CN104539888B - The video frequency monitoring method of closed cardiac massage art in CPR first aid training - Google Patents
The video frequency monitoring method of closed cardiac massage art in CPR first aid training Download PDFInfo
- Publication number
- CN104539888B CN104539888B CN201410774317.0A CN201410774317A CN104539888B CN 104539888 B CN104539888 B CN 104539888B CN 201410774317 A CN201410774317 A CN 201410774317A CN 104539888 B CN104539888 B CN 104539888B
- Authority
- CN
- China
- Prior art keywords
- image
- video
- pixel
- cpr
- cardiac massage
- 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.)
- Expired - Fee Related
Links
Abstract
The invention discloses a kind of video frequency monitoring methods of closed cardiac massage art in CPR first aid training, comprise the following steps：The video of monitoring is truncated into single image by operating frequency；Two images are subtracted each other in the adjacent time that will be obtained in single image, obtain video difference image；Obtained video difference image is obtained into bianry image with the method for Threshold segmentation；Correct body position and incorrect posture are distinguished in black pixel point institute distributed areas face in the bianry image being calculated according to size.Whether correct reach posture during complete monitoring trainee entirely sues and labours, so as to improve the purpose of training effect.
Description
Technical field
The present invention relates to a kind of video frequency monitoring methods of closed cardiac massage art in CPR first aid training.
Background technology
Sudden arrest of heart beat is emergency case common in daily life, patient such as cannot rescue recovery in time at once, 4~
The irreversible damage of patient's brain and other people body organs in adult can be caused after 6min.Therefore, the cardiopulmonary after sudden arrest of heart beat
Recovery must carry out immediately at the scene, this causes the training of cardiopulmonary resuscitation to be increasingly becoming the culture of the daily survival ability of people
A part.It is the closed cardiac massage art of major way due to auxiliary instrument demand using external chest compression in cardiopulmonary resuscitation
It is relatively low, become trained emphasis.
To improve the training effect of cardiopulmonary resuscitation, existing substantial amounts of supplemental training instrument, such as simulation dummy.But
These exercising devices are mostly using the result sued and laboured as reflection object, and the process to suing and labouring lacks monitoring, this is in closed cardiac massage
It is especially prominent in art.In closed cardiac massage art, the posture of mistake is sued and laboured, although obtained effect can be with correct appearance
Gesture is equal, but since more laborious such effect can not be lasting.And for opposite rescuer oneself, use correct body position
The action of suing and labouring of higher frequency can be obtained.So correct posture is a main points in the training of closed cardiac massage art, but
Be the equipment such as existing dummy only using the dynamics of pressing, position etc. as feedback, can not monitor the action of rescuer.
The content of the invention
It is an object of the present invention in view of the above-mentioned problems, propose closed cardiac massage in a kind of CPR first aid training
The video frequency monitoring method of art, whether posture is correct during entirely being sued and laboured with the complete monitoring trainee of realization, so as to improve
The advantages of training effect.
To achieve the above object, the technical solution adopted by the present invention is：
The video frequency monitoring method of closed cardiac massage art, comprises the following steps in a kind of CPR first aid training：
The video of monitoring is truncated into single image by step 1 by operating frequency；
Above-mentioned steps 1 are obtained two images in the adjacent time in single image and subtract each other by step 2, obtain video
Difference image；
Step 3, the video difference image for obtaining above-mentioned steps 2 obtain bianry image with the method for Threshold segmentation；
Step 4 calculates black pixel point institute distributed areas face in the bianry image that above-mentioned steps 3 obtain, big according to area
Small differentiation correct body position and incorrect posture.
Preferably, the step 1 specifically includes：
Step 101 determined a time cycle in the range of 0.2-0.5 seconds；
Step 102, the time cycle to be determined in above-mentioned steps 101, a rank is generated at the end of each time cycle
Jump signal；
Step 103 plays video, and sectional drawing is carried out when step signal is received, and extraction current video is playing
Frame is as truncated picture.
Preferably, the step 2 specifically includes：
The single image intercepted in step 201, step 1 is RGB image, and 24 RGB images are carried out expansion position, are extracted respectively
R, G, B value of every each pixel of width single image；
Step 202, the time sequencing that truncated picture is pressed to interception, every width single image are believed with adjacent next step
Number interception single image form one group, i.e., as altogether interception n width images, then obtain n-1 group adjacent images；
In step 203, every group of image, subtracted respectively with R, G, B value of each pixel in the forward image of interception time
Go R, G, B value of the latter as same position pixel；
After step 204, every group of image subtraction, each pixel obtains a new value, the institute that will be obtained after image subtraction
Pixel difference RGB image is obtained after having pixel point value normalization.
Preferably, the step 3 specifically includes：
Step 301, to pixel difference RGB image obtained above, be worth characterized by R+G+B, by R, G, B of each pixel
Three values are added, and obtain pixel difference gray level image；
Step 302, the histogram for drawing pixel difference gray level image determine segmentation threshold by ostu methods；
Pixel difference gray level image is divided into bianry image, wherein black picture element by step 303 using the method for Threshold segmentation
Point represents that the body movement generated due to action and arm action cause the difference of adjacent time two images.
Preferably, the step 4 specifically includes：
Step 401, the distribution according to black pixel point in bianry image, sentence the coordinate of all black pixel points
Disconnected, interior point and exterior point are removed in differentiation；
Step 402, all interior points of connection, form a polygon rectangle, calculate the area of polygon rectangle；
Step 403, using the area of polygon rectangle in image as bianry image in black pixel point distributed areas area, lead to
It crosses a threshold value to be judged, is judged as incorrect posture occur if the area of black pixel point distributed areas is more than threshold value.
Preferably, the selection of above-mentioned threshold value is determined by camera calibration.
Technical scheme has the advantages that：
Technical scheme, in being trained for cardiopulmonary resuscitation, the method that introduces video monitoring, for chest unfaithful intention
It is dirty to be monitored by the training process of the magic, with the posture of the action of suing and labouring of trainee in training process whether correctly for monitoring
Object.And in video monitoring, binaryzation is carried out with the pixel difference image of adjacent moment image, is generated so as to fulfill due to action
Body movement and arm action black pixel point is shown as in bianry image.Reach complete monitoring trainee entirely to apply
Whether posture is correct during rescuing, so as to improve the purpose of training effect.
Below by drawings and examples, technical scheme is described in further detail.
Description of the drawings
Fig. 1 be the embodiment of the present invention described in CPR first aid training in closed cardiac massage art video frequency monitoring method
Flow chart；
Fig. 2 a are the sectional drawing of closed cardiac massage art correct body position in CPR first aid training；
Fig. 2 b are the sectional drawing of closed cardiac massage art incorrect posture in CPR first aid training；
Fig. 3 a are that closed cardiac massage art correct body position regards in CPR first aid training described in the embodiment of the present invention
Frequency difference binary map result schematic diagram；
Fig. 3 b are that closed cardiac massage art incorrect posture regards in CPR first aid training described in the embodiment of the present invention
Frequency difference binary map result schematic diagram.
Specific embodiment
The preferred embodiment of the present invention is illustrated below in conjunction with attached drawing, it should be understood that preferred reality described herein
It applies example to be merely to illustrate and explain the present invention, be not intended to limit the present invention.
As shown in Figure 1, in a kind of CPR first aid training closed cardiac massage art video frequency monitoring method, specific steps
It is as follows：
1st, the video of monitoring is truncated into single image by operating frequency.Due to requirement " adult compressions' frequency in cardiopulmonary resuscitation
Rate is at least 100 times/min ", therefore carries out sectional drawing with 0.2-0.5 seconds for a time cycle.The sectional drawing of correct body position such as Fig. 2 a institutes
Show and the sectional drawing of incorrect posture as shown in Figure 2 b.
1.1st, determine a time cycle by the scope of 0.2-0.5 seconds, can be specifically chosen 0.2s, 0.3s, 0.4s or
0.5s is a time cycle；
1.2nd, each time cycle terminates to generate a step signal；
1.3rd, video is played, sectional drawing is carried out when step signal is received, the frame that extraction current video is playing is made
For truncated picture.
2nd, subtracted each other by two images in adjacent time, obtain video difference image.
2.1st, truncated picture is RGB image, and 24 RGB images are carried out expansion position, extracts each picture of each image respectively
R, G, B value of vegetarian refreshments；
2.2nd, by truncated picture by the time sequencing of interception, each image forms one group with subsequent piece image, cuts
N width images are taken, n-1 group adjacent images can be obtained altogether
2.3rd, in every group of image, after being individually subtracted with R, G, B value of each pixel in the forward image of interception time
R, G, B value of piece image same position pixel.
2.4th, after every group of image subtraction, each pixel obtains a new value, by the value normalizing of image all pixels point
Pixel difference RGB image is obtained after change.
3rd, video difference image is obtained into bianry image as shown in Figure 3a and Figure 3b shows with the method for Threshold segmentation.At this moment due to
It acts the body movement generated and arm action is all showed in the form of black picture element.
3.1st, to pixel difference RGB image, it is worth characterized by R+G+B, tri- values of R, G, B of each pixel is added, are obtained
To pixel difference gray level image；
3.2nd, the histogram of pixel difference gray level image is drawn, segmentation threshold is determined by ostu methods；
3.3rd, pixel difference gray level image is divided by bianry image, wherein black pixel point table using the method for Threshold segmentation
Show that the body movement generated due to action and arm action cause the difference of adjacent time two images.
4th, black pixel point institute distributed areas area in video difference bianry image is calculated, since correct body position requirement " is sued and laboured
Person's arms stretching, perpendicular with patient body ", and common fault posture is all that can not ensure " arms stretching ", this allows for mistake
Gesture actions amplitude is larger by mistake, and more laborious.It in Fig. 2 b, will appear as in incorrect posture, the body generated due to action
Black pixel point institute distributed areas area corresponding to mobile and arm action is larger.Therefore, can be distinguished according to size
Correct body position and incorrect posture.
4.1st, according to the distribution of black pixel point in bianry image, the coordinate of all black pixel points is judged.If
For a pixel, in the picture no matter abscissa or ordinate, the coordinate at least there are a pixel is more than it,
The coordinate at least there are a pixel is less than it simultaneously, this claims point in such point, is otherwise exterior point；
4.2nd, all interior points are connected, form a polygon rectangle, calculate the area of polygon rectangle；
4.3rd, using the area of polygon rectangle in image as bianry image in black pixel point distributed areas area, pass through one
A threshold value is judged, is incorrect posture occur more than threshold value.
The selection of threshold value is determined by camera calibration.
Finally it should be noted that：The foregoing is only a preferred embodiment of the present invention, is not intended to limit the invention,
Although the present invention is described in detail with reference to the foregoing embodiments, for those skilled in the art, still may be used
To modify to the technical solution recorded in foregoing embodiments or carry out equivalent substitution to which part technical characteristic.
Within the spirit and principles of the invention, any modifications, equivalent replacements and improvements are made should be included in the present invention's
Within protection domain.
Claims (5)
1. the video frequency monitoring method of closed cardiac massage art in a kind of CPR first aid training, which is characterized in that including following
Step：
The video of monitoring is truncated into single image by step 1 by operating frequency；
Above-mentioned steps 1 are obtained two images in the adjacent time in single image and subtract each other by step 2, obtain video difference figure
Picture；
Step 3, the video difference image for obtaining above-mentioned steps 2 obtain bianry image with the method for Threshold segmentation；
Step 4 calculates black pixel point institute distributed areas face in the bianry image that above-mentioned steps 3 obtain, according to size area
Divide correct body position and incorrect posture；The step 4 specifically includes：
Step 401, the distribution according to black pixel point in bianry image, judge the coordinate of all black pixel points, area
Divide and remove interior point and exterior point；
Step 402, all interior points of connection, form a polygon rectangle, calculate the area of polygon rectangle；
Step 403, using the area of polygon rectangle in image as bianry image in black pixel point distributed areas area, pass through one
A threshold value is judged, is judged as incorrect posture occur if the area of black pixel point distributed areas is more than threshold value
In being trained for cardiopulmonary resuscitation, the method that introduces video monitoring, for closed cardiac massage art training process into
Row monitoring, with the posture of the action of suing and labouring of trainee in training process whether correctly for monitored object；And in video monitoring,
Binaryzation is carried out with the pixel difference image of adjacent moment image, realizes the body movement generated due to action and arm action two
Black pixel point is shown as in value image；Whether correct reach posture during complete monitoring trainee entirely sues and labours.
2. the video frequency monitoring method of closed cardiac massage art in CPR first aid training according to claim 1, special
Sign is that the step 1 specifically includes：
Step 101 determined a time cycle in the range of 0.2-0.5 seconds；
Step 102, the time cycle to be determined in above-mentioned steps 101 generate a step letter at the end of each time cycle
Number；
Step 103 plays video, and sectional drawing is carried out when step signal is received, and the frame that extraction current video is playing is made
For truncated picture.
3. the video frequency monitoring method of closed cardiac massage art in CPR first aid training according to claim 2, special
Sign is that the step 2 specifically includes：
The single image intercepted in step 201, step 1 is RGB image, and 24 RGB images are carried out expansion position, extract every width respectively
R, G, B value of each pixel of single image；
Step 202, by truncated picture by interception time sequencing, every width single image with adjacent next step signal
The single image of interception forms one group, i.e., as intercepted n width images altogether, then obtains n-1 group adjacent images；
In step 203, every group of image, after being individually subtracted with R, G, B value of each pixel in the forward image of interception time
R, G, B value of piece image same position pixel；
After step 204, every group of image subtraction, each pixel obtains a new value, all pictures that will be obtained after image subtraction
Pixel difference RGB image is obtained after the normalization of vegetarian refreshments value.
4. the video frequency monitoring method of closed cardiac massage art in CPR first aid training according to claim 3, special
Sign is that the step 3 specifically includes：
Step 301, to pixel difference RGB image obtained above, be worth characterized by R+G+B, by R, G, B tri- of each pixel
Value is added, and obtains pixel difference gray level image；
Step 302, the histogram for drawing pixel difference gray level image determine segmentation threshold by ostu methods；
Pixel difference gray level image is divided into bianry image, wherein black pixel point table by step 303 using the method for Threshold segmentation
Show that the body movement generated due to action and arm action cause the difference of adjacent time two images.
5. the video frequency monitoring method of closed cardiac massage art in CPR first aid training according to claim 4, special
Sign is that the selection of above-mentioned threshold value is determined by camera calibration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410774317.0A CN104539888B (en) | 2014-12-16 | 2014-12-16 | The video frequency monitoring method of closed cardiac massage art in CPR first aid training |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410774317.0A CN104539888B (en) | 2014-12-16 | 2014-12-16 | The video frequency monitoring method of closed cardiac massage art in CPR first aid training |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104539888A CN104539888A (en) | 2015-04-22 |
| CN104539888B true CN104539888B (en) | 2018-06-05 |
Family
ID=52855347
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410774317.0A Expired - Fee Related CN104539888B (en) | 2014-12-16 | 2014-12-16 | The video frequency monitoring method of closed cardiac massage art in CPR first aid training |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104539888B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108769391B (en) * | 2018-05-14 | 2021-04-06 | 安徽省立医院 | Sudden death prevention artificial intelligence life monitoring cardio-pulmonary resuscitation system |
| CN111862758A (en) * | 2020-09-02 | 2020-10-30 | 思迈(青岛)防护科技有限公司 | Cardio-pulmonary resuscitation training and checking system and method based on artificial intelligence |
| CN112749684A (en) * | 2021-01-27 | 2021-05-04 | 萱闱(北京)生物科技有限公司 | Cardiopulmonary resuscitation training and evaluating method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699469A (en) * | 2009-11-09 | 2010-04-28 | 南京邮电大学 | Method for automatically identifying action of writing on blackboard of teacher in class video recording |
| CN102096812A (en) * | 2011-01-30 | 2011-06-15 | 吴柯维 | Teacher blackboard writing action detection method for intelligent teaching recording and playing system |
| CN102221369A (en) * | 2011-04-29 | 2011-10-19 | 韩铮 | Gesture recognizing method and device of ball game and gesture auxiliary device |
| CN102521579A (en) * | 2011-12-21 | 2012-06-27 | Tcl集团股份有限公司 | Method for identifying pushing action based on two-dimensional planar camera and system |
| CN102724449A (en) * | 2011-03-31 | 2012-10-10 | 青岛海信电器股份有限公司 | Interactive TV and method for realizing interaction with user by utilizing display device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4290462B2 (en) * | 2003-04-16 | 2009-07-08 | Ｓｒｉスポーツ株式会社 | Golf swing diagnostic system |
-
2014
- 2014-12-16 CN CN201410774317.0A patent/CN104539888B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699469A (en) * | 2009-11-09 | 2010-04-28 | 南京邮电大学 | Method for automatically identifying action of writing on blackboard of teacher in class video recording |
| CN102096812A (en) * | 2011-01-30 | 2011-06-15 | 吴柯维 | Teacher blackboard writing action detection method for intelligent teaching recording and playing system |
| CN102724449A (en) * | 2011-03-31 | 2012-10-10 | 青岛海信电器股份有限公司 | Interactive TV and method for realizing interaction with user by utilizing display device |
| CN102221369A (en) * | 2011-04-29 | 2011-10-19 | 韩铮 | Gesture recognizing method and device of ball game and gesture auxiliary device |
| CN102521579A (en) * | 2011-12-21 | 2012-06-27 | Tcl集团股份有限公司 | Method for identifying pushing action based on two-dimensional planar camera and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104539888A (en) | 2015-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109432753B (en) | Action correcting method, device, storage medium and electronic equipment | |
| US10134307B2 (en) | Software application for a portable device for CPR guidance using augmented reality | |
| JP6124308B2 (en) | Operation evaluation apparatus and program thereof | |
| US20180192765A1 (en) | Methods and systems for extracting motion characteristics of a user using a hall effect sensor to provide feedback to the user | |
| CN111091732B (en) | Cardiopulmonary resuscitation (CPR) instructor based on AR technology and guiding method | |
| CN104539888B (en) | The video frequency monitoring method of closed cardiac massage art in CPR first aid training | |
| CN107220608B (en) | Basketball action model reconstruction and defense guidance system and method | |
| CN108550310A (en) | A kind of CPR simulated training method and system based on virtual reality technology | |
| CN108671401A (en) | A kind of intelligent medical treatment Internet of Things collaboration AED automated external defibrillator system and method | |
| CN112233515A (en) | Unmanned examination and intelligent scoring method applied to physician CPR examination | |
| CN109407826B (en) | Ball game simulation method and device, storage medium and electronic equipment | |
| WO2016107226A1 (en) | Image processing method and apparatus | |
| Lee et al. | Development of an extended reality simulator for basic life support training | |
| Amemiya et al. | Poster: depth and rate estimation for chest compression CPR with smartphone | |
| Lins et al. | Determining Cardiopulmonary Resuscitation Parameters with Differential Evolution Optimization of Sinusoidal Curves. | |
| Rupanagudi et al. | Novel methodology for blink recognition using video oculography for communicating | |
| WO2017002012A1 (en) | Methods and systems for extracting motion characteristics of a user using a hall effect sensor to provide feedback to the user | |
| KR101251303B1 (en) | Method for providing cardiopulmonary resuscitation using mannequin and mobile terminal | |
| CN107358657B (en) | The method and system of interaction is realized based on augmented reality | |
| CN115564795A (en) | Three-dimensional human body posture estimation method based on multi-mode information | |
| KR100445846B1 (en) | A Public Speaking Simulator for treating anthropophobia | |
| CN114225343A (en) | Method for swimming by utilizing AR | |
| CN116963807A (en) | Motion data display method and system | |
| CN107239148B (en) | Breathing simulation equipment, virtual diving experience system and image display method | |
| Song et al. | Development of android based chest compression feedback application using the accelerometer in smartphone |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180605 Termination date: 20191216 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |