiment, the face extraction module may use an open source toolkit openface to perform face detection on each frame, meanwhile, retain 68 facial feature points of each frame, extract a facial feature point region below the eyes and above the mouth, then set the region reshape to 64 × 64, when rewriting getitem in the pitorch, horizontally turn over the video frame with the size of 64 × 64, and finally continuously take 128 frames of all the video frames with the size of 64 × 64 as a face region sample.
The data processing module may extract rPPG signals with heart rate information from the video using a three-dimensional convolution and residual network.
And then the band-pass filtering module is used for carrying out band-pass filtering on the extracted rPPG signal.
And finally, converting the filtered signals into heart rate values by using a PSD algorithm through a heart rate calculation module.
Embodiments of the present invention also provide a computer-readable storage medium, which stores one or more computer programs, where the one or more computer programs are executable by one or more processors to implement the steps of the non-contact heart rate measurement method based on a three-dimensional convolutional network according to the first embodiment.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (9)
1. A non-contact heart rate measuring method based on a three-dimensional convolution network is characterized by comprising the following steps:
after receiving a target video, determining a face interesting area sample according to the target video;
and determining corresponding heart rate information through a preset algorithm based on the face region of interest sample.
2. The three-dimensional convolutional network-based non-contact heart rate measurement method of claim 1, wherein determining facial region-of-interest samples from the target video comprises:
carrying out face detection on the image frame of the target video to determine a corresponding face area image;
adjusting the face region image according to preset image parameters to obtain a face region-of-interest image;
and selecting a specified number of face interesting region images from the face interesting region images corresponding to the target video according to a preset rule so as to obtain the face interesting region sample.
3. The non-contact heart rate measurement method based on the three-dimensional convolutional network as claimed in claim 1, wherein determining the corresponding heart rate information through a preset algorithm based on the facial region of interest sample comprises:
and determining corresponding heart rate information according to the facial region of interest sample through a preset three-dimensional convolution network and a residual error network.
4. The non-contact heart rate measurement method based on the three-dimensional convolution network as claimed in claim 3, wherein determining corresponding heart rate information from the facial region-of-interest sample through a preset three-dimensional convolution and residual error network comprises:
and tracking the PPG peak time of the electrocardio PPG signal output by the three-dimensional convolution through a preset loss function.
5. The non-contact heart rate measurement method based on the three-dimensional convolution network as claimed in claim 4, wherein the corresponding heart rate information is determined from the facial region of interest sample through a preset three-dimensional convolution and residual error network, further comprising:
and carrying out identity mapping on the redundant layer corresponding to the residual error network so as to keep the corresponding heart rate characteristic information.
6. The three-dimensional convolutional network-based non-contact heart rate measurement method of any one of claims 1-5, wherein after determining corresponding heart rate information through a preset algorithm based on the facial region-of-interest sample, the method further comprises:
and carrying out filtering processing on the heart rate information through a specified filter.
7. The three-dimensional convolutional network-based non-contact heart rate measurement method of claim 6, wherein after the heart rate information is subjected to filtering processing by a specified filter, the method further comprises:
and determining a corresponding heart rate value according to the heart rate information after the filtering processing by a power spectral density method.
8. A non-contact heart rate measurement device, comprising:
the face extraction module is used for determining a face interesting region sample according to a target video after the target video is received;
and the data processing module is used for determining corresponding heart rate information through a preset algorithm based on the face interesting region sample.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium stores one or more computer programs which are executable by one or more processors to implement the steps of the three-dimensional convolutional network-based non-contact heart rate measurement method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011466448.4A CN112716468A (en) | 2020-12-14 | 2020-12-14 | Non-contact heart rate measuring method and device based on three-dimensional convolution network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011466448.4A CN112716468A (en) | 2020-12-14 | 2020-12-14 | Non-contact heart rate measuring method and device based on three-dimensional convolution network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112716468A true CN112716468A (en) | 2021-04-30 |
Family
ID=75599774
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011466448.4A Pending CN112716468A (en) | 2020-12-14 | 2020-12-14 | Non-contact heart rate measuring method and device based on three-dimensional convolution network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112716468A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113456042A (en) * | 2021-06-30 | 2021-10-01 | 浙江师范大学 | Non-contact facial blood pressure measuring method based on 3D CNN |
| CN114052692A (en) * | 2021-10-26 | 2022-02-18 | 珠海脉动时代健康科技有限公司 | Heart rate analysis method and equipment based on millimeter wave radar |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109846469A (en) * | 2019-04-16 | 2019-06-07 | 合肥工业大学 | A kind of contactless method for measuring heart rate based on convolutional neural networks |
| CN111192237A (en) * | 2019-12-16 | 2020-05-22 | 重庆大学 | Glue coating detection system and method based on deep learning |
| CN111839490A (en) * | 2020-05-26 | 2020-10-30 | 合肥工业大学 | Non-contact heart rate monitoring method and system |
-
2020
- 2020-12-14 CN CN202011466448.4A patent/CN112716468A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109846469A (en) * | 2019-04-16 | 2019-06-07 | 合肥工业大学 | A kind of contactless method for measuring heart rate based on convolutional neural networks |
| CN111192237A (en) * | 2019-12-16 | 2020-05-22 | 重庆大学 | Glue coating detection system and method based on deep learning |
| CN111839490A (en) * | 2020-05-26 | 2020-10-30 | 合肥工业大学 | Non-contact heart rate monitoring method and system |
Non-Patent Citations (5)
| Title |
|---|
| ZHAOFAN QIU等: "Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks", 《ARXIV.ORG》 * |
| ZITONG YU 等: "Remote Photoplethysmograph Signal Measurement from Facial Videos Using Spatio-Temporal Networks", 《ARXIV.ORG》 * |
| 双锴: "《计算机视觉》", 31 January 2020, 北京邮电大学出版社 * |
| 孙其功: "《深度神经网络FPGA设计与实现》", 30 June 2020, 西安电子科技大学出版社 * |
| 高磊等: "基于残差的改进卷积神经网络图像分类算法", 《计算机***应用》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113456042A (en) * | 2021-06-30 | 2021-10-01 | 浙江师范大学 | Non-contact facial blood pressure measuring method based on 3D CNN |
| CN114052692A (en) * | 2021-10-26 | 2022-02-18 | 珠海脉动时代健康科技有限公司 | Heart rate analysis method and equipment based on millimeter wave radar |
| CN114052692B (en) * | 2021-10-26 | 2024-01-16 | 珠海脉动时代健康科技有限公司 | Heart rate analysis method and equipment based on millimeter wave radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113420624B (en) | Non-contact fatigue detection method and system | |
| CN107529646B (en) | Non-contact heart rate measurement method and device based on Euler image amplification | |
| CN105147274B (en) | A kind of method that heart rate is extracted in the face video signal from visible spectrum | |
| CN111524608B (en) | Intelligent detection and epidemic prevention system and method | |
| CN112200162B (en) | Non-contact heart rate measuring method, system and device based on end-to-end network | |
| KR101738278B1 (en) | Emotion recognition method based on image | |
| CN112587153B (en) | End-to-end non-contact atrial fibrillation automatic detection system and method based on vPPG signal | |
| CN112716468A (en) | Non-contact heart rate measuring method and device based on three-dimensional convolution network | |
| CN112001122A (en) | Non-contact physiological signal measuring method based on end-to-end generation countermeasure network | |
| CN113378649A (en) | Identity, position and action recognition method, system, electronic equipment and storage medium | |
| CN111429345A (en) | Method for visually calculating heart rate and heart rate variability with ultra-low power consumption | |
| Szankin et al. | Long distance vital signs monitoring with person identification for smart home solutions | |
| CN112017155A (en) | Method, device and system for measuring health sign data and storage medium | |
| CN106096544B (en) | Non-contact blink and heart rate joint detection system and method based on second-order blind identification | |
| Bousefsaf et al. | Estimation of blood pressure waveform from facial video using a deep U-shaped network and the wavelet representation of imaging photoplethysmographic signals | |
| CN113326781B (en) | Non-contact anxiety recognition method and device based on face video | |
| CN110801227B (en) | Method and system for testing three-dimensional color block obstacle based on wearable equipment | |
| Cai et al. | Combining chrominance features and fast ICA for noncontact imaging photoplethysmography | |
| CN111640097A (en) | Skin mirror image identification method and equipment | |
| CN111640127A (en) | Accurate clinical diagnosis navigation method for orthopedics department | |
| CN107731306B (en) | Non-contact heart rate extraction method based on thermal imaging technology | |
| Arppana et al. | Real time heart beat monitoring using computer vision | |
| Suriani et al. | Non-contact facial based vital sign estimation using convolutional neural network approach | |
| Nair et al. | Illumination invariant non-invasive heart rate and blood pressure estimation from facial thermal images using deep learning | |
| Pansare et al. | Heart Rate Measurement from Face and Wrist Video |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210430 |
|
| RJ01 | Rejection of invention patent application after publication |