KR101787828B1 - Heartrate measuring system using skin color filter - Google Patents
Heartrate measuring system using skin color filter Download PDFInfo
- Publication number
- KR101787828B1 KR101787828B1 KR1020150124988A KR20150124988A KR101787828B1 KR 101787828 B1 KR101787828 B1 KR 101787828B1 KR 1020150124988 A KR1020150124988 A KR 1020150124988A KR 20150124988 A KR20150124988 A KR 20150124988A KR 101787828 B1 KR101787828 B1 KR 101787828B1
- Authority
- KR
- South Korea
- Prior art keywords
- value
- peak value
- unit
- heart rate
- skin color
- Prior art date
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
- A61B5/0062—Arrangements for scanning
- A61B5/0064—Body surface scanning
-
- 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
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/04—Babies, e.g. for SIDS detection
- A61B2503/045—Newborns, e.g. premature baby monitoring
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Cardiology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Physiology (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
According to the present invention, an image obtaining unit 110 for obtaining image data of a newborn baby photographed; The entire image of the image data filtered on the basis of the general skin color band is divided into blocks of a predetermined size and subjected to frequency conversion to select a plurality of blocks having a relatively high frequency component, A skin color band generating unit 120 for generating a skin color band having a lower limit value as a band range; An image filtering unit 130 for filtering the image data obtained on the basis of the generated skin color band and extracting a face skin region for heart rate extraction; A BVP data extracting unit 140 for extracting BVP data (Blood Volume Pulse Data) that changes per unit time using pixel values of the extracted face skin region; And a heart rate calculator 150 for calculating a heart rate using the extracted BVP data.
Description
The present invention relates to a heart rate measuring system using a skin color filter, and more particularly, to a heart rate measuring system for measuring a heart rate by detecting a change in a pixel value of a face region through image analysis of image data of a newborn baby .
Conventionally, in order to measure the heart rate, it was possible to calculate the heart rate through the pulse sensed after placing the sensor at the pulse area. However, the method of measuring the heart rate using the sensor was limited to the newborn having a small body.
There was an attempt to measure the heart rate indirectly by sensing the minute movement of the head or the body part of the newborn during heartbeat by image analysis of the image data of the newborn baby. However, since there is an error in the measurement data, .
In recent years, in order to solve such a problem, a method of measuring the heart rate by indirectly measuring the change of the pixel value of the face region by analyzing the image data of the newborn baby using the feature that the face color of the newborn baby changes minutely during heartbeat Is used.
The heart rate measurement through this image analysis is measured through the average change of the skin pixels of the face, but the fluctuation is very small, so that it is greatly affected by the fine noise.
Generally, video images obtained from a camera or a CCTV are transmitted in a compressed state, so that video loss due to compression is inevitable. However, such a video loss is more likely to occur in a region where the change is severe.
The areas where the change in the face area of the newborn baby is severe include eyes, nose, mouth, ear, and jaw. When the area is included in the detection target area for detecting a change in the pixel value, information loss due to compression There is a problem that the measured value greatly fluctuates even in a small motion such as a change in the facial expression and acts as noise in the measurement of the heart rate.
SUMMARY OF THE INVENTION The present invention has been made in order to solve the above-mentioned problems, and an object of the present invention is to provide a method and apparatus for eliminating areas where facial expressions and movement changes frequently, such as eyes, nose, mouth, The present invention is to provide a heart rate measuring system that can measure a heart rate more precisely by minimizing a measurement error of a heart rate by applying a skin color filter.
According to an aspect of the present invention, there is provided a heart rate measuring system comprising: an image acquiring unit (110) for acquiring image data of a newborn baby; The entire image of the image data filtered on the basis of the general skin color band is divided into blocks of a predetermined size and subjected to frequency conversion to select a plurality of blocks having a relatively high frequency component, A skin color
The skin color
In addition, the
The
In addition, the peak
In addition, the peak value
The peak
The peak
The peak
In addition, the weighted
According to the heart rate measuring system of the present invention,
First, the measurement error is caused by applying a skin color filter to exclude areas with frequent facial expressions and motion changes such as eyes, nose, mouth, ear, and jaw in the face region of acquired neonatal image data from the pixel value change detection region More precise heart rate measurement can be performed by sensing the change of the pixel value only in the region where the possibility is relatively low.
Second, in dividing an entire image into blocks to generate skin color bands, macroblocks, which are video compression units, are normally normalized for each block, so that a deviation occurs between blocks, and a change in pixel value However, it is possible to minimize the error in judging whether there is a block (eye, nose, mouth, ear, jaw or the like) in which the change is severe by uniformly including the block boundary by dividing the block into blocks of the same size as the video compression format have.
Third, the heart rate is calculated using the pixel values of the facial skin measured through the image analysis of the image data of the newborn baby. The candidates of the peak value for determining the heart rate are selected by applying the sub window, and the time interval The error of the measured heart rate can be minimized by reflecting the weight to the value.
1 is a block diagram illustrating a functional configuration of a heart rate measuring system according to a preferred embodiment of the present invention.
FIG. 2 is a schematic view showing a configuration in which an image acquiring unit according to a preferred embodiment of the present invention is installed in a neonate bed;
FIGS. 3 to 5 are diagrams for explaining the principle of operation of the heart rate measuring system according to the preferred embodiment of the present invention. FIG.
FIG. 6 is a photograph showing a state of a newborn in the image acquiring unit according to a preferred embodiment of the present invention,
FIGS. 7 and 8 are graphs for explaining the operation principle of the heart rate calculation unit according to the preferred embodiment of the present invention.
Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. Prior to this, terms and words used in the present specification and claims should not be construed as limited to ordinary or dictionary terms, and the inventor should appropriately interpret the concepts of the terms appropriately The present invention should be construed in accordance with the meaning and concept consistent with the technical idea of the present invention.
Therefore, the embodiments described in this specification and the configurations shown in the drawings are merely the most preferred embodiments of the present invention and do not represent all the technical ideas of the present invention. Therefore, It is to be understood that equivalents and modifications are possible.
The heart
First, the
Here, as shown in FIG. 1, it is mounted on one side of a
In addition, when the system is operated in a neonatal room where a large number of newborn babies are densely arranged, such as an anus part and a postpartum care unit, each
The skin color
Here, when a high frequency component of values obtained by frequency-transforming an image through a Fast Fourier Transform (FFT) or a Discrete Cosine Transform (DCT) in block units is large, it means that there are many changes with a short period in the spatial domain. This indicates that the change is complicated and large, and the change of the pixel value occurs in such a region even with small movement or trembling. Based heartbeat measurement in which the variation of the mean ± 0.2 pixel value in the period of the information of 0.9 Hz to 2 Hz in the time domain must be measured.
More specifically, the skin color
Here, in dividing the entire image into blocks in order to generate skin color bands, macroblocks, which are video compression units, are normally normalized for each block, so that a deviation occurs between blocks, and a change in pixel value However, it is possible to minimize the error in judging whether there is a block (eye, nose, mouth, ear, jaw or the like) in which the change is severe by uniformly including the block boundary by dividing the block into blocks of the same size as the video compression format have.
4 and 6, the
The
FIG. 3 illustrates an image in which image data is primarily filtered by applying a general skin color band by the
Here, a general color filter defines a range of values for each channel (R, G, B), and a commonly used skin color filter has a wide band for each channel so as to cover all the skin colors of various people and various parts.
FIG. 5 shows an image in which image data is finally filtered by applying the skin color band generated by the
That is, if the color filter bands are defined by determining the maximum and minimum values for each channel based on the pixel values of the stable face region such as the balls and forehead except for the unstable regions such as eyes, nose, mouth, ear and jaw in the entire face region of the newborn, It is possible to generate a skin color filter specialized for the face ball and the forehead. By applying the skin color filter thus generated to only the face region of the newborn baby, only the pixels of the stable region such as the ball and the forehead can be obtained, and only the change of the skin pixel value due to the heartbeat over time can be clearly seen.
6 and 7, the BVP
Here, the BVP
2, the heart
The peak value
Here, a position having a slope value of '0' on the variation curve of the BVP data is extracted as a peak value candidate. At this time, a slope value that is '0' on the variation curve of the BVP data and whose slope does not change from + to - is excluded from the peak value candidate.
In addition, the peak
In addition, the center of a subwindow having a minimum size is arranged at a position of each peak value, and a corresponding peak value candidate having a single peak value candidate in the subwindow or having a larger value than another peak value candidate is set as a peak value And then the peak value selection process is repeated a predetermined number of times while gradually increasing the width on the time axis of the sub window.
That is, the width of the sub-window is gradually widened and the deviation of the values of the time intervals is compared. Through this procedure, the peak value detection is repeated to determine the optimum sub-window width. Specify the window to be applied and reflect it to the peak value selection.
The peak
For example, when the average heartbeat period category of the newborn infants is 100 / s to 150 / s, the width on the time axis of the minimum size of the sub window is set to 100 / s, The line width can be set to 150 / s.
The weighted
Here, in a state in which each peak value is sorted in order of magnitude, a reflection ratio of a time interval value having a relatively large value or a relatively low value is decreased using the Gaussian normal distribution curve, and the reflection ratio of the intermediate data value or the average value is increased The weighted average value is calculated.
More specifically, a peak value candidate is extracted using the slope value on the extracted BVP data, and a subwindow having a predetermined width on the time axis (a? -Shaped display portion in FIG. 7) is arranged at each peak value candidate position A peak value candidate having a maximum size in each sub window is selected as a peak value.
8, a time interval value (tick) of each peak value is measured, a measured time interval value is sorted in order of magnitude, a weight value is reflected in an intermediate value or an average value of each time interval value, And calculates the heart rate by converting the calculated weighted average value into a heart rate cycle and converting it into a time unit.
Here, since the weighted average value is a heart rate cycle and the unit is time (second), the heart rate can be calculated by converting this per minute.
Further, in selecting the peak value, the peak value selection process is repeated a predetermined number of times while gradually increasing the width on the time axis of the sub window. That is, the width of the sub window is gradually widened and the deviation of each time interval value is compared. The peak value detection is repeated through this procedure to determine the optimum sub window width, A small subwindow is designated as the applicable target and reflected in the peak value selection.
As described above, the heart rate is calculated using the pixel values of the facial skin measured through the image analysis of the image data of the newborn baby. The candidates of the peak value for determining the heart rate are selected by applying the sub window, The error of the measured heart rate can be minimized by reflecting the weight to the interval value.
While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments. It is to be understood that various modifications and changes may be made without departing from the scope of the appended claims.
100 ... heart
120 ... skin color
140 ... BVP
Claims (10)
The entire image of the image data filtered on the basis of the skin color band is divided into blocks each having a predetermined size and subjected to frequency conversion to select a plurality of blocks having a relatively high frequency component and to select an upper limit value and a lower limit value A skin color band generating unit 120 for generating a skin color band having a band range;
An image filtering unit 130 for filtering the image data obtained on the basis of the generated skin color band and extracting a face skin region for heart rate extraction;
A BVP data extracting unit 140 for extracting BVP data (Blood Volume Pulse Data) that changes per unit time using pixel values of the extracted face skin region; And
And a heart rate calculator 150 for calculating a heart rate using the extracted BVP data,
The skin color band generation unit 120 generates a skin color band,
An image dividing unit 121 dividing the entire image of the filtered image data into blocks having the same size as the compression block of the video compression format,
A block extracting unit 122 for extracting a block corresponding to a face region of a newborn baby from all blocks,
A frequency conversion unit 123 for frequency-converting the image of the extracted block,
And a band setting unit (124) for comparing the frequencies of the extracted blocks and extracting the upper and lower limit values, and setting a band range of the skin color band based on the extracted upper and lower limit values.
The block extracting unit (122)
The face position in the entire block is detected based on the feature points on the face of the newborn baby, the face background region is set based on the detected face position, and the heart rate Measuring system.
The heart rate calculator 150 calculates a heart rate
A peak value candidate extracting unit 151 for extracting a peak value candidate using the slope value on the extracted BVP data,
A peak value selection unit 152 for arranging a subwindow having a predetermined width on the time axis line at each peak value candidate position and selecting a peak value candidate having a maximum size within each subwindow as a peak value,
A weighted average value calculator 153 for calculating a time interval value of each peak value, arranging the measured time interval values in order of magnitude, reflecting a weight on the intermediate value of each time interval value to calculate a weighted average value of the time interval value, ,
And a heart rate conversion unit (154) for calculating a calculated weighted average value by a heart rate cycle and converting the calculated weighted average value into a time unit to calculate a heart rate.
The peak value candidate extracting unit 151 extracts,
And a position where a slope value is '0' on a change curve of the BVP data is extracted as a peak value candidate.
The peak value candidate extracting unit 151 extracts,
Wherein the slope value of the BVP data is set to '0' and the slope value of the BVP data does not change from + to -, from the peak value candidate.
The peak value selection unit 152 selects,
Wherein a predetermined width of the sub window is set in consideration of a mean heartbeat period of a typical newborn baby.
The peak value selection unit 152 selects,
Selecting a peak value candidate having a single peak value candidate in the subwindow or having a larger value than another peak value candidate by arranging the center of the subwindow having the minimum size at the position of each peak value, The peak value selection process is repeated a predetermined number of times while gradually increasing the width on the time axis of the sub window to determine the optimal width of the sub window in the time axis direction, The heart rate measurement system that is specified as the applicable target and reflected in the peak value selection.
The peak value selection unit 152 selects,
Setting a width on the time axis of the sub window having the minimum size to reflect the minimum value of the average heartbeat category,
Wherein a peak value is selected while gradually increasing a width of a subwindow set reflecting the maximum value of the average heartbeat cycle category.
The weighted average value calculator 153 calculates a weighted average value
Using the Gaussian normal distribution curve with each peak value sorted in order of magnitude, the reflection ratio of the time interval value having a relatively large or low value is lowered, and the reflection ratio of the intermediate data value is increased, Heart rate measurement system to calculate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020150124988A KR101787828B1 (en) | 2015-09-03 | 2015-09-03 | Heartrate measuring system using skin color filter |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020150124988A KR101787828B1 (en) | 2015-09-03 | 2015-09-03 | Heartrate measuring system using skin color filter |
Publications (2)
Publication Number | Publication Date |
---|---|
KR20170028113A KR20170028113A (en) | 2017-03-13 |
KR101787828B1 true KR101787828B1 (en) | 2017-10-19 |
Family
ID=58411868
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020150124988A KR101787828B1 (en) | 2015-09-03 | 2015-09-03 | Heartrate measuring system using skin color filter |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR101787828B1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20220143307A (en) | 2021-04-16 | 2022-10-25 | (주)비스토스 | Heart rate measurement method and device using color image |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102132925B1 (en) * | 2018-02-19 | 2020-07-10 | 와이케이씨테크(주) | Method and apparatus for estimating blood volume based on a skin image |
KR102487926B1 (en) | 2018-03-07 | 2023-01-13 | 삼성전자주식회사 | Electronic device and method for measuring heart rate |
CN111166313A (en) * | 2019-12-26 | 2020-05-19 | 中国电子科技集团公司电子科学研究院 | Heart rate measuring method and device and readable storage medium |
KR102570982B1 (en) * | 2023-01-12 | 2023-08-25 | (주) 에버정보기술 | A Method For Measuring Biometric Information non-contact |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014198200A (en) * | 2013-03-29 | 2014-10-23 | 富士通株式会社 | Pulse wave detection device, pulse wave detection program, and pulse wave detection method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102176001B1 (en) | 2014-02-06 | 2020-11-09 | 한국전자통신연구원 | Apparatus for measuring Biometric Information and Method thereof |
-
2015
- 2015-09-03 KR KR1020150124988A patent/KR101787828B1/en not_active Application Discontinuation
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014198200A (en) * | 2013-03-29 | 2014-10-23 | 富士通株式会社 | Pulse wave detection device, pulse wave detection program, and pulse wave detection method |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20220143307A (en) | 2021-04-16 | 2022-10-25 | (주)비스토스 | Heart rate measurement method and device using color image |
Also Published As
Publication number | Publication date |
---|---|
KR20170028113A (en) | 2017-03-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101787828B1 (en) | Heartrate measuring system using skin color filter | |
US8805019B2 (en) | Processing images of at least one living being | |
CN107427233B (en) | Pulse wave detection device and pulse wave detection program | |
JP6521845B2 (en) | Device and method for measuring periodic fluctuation linked to heart beat | |
JP6102433B2 (en) | Pulse wave detection program, pulse wave detection method, and pulse wave detection device | |
JP6052027B2 (en) | Pulse wave detection device, pulse wave detection program, and pulse wave detection method | |
Feng et al. | Motion artifacts suppression for remote imaging photoplethysmography | |
McDuff et al. | Fusing partial camera signals for noncontact pulse rate variability measurement | |
JP6716712B2 (en) | Image analysis device and biological information generation system | |
KR102358325B1 (en) | Method and apparatus for measuring robust pulse rate and respiratory rate using face images | |
US11083382B2 (en) | Method, information processing apparatus and server for determining a physiological parameter of an individual | |
KR20200079691A (en) | Camera-based contactless bio-signal measurement apparatus and operating method thereof | |
CN111281367A (en) | Anti-interference non-contact heart rate detection method based on face video | |
JP2019000474A (en) | Pulse period detection device, pulse period detection method, pulse period detection program, and pulse wave detection device | |
JP2019097757A5 (en) | ||
JP6504959B2 (en) | Image processing method and program for stress monitoring | |
JP2021146061A (en) | Biological information acquisition device, biological information acquisition method and program | |
KR20170010641A (en) | Image-processing-based heartrate measuring method and, newborn baby image providing system | |
EP3318179B1 (en) | Method for measuring respiration rate and heart rate using dual camera of smartphone | |
CN111050638B (en) | Computer-implemented method and system for contact photoplethysmography (PPG) | |
US11701015B2 (en) | Computer-implemented method and system for direct photoplethysmography (PPG) with multiple sensors | |
CN105046209B (en) | A kind of contactless method for measuring heart rate based on canonical correlation analysis | |
JP7396143B2 (en) | Pulse wave analysis device, pulse wave analysis method and program | |
JP7106821B2 (en) | BIOLOGICAL SIGNAL ANALYZER, BIOLOGICAL SIGNAL ANALYSIS METHOD AND PROGRAM | |
Ben Salah et al. | Contactless heart rate estimation from facial video using skin detection and multi-resolution analysis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
E902 | Notification of reason for refusal |