CN111539245A - CPR (CPR) technology training evaluation method based on virtual environment - Google Patents
CPR (CPR) technology training evaluation method based on virtual environment Download PDFInfo
- Publication number
- CN111539245A CN111539245A CN202010096116.5A CN202010096116A CN111539245A CN 111539245 A CN111539245 A CN 111539245A CN 202010096116 A CN202010096116 A CN 202010096116A CN 111539245 A CN111539245 A CN 111539245A
- Authority
- CN
- China
- Prior art keywords
- action
- chest compression
- training
- frame
- cpr
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
- G06T13/20—3D [Three Dimensional] animation
- G06T13/40—3D [Three Dimensional] animation of characters, e.g. humans, animals or virtual beings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/50—Lighting effects
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B9/00—Simulators for teaching or training purposes
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention belongs to the field of somatosensory interaction, and particularly relates to a CPR (CPR) technical training evaluation method based on a virtual environment. The evaluation method comprises the steps of firstly, constructing a virtual teaching platform; step two, judging the training action; step three, evaluating training actions; a virtual teaching platform is designed through Unity3D, and based on skeleton points collected by Kinect V2, collecting human body dynamic coordinate data of 30 frames per second is kept, corresponding dynamic parameters are calculated to classify actions, and the actions are compared with static standard points and offset and related parameters are calculated; and judging the standard degree of each type of action by combining the dynamic parameters, finally calculating action scores according to the scoring standards, and giving an improvement suggestion, thereby playing a role in guiding teaching and reducing the learning threshold and the teaching cost.
Description
Technical Field
The invention belongs to the field of somatosensory interaction, and particularly relates to a CPR (CPR) technical training evaluation method based on a virtual environment.
Background
CPR is a first aid technique of the nature of the whole nation, and the teaching training of the nature of the whole nation can occupy a large amount of manpower resources and teaching resources, and the teaching of field guidance is mostly needed to carry out in current motion training, and the training cost demand is too high, perhaps watches follow study after the video recording, can not self-correct irregular action after the end. On the basis of the virtual reality technology, the teaching and training under the virtual environment has the advantages of small occupation area, strong autonomy and good repeatability, and is technically popularized in the home of a user.
Disclosure of Invention
The invention provides a CPR technology training evaluation method based on a virtual environment, which designs a virtual teaching platform through Unity3D, keeps acquiring human body dynamic coordinate data at 30 frames per second on the basis of skeleton points acquired by Kinect V2, calculates corresponding dynamic parameters to classify and process actions, compares the corresponding dynamic parameters with static standard points, and calculates offset and related parameters; and judging the standard degree of each type of action by combining with the dynamic parameters, finally calculating the action score according to the score standard, and giving an improvement suggestion, thereby playing a role in guiding teaching and filling the blank of the field in the market.
The technical scheme of the invention is described as follows by combining the attached drawings:
a CPR technology training evaluation method based on a virtual environment is characterized by comprising the following steps:
step one, constructing a virtual teaching platform;
step two, judging the training action;
and step three, evaluating the training action.
The specific method of the first step comprises the following steps: inserting a video of CPR teaching demonstration in the Unity3D environment, and performing text reminding of the next action after the video is played; a user can control video playing and stopping through speech recognition of Kinect V2, environment reconstruction and preaction recognition are achieved, highlight display is provided for important human body part points in a training scene through the function of a shader in the Unity3D, and the user can find correct force application points quickly in the learning process.
The specific method of the second step is as follows:
acquiring dynamic coordinates of human skeleton points by using 30 frames per second of Kinect V2 and calculating vectors among corresponding nodes and offset distances of partial skeleton points; the method comprises the following specific steps:
21) positioning of a main environmental point;
after the Unity3D activates the scene, the training system carries out coordinate calibration to generate a virtual human body model, and the correct force application point P of chest compression is positioned according to the coordinate system of Kniecta(-20,25, 200) model respiration center point Pb(20,20,200);
22) Identifying human skeleton points;
collecting skeletal coordinate data of a user including a head A by Kniect1,γ(x1,γ,y1,γ,z1,γ) Neck part A2,γ(x2,γ,y2,γ,z2,γ) Shoulder center A3,γ(x3,γ,y3,γ,z3,γ) The left wrist A4,γ(x4,γ,y4,γ,z4,γ) Right wrist A5,γ(x5,γ,y5,γ,z5,γ) Left elbow A6,γ(x6,γ,y6,γ,z6,γ) Right elbow A7,γ(x7,γ,y7,γ,z7,γ) Left shoulder A8,γ(x8,γ,y8,γ,z8,γ) Right shoulder A9,γ(x9,γ,y9,γ,z9,γ) Spinal column A10,γ(x10,γ,y10,γ,z10,γ) Hip joint center A11,γ(x11,γ,y11,γ,z11,γ) Left palm center A12,γ(x12,γ,y12,γ,z12,γ) Right palm center A13,γ(x13,γ,y13,γ,z13,γ);
23) Classifying actions;
45s after the system is started is used for coordinate system calibration and voice and text interaction functions, a user is guided to give an alarm and check the state of a patient, namely a human body model, and after 45s, actions are carried out for classification and operation time is recorded;
the CPR technical operation comprises chest compression and artificial respiration, the two motions are classified through two vector included angles extending from elbow joint points, the elbow joints of two arms are taken as central points and respectively extend to shoulder joints and wrist joints to obtain four vectors, and the vector from the left elbow to the left wrist is recorded asThe vector from the left elbow to the left shoulder isThe vector from the right elbow to the right wrist isThe vector from the right elbow to the right shoulder is
Thus, the angle between two pairs of vectors in space isWhere | theta1|,|θ2All is less than or equal to 180 degrees, takeWhen theta is3When the temperature is more than or equal to 175 degrees, the action is classified as external chest compression, standardized judgment is carried out according to the external chest compression action, otherwise, the action is classified as artificial respiration action, and standardized judgment is carried out according to the artificial respiration judgment standard;
recording the time of two types of actions in the training process, recording m as the chest compression duration, wherein the initial value is 0, and when one frame is classified as the chest compression action, m is m + 1; marking n as the artificial respiration duration, wherein the initial value is 0, and each frame is classified as an artificial respiration action, then n is n +1, then respectively judging and evaluating the two types of actions, and finally carrying out comprehensive evaluation to give a total score;
23) judging standardized actions;
invalid actions exist in the two operation processes of chest compression and artificial respiration, and influence the training score of the user; according to the standard action, the two types of operation and invalid action are judged in the virtual environment according to the following method;
for the time frame classified into the chest compression action, the hip joint coordinate in the first frame is taken as the central point and is marked as Pc(x0,y0,z0) The distance from the hip joint coordinate to the central point in all the external chest compression action time frames is l1,γThen, thenProvision of l1,γNo more than 5cm, introducing variable s to record the number of frame which does not reach the standard, setting the initial value s to be 0, and judging l under a certain frame1,γIf the distance is more than 5cm, s is equal to s +1 and is marked as the I-type invalid action, and s is the duration of the I-type invalid action; recording the vector from hip joint to spine asPoint of application PaVector to the center of the shoulder isVector included angle ofThe angle under the first frame is taken as the initial angle and is marked as theta0The difference between the included vector angle and the initial angle in all the subsequent time frames is delta thetaγ=θ4,γ-θ0The absolute value of the difference is not more than 3 DEG, if Delta thetaγIf the angle is more than 3 degrees, recording the action as type II invalid action; introducing a variable t, recording the number of frames which do not reach the standard, setting the initial value t to be 0, and judging delta theta under a certain frameγIf the angle is more than 3 degrees, t is t +1 and is marked as type II invalid action, and t is the duration of the type II invalid action;
for the time frame classified into the artificial respiration action, the head position of the operator is judged, and the neck is takenMidpoint of portion and head coordinatesPd,γCoordinate and model respiration midpoint PbIs a distance ofIf the record is effective in a specified range, introducing a variable p to record the number of frames which do not reach the standard, setting the initial value p to be 0, and judging l under a certain frame2,γIf the length is more than 10cm, p is equal to p +1 and is marked as the invalid action of the III class, and p is the invalid action time length of the III class.
The third step is specifically as follows:
the external chest compression process requires the superposition of two hands for compression, and is an important index for ensuring the standard of compression action; therefore, in the virtual environment, the distance constraint is needed to be carried out on the skeletal points of the left palm and the right palm of the human body, and the distance of the right palm of the right hand is dynamically measured in the chest compression time frameThe partial score coefficient is ω1Giving a standard range l according to the average thickness of the palm of the human body3,γLess than or equal to 5cm, at this time omega1Taking 1; l3,γ∈(5,7.5]Time omega1Taking 0.8; l3,γ∈(7.5,10]Time omega1Taking 0.6, and not scoring when the range is out;
obtaining a compression position according to the position of the palms of the first frame of hands in the chest compression action, wherein the compression position is the midpoint of the coordinates of the palms of the first frame in the chest compression action time sequence and is recorded asThe distance between the pressing position and the pressing point is recorded as r,the partial score coefficient is ω2When r is less than or equal to 6cm, omega2Take 1, r ∈ (6, 8)]Then omega2Take 0.8, r ∈ (8, 10)]Then omega2Taking 0.6, and not scoring when the range is out;
the score coefficient of the pressing time length isω3If m + n is not less than 3600, then ω3Taking 1, if m + n ∈ (3000,3600), omega3Taking 0.8, if m + n ∈ (2400,3000), omega3Taking 0.6, and leaving the rest intervals without scoring;
the frequency ratio of chest compression and artificial respiration is approximately expressed in a time scale in a virtual environment, and a scaling coefficient is takenThe partial score coefficient is ω4If η∈ [0.95, 1.05%]Then ω is4Taking 1, if η∈ [0.90,0.95) ] ∪ (1.05, 1.10)],ω4Taking 0.8 part of the total weight of the mixture, if η∈ [0.85,0.90 ]) ∪ (1.10, 1.15)],ω4Taking 0.6, and leaving the rest intervals without scoring;
the composite score Q ═ ω (ω)1+ω2+ω3)×30+ω4× 10, the scores and total scores are displayed on the system interactive interface, and the scores and total scores are fed back to the user action improvement points and suggestions are made.
The invention has the beneficial effects that:
a virtual teaching platform is designed through Unity3D, and based on skeleton points collected by Kinect V2, collecting human body dynamic coordinate data of 30 frames per second is kept, corresponding dynamic parameters are calculated to classify actions, and the actions are compared with static standard points and offset and related parameters are calculated; and judging the standard degree of each type of action by combining the dynamic parameters, finally calculating action scores according to the scoring standards, and giving an improvement suggestion, thereby playing a role in guiding teaching and reducing the learning threshold and the teaching cost.
Drawings
FIG. 1 is a schematic diagram of a virtual environment coordinate system of the present invention;
FIG. 2 is a schematic view of the principal bone collection points of the present invention;
FIG. 3 is a schematic diagram of a standard action position of the present invention.
Detailed Description
Step one, constructing a virtual teaching platform;
and inserting a video of the CPR teaching demonstration in the Unity3D environment, and performing text reminding of the next action after the video is played. The user can control video playing and stopping through the speech recognition of Kinect V2, can realize the environmental reconstruction simultaneously, and preaction discernment, mannequin extrathoracic press point and artifical respiratory point in the training scene provide highlight through the shader function in the Unity3D, and the user of being convenient for finds correct application of force point fast in the learning process.
Step two, judging the training action;
and acquiring dynamic coordinates of human skeleton points by using 30 frames per second of Kinect V2, and calculating vectors between corresponding nodes and offset distances of partial skeleton points.
21) Positioning of a main environmental point;
as shown in FIG. 1, after the Unity3D activates the scene, the training system performs coordinate calibration to generate a virtual human body model, and the correct application point P of chest compression is positioned according to the coordinate system of Kniecta(-20,25, 200) model respiration center point Pb(20,20,200);
22) Identifying human skeleton points;
as shown in FIG. 2, the skeletal coordinate data of the user, including the head A, is collected by Kniect1,γ(x1,γ,y1,γ,z1,γ) Neck part A2,γ(x2,γ,y2,γ,z2,γ) Shoulder center A3,γ(x3,γ,y3,γ,z3,γ) The left wrist A4,γ(x4,γ,y4,γ,z4,γ) Right wrist A5,γ(x5,γ,y5,γ,z5,γ) Left elbow A6,γ(x6,γ,y6,γ,z6,γ) Right elbow A7,γ(x7,γ,y7,γ,z7,γ) Left shoulder A8,γ(x8,γ,y8,γ,z8,γ) Right shoulder A9,γ(x9,γ,y9,γ,z9,γ) Spinal column A10,γ(x10,γ,y10,γ,z10,γ) Hip joint center A11,γ(x11,γ,y11,γ,z11,γ) Left palm center A12,γ(x12,γ,y12,γ,z12,γ) Right palm center A13,γ(x13,γ,y13,γ,z13,γ)。
23) Classifying actions;
45s after the system is started is used for coordinate system calibration and a voice and text interaction function, the function can be set based on a Kniec device SDK, a user is guided to give an alarm and check the state of a patient (a human body model), and after 45s, action classification processing is carried out and operation time is recorded.
The CPR technique mainly comprises two partial actions of chest compression and artificial respiration, the invention classifies the two actions by two vector included angles extended from elbow joint points, takes the elbow joints of two arms as central points and respectively extends to shoulder joints and wrist joints to obtain four vectors, and records the vector from the left elbow to the left wrist asThe vector from the left elbow to the left shoulder isThe vector from the right elbow to the right wrist isThe vector from the right elbow to the right shoulder is
Thus, the angle between two pairs of vectors in space isWhere | theta1|,|θ2All is less than or equal to 180 degrees, takeWhen theta is3When the temperature is more than or equal to 175 degrees, the motion is classified as external chest compression, standardized judgment is carried out according to the external chest compression motion, otherwise, the motion is classified as artificial respiration motion, and standardized judgment is carried out according to the artificial respiration judgment standard.
Recording the time of two types of actions in the training process, recording m as the chest compression duration, wherein the initial value is 0, and when one frame is classified as the chest compression action, m is m + 1; and (3) recording n as the artificial respiration duration, setting the initial value to be 0, judging and evaluating the two types of actions respectively when each frame is classified as the artificial respiration action, and finally carrying out comprehensive evaluation to give a total score.
23) Judging standardized actions;
invalid actions exist in the two operation processes of chest compression and artificial respiration, and influence the training score of the user. The present invention establishes evaluation criteria with reference to the international guidelines of the 2005 edition of cardiopulmonary resuscitation, as shown in fig. 3, and determines the two types of operations and ineffective actions in the virtual environment according to the following methods according to the standard actions:
for the time frame classified into the chest compression action, the hip joint coordinate in the first frame is taken as the central point and is marked as Pc(x0,y0,z0) The distance from the hip joint coordinate to the central point in all the external chest compression action time frames is l1,γThen, thenProvision of l1,γNo more than 5cm, introducing variable s to record the number of frame which does not reach the standard, setting the initial value s to be 0, and judging l under a certain frame1,γIf the distance is more than 5cm, s is equal to s +1 and is marked as the I-type invalid action, and s is the duration of the I-type invalid action; recording the vector from hip joint to spine asPoint of application PaVector to the center of the shoulder isVector included angle ofThe angle under the first frame is taken as the initial angle and is marked as theta0The difference between the included vector angle and the initial angle in all the subsequent time frames is delta thetaγ=θ4,γ-θ0The absolute value of the difference is not more than 3 DEG, if Delta thetaγ> 3 ° is recorded as a type II null action. Introducing variable tRecording frame number not meeting the standard, setting the initial value t as 0, and judging delta theta under a certain frameγAnd if the angle is more than 3 degrees, t is t +1 and is marked as the type II invalid action, and t is the duration of the type II invalid action.
For the time frame classified into the artificial respiration action, the head position of the operator is judged, and the midpoint of the coordinates of the neck and the head is takenPd,γCoordinate and model respiration midpoint PbIs a distance ofIf the record is effective in a specified range, introducing a variable p to record the number of frames which do not reach the standard, setting the initial value p to be 0, and judging l under a certain frame2,γIf the length is more than 10cm, p is equal to p +1 and is marked as the invalid action of the III class, and p is the invalid action time length of the III class.
Step three, evaluating training actions;
the external chest compression process requires two hands to perform superimposed compression, and is an important index for ensuring the compression action standard. Therefore, in a virtual environment, distance constraint is required to be carried out on skeletal points of the left palm and the right palm of a human body, and the distance between the left palm and the right palm is dynamically measured in an external chest compression time frameThe partial score coefficient is ω1Giving a standard range l according to the average thickness of the palm of the human body3,γLess than or equal to 5cm, at this time omega1Taking 1; l3,γ∈(5,7.5]Time omega1Taking 0.8; l3,γ∈(7.5,10]Time omega1Take 0.6 and out of range does not score.
Obtaining a compression position according to the position of the palms of the first frame of hands in the chest compression action, wherein the compression position is the midpoint of the coordinates of the palms of the first frame in the chest compression action time sequence and is recorded asThe distance between the pressing position and the pressing point is recorded as r,the partial score coefficient is ω2When r is less than or equal to 6cm, omega2Take 1, r ∈ (6, 8)]Then omega2Take 0.8, r ∈ (8, 10)]Then omega2Take 0.6 and out of range does not score.
The score coefficient of the pressing time length is omega3If m + n is not less than 3600, then ω3Taking 1, if m + n ∈ (3000,3600), omega3Taking 0.8, if m + n ∈ (2400,3000), omega3Take 0.6 and leave out the score in the rest intervals.
The frequency ratio of chest compression and artificial respiration is approximately expressed in a time scale in a virtual environment, and a scaling coefficient is takenThe partial score coefficient is ω4If η∈ [0.95,1.05]Then ω is4Taking 1, if η∈ [0.90,0.95) ] ∪ (1.05, 1.10)],ω4Taking 0.8 part of the total weight of the mixture, if η∈ [0.85,0.90 ]) ∪ (1.10, 1.15)],ω4Take 0.6 and leave out the score in the rest intervals.
The composite score Q ═ ω (ω)1+ω2+ω3)×30+ω4× 10, displaying each score and total score on the system interface, feeding back to the user action improvement points and proposing suggestions, wherein the total score is higher than 80 to determine that the training standard is achieved, the score is 60-80 to improve the training effect by increasing the training times, the score is less than 60 to determine that the training effect is unqualified, and the teaching demonstration needs to be watched again, and for the evaluation index with the classification score coefficient less than 0.6, the evaluation index is determined to be unqualified, and the voice prompt of the index is given in the next training test.
Claims (4)
1. A CPR technology training evaluation method based on a virtual environment is characterized by comprising the following steps:
step one, constructing a virtual teaching platform;
step two, judging the training action;
and step three, evaluating the training action.
2. The CPR technique training evaluation method based on virtual environment according to claim 1, wherein the specific method of the step one is as follows: inserting a video of CPR teaching demonstration in the Unity3D environment, and performing text reminding of the next action after the video is played; a user can control video playing and stopping through speech recognition of Kinect V2, environment reconstruction and preaction recognition are achieved, highlight display is provided for important human body part points in a training scene through the function of a shader in the Unity3D, and the user can find correct force application points quickly in the learning process.
3. The CPR technique training evaluation method based on virtual environment according to claim 1, wherein the specific method of the second step is:
acquiring dynamic coordinates of human skeleton points by using 30 frames per second of Kinect V2 and calculating vectors among corresponding nodes and offset distances of partial skeleton points; the method comprises the following specific steps:
21) positioning of a main environmental point;
after the Unity3D activates the scene, the training system carries out coordinate calibration to generate a virtual human body model, and the correct force application point P of chest compression is positioned according to the coordinate system of Kniecta(-20,25, 200) model respiration center point Pb(20,20,200);
22) Identifying human skeleton points;
collecting skeletal coordinate data of a user including a head A by Kniect1,γ(x1,γ,y1,γ,z1,γ) Neck part A2,γ(x2,γ,y2,γ,z2,γ) Shoulder center A3,γ(x3,γ,y3,γ,z3,γ) The left wrist A4,γ(x4,γ,y4,γ,z4,γ) Right wrist A5,γ(x5,γ,y5,γ,z5,γ) Left elbow A6,γ(x6,γ,y6,γ,z6,γ) Right elbow A7,γ(x7,γ,y7,γ,z7,γ) Left shoulder A8,γ(x8,γ,y8,γ,z8,γ) Right shoulder A9,γ(x9,γ,y9,γ,z9,γ) Spinal columnA10,γ(x10,γ,y10,γ,z10,γ) Hip joint center A11,γ(x11,γ,y11,γ,z11,γ) Left palm center A12,γ(x12,γ,y12,γ,z12,γ) Right palm center A13,γ(x13,γ,y13,γ,z13,γ);
23) Classifying actions;
45s after the system is started is used for coordinate system calibration and voice and text interaction functions, a user is guided to give an alarm and check the state of a patient, namely a human body model, and after 45s, actions are carried out for classification and operation time is recorded;
the CPR technical operation comprises chest compression and artificial respiration, the two motions are classified through two vector included angles extending from elbow joint points, the elbow joints of two arms are taken as central points and respectively extend to shoulder joints and wrist joints to obtain four vectors, and the vector from the left elbow to the left wrist is recorded asThe vector from the left elbow to the left shoulder isThe vector from the right elbow to the right wrist isThe vector from the right elbow to the right shoulder is
Thus, the angle between two pairs of vectors in space isWhere | theta1|,|θ2All is less than or equal to 180 degrees, takeWhen theta is3When the angle is more than or equal to 175 degrees, the action is returned toThe category is chest compression, standardized judgment is carried out according to the chest compression action, otherwise, the category is classified into artificial respiration action, and standardized judgment is carried out according to the artificial respiration judgment standard;
recording the time of two types of actions in the training process, recording m as the chest compression duration, wherein the initial value is 0, and when one frame is classified as the chest compression action, m is m + 1; marking n as the artificial respiration duration, wherein the initial value is 0, and each frame is classified as an artificial respiration action, then n is n +1, then respectively judging and evaluating the two types of actions, and finally carrying out comprehensive evaluation to give a total score;
23) judging standardized actions;
invalid actions exist in the two operation processes of chest compression and artificial respiration, and influence the training score of the user; according to the standard action, the two types of operation and invalid action are judged in the virtual environment according to the following method;
for the time frame classified into the chest compression action, the hip joint coordinate in the first frame is taken as the central point and is marked as Pc(x0,y0,z0) The distance from the hip joint coordinate to the central point in all the external chest compression action time frames is l1,γThen, thenProvision of l1,γNo more than 5cm, introducing variable s to record the number of frame which does not reach the standard, setting the initial value s to be 0, and judging l under a certain frame1,γIf the distance is more than 5cm, s is equal to s +1 and is marked as the I-type invalid action, and s is the duration of the I-type invalid action; recording the vector from hip joint to spine asPoint of application PaVector to the center of the shoulder isVector included angle ofThe included angle under the first frame isInitial angle, noted as θ0The difference between the included vector angle and the initial angle in all the subsequent time frames is delta thetaγ=θ4,γ-θ0The absolute value of the difference is not more than 3 DEG, if Delta thetaγIf the angle is more than 3 degrees, recording the action as type II invalid action; introducing a variable t, recording the number of frames which do not reach the standard, setting the initial value t to be 0, and judging delta theta under a certain frameγIf the angle is more than 3 degrees, t is t +1 and is marked as type II invalid action, and t is the duration of the type II invalid action;
for the time frame classified into the artificial respiration action, the head position of the operator is judged, and the midpoint of the coordinates of the neck and the head is takenPd,γCoordinate and model respiration midpoint PbIs a distance ofIf the record is effective in a specified range, introducing a variable p to record the number of frames which do not reach the standard, setting the initial value p to be 0, and judging l under a certain frame2,γIf the length is more than 10cm, p is equal to p +1 and is marked as the invalid action of the III class, and p is the invalid action time length of the III class.
4. The CPR technique training evaluation method based on virtual environment according to claim 3, wherein the concrete method of the third step is:
the external chest compression process requires the superposition of two hands for compression, and is an important index for ensuring the standard of compression action; therefore, in the virtual environment, the distance constraint is needed to be carried out on the skeletal points of the left palm and the right palm of the human body, and the distance of the right palm of the right hand is dynamically measured in the chest compression time frameThe partial score coefficient is ω1Giving a standard range l according to the average thickness of the palm of the human body3,γLess than or equal to 5cm, at this time omega1Taking 1; l3,γ∈(5,7.5]Time omega1Taking 0.8; l3,γ∈(7.5,10]Time omega1Taking 0.6, and not scoring when the range is out;
obtaining a compression position according to the position of the palms of the first frame of hands in the chest compression action, wherein the compression position is the midpoint of the coordinates of the palms of the first frame in the chest compression action time sequence and is recorded asThe distance between the pressing position and the pressing point is recorded as r,the partial score coefficient is ω2When r is less than or equal to 6cm, omega2Take 1, r ∈ (6, 8)]Then omega2Take 0.8, r ∈ [8,10 ]]Then omega2Taking 0.6, and not scoring when the range is out;
the score coefficient of the pressing time length is omega3If m + n is not less than 3600, then ω3Taking 1, if m + n ∈ (3000,3600), omega3Taking 0.8, if m + n ∈ (2400,3000), omega3Taking 0.6, and leaving the rest intervals without scoring;
the frequency ratio of chest compression and artificial respiration is approximately expressed in a time scale in a virtual environment, and a scaling coefficient is takenThe partial score coefficient is ω4If η∈ [0.95, 1.05%]Then ω is4Taking 1, if η∈ [0.90,0.95) ] ∪ (1.05, 1.10)],ω4Taking 0.8 part of the total weight of the mixture, if η∈ [0.85,0.90 ]) ∪ (1.10, 1.15)],ω4Taking 0.6, and leaving the rest intervals without scoring;
the composite score Q ═ ω (ω)1+ω2+ω3)×30+ω4× 10, the scores and total scores are displayed on the system interactive interface, and the scores and total scores are fed back to the user action improvement points and suggestions are made.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010096116.5A CN111539245B (en) | 2020-02-17 | 2020-02-17 | CPR (CPR) technology training evaluation method based on virtual environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010096116.5A CN111539245B (en) | 2020-02-17 | 2020-02-17 | CPR (CPR) technology training evaluation method based on virtual environment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111539245A true CN111539245A (en) | 2020-08-14 |
CN111539245B CN111539245B (en) | 2023-04-07 |
Family
ID=71976666
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010096116.5A Active CN111539245B (en) | 2020-02-17 | 2020-02-17 | CPR (CPR) technology training evaluation method based on virtual environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111539245B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112233515A (en) * | 2020-10-12 | 2021-01-15 | 萱闱(北京)生物科技有限公司 | Unmanned examination and intelligent scoring method applied to physician CPR examination |
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 |
CN114706513A (en) * | 2022-04-20 | 2022-07-05 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | VR chemical laboratory implementation method and system based on unity3D and hand motion capture |
CN117710165A (en) * | 2024-02-05 | 2024-03-15 | 氧乐互动(天津)科技有限公司 | First-aid effect analysis method and system based on dummy |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104766503A (en) * | 2014-01-08 | 2015-07-08 | 财团法人工业技术研究院 | cardiopulmonary resuscitation teaching system and method |
US20150255005A1 (en) * | 2012-09-12 | 2015-09-10 | National Institute Of Advanced Industrial Science And Technology | Movement evaluation device and program therefor |
CN105469679A (en) * | 2015-11-14 | 2016-04-06 | 辽宁大学 | Cardio-pulmonary resuscitation assisted training system and cardio-pulmonary resuscitation assisted training method based on Kinect |
CN205984073U (en) * | 2016-05-11 | 2017-02-22 | 天津天堰科技股份有限公司 | Training simulation people is pressed outward to chest |
CN107213619A (en) * | 2017-07-04 | 2017-09-29 | 曲阜师范大学 | Sports training assessment system |
CN107783654A (en) * | 2017-11-08 | 2018-03-09 | 吉林大学 | Body bending class motion detection method in a kind of Virtual assemble operation |
CN108170281A (en) * | 2018-01-19 | 2018-06-15 | 吉林大学 | A kind of work posture analysis system measuring method |
CN108721870A (en) * | 2018-01-23 | 2018-11-02 | 吉林大学 | A kind of training evaluation method based on virtual environment |
CN108785051A (en) * | 2018-06-01 | 2018-11-13 | 大连理工大学 | A kind of the parametrization monitoring device and method of During Cardiopulmonary Resuscitation |
CN109313934A (en) * | 2016-05-06 | 2019-02-05 | 皇家飞利浦有限公司 | For determining the CPR ancillary equipment and method of patient chest according to pressing depth |
CN109754691A (en) * | 2018-12-07 | 2019-05-14 | 广西英腾教育科技股份有限公司 | A kind of CPR teaching and training device, data processing method and storage medium |
-
2020
- 2020-02-17 CN CN202010096116.5A patent/CN111539245B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150255005A1 (en) * | 2012-09-12 | 2015-09-10 | National Institute Of Advanced Industrial Science And Technology | Movement evaluation device and program therefor |
CN104766503A (en) * | 2014-01-08 | 2015-07-08 | 财团法人工业技术研究院 | cardiopulmonary resuscitation teaching system and method |
US20150194074A1 (en) * | 2014-01-08 | 2015-07-09 | Industrial Technology Research Institute | Cardiopulmonary resuscitation teaching system and method |
CN105469679A (en) * | 2015-11-14 | 2016-04-06 | 辽宁大学 | Cardio-pulmonary resuscitation assisted training system and cardio-pulmonary resuscitation assisted training method based on Kinect |
CN109313934A (en) * | 2016-05-06 | 2019-02-05 | 皇家飞利浦有限公司 | For determining the CPR ancillary equipment and method of patient chest according to pressing depth |
CN205984073U (en) * | 2016-05-11 | 2017-02-22 | 天津天堰科技股份有限公司 | Training simulation people is pressed outward to chest |
CN107213619A (en) * | 2017-07-04 | 2017-09-29 | 曲阜师范大学 | Sports training assessment system |
CN107783654A (en) * | 2017-11-08 | 2018-03-09 | 吉林大学 | Body bending class motion detection method in a kind of Virtual assemble operation |
CN108170281A (en) * | 2018-01-19 | 2018-06-15 | 吉林大学 | A kind of work posture analysis system measuring method |
CN108721870A (en) * | 2018-01-23 | 2018-11-02 | 吉林大学 | A kind of training evaluation method based on virtual environment |
CN108785051A (en) * | 2018-06-01 | 2018-11-13 | 大连理工大学 | A kind of the parametrization monitoring device and method of During Cardiopulmonary Resuscitation |
CN109754691A (en) * | 2018-12-07 | 2019-05-14 | 广西英腾教育科技股份有限公司 | A kind of CPR teaching and training device, data processing method and storage medium |
Non-Patent Citations (3)
Title |
---|
徐奎诰,姜明: "心肺复苏" * |
李闺臣 等: "护理学虚拟仿真实验建设现状及发展模式探索", 《中国高等医学教育》 * |
陈沈俭: "心肺复苏训练模型的优化设计与操作质量评价方法研究" * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112233515A (en) * | 2020-10-12 | 2021-01-15 | 萱闱(北京)生物科技有限公司 | Unmanned examination and intelligent scoring method applied to physician CPR examination |
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 |
CN114706513A (en) * | 2022-04-20 | 2022-07-05 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | VR chemical laboratory implementation method and system based on unity3D and hand motion capture |
CN117710165A (en) * | 2024-02-05 | 2024-03-15 | 氧乐互动(天津)科技有限公司 | First-aid effect analysis method and system based on dummy |
Also Published As
Publication number | Publication date |
---|---|
CN111539245B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111539245B (en) | CPR (CPR) technology training evaluation method based on virtual environment | |
CN110711374B (en) | Multi-modal dance action evaluation method | |
CN108764120B (en) | Human body standard action evaluation method | |
CN113706960B (en) | Nursing operation exercise platform based on VR technology and use method | |
Thar et al. | A proposal of yoga pose assessment method using pose detection for self-learning | |
CN111437583B (en) | Badminton basic action auxiliary training system based on Kinect | |
CN110349667B (en) | Autism assessment system combining questionnaire and multi-modal model behavior data analysis | |
JP6124308B2 (en) | Operation evaluation apparatus and program thereof | |
CN106205633B (en) | It is a kind of to imitate, perform practice scoring system | |
CN110162163B (en) | Virtual fire-fighting exercise method and system based on somatosensory and VR technology | |
JP7126812B2 (en) | Detection device, detection system, image processing device, detection method, image processing program, image display method, and image display system | |
CN107243141A (en) | A kind of action auxiliary training system based on motion identification | |
CN112749684A (en) | Cardiopulmonary resuscitation training and evaluating method, device, equipment and storage medium | |
CN109815930B (en) | Method for evaluating action simulation fitting degree | |
CN104766503A (en) | cardiopulmonary resuscitation teaching system and method | |
CN108269309B (en) | Parachute jumping operation action quantitative evaluation method and system | |
CN110490173B (en) | Intelligent action scoring system based on 3D somatosensory model | |
CN111444879A (en) | Joint strain autonomous rehabilitation action recognition method and system | |
CN115188074A (en) | Interactive physical training evaluation method, device and system and computer equipment | |
Hazari et al. | Designing a sign language translation system using kinect motion sensor device | |
CN112085105B (en) | Action similarity evaluation method based on human body shape and posture estimation | |
CN112818800A (en) | Physical exercise evaluation method and system based on human skeleton point depth image | |
Ding et al. | On the Use of Kinect Sensors to Design a Sport Instructor Robot for Rehabilitation and Exercise Training of the Elderly. | |
CN111310655A (en) | Human body action recognition method and system based on key frame and combined attention model | |
CN115798040A (en) | Automatic segmentation system for cardio-pulmonary resuscitation AI |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |