CN114140496A - Non-contact respiration detection method and device - Google Patents
Non-contact respiration detection method and device Download PDFInfo
- Publication number
- CN114140496A CN114140496A CN202111345071.1A CN202111345071A CN114140496A CN 114140496 A CN114140496 A CN 114140496A CN 202111345071 A CN202111345071 A CN 202111345071A CN 114140496 A CN114140496 A CN 114140496A
- Authority
- CN
- China
- Prior art keywords
- image
- respiratory
- respiration
- axis direction
- chest
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- 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
Abstract
The invention belongs to the technical field of machine vision, and discloses a non-contact respiration detection method and a non-contact respiration detection device; the detection method comprises the following steps: acquiring a respiratory image of a chest and abdomen area of a human body; converting the respiratory image into a gray image, and acquiring the movement speed of each pixel point in each frame of gray image in the X-axis direction and the movement speed of each pixel point in each frame of gray image in the Y-axis direction by using an optical flow method; and acquiring the sum of the motion speeds of all pixel points of each frame of gray level image in the X-axis direction and the Y-axis direction to obtain a respiratory oscillogram. Has the advantages that: the respiration oscillogram is obtained by adopting the respiration image of the chest and abdomen area of the human body, and the respiration image can be collected by the camera, so that the data source is wide, and the respiration detection method can be suitable for detecting the respiration in more application scenes.
Description
Technical Field
The invention relates to the technical field of machine vision, in particular to a non-contact respiration detection method and a non-contact respiration detection device.
Background
The breath of the human body is used as an index for human body health detection, and can reflect various states of the human body. Generally speaking, breath testing requires a visit to a hospital and testing using specialized medical equipment. However, the use of medical instruments to detect respiration limits the use scenarios of detection and the cost of using medical instruments to perform detection is high, which is not favorable for wide application.
In order to facilitate the breath detection and expand the application scenarios of breath detection, a contact type breath detection method and a non-contact type breath detection method are further researched in the prior art. Contact respiration detection methods generally require the use of wearable electronics for detection, while non-contact respiration detection methods generally utilize radar, acoustic, temperature sensors, and other related information for detection. Therefore, the contact type and non-contact type breathing detection methods both use special equipment and still have certain limitations.
Therefore, the invention provides a non-contact respiration detection method and a non-contact respiration detection device, which adopt more common equipment, not only have the convenience and safety of the non-contact respiration detection method, but also make the detection method more universal.
Disclosure of Invention
The purpose of the invention is: a novel non-contact respiration detection method and a device are provided, and more common equipment is adopted, so that the method not only has the convenience and safety of the non-contact respiration detection method, but also has universality.
In order to achieve the above object, the present invention provides a non-contact respiration detection method, including:
and acquiring a respiratory image of the chest and abdomen area of the human body.
And converting the respiratory image into a gray image, and extracting the movement speed of each pixel point in each frame of gray image in the X-axis direction and the movement speed of each pixel point in each frame of gray image in the Y-axis direction by using an optical flow method.
And acquiring the sum of the motion speeds of all pixel points of each frame of gray level image in the X-axis direction and the Y-axis direction to obtain a respiratory oscillogram.
Further, the acquiring of the image of the chest and abdomen area of the human body specifically includes:
the method comprises the steps of obtaining a first respiratory image of the front face of a human body, determining the position of the face through a face recognition algorithm, determining the position of the chest and the abdomen according to the distance ratio between the face and the chest and abdomen area, and extracting according to the position of the chest and the abdomen to obtain the respiratory image of the chest and abdomen area of the human body.
Further, acquiring a respiratory image of the chest and abdomen area of the human body specifically comprises:
and acquiring a second respiratory image comprising the chest and abdomen area, and extracting an image of a preset detection area to obtain a respiratory image of the chest and abdomen area of the human body.
Further, the extracting, by using an optical flow method, a motion speed of each pixel point in each frame of gray scale image in the X-axis direction and a motion speed of each pixel point in the Y-axis direction specifically includes:
obtaining a first constraint equation according to the assumption that the brightness of pixel points before and after the movement of the optical flow method is constant, obtaining a second constraint equation according to the optical flow field calculation method, and obtaining the movement speed of each pixel point in the gray level image in the X-axis direction and the movement speed of each pixel point in the Y-axis direction by combining the first constraint equation and the second constraint equation.
Further, the method for obtaining the first constraint equation specifically includes:
setting the light intensity of a pixel point in a certain frame image as I (x, y, t), and obtaining a first equation according to the assumption that the pixel point brightness before and after the optical flow method movement is constant:
I(x,y,t)＝I(x+dx,y+dy,t+dt)；
and performing Taylor expansion on the right equation of the first equation to obtain a second equation:
substituting the second equation into the first equation and then dividing dt to obtain a third equation:
let u, v be the velocity vectors of the flow along the X-axis and Y-axis, respectively, i.e.
Is provided with
Respectively representing partial derivatives of the gray levels of pixel points in the image along the directions of x, y and t, and converting a third equation into a first constraint equation:
Ixu+Iyv+It＝0。
further, the obtaining of the second constraint equation according to the optical flow field calculation method specifically includes:
and calculating the optical flow field of the respiration image by adopting one of a gradient-based method, a matching-based method, an energy-based method, a phase-based method and a nerve power-based method to obtain a second constraint equation.
Further, before obtaining the respiratory waveform map, the method further comprises:
and filtering and screening the speed of all pixel points of each frame of image in the X-axis movement direction and the speed of all pixel points of each frame of image in the Y-axis movement direction to remove the maximum value and the minimum value.
Further, after obtaining the respiratory waveform map, the method further comprises:
and smoothing the respiratory oscillogram by adopting a median filtering method or a wavelet transform method. A
The invention also discloses a non-contact respiration detection device, which comprises: the system comprises an image acquisition module, an image processing module and a data processing module;
the image acquisition module is used for acquiring a respiratory image of the chest and abdomen area of the human body.
The image processing module is used for converting the respiratory image into a gray image and extracting the movement speed of each pixel point in each frame of gray image in the X-axis direction and the movement speed of each pixel point in the Y-axis direction by using an optical flow method.
The data processing module is used for obtaining the sum of the movement speeds of all pixel points of each frame of gray level image in the X-axis direction and the sum of the movement speeds of all pixel points in the Y-axis direction to obtain a respiratory oscillogram.
Further, the detection device further comprises: and the data analysis module is used for extracting the respiratory characteristics in the respiratory oscillogram, comparing the respiratory characteristics with the respiratory characteristics of the healthy person and outputting a comparison result.
Compared with the prior art, the non-contact respiration detection method and the non-contact respiration detection device provided by the embodiment of the invention have the beneficial effects that: the respiration oscillogram is obtained by adopting the respiration image of the chest and abdomen area of the human body, and the respiration image can be collected by the camera, so that the data source is wide, and the respiration detection method can be suitable for detecting the respiration in more application scenes. The displacement characteristics of the pixels are extracted through an optical flow method, the respiratory oscillogram is obtained through the displacement characteristics, the method is simple and easy to implement, various processing devices can be realized, and the method is implemented and popularized.
Drawings
FIG. 1 is a first flow diagram of a non-contact breath detection method of the present invention;
FIG. 2 is a second flow diagram of a non-contact breath detection method of the present invention;
fig. 3 is a schematic structural diagram of a non-contact respiration detection device according to the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Example 1:
referring to fig. 1 or fig. 2, the present invention discloses a non-contact respiration detection method for obtaining a respiration oscillogram according to a respiration image of a chest and abdomen region of a human body, which mainly comprises the following steps:
in step S1, a respiratory image of the chest and abdomen area of the human body is acquired.
And step S2, converting the respiratory image into a gray image, and extracting the movement speed of each pixel point in each frame of gray image in the X-axis direction and the movement speed of each pixel point in each frame of gray image in the Y-axis direction by using an optical flow method.
And step S3, acquiring the sum of the motion speeds of all pixel points of each frame of gray level image in the X-axis direction and the Y-axis direction to obtain a respiration oscillogram.
In step S1, one method for acquiring the image of the human thorax-abdomen region is as follows:
the method comprises the steps of obtaining a first respiratory image of the front face of a human body, determining the position of the face through a face recognition algorithm, determining the position of the chest and the abdomen according to the distance ratio between the face and the chest and abdomen area, and extracting according to the position of the chest and the abdomen to obtain the respiratory image of the chest and abdomen area of the human body.
In this embodiment, the breathing image of the human body may be obtained by an active obtaining method, but since the breathing image of the human body includes many human body features and cannot be directly used for breathing detection, the position of the chest and abdomen needs to be located and then the corresponding breathing image is extracted. In the prior art, human face recognition is a mature technology, and can accurately judge the facial features of a human body and determine the position of the facial features. The figure proportion of the human body accords with the statistical rule, except the condition that the individual body proportion is different from that of a normal person, the person with the special figure proportion brings certain errors, and the image can be obtained by other modes. According to the statistical rule of the face position and the body figure, the chest and abdomen position can be determined according to the face position, and then the respiratory image of the corresponding region is extracted.
In the embodiment, further, the age of the person is judged according to the face recognition characteristics, and the corresponding proportion from the face to the chest is selected according to the age so as to determine the position of the chest and abdomen; or acquiring the four limbs characteristics of the human body according to the image identification, and acquiring the position of the chest and abdomen area according to the extracted four limbs characteristics. Other human features can be used to determine the position of the chest and abdomen, and then the image of the chest and abdomen position can be extracted by those skilled in the art.
In step S1, one method for acquiring the image of the human thorax-abdomen region is as follows:
and acquiring a second respiratory image comprising the chest and abdomen area, and extracting an image of a preset detection area to obtain a respiratory image of the chest and abdomen area of the human body.
In this embodiment, in order to reduce the difficulty of data processing and increase the data processing speed, the chest and abdomen area of the subject may be made to appear at a specific position in the image at the time of data acquisition, and the specific position may be directly acquired at the time of data processing. The specific position is a preset detection area. Therefore, the position of the chest and abdomen area is not required to be acquired by adopting an image recognition method, and the data processing flow is simplified.
In step S2, the extracting, by using an optical flow method, a motion velocity of each pixel point in each frame of grayscale image in the X-axis direction and a motion velocity in the Y-axis direction specifically includes:
obtaining a first constraint equation according to the assumption that the brightness of pixel points before and after the movement of the optical flow method is constant, obtaining a second constraint equation according to the optical flow field calculation method, and obtaining the movement speed of each pixel point in the gray level image in the X-axis direction and the movement speed of each pixel point in the Y-axis direction by combining the first constraint equation and the second constraint equation.
In this embodiment, only two sets of equations are needed to solve because there are only two unknown parameters.
The optical flow method is introduced and explained: optical flow is an algorithm that acquires motion information from an image. The algorithm proposes two basic assumptions:
condition one, constant brightness: the brightness of the same object does not change when the same object moves in different frames, and the condition is used for obtaining the first constraint condition of the optical flow method. In this embodiment, in order to make the acquired respiratory image more conform to the preset condition, it is necessary to acquire the image under a stable external light source, and as long as the external light intensity remains stable, the preset condition can be satisfied.
Condition two, time continuous or motion is "small motion": the time change does not cause the drastic change of the target position, and the displacement between the adjacent frames is smaller. Because the fluctuation of the chest cavity is changed step by step in the breathing process, the respiratory change displacement of two adjacent frames is small enough to meet the assumed condition. This also requires that the human body should be in a state of quiet breathing during image acquisition, such as a breathing state after a strenuous exercise, which needs to be eliminated.
In this embodiment, the method for obtaining the first constraint equation specifically includes:
setting the light intensity of a pixel point in a certain frame image as I (x, y, t), and obtaining a first equation according to the assumption that the pixel point brightness before and after the optical flow method movement is constant:
I(x，y，t)＝I(x+dx,y+dy,t+dt)；
and performing Taylor expansion on the right equation of the first equation to obtain a second equation:
substituting the second equation into the first equation and then dividing dt to obtain a third equation:
let u, v be the velocity vectors of the flow along the X-axis and Y-axis, respectively, i.e.
Is provided with
Respectively representing partial derivatives of the gray levels of pixel points in the image along the directions of x, y and t, and converting a third equation into a first constraint equation:
Ixu+Iyv+It＝0。
in this embodiment, the obtaining a second constraint equation according to the optical flow field calculation method specifically includes:
and calculating the optical flow field of the respiration image by adopting one of a gradient-based method, a matching-based method, an energy-based method, a phase-based method and a nerve power-based method to obtain a second constraint equation.
Because the calculation methods of the optical flow field are more, different second constraint equations and different first constraint equations can be obtained to carry out simultaneous solution. These methods are all prior art, and those skilled in the art can obtain corresponding calculation methods from the prior art to solve the problem as long as they want to know, so that each method is not necessarily exemplified.
In the present embodiment, in consideration of simplicity of calculation and real-time performance, a gradient (differential) based method is used, which calculates a velocity vector of a pixel using a time-varying image gray-scale spatiotemporal differential, and the method is simple in calculation and can achieve a good effect. And the method is divided into two solutions: (1) global differentiation: Horn-Schunck algorithm: it is assumed that the optical flow varies smoothly across the image, i.e. the rate of change of velocity is zero. (2) Local differentiation: Lucas-Kanade algorithm: assuming that the motion vectors remain constant over a small spatial domain (spatially uniform, i.e., adjacent points on the same surface in a scene have similar motion), the optical flow is estimated using a weighted least squares method. And other improved algorithms based on both of these approaches. The fluctuation change of the thoracoabdominal region is measured, and the fluctuation change of the thoracoabdominal region belongs to a small space field, and has similar movement, so the Lucas-Kanade algorithm is suitable.
Introduction of Lucas-Kanade algorithm: the algorithm assumes that the optical flow is a constant in the local neighborhood of the pixel points, and then solves the basic optical flow equation for all the pixel points in the neighborhood by using the least square method. Thereby calculating the movement of each pixel point between time t and t + dt for the two frames.
According to the assumption of Lucas-Kanade algorithm, that is, all pixel points in the neighborhood of the feature point do similar motion, this means that n basic optical flow equations can be simultaneously established to solve the speed in the x and y directions (n is the total number of points in the neighborhood of the feature point, including the feature point)
Because the first constraint equation and the second constraint equation only have two unknowns u and v, and n equations exist, the optimal solution of the equation set can be obtained by adopting a least square method:
by
The following can be obtained:
further, the method comprises
Can be expressed as:
tracking can obtain the values of u and v. u denotes a moving speed in the x direction, and v denotes a moving speed in the y direction.
In this embodiment, by selecting one type of method and obtaining the final (u, v) value, and applying this method to the thoracoabdominal region, the fluctuation of the thoracoabdominal region can be obtained, and finally the respiration variation of the human body can be known.
In step S3, the sum of the movement velocities of all the pixels in each frame of gray image in the X-axis direction and the sum of the movement velocities in the Y-axis direction are obtained, and a respiratory waveform map is obtained.
In this embodiment, the obtained respiratory waveform map includes a waveform map in which the velocity change in the X-axis direction changes with the video frame (time) and a waveform map in which the velocity change in the Y-axis direction changes with the video frame (time).
In this embodiment, before obtaining the respiratory waveform map, the method further includes:
and filtering and screening the speed of all pixel points of each frame of image in the X-axis movement direction and the speed of all pixel points of each frame of image in the Y-axis movement direction to remove the maximum value and the minimum value.
In the embodiment, after acquiring the fluctuation data of the thoracoabdominal region, the data is filtered and screened once: and removing the maximum value and the minimum value. By doing so, false detection caused by non-normative, small floating movement and the like in the measurement process can be avoided as much as possible.
In this embodiment, after obtaining the respiratory waveform map, the method further includes:
and smoothing the respiratory oscillogram by adopting a median filtering method or a wavelet transform method.
In this embodiment, since there may be jaggies in the obtained waveform, it is necessary to adopt an appropriate method to remove the jaggies, and there are two methods to remove the jaggies, the first method is to use median filtering to smooth the waveform, so as to obtain a smoother respiration waveform; the second method is to perform wavelet transform on the data and extract the principal components in the data, so as to obtain a smoother respiratory waveform image.
In this embodiment, the detection method further includes: and extracting the respiratory characteristics in the respiratory oscillogram, and comparing the respiratory characteristics with the respiratory characteristics of the healthy person.
In this embodiment, more breathing characteristics, such as the maximum amplitude, the minimum amplitude, the breathing cycle and the variation rule thereof, the amplitude variation rule, the frequency breathing information obtained by performing fast fourier transform FFT, and the like, can be obtained by performing correlation calculation on the breathing oscillogram, and then various breathing characteristics are compared with the breathing characteristics of a healthy human body, and a comparison result is output.
In the embodiment, the respiration oscillogram is acquired by adopting the respiration image of the chest and abdomen area of the human body, and the respiration image can be acquired by using the camera, so that the data source is wide, and the respiration detection method can be suitable for detecting the respiration in more application scenes. The displacement characteristics of the pixels are extracted through an optical flow method, the respiratory oscillogram is obtained through the displacement characteristics, the method is simple and easy to implement, various processing devices can be realized, and the method is implemented and popularized.
Example 2:
referring to fig. 3, the invention also discloses a non-contact respiration detection device, which is used in the same application scenario as embodiment 1 and comprises: an image acquisition module 101, an image processing module 102 and a data processing module 103.
The image acquisition module 101 is used for acquiring a respiratory image of a chest and abdomen area of a human body.
The image processing module 102 is configured to convert the respiratory image into a grayscale image, and extract a motion speed of each pixel point in each frame of the grayscale image in the X-axis direction and a motion speed of each pixel point in the Y-axis direction by using an optical flow method.
The data processing module 103 is configured to obtain a sum of motion speeds of all pixels of each frame of gray scale image in the X-axis direction and a sum of motion speeds of all pixels in the Y-axis direction, so as to obtain a respiratory oscillogram.
Further, the apparatus further comprises: the data analysis module 104 is configured to extract a respiratory feature in the respiratory oscillogram, compare the respiratory feature with a respiratory feature of a healthy person, and output a comparison result.
Further, the apparatus further comprises: a result presentation module 105; and the result display module is used for displaying the analysis result of the data analysis module.
Since example 2 was written based on example 1, some of the repeated features are not repeated.
In summary, the embodiments of the present invention provide a non-contact respiration detection method and device, compared with the prior art, which have the following beneficial effects: the respiration oscillogram is obtained by adopting the respiration image of the chest and abdomen area of the human body, and the respiration image can be collected by the camera, so that the data source is wide, and the respiration detection method can be suitable for detecting the respiration in more application scenes. The displacement characteristics of the pixels are extracted through an optical flow method, the respiratory oscillogram is obtained through the displacement characteristics, the method is simple and easy to implement, various processing devices can be realized, and the method is implemented and popularized.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and substitutions can be made without departing from the technical principle of the present invention, and these modifications and substitutions should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method of contactless breath detection, comprising:
acquiring a respiratory image of a chest and abdomen area of a human body;
converting the respiratory image into a gray image, and acquiring the movement speed of each pixel point in each frame of gray image in the X-axis direction and the movement speed of each pixel point in each frame of gray image in the Y-axis direction by using an optical flow method;
and acquiring the sum of the motion speeds of all pixel points of each frame of gray level image in the X-axis direction and the Y-axis direction to obtain a respiratory oscillogram.
2. The non-contact respiration detection method according to claim 1, wherein the acquiring of the image of the chest and abdomen area of the human body specifically comprises:
the method comprises the steps of obtaining a first respiratory image of the front face of a human body, determining the position of the face through a face recognition algorithm, determining the position of the chest and the abdomen according to the distance ratio between the face and the chest and abdomen area, and extracting according to the position of the chest and the abdomen to obtain the respiratory image of the chest and abdomen area of the human body.
3. The non-contact respiration detection method according to claim 1, wherein the acquiring of the respiration image of the chest and abdomen area of the human body specifically comprises:
and acquiring a second respiratory image comprising the chest and abdomen area, and extracting an image of a preset detection area to obtain a respiratory image of the chest and abdomen area of the human body.
4. The method according to claim 1, wherein the extracting, by using an optical flow method, a movement velocity of each pixel point in each frame of the grayscale image in an X-axis direction and a movement velocity of each pixel point in a Y-axis direction specifically comprises:
obtaining a first constraint equation according to the assumption that the brightness of pixel points before and after the movement of the optical flow method is constant, obtaining a second constraint equation according to the optical flow field calculation method, and obtaining the movement speed of each pixel point in the gray level image in the X-axis direction and the movement speed of each pixel point in the Y-axis direction by combining the first constraint equation and the second constraint equation.
5. The method according to claim 4, wherein the method for obtaining the first constraint equation specifically comprises:
setting the light intensity of a pixel point in a certain frame image as I (x, y, t), and obtaining a first equation according to the assumption that the pixel point brightness before and after the optical flow method movement is constant:
I(x，y，t)＝I(x+dx，y+dy，t+dt)；
and performing Taylor expansion on the right equation of the first equation to obtain a second equation:
substituting the second equation into the first equation and then dividing dt to obtain a third equation:
let u, v be the velocity vectors of the flow along the X-axis and Y-axis, respectively, i.e.
Is provided with
Respectively representing partial derivatives of the gray levels of pixel points in the image along the directions of x, y and t, and converting a third equation into a first constraint equation:
Ixu+Iyv+It＝0。
6. the non-contact respiration detection method according to claim 4, wherein the second constraint equation is obtained according to an optical flow field calculation method, specifically:
and calculating the optical flow field of the respiration image by adopting one of a gradient-based method, a matching-based method, an energy-based method, a phase-based method and a nerve power-based method to obtain a second constraint equation.
7. A method of contactless breath detection according to claim 1, wherein prior to obtaining the breath waveform map, the method further comprises:
and filtering and screening the speed of all pixel points of each frame of image in the X-axis movement direction and the speed of all pixel points of each frame of image in the Y-axis movement direction to remove the maximum value and the minimum value.
8. The method of claim 1, wherein after obtaining the respiration waveform map, the method further comprises:
and smoothing the respiratory oscillogram by adopting a median filtering method or a wavelet transform method.
9. A non-contact breath detection device, comprising: the system comprises an image acquisition module, an image processing module and a data processing module;
the image acquisition module is used for acquiring a respiratory image of the chest and abdomen area of the human body;
the image processing module is used for converting the respiratory image into a gray image and extracting the movement speed of each pixel point in each frame of gray image in the X-axis direction and the movement speed of each pixel point in the Y-axis direction by using an optical flow method;
the data processing module is used for obtaining the sum of the movement speeds of all pixel points of each frame of gray level image in the X-axis direction and the sum of the movement speeds of all pixel points in the Y-axis direction to obtain a respiratory oscillogram.
10. The non-contact respiration detection device of claim 9, wherein the data analysis module is configured to extract respiration characteristics in the respiration oscillogram, compare the respiration characteristics with the respiration characteristics of a healthy person, and output a comparison result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111345071.1A CN114140496A (en) | 2021-11-12 | 2021-11-12 | Non-contact respiration detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111345071.1A CN114140496A (en) | 2021-11-12 | 2021-11-12 | Non-contact respiration detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114140496A true CN114140496A (en) | 2022-03-04 |
Family
ID=80393266
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111345071.1A Pending CN114140496A (en) | 2021-11-12 | 2021-11-12 | Non-contact respiration detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114140496A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024001588A1 (en) * | 2022-07-01 | 2024-01-04 | 上海商汤智能科技有限公司 | Breathing state detection method and apparatus, device, storage medium and computer program product |
| WO2024060076A1 (en) * | 2022-09-21 | 2024-03-28 | 鲍尚琦 | Respiration monitoring method, apparatus and device, and computer-readable storage medium |
-
2021
- 2021-11-12 CN CN202111345071.1A patent/CN114140496A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024001588A1 (en) * | 2022-07-01 | 2024-01-04 | 上海商汤智能科技有限公司 | Breathing state detection method and apparatus, device, storage medium and computer program product |
| WO2024060076A1 (en) * | 2022-09-21 | 2024-03-28 | 鲍尚琦 | Respiration monitoring method, apparatus and device, and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cuppens et al. | Automatic video detection of body movement during sleep based on optical flow in pediatric patients with epilepsy | |
| CN114140496A (en) | Non-contact respiration detection method and device | |
| CN103119623A (en) | Pupil detection device and pupil detection method | |
| US20220218218A1 (en) | Video-based method and system for accurately estimating human body heart rate and facial blood volume distribution | |
| CN106846372B (en) | Human motion quality visual analysis and evaluation system and method thereof | |
| US20210186346A1 (en) | Information processing device, non-transitory computer-readable medium, and information processing method | |
| CN112017155B (en) | Method, device, system and storage medium for measuring health sign data | |
| CN103824057A (en) | Pig respiratory rate detection method based on area feature operator | |
| Szankin et al. | Long distance vital signs monitoring with person identification for smart home solutions | |
| Lukáč et al. | Contactless recognition of respiration phases using web camera | |
| CN104732586B (en) | A kind of dynamic body of 3 D human body and three-dimensional motion light stream fast reconstructing method | |
| Yang et al. | Estimating heart rate via depth video motion tracking | |
| Wiede et al. | Signal fusion based on intensity and motion variations for remote heart rate determination | |
| Zhao et al. | Remote estimation of heart rate based on multi-scale facial rois | |
| Xu et al. | An inertial sensing-based approach to swimming pose recognition and data analysis | |
| Guo et al. | Remote estimation of respiration rate by optical flow using convolutional neural networks | |
| Abd Shattar et al. | Experimental Setup for Markerless Motion Capture and Landmarks Detection using OpenPose During Dynamic Gait Index Measurement | |
| Karmuse et al. | A robust rppg approach for continuous heart rate measurement based on face | |
| JP2023549865A (en) | Method and system for measuring binocular distance for children | |
| CN111861275B (en) | Household work mode identification method and device | |
| TWI577338B (en) | Based on the real-time image-based respiration rate measurement technology method | |
| Chan et al. | Stereo vision human motion detection and tracking in uncontrolled environment | |
| Ibrahim et al. | Analysis of minimum face video duration and the effect of video compression to image-based non-contact heart rate monitoring system | |
| Zhang et al. | An approach of region of interest detection based on visual attention and gaze tracking | |
| CN112861699A (en) | Method for estimating height of human body in any posture based on single depth image and multi-stage neural network |
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 |