CN104539888A - Video monitoring method for closed-chest cardiac massage in cardio-pulmonary resuscitation first aid training - Google Patents
Video monitoring method for closed-chest cardiac massage in cardio-pulmonary resuscitation first aid training Download PDFInfo
- Publication number
- CN104539888A CN104539888A CN201410774317.0A CN201410774317A CN104539888A CN 104539888 A CN104539888 A CN 104539888A CN 201410774317 A CN201410774317 A CN 201410774317A CN 104539888 A CN104539888 A CN 104539888A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- video
- cardiac massage
- monitoring method
- 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.)
- Granted
Links
Abstract
The invention discloses a video monitoring method for closed-chest cardiac massage in cardio-pulmonary resuscitation first aid training. The method comprises the following steps of clipping a monitored video into single images according to motion frequencies, carrying subtraction on every two images in adjacent times in the single images to obtain video difference images, carrying out threshold segmentation on the obtained video difference images to obtain binary images, calculating the area of a distribution region of black pixel points in the obtained binary images, and distinguishing correct postures from wrong postures according to the area. Whether the posture of a trainee is correct in the whole rescuing process can be completely monitored, and therefore the training effect can be achieved.
Description
Technical field
The present invention relates to the video frequency monitoring method of closed cardiac massage art in a kind of CPR first aid training.
Background technology
Sudden arrest of heart beat is emergency case common in daily life, and patient, as can not get at once rescue recovery in time, can cause the irreversible infringement of patient's brain and other people body organs in adult after 4 ~ 6min.Therefore, the CPR after sudden arrest of heart beat must be carried out at the scene immediately, and this makes the training of cardiopulmonary resuscitation become a part for the cultivation of the daily survival ability of people gradually.In cardiopulmonary resuscitation, the closed cardiac massage art taking external chest compression as major way, due to lower to assistive device demand, becomes the emphasis of training.
For improving the training effect of cardiopulmonary resuscitation, existing a large amount of supplemental training apparatus, as simulation dummy etc.But these exercising devices are reflection object mainly with the result of suing and labouring, and lack monitoring to the process of suing and labouring, this is particularly outstanding in closed cardiac massage art.In closed cardiac massage art, the posture of mistake is sued and laboured, although the effect obtained can be equal with correct body position, owing to comparatively requiring great effort, such effect cannot be lasting.And relative rescuer oneself, use correct body position can obtain the action of suing and labouring of higher frequency.So correct posture is main points in the training of closed cardiac massage art, but the equipment such as existing dummy are only using the dynamics, position etc. of pressing as feedback, cannot monitor the action of rescuer.
Summary of the invention
The object of the invention is to, for the problems referred to above, the video frequency monitoring method of closed cardiac massage art in a kind of CPR first aid training is proposed, whether correct to realize posture in the whole process of suing and labouring of complete monitoring trainee, thus improve the advantage of training effect.
For achieving the above object, the technical solution used in the present invention is:
A video frequency monitoring method for closed cardiac massage art in CPR first aid training, comprises the following steps:
Step 1, the video of supervision is truncated into single image by operating frequency;
Step 2, obtain above-mentioned steps 1 in single image adjacent time in two width images subtract each other, obtain video difference image;
Step 3, video difference image above-mentioned steps 2 obtained use the method for Threshold segmentation to obtain bianry image;
Face, black pixel point institute distributed areas in the bianry image that step 4, calculating above-mentioned steps 3 obtain, distinguishes correct body position and incorrect posture according to size.
Preferably, described step 1 specifically comprises:
Step 101, within 0.2-0.5 second, determine a time cycle;
Step 102, with the time cycle determined in above-mentioned steps 101, at the end of each time cycle generate a step signal;
Step 103, displaying video, carry out sectional drawing in time receiving step signal, and the frame that extraction current video is being play is as truncated picture.
Preferably, described step 2 specifically comprises:
The single image intercepted in step 201, step 1 is RGB image, 24 RGB images is carried out expansion position, extracts R, G, B value of each pixel of every width single image respectively;
Step 202, by truncated picture by the time sequencing intercepted, every width single image all forms one group with the single image of the intercepting of adjacent next step signal, namely as intercepting n width image, then acquisition n-1 group adjacent image altogether;
In step 203, often group image, deduct R, G, B value of rear piece image same position pixel respectively by R, G, B value of each pixel in the image that the intercepting time is forward;
After step 204, often group image subtraction, each pixel obtains a new value, will obtain pixel difference RGB image after image subtraction after all pixel point values normalization obtained.
Preferably, described step 3 specifically comprises:
Step 301, to pixel obtained above difference RGB image, take R+G+B as characteristic value, R, G, B tri-of each pixel is worth and is added, obtain pixel difference gray level image;
Step 302, draw pixel difference gray level image histogram, by ostu method determination segmentation threshold;
Pixel difference gray level image is divided into bianry image by the method for step 303, employing Threshold segmentation, and wherein black pixel point represents that the health produced due to action moves the difference causing adjacent time two width image with arm action.
Preferably, described step 4 specifically comprises:
Step 401, distribution according to black pixel point in bianry image, judge the coordinate of all black pixel points, distinguishes and remove interior point and exterior point;
Step 402, connect all interior points, form a polygon rectangle, calculate the area of polygon rectangle;
Step 403, with the area of the area of rectangle polygon in image for black pixel point distributed areas in bianry image, judged by a threshold value, the area as black pixel point distributed areas is greater than threshold value and is then judged as occurring incorrect posture.
Preferably, choosing of above-mentioned threshold value is determined by camera calibration.
Technical scheme of the present invention has following beneficial effect:
Technical scheme of the present invention, in training for cardiopulmonary resuscitation, introduce the method for video monitoring, whether the training process for closed cardiac massage art is monitored, correct in monitored object with the posture of the action of suing and labouring of trainee in training process.And in video monitoring, carry out binaryzation with the pixel difference image of adjacent moment image, thus realize in bianry image, showing as black pixel point with arm action because the health of action generation moves.Whether correctly reach posture in the complete whole process of suing and labouring of monitoring trainee, thus improve the object of training effect.
Below by drawings and Examples, technical scheme of the present invention is described in further detail.
Accompanying drawing explanation
Fig. 1 is the video frequency monitoring method flow chart of closed cardiac massage art in the CPR first aid training described in the embodiment of the present invention;
Fig. 2 a is the sectional drawing of closed cardiac massage art correct body position in CPR first aid training;
Fig. 2 b is the sectional drawing of closed cardiac massage art incorrect posture in CPR first aid training;
Fig. 3 a is the video difference binary map result schematic diagram of closed cardiac massage art correct body position in the CPR first aid training described in the embodiment of the present invention;
Fig. 3 b is the video difference binary map result schematic diagram of closed cardiac massage art incorrect posture in the CPR first aid training described in the embodiment of the present invention.
Embodiment
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are described, should be appreciated that preferred embodiment described herein is only for instruction and explanation of the present invention, is not intended to limit the present invention.
As shown in Figure 1, the video frequency monitoring method of closed cardiac massage art in a kind of CPR first aid training, concrete steps are as follows:
1, the video of supervision is truncated into single image by operating frequency.Owing to requiring " adult compressions's frequency is at least 100 times/min " in cardiopulmonary resuscitation, therefore be a time cycle carry out sectional drawing with 0.2-0.5 second.As shown in Figure 2 a, and the sectional drawing of incorrect posture as shown in Figure 2 b for the sectional drawing of correct body position.
1.1, determine a time cycle by the scope of 0.2-0.5 second, can specifically select 0.2s, 0.3s, 0.4s or 0.5s to be a time cycle;
1.2, each time cycle terminates generation step signal;
1.3, displaying video, carries out sectional drawing in time receiving step signal, and the frame that extraction current video is being play is as truncated picture.
2, subtract each other by two width images in adjacent time, obtain video difference image.
2.1, truncated picture is RGB image, and 24 RGB images are carried out expansion position, extracts R, G, B value of each pixel of every width image respectively;
2.2, by the time sequencing of truncated picture by intercepting, every width image and follow-up piece image form one group, intercept n width image, can obtain altogether n-1 group adjacent image
2.3, often organize in image, deduct R, G, B value of rear piece image same position pixel by R, G, B value of each pixel in the image that the intercepting time is forward respectively.
2.4, after often organizing image subtraction, each pixel obtains a new value, will obtain pixel difference RGB image after the value normalization of all for image pixels.
3, the method for Threshold segmentation is used by video difference image to obtain bianry image as shown in Figure 3 a and Figure 3 b shows.At this moment the health produced due to action moves and all shows with the form of black picture element with arm action.
3.1, to pixel difference RGB image, take R+G+B as characteristic value, R, G, B tri-of each pixel is worth and is added, obtain pixel difference gray level image;
3.2, the histogram of portrait element difference gray level image, by ostu method determination segmentation threshold;
3.3, adopt the method for Threshold segmentation that pixel difference gray level image is divided into bianry image, wherein black pixel point represents that the health produced due to action moves the difference causing adjacent time two width image with arm action.
4, black pixel point institute distributed areas area in video difference bianry image is calculated, because correct body position requires " rescuer's arms stretching; be vertical with patient body ", and common fault posture is all to ensure " arms stretching ", this just makes incorrect posture movement range comparatively large, and comparatively requires great effort.At Fig. 2 b, just show as in incorrect posture, the health produced due to action moves with the black pixel point institute distributed areas area corresponding to arm action larger.Therefore, correct body position and incorrect posture can be distinguished according to size.
4.1, according to the distribution of black pixel point in bianry image, the coordinate of all black pixel points is judged.If for a pixel, no matter abscissa or ordinate in the picture, the coordinate that all at least there is a pixel is greater than it, and the coordinate that simultaneously at least there is a pixel is less than it, and this claims point in such point, otherwise is exterior point;
4.2, connect all interior points, form a polygon rectangle, calculate the area of polygon rectangle;
4.3, with the area of the area of rectangle polygon in image for black pixel point distributed areas in bianry image, being judged by a threshold value, being greater than threshold value for there is incorrect posture.
Choosing of threshold value is determined by camera calibration.
Last it is noted that the foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, although with reference to previous embodiment to invention has been detailed description, for a person skilled in the art, it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein portion of techniques feature.Within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (6)
1. the video frequency monitoring method of closed cardiac massage art in CPR first aid training, is characterized in that, comprise the following steps:
Step 1, the video of supervision is truncated into single image by operating frequency;
Step 2, obtain above-mentioned steps 1 in single image adjacent time in two width images subtract each other, obtain video difference image;
Step 3, video difference image above-mentioned steps 2 obtained use the method for Threshold segmentation to obtain bianry image;
Face, black pixel point institute distributed areas in the bianry image that step 4, calculating above-mentioned steps 3 obtain, distinguishes correct body position and incorrect posture according to size.
2. the video frequency monitoring method of closed cardiac massage art in CPR first aid training according to claim 1, it is characterized in that, described step 1 specifically comprises:
Step 101, within 0.2-0.5 second, determine a time cycle;
Step 102, with the time cycle determined in above-mentioned steps 101, at the end of each time cycle generate a step signal;
Step 103, displaying video, carry out sectional drawing in time receiving step signal, and the frame that extraction current video is being play is as truncated picture.
3. the video frequency monitoring method of closed cardiac massage art in CPR first aid training according to claim 2, it is characterized in that, described step 2 specifically comprises:
The single image intercepted in step 201, step 1 is RGB image, 24 RGB images is carried out expansion position, extracts R, G, B value of each pixel of every width single image respectively;
Step 202, by truncated picture by the time sequencing intercepted, every width single image all forms one group with the single image of the intercepting of adjacent next step signal, namely as intercepting n width image, then acquisition n-1 group adjacent image altogether;
In step 203, often group image, deduct R, G, B value of rear piece image same position pixel respectively by R, G, B value of each pixel in the image that the intercepting time is forward;
After step 204, often group image subtraction, each pixel obtains a new value, will obtain pixel difference RGB image after image subtraction after all pixel point values normalization obtained.
4. the video frequency monitoring method of closed cardiac massage art in CPR first aid training according to claim 3, it is characterized in that, described step 3 specifically comprises:
Step 301, to pixel obtained above difference RGB image, take R+G+B as characteristic value, R, G, B tri-of each pixel is worth and is added, obtain pixel difference gray level image;
Step 302, draw pixel difference gray level image histogram, by ostu method determination segmentation threshold;
Pixel difference gray level image is divided into bianry image by the method for step 303, employing Threshold segmentation, and wherein black pixel point represents that the health produced due to action moves the difference causing adjacent time two width image with arm action.
5. the video frequency monitoring method of closed cardiac massage art in CPR first aid training according to claim 4, it is characterized in that, described step 4 specifically comprises:
Step 401, distribution according to black pixel point in bianry image, judge the coordinate of all black pixel points, distinguishes and remove interior point and exterior point;
Step 402, connect all interior points, form a polygon rectangle, calculate the area of polygon rectangle;
Step 403, with the area of the area of rectangle polygon in image for black pixel point distributed areas in bianry image, judged by a threshold value, the area as black pixel point distributed areas is greater than threshold value and is then judged as occurring incorrect posture.
6. the video frequency monitoring method of closed cardiac massage art in CPR first aid training according to claim 5, it is characterized in that, choosing 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 true CN104539888A (en) | 2015-04-22 |
CN104539888B 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) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108769391A (en) * | 2018-05-14 | 2018-11-06 | 谭诗涵 | The anti-sudden death artificial intelligence life monitoring CPR mobile phone of one kind and method |
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 (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040209698A1 (en) * | 2003-04-16 | 2004-10-21 | Masahiko Ueda | Golf swing diagnosis system |
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 |
-
2014
- 2014-12-16 CN CN201410774317.0A patent/CN104539888B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040209698A1 (en) * | 2003-04-16 | 2004-10-21 | Masahiko Ueda | Golf swing diagnosis system |
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 |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108769391A (en) * | 2018-05-14 | 2018-11-06 | 谭诗涵 | The anti-sudden death artificial intelligence life monitoring CPR mobile phone of one kind and method |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN104539888B (en) | 2018-06-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6124308B2 (en) | Operation evaluation apparatus and program thereof | |
US10134307B2 (en) | Software application for a portable device for CPR guidance using augmented reality | |
US10089522B2 (en) | Head-mounted display with facial expression detecting capability | |
US11210500B2 (en) | Spoofing detection device, spoofing detection method, and recording medium | |
CN109432753B (en) | Action correcting method, device, storage medium and electronic equipment | |
JP2018531731A5 (en) | ||
CN111091732B (en) | Cardiopulmonary resuscitation (CPR) instructor based on AR technology and guiding method | |
CN111460875A (en) | Image processing method and apparatus, image device, and storage medium | |
US20210110146A1 (en) | Action recognition method and apparatus and electronic equipment | |
US20150301590A1 (en) | System and method for producing computer control signals from breath attributes | |
CN111191599A (en) | Gesture recognition method, device, equipment and storage medium | |
CN104539888A (en) | Video monitoring method for closed-chest cardiac massage in cardio-pulmonary resuscitation first aid training | |
WO2019135621A9 (en) | Video playback device and control method thereof | |
Huang et al. | Smartglove for upper extremities rehabilitative gaming assessment | |
CN114783001A (en) | Swimming posture evaluation method, system, device and computer readable storage medium | |
CN103914677B (en) | A kind of action identification method and device | |
Rahman et al. | Non-Contact Heart Rate Monitoring Using Lab Color Space. | |
CN106778658A (en) | Method based on classroom scene and learner's Retina transplantation learner's notice | |
US20230237677A1 (en) | Cpr posture evaluation model and system | |
US11423561B2 (en) | Learning apparatus, estimation apparatus, learning method, estimation method, and computer programs | |
CN104906776B (en) | Somatosensory motion points-scoring system, device and method | |
WO2016107226A1 (en) | Image processing method and apparatus | |
CN114191803A (en) | Method and device for judging whether flat plate supporting posture is standard or not based on deep learning | |
Corkery et al. | A Smartphone Tool for Evaluating Cardiopulmonary Resuscitation (CPR) Delivery. | |
KR102378632B1 (en) | Apparatus for detecting chest compression position and electrode pad attachment location |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180605 Termination date: 20191216 |