Frequency measurement method for cardio-pulmonary resuscitation and related device

Abstract

The embodiment of the invention provides a frequency measurement method for cardio-pulmonary resuscitation and a related device. The method comprises the following steps: acquiring image measurement data when a target object executes a cardio-pulmonary resuscitation operation; performing pressing period analysis on the shoulder information of the target object by using the image measurement data to obtain target pressing time of the target object; and according to the target pressing time, determining a pressing frequency measurement result when the target object executes the cardio-pulmonary resuscitation operation. By analyzing the shoulder information of the target object, automatic measurement of the pressing frequency when the cardiopulmonary resuscitation operation is performed on the target object is realized, the measurement difficulty of the pressing frequency is reduced, the measurement efficiency of the cardiopulmonary resuscitation pressing frequency is improved, the accuracy of the measurement result of the cardiopulmonary resuscitation pressing frequency is improved, and the measurement accuracy of the cardiopulmonary resuscitation pressing frequency is improved. And the score quality of the cardio-pulmonary resuscitation assessment is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of image processing technology. More specifically, the embodiments of the present application relate to a frequency measurement method and related devices for cardiopulmonary resuscitation. Background Art

[0002] During the cardiopulmonary resuscitation (CPR) exam, examiners need to strictly manage time to ensure that candidates complete the first aid procedures within the specified time and meet the requirements of urgency and efficiency in real first aid situations.

[0003] In the related art, manual scoring is usually used for cardiopulmonary resuscitation tests. Specifically, the examiner needs to pay close attention to the compression depth and frequency of the simulated person. The examiner needs to confirm with the naked eye and use a stopwatch to confirm that the candidate uses the correct operation method to perform compressions to simulate actual first aid situations. For example, in a cardiopulmonary resuscitation test, compression depth, frequency, etc. are all assessment indicators. At present, the main method is that multiple examiners supervise one candidate, and observe, judge and score the rescue process and the above-mentioned assessment indicators. Obviously, this current assessment method is not only inefficient, but also makes the assessment results highly subjective, and there may be human errors, which greatly reduces the quality of the assessment.

[0004] Therefore, it is urgent to design a new technical solution to solve the above-mentioned technical problems. Summary of the invention

[0005] In this context, the embodiments of the present application hope to provide a frequency measurement method and related devices for cardiopulmonary resuscitation, so as to realize the automated measurement of the compression frequency when performing cardiopulmonary resuscitation operations on the target object, improve the measurement efficiency of the cardiopulmonary resuscitation compression frequency, and enhance the accuracy of the measurement results of the cardiopulmonary resuscitation compression frequency and the scoring quality of the cardiopulmonary resuscitation assessment.

[0006] In a first aspect of the embodiments of the present application, a frequency measurement method for cardiopulmonary resuscitation is provided, the method comprising:

[0007] Acquire image measurement data when the target object performs cardiopulmonary resuscitation;

[0008] Performing a compression cycle analysis on the shoulder information of the target object using the image measurement data to obtain a target compression time of the target object;

[0009] A compression frequency measurement result when the target object performs a cardiopulmonary resuscitation operation is determined according to the target compression time.

[0010] In a second aspect of the embodiments of the present application, a frequency measurement device for cardiopulmonary resuscitation is provided, the device comprising:

[0011] An acquisition unit, used for acquiring image measurement data when a target object performs a cardiopulmonary resuscitation operation;

[0012] an analyzing unit, configured to perform a compression cycle analysis on the shoulder information of the target object using the image measurement data to obtain a target compression time of the target object;

[0013] A determination unit is used to determine a compression frequency measurement result when the target object performs a cardiopulmonary resuscitation operation according to the target compression time.

[0014] In a third aspect of the embodiments of the present application, a computing device is provided, the computing device comprising:

[0015] at least one processor, memory, and input-output unit;

[0016] The memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the frequency measurement method for cardiopulmonary resuscitation of the first aspect.

[0017] In a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, which includes instructions. When the instructions are executed on a computer, the computer executes the frequency measurement method for cardiopulmonary resuscitation of the first aspect.

[0018] In the implementation mode of the present application, a frequency measurement method and related device for cardiopulmonary resuscitation are provided. In the implementation mode of the present application, first, image measurement data of the target object when performing cardiopulmonary resuscitation operation is obtained. Then, the shoulder information of the target object is analyzed by using the image measurement data to perform compression cycle analysis to obtain the target compression time of the target object. Finally, the compression frequency measurement result of the target object when performing cardiopulmonary resuscitation operation is determined according to the target compression time. Through the above implementation mode, it is possible to realize the automatic measurement of the compression frequency when the target object performs cardiopulmonary resuscitation operation by analyzing the shoulder information of the target object, which helps to overcome the problems of low assessment efficiency and poor assessment quality caused by manual scoring in related technologies, and can not only effectively reduce the measurement difficulty of compression frequency and improve the measurement efficiency of cardiopulmonary resuscitation compression frequency, but also effectively eliminate human errors, improve the accuracy of the measurement results of cardiopulmonary resuscitation compression frequency, and the scoring quality of cardiopulmonary resuscitation assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become readily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, wherein:

[0020] Figure 1A flow chart of a frequency measurement method for cardiopulmonary resuscitation provided in one embodiment of the present application;

[0021] Figure 2 A schematic diagram of the principle of a method for acquiring image measurement data provided in an embodiment of the present application;

[0022] Figure 3 A schematic diagram of image measurement data provided by an embodiment of the present application;

[0023] Figure 4 A schematic diagram of the principle of a method for obtaining a target pressing time provided in an embodiment of the present application;

[0024] Figure 5 A schematic diagram of the principle of a method for obtaining a low point pressing time provided in an embodiment of the present application;

[0025] Figure 6 A schematic diagram of a shoulder height change trend during cardiopulmonary resuscitation provided in an embodiment of the present application;

[0026] Figure 7 A schematic diagram of the coordinate change of an image measurement frame provided by an embodiment of the present application;

[0027] Figure 8 A schematic diagram of a change in pressing frequency provided by an embodiment of the present application;

[0028] Fig. 9 A schematic diagram of changes in the pressing frequency measurement results provided by an embodiment of the present application;

[0029] Fig.10 A schematic diagram of the structure of a frequency measurement device for cardiopulmonary resuscitation provided in one embodiment of the present application;

[0030] Fig.11 A schematic diagram of the structure of a medium in an embodiment of the present application is schematically shown;

[0031] Fig.12 A schematic diagram of the structure of a computing device according to an embodiment of the present application is shown schematically.

[0032] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0033] The principles and spirit of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present application, and are not intended to limit the scope of the present application in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0034] Those skilled in the art know that the embodiments of the present application can be implemented as a system, device, equipment, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0035] During the cardiopulmonary resuscitation (CPR) test, examiners need to strictly manage time to ensure that candidates complete the first aid procedures within the specified time and meet the requirements of urgency and efficiency in real first aid situations.

[0036] In the related art, manual scoring is usually used for cardiopulmonary resuscitation tests. Specifically, the examiner needs to pay close attention to the compression depth and frequency of the simulated person. The examiner needs to confirm with the naked eye and use a stopwatch to confirm that the candidate uses the correct operation method to perform compressions to simulate actual first aid situations. For example, in a cardiopulmonary resuscitation test, compression depth, frequency, etc. are all assessment indicators. At present, the main method is that multiple examiners supervise one candidate, and observe, judge and score the rescue process and the above-mentioned assessment indicators. Obviously, this current assessment method is not only inefficient, but also makes the assessment results highly subjective, and there may be human errors, which greatly reduces the quality of the assessment.

[0037] In addition, during the cardiopulmonary resuscitation (CPR) test, the tools used include disposable gauze, pads, and manikins. The manikins' surface skin is mostly made of plastic or silicone, and usually have matching clothing. Currently, most tests use manikins with limited feedback. That is, each compression and ventilation is displayed with a light, but no specific value is displayed, which is of limited help to the examiner in scoring.

[0038] In summary, a new solution needs to be designed to solve the above technical problems.

[0039] In order to overcome the above technical problems, according to the implementation of the present application, a frequency measurement method and related device for cardiopulmonary resuscitation are proposed. In the implementation of the present application, first, image measurement data when the target object performs cardiopulmonary resuscitation is obtained. Then, the shoulder information of the target object is analyzed by the image measurement data to perform a compression cycle analysis to obtain the target compression time of the target object. Finally, the compression frequency measurement result when the target object performs cardiopulmonary resuscitation is determined according to the target compression time. Through the above implementation, the shoulder information of the target object can be analyzed to realize the automatic measurement of the compression frequency when the target object performs cardiopulmonary resuscitation, which helps to overcome the problems of low assessment efficiency and poor assessment quality caused by manual scoring in the relevant technology, effectively reduce the measurement difficulty of the compression frequency, improve the measurement efficiency of the cardiopulmonary resuscitation compression frequency, and help to realize the real-time monitoring of the compression frequency when the target object performs cardiopulmonary resuscitation. In addition, by performing compression cycle analysis and processing on the shoulder information in the image measurement data, automatic compression cycle recognition is realized, which also helps to eliminate the human error caused by manual judgment of the compression operation in the relevant technology, improve the accuracy of the measurement results of the cardiopulmonary resuscitation compression frequency, and the scoring quality of the cardiopulmonary resuscitation assessment.

[0040] The technical solution provided in the implementation mode of the present application can be implemented by a server and / or a terminal device. The server and / or the terminal device can be deployed in the cardiopulmonary resuscitation detection device, or can be independent of the cardiopulmonary resuscitation detection device, and the transmission of data instructions can be achieved by establishing wireless communication and / or wired communication. In practical applications, the cardiopulmonary resuscitation detection device can be an assessment device for cardiopulmonary resuscitation, or a teaching device for learning cardiopulmonary resuscitation operations.

[0041] It should be noted that the server involved in the embodiments of the present application can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, big data and artificial intelligence platforms.

[0042] The terminal device involved in the embodiments of the present application may be a device that provides voice and / or data connectivity to a user, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem. For example, a mobile phone (or "cellular" phone) and a computer with a mobile terminal, for example, may be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device that exchanges voice and / or data with a wireless access network. For example, Personal Communication Service (PCS) phones, cordless phones, Session Initiation Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistants (PDAs) and other devices.

[0043] It should be understood herein that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction rather than having any limiting meaning.

[0044] The principles and spirit of the present application are explained in detail below with reference to several representative implementations of the present application.

[0045] Reference below Figure 1 , Figure 1 A flow chart of a frequency measurement method for cardiopulmonary resuscitation provided in an embodiment of the present application. A frequency measurement method for cardiopulmonary resuscitation provided in an embodiment of the present application includes:

[0046] Step S101, acquiring image measurement data of a target object performing a cardiopulmonary resuscitation operation.

[0047] In the embodiment of the present application, the target object refers to an individual who performs cardiopulmonary resuscitation. It can be a person taking an exam, or an emergency personnel, or other person or equipment performing cardiopulmonary resuscitation. The equipment here can be understood as an emergency robot, which can include a mechanical arm for pressing, and the shoulder height hereinafter can be understood as the joint height of the mechanical arm.

[0048] Among them, the image measurement data can be acquired by an image acquisition device. Specifically, the image acquisition device can be a camera device based on a monocular camera, which is not limited in the embodiments of the present application. For example, the image measurement data is acquired by a monocular camera. For example, the image acquisition device can be a camera module in a cardiopulmonary resuscitation inspection device, or a camera module arranged outside the cardiopulmonary resuscitation inspection device, which is connected to the cardiopulmonary resuscitation inspection device by a matching connection structure. In an optional embodiment, the image measurement data can be a video acquired by a cardiopulmonary resuscitation inspection device including a monocular camera.

[0049] For example, a PCI video capture card, a USB video capture card, or other computer networks are used to capture real-time video, and the captured real-time video is played. Alternatively, in another example, a pre-recorded video is loaded from a local storage or a network storage for playback. Specifically, image frames (i.e., image measurement data) are extracted from the video.

[0050] In an alternative embodiment, see Figure 2 As shown, the image measurement data of the target object performing the cardiopulmonary resuscitation operation in step S101 can be specifically implemented as follows:

[0051] S201. Obtain video stream data collected when a target object performs cardiopulmonary resuscitation.

[0052] In an embodiment of the present application, a camera device, such as a surveillance camera, a wearable camera, etc., can be used to shoot or record the target object to obtain video stream data of the target object when performing cardiopulmonary resuscitation operations. For example, a timer is used to set a feedback cycle, so that the video stream data of the cardiopulmonary resuscitation candidate is read from the storage medium regularly based on the feedback cycle. Or, in another example, after the candidate's assessment is completed, the candidate's video stream data is read from the storage service in real time.

[0053] For example, if the target object is a candidate who is performing cardiopulmonary resuscitation, based on this, in S201, a camera device can be used to record the process of the candidate performing cardiopulmonary resuscitation. The video stream data includes various movements and postures of the candidate during the cardiopulmonary resuscitation assessment.

[0054] S202: Use a human body posture model to split the video stream data to obtain a start frame position and an end frame position corresponding to each pressing cycle of the target object.

[0055] For example, a human posture model built based on artificial intelligence is called to infer the video stream data to obtain the human posture coordinates. Then, the video stream data is split according to the human posture coordinates to obtain the start frame position and end frame position corresponding to each pressing cycle of the target object.

[0056] In S202, by using the human posture model, the shoulder position of the examinee can be automatically identified and tracked, and the positions of the start frame and the end frame corresponding to each pressing cycle can be determined.

[0057] For example, by using a human posture model, human posture coordinate data can be extracted from video stream data and stored as a human posture coordinate data sequence. The human posture coordinate data sequence includes at least: the acquisition time of each group of human posture coordinate data, each joint number in each group of human posture coordinate data, and the coordinate value corresponding to each joint number. Each joint coordinate value can be expressed as the actual pixel coordinate (denoted as img_x and img_y) divided by the width (width) or height (height) of the current graphic to obtain a human posture coordinate data file. The file format is shown in Figure 3 .

[0058] The acquisition time of each group of human posture coordinate data can be expressed as a timestamp, and the unit of the timestamp can be expressed in the format of hours, minutes, milliseconds, seconds, etc. Further, assuming that the total number of lines in the human posture coordinate data file is recorded as lines, and each line of data is recorded as line, based on this, a regular expression is used to extract the timestamp, horizontal and vertical coordinate values ​​(i.e., the coordinate values ​​of the x-axis and the y-axis) from the human posture coordinate data file. The expression of the file is as follows:

[0059] (\d+:\d+\·\d+),x=([\d·]+)y=([\d·]+)

[0060] Further optionally, the left shoulder joint number and the right shoulder joint number are obtained by searching the joint numbers, and the result output by the expression is aligned by the joint numbers to extract the x-axis coordinate and y-axis coordinate of the corresponding joint number in each row of data.

[0061] For example, in the file line data line arr Extract the left shoulder array y corresponding to timestamp t l and the right shoulder array yr. Among them, line arr It is expressed as the following formula:

[0062] line arr =[t,(no1,x1,y1),(no2,x2,y2),…,(no m ,x k ,y k )],m∈[0,class),k∈[0,1]

[0063] Among them, class is the total number of joint categories set in the human posture model, no k is the joint number, x k andk They are joint numbers no. m The corresponding x-axis and y-axis coordinates.

[0064] S203 . Divide the video stream data into image measurement data corresponding to each pressing cycle of the target object according to the start frame position and the end frame position.

[0065] In S203, according to the positions of the start and end frames, image measurement data corresponding to each compression cycle is extracted from the entire video stream data. These image measurement data can be used for subsequent analysis to measure parameters such as compression cycle and frequency, so as to evaluate the quality and effect of the cardiopulmonary resuscitation operation.

[0066] For example, in S203, according to the start frame index position bgn corresponding to the five-round pressing cycle, i and the end frame index position end i Finally, the image measurement data corresponding to the five-round pressing cycle of the target object is obtained. arr , expressed as follows:

[0067] push arr =[push1,push2,push3,push4,push5]

[0068] Among them, set i to push the image measurement data arr Array index of the image measurement frame coordinate array push for each pressing cycle i The composition is as follows:

[0069] push i =lines arr [bgn i :end i ]

[0070] Through steps S201 to S203, a human posture model can be used to extract more accurate image measurement data from the video stream data, further improving the accuracy of the image measurement data, which helps to improve the evaluation quality and scoring effect of cardiopulmonary resuscitation operations. Further, optionally, the timestamp is converted into the duration corresponding to the time interval, and the duration calculation process is as follows:

[0071]

[0072] Among them, min is the function to extract the minimum number of the array, and len is the function to extract the length of the array. By calculating the difference between each timestamp and the minimum timestamp, and converting the calculation result into the total number of seconds between the two timestamps. Among them, the minimum timestamp can be understood as the starting time of each cycle. The result after the above steps is as follows:

[0073]

[0074]

[0075] Among them, Serial is the data transmission interface, Raw Data is the original pressing time data, and Standard Data is the processed pressing time data.

[0076] Further optionally, each cardiopulmonary resuscitation test includes at least five compression cycles. Each compression cycle includes a complete cardiopulmonary resuscitation operation.

[0077] When testing CPR, at least five compression cycles are performed, each cycle consisting of a complete CPR maneuver. Specifically, at the beginning of each compression cycle, the subject first confirms that the surroundings are safe and assesses the mannequin's consciousness and response. Then, the subject calls for help or asks someone to call emergency services, and immediately begins chest compressions after ensuring that emergency personnel are about to arrive. Next, the subject needs to stand on one side of the mannequin, place the palm of one hand flat on the heart, and cross the other hand on top. The subject uses straight arm strength to perform chest compressions at a rate of 100-120 times per minute. Then, after completing 30 chest compressions, the subject will perform two artificial respirations. The subject gently lifts the mannequin's forehead and jaw with the palm of his hand to ensure that the airway is open. The subject closes the mannequin's mouth and blows with his own mouth to lift the chest. Each blow should last about 1 second to lift the chest. Pay attention to the rise and fall of the chest and whether the breathing is effective. Next, after performing two artificial respirations, the subject will move to the observation phase. In this phase, the subject will observe the breathing status and reactions of the prosthetic model. For example, observe the prosthetic model's state of consciousness and whether there are any signs of resuscitation, such as breathing recovery, consciousness or other reactions. Finally, after completing a full round of CPR, the subject will record relevant data. This data can include the duration of compressions, compression frequency, number of artificial respirations, etc. These records help evaluate the quality of CPR and provide reference for further first aid. The completion of each round of compression cycle marks a complete CPR operation. The repetition of these five rounds of compression cycles can maintain continuous and effective CPR. It is worth noting that in actual applications, the ratio of compressions to artificial respirations may vary according to different guidelines and assessment standards.

[0078] After the image measurement data is acquired, in step S102, the image measurement data is used to perform a compression cycle analysis on the shoulder information of the target object to obtain a target compression time of the target object.

[0079] It is understandable that the target compression time is the execution time or action acquisition time of the target object's iconic action in the cardiopulmonary resuscitation operation. For example, when pressing, the shoulder compression time corresponding to when the shoulder falls to the lowest point (or within the preset shoulder height range).

[0080] As an alternative implementation, see Figure 4 As shown, in step S102, the image measurement data is used to perform compression cycle analysis on the shoulder information of the target object to obtain the target compression time of the target object, which can be specifically implemented as follows:

[0081] S401, identifying the posture information of the target object in the image measurement data, and obtaining the target posture information corresponding to the target object in the image measurement data;

[0082] S402, acquiring the shoulder height corresponding to the target object and the shoulder pressing time corresponding to the shoulder height from the target posture information;

[0083] S403: Determine a target pressing time corresponding to the target object according to the shoulder height and the shoulder pressing time.

[0084] Exemplarily, it is assumed that the target posture information at least includes the joint serial number and the joint frame image information corresponding to the joint serial number. Based on the above assumption, in S402, the shoulder height corresponding to the target object and the shoulder pressing time corresponding to the shoulder height are obtained from the target posture information, such as Figure 5 As shown, it can be implemented as follows:

[0085] S501, filtering the target posture information according to the target joint serial number to obtain the shoulder frame image information corresponding to the target object;

[0086] S502, obtaining a first vertical coordinate corresponding to the left shoulder and a second vertical coordinate corresponding to the right shoulder of the target object according to the shoulder frame image information;

[0087] S503 . Calculate the mean of the first vertical coordinate and the second vertical coordinate to obtain the shoulder height corresponding to the target object, and obtain the shoulder pressing time corresponding to the shoulder height.

[0088] For example, in the above steps S401 to S403, the image measurement data push is started arr , get the image measurement frame coordinate array push for each cycle i , start traversing the image measurement frame coordinate array push i All rows in . Assume that each time the image measurement frame coordinate array is pushed i Each line of data in line = push i [i].

[0089] Based on the above assumptions, the y-axis coordinate of the left shoulder (corresponding to the target joint number LS) is recorded as line[LS][2], i.e., the first vertical coordinate; and the y-axis coordinate of the right shoulder (corresponding to the target joint number RS) is recorded as line[RS][2], i.e., the second vertical coordinate. The average of the above two values ​​is ym k (i.e. the shoulder height value corresponding to the target object), which is specifically expressed as the following formula:

[0090]

[0091] Furthermore, ym k Tail insertion shoulder height sequence y arr Here, k is set as the index value, indicating the current round of pressing cycle traversed. arr It is expressed as the following formula:

[0092] yarr=[ym0,ym1,…,ymk],k∈[0,n)

[0093] And synchronize from array ts arr Extract the time series T corresponding to the cycle, and the time series T is recorded as the following formula:

[0094] T=[tsarr0,tsarr1,…,tsarrk],k∈[0,n)

[0095] For example, the change in shoulder height during the entire CPR process of the left and right shoulders can be seen in Figure 6 , each image measurement frame coordinate array push i The data visualization effect of the left and right shoulders and the average height of the shoulders can be seen in Figure 7 .

[0096] Further, in 403, the target pressing time corresponding to the target object is determined according to the shoulder height and the shoulder pressing time, such as Figure 5 As shown, it can be implemented as follows:

[0097] S504, calculating the average of the shoulder heights to obtain a shoulder average;

[0098] S505, comparing the shoulder height with the shoulder mean, if the shoulder height is less than the shoulder mean, taking the shoulder pressing time corresponding to the shoulder height as the corresponding pressing low point time of the target object;

[0099] S506: Calculate the time interval according to the pressing low point time to obtain the target pressing time.

[0100] Exemplarily, it is assumed that the shoulder height is a shoulder height value sequence. It is assumed that each shoulder height value sequence at least includes: all shoulder height values ​​in each round of cardiopulmonary resuscitation stage.

[0101] Based on the above assumptions, in S505, the shoulder height is compared with the shoulder mean value. If the shoulder height is less than the shoulder mean value, the shoulder pressing time corresponding to the shoulder height is used as the pressing low point time corresponding to the target object. Specifically, first, traverse each sequence of shoulder height values, and compare each shoulder height value in each sequence of shoulder height values with the shoulder mean value one by one. Furthermore, if the currently traversed shoulder height value is less than the shoulder mean value, the shoulder pressing time corresponding to the currently traversed shoulder height value is used as the pressing low point time of the target object in the current round.

[0102] In another alternative example, if the currently traversed shoulder height value is greater than or equal to the shoulder mean value, continue to compare the next shoulder height value in the sequence of shoulder height values with the shoulder height mean value until all shoulder height values in the sequence of shoulder height values in the current round are traversed.

[0103] For example, in the above step S504, calculate the mean value of all shoulder height values in the shoulder height sequence y arr and denote it as mean. In the above step S505, set a temporary variable tmp and assign -1 to this temporary variable. At the same time, set an array low p for storing the low point coordinates and an array low t for the corresponding pressing times.

[0104] Based on the above settings, traverse the shoulder height sequence y arr , compare the size of each shoulder height value in the shoulder height sequence y arr with the mean value mean, and select a processing method based on the comparison result. Assume that i is the index value, and the currently traversed shoulder height value is y arr [i].

[0105] If the currently traversed shoulder height value y arr [i] is less than the shoulder mean value mean, that is, y arr [i]<mean, and tmp is not 1, in this case, insert tmp at the end of the array low p for storing the low point coordinates, and insert T[i] into the array low t for the pressing times. At the same time, in this case, also reassign -1 to tmp.

[0106] If the currently traversed shoulder height value y arr [i] is greater than or equal to the shoulder mean value mean, that is, y arr [i]≥mean, then perform an assignment operation on tmp according to the following formula, that is:

[0107]

[0108] In step S506, the low point coordinate storage array low is traversed. p And the pressing time array low t , that is, the time end corresponding to the coordinates of two adjacent low points is the duration of each press Δt. Here, Δt can also be understood as the time interval between the adjacent low point presses. The calculation process of Δt is as follows:

[0109] Δt=low t [i]-low t [i-1]

[0110] After the target compression time of the target object is obtained, in step S103, a compression frequency measurement result when the target object performs a cardiopulmonary resuscitation operation is determined according to the target compression time.

[0111] As an optional embodiment, in S103, first, the initial pressing frequency corresponding to the target object is calculated according to the target pressing time, and then the initial pressing frequency is subjected to noise reduction screening to obtain the pressing frequency measurement result corresponding to the target object.

[0112] Specifically, in the above steps, the inverse of the target pressing time is used as the initial pressing frequency corresponding to the target object. Then, according to the preset minimum preset pressing frequency and maximum preset pressing frequency, the abnormal pressing frequency exceeding the minimum preset pressing frequency or the maximum preset pressing frequency in the initial pressing frequency is deleted to obtain the pressing frequency measurement result corresponding to the target object.

[0113] Based on the above example, the initial pressing frequency F corresponding to the target object can be: the reciprocal of the low point time interval Δt (i.e., the time interval between adjacent low point pressing times in the above example). The calculation process of the initial pressing frequency F is expressed by the following formula:

[0114]

[0115] Then, according to the preset minimum frequency threshold MIN_FREQ (i.e., the minimum preset pressing frequency) and the maximum frequency threshold MAX_FREQ (i.e., the maximum preset pressing frequency), the abnormal pressing frequencies exceeding MIN_FREQ or MAX_FREQ in the initial pressing frequency F are deleted to filter random noise. For example, the abnormal frequency elimination process can be expressed as the following formula:

[0116] MIN_FREQ ≤ F ≤ MAX_FREQ

[0117] The initial pressing frequency F obtained after filtering through the above formula is as follows: Figure 8 shown.

[0118] Based on the above example, set the pressing frequency measurement result array F arr, used to store the specific value of the pressing frequency measurement result. Based on this setting, the initial pressing frequency F that meets the conditions (i.e. does not exceed MIN_FREQ or MAX_FREQ) is inserted into the pressing frequency measurement result array F arr , get the push cycle of this press i For example, the pressing frequency measurement result array F arr For specific values, see Fig. 9 shown.

[0119] In the implementation mode of the present application, through the above steps S101 to S103, it is possible to realize automatic measurement of the compression frequency when performing cardiopulmonary resuscitation on the target object by analyzing the shoulder information of the target object, which helps to overcome the problems of low assessment efficiency and poor assessment quality caused by manual scoring in related technologies. It can not only effectively reduce the measurement difficulty of compression frequency and improve the measurement efficiency of compression frequency of cardiopulmonary resuscitation, but also effectively eliminate human errors, improve the accuracy of compression frequency measurement results of cardiopulmonary resuscitation, and the scoring quality of cardiopulmonary resuscitation assessment.

[0120] After introducing the method of the exemplary embodiment of the present application, next, refer to Fig.10 A frequency measuring device for cardiopulmonary resuscitation in an exemplary embodiment of the present application is described. The frequency measuring device for cardiopulmonary resuscitation can be set in a cardiopulmonary resuscitation detection device, or can be other learning, detection, and assessment equipment related to cardiopulmonary resuscitation operations. The frequency measuring device includes the following units:

[0121] An acquisition unit 110 is used to acquire image measurement data when a target object performs a cardiopulmonary resuscitation operation;

[0122] An analysis unit 120, configured to perform a compression cycle analysis on the shoulder information of the target object using the image measurement data to obtain a target compression time of the target object;

[0123] The determination unit 130 is used to determine the compression frequency measurement result when the target object performs a cardiopulmonary resuscitation operation according to the target compression time.

[0124] As an optional implementation manner, the acquiring unit 110 is specifically configured to:

[0125] Acquire video stream data collected when the target object performs cardiopulmonary resuscitation operation;

[0126] Using a human body posture model, the video stream data is split to obtain a start frame position and an end frame position corresponding to each pressing cycle of the target object;

[0127] The video stream data is divided into image measurement data corresponding to each pressing cycle of the target object according to the start frame position and the end frame position.

[0128] As an optional embodiment, each cardiopulmonary resuscitation test includes at least five compression cycles.

[0129] As an optional implementation manner, the analysis unit 120 is specifically configured to:

[0130] Recognize the posture information of the target object in the image measurement data to obtain the target posture information corresponding to the target object in the image measurement data;

[0131] Acquire the shoulder height corresponding to the target object and the shoulder pressing time corresponding to the shoulder height from the target posture information;

[0132] The target pressing time corresponding to the target object is determined according to the shoulder height and the shoulder pressing time.

[0133] As an optional implementation, the target posture information at least includes a joint serial number and joint frame image information corresponding to the joint serial number.

[0134] When the analysis unit 120 obtains the shoulder height corresponding to the target object and the shoulder pressing time corresponding to the shoulder height from the target posture information, it is specifically used to:

[0135] Filtering the target posture information according to the target joint serial number to obtain the shoulder frame image information corresponding to the target object;

[0136] According to the shoulder frame image information, obtaining a first vertical coordinate corresponding to the left shoulder and a second vertical coordinate corresponding to the right shoulder of the target object;

[0137] A mean value is calculated according to the first vertical coordinate and the second vertical coordinate to obtain a shoulder height corresponding to the target object, and a shoulder pressing time corresponding to the shoulder height is obtained.

[0138] As an optional implementation manner, when the analyzing unit 120 determines the target pressing time corresponding to the target object according to the shoulder height and the shoulder pressing time, it is specifically used to:

[0139] Calculating the mean of the shoulder heights to obtain a shoulder mean;

[0140] Compare the shoulder height with the shoulder mean, and if the shoulder height is less than the shoulder mean, use the shoulder pressing time corresponding to the shoulder height as the pressing low point time corresponding to the target object;

[0141] The target pressing time is obtained by calculating the time interval according to the pressing low point time.

[0142] As an optional implementation, the shoulder height is the shoulder height value sequence; each shoulder height value sequence at least includes: all shoulder height values ​​in each round of cardiopulmonary resuscitation stage.

[0143] The analysis unit 120 compares the shoulder height with the shoulder mean. If the shoulder height is less than the shoulder mean, the shoulder pressing time corresponding to the shoulder height is used as the pressing low point time corresponding to the target object, specifically for:

[0144] Traversing each shoulder height value sequence, and comparing the shoulder height values ​​in each shoulder height value sequence with the shoulder mean value one by one;

[0145] If the currently traversed shoulder height value is less than the shoulder average value, the shoulder pressing time corresponding to the currently traversed shoulder height value is used as the pressing low point time of the target object in the current round.

[0146] The analysis unit 120 is also used for: if the current shoulder height value is greater than or equal to the shoulder mean value, then continue to compare the next shoulder height value in the shoulder height value sequence with the shoulder height mean value until all shoulder height values ​​of the shoulder height value sequence in the current round are traversed.

[0147] As an optional implementation, the determination unit 130 is specifically used to: calculate the initial pressing frequency corresponding to the target object according to the target pressing time; perform noise reduction screening on the initial pressing frequency to obtain the pressing frequency measurement result corresponding to the target object.

[0148] As an optional implementation manner, when the determination unit 130 calculates the initial pressing frequency corresponding to the target object according to the target pressing time, it is specifically used to:

[0149] The reciprocal of the target pressing time is used as the initial pressing frequency corresponding to the target object;

[0150] When the determination unit 130 performs noise reduction screening on the initial pressing frequency to obtain the pressing frequency measurement result corresponding to the target object, it is specifically used to:

[0151] According to the preset minimum preset pressing frequency and maximum preset pressing frequency, the abnormal pressing frequency in the initial pressing frequency that exceeds the minimum preset pressing frequency or the maximum preset pressing frequency is deleted to obtain the pressing frequency measurement result corresponding to the target object.

[0152] In the embodiment of the present application, through the frequency measurement device used for cardiopulmonary resuscitation, it is possible to realize automatic measurement of the compression frequency when performing cardiopulmonary resuscitation operations on the target object by analyzing the shoulder information of the target object, which helps to overcome the problems of low assessment efficiency and poor assessment quality caused by manual scoring in related technologies. It can not only effectively reduce the measurement difficulty of the compression frequency and improve the measurement efficiency of the cardiopulmonary resuscitation compression frequency, but also effectively eliminate human errors, improve the accuracy of the measurement results of the cardiopulmonary resuscitation compression frequency, and the scoring quality of the cardiopulmonary resuscitation assessment.

[0153] After introducing the devices, methods and apparatus of the exemplary embodiments of the present application, next, reference is made to Fig.11 The computer-readable storage medium of the exemplary embodiment of the present application is described. The computer-readable storage medium can be set in a cardiopulmonary resuscitation frequency measurement device. Please refer to Fig.11 , the computer-readable storage medium shown is a CD 1100, on which a computer program (i.e., a program product) is stored. When the computer program is executed by the processor, each step recorded in the above method implementation is implemented, for example, image measurement data of the target object when performing cardiopulmonary resuscitation is obtained; the image measurement data is used to perform compression cycle analysis on the shoulder information of the target object to obtain the target compression time of the target object; the compression frequency measurement result of the target object when performing cardiopulmonary resuscitation is determined according to the target compression time; the specific implementation method of each step is not repeated here.

[0154] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0155] After introducing the devices, methods, media and apparatus of the exemplary embodiments of the present application, reference is now made to Fig.12 For the computing device for frequency measurement for cardiopulmonary resuscitation according to the exemplary embodiment of the present application, the computing device may be provided in a frequency measurement device for cardiopulmonary resuscitation.

[0156] Fig.12 A block diagram of an exemplary computing device 100 suitable for implementing the embodiments of the present application is shown. The computing device 100 may be a computer system or a server. Fig.12 The computing device 100 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0157] like Fig.12 As shown, the components of the computing device 100 may include, but are not limited to: one or more processors or processing units 1001, a system memory 1002, and a bus 1003 connecting different system components (including the system memory 1002 and the processing unit 1001).

[0158] The computing device 100 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computing device 100, including volatile and nonvolatile media, removable and non-removable media.

[0159] The system memory 1002 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 10021 and / or cache memory 10022. The computing device 100 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the ROM 10023 may be used to read and write non-removable, non-volatile magnetic media ( Fig.12 is not shown in the Fig.12 As shown in FIG. 1 , a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) can be provided. In these cases, each drive can be connected to bus 1003 via one or more data medium interfaces. System memory 1002 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of each embodiment of the present application.

[0160] A program / utility 10025 having a set (at least one) of program modules 10024 may be stored, for example, in system memory 1002, and such program modules 10024 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 10024 generally perform the functions and / or methods of the embodiments described herein.

[0161] The computing device 100 may also communicate with one or more external devices 1004 (e.g., a keyboard, a pointing device, a display, etc.). Such communication may be performed via an input / output (I / O) interface 1005. In addition, the computing device 100 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 1006. Fig.12As shown, the network adapter 1006 communicates with other modules (such as the processing unit 1001, etc.) of the computing device 100 via the bus 1003. It should be understood that although Fig.12 Not shown, other hardware and / or software modules may be used in conjunction with computing device 100 .

[0162] The processing unit 1001 executes various functional applications and data processing by running the program stored in the system memory 1002, for example, obtaining image measurement data when the target object performs cardiopulmonary resuscitation; using the image measurement data to perform compression cycle analysis on the shoulder information of the target object to obtain the target compression time of the target object; determining the compression frequency measurement result when the target object performs cardiopulmonary resuscitation according to the target compression time. The specific implementation of each step is not repeated here. It should be noted that although several units / modules or subunits / submodules of the frequency measurement device for cardiopulmonary resuscitation are mentioned in the above detailed description, this division is only exemplary and not mandatory. In fact, according to the embodiment of the present application, the features and functions of two or more units / modules described above can be concretized in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be concretized.

[0163] In the description of the present application, it should be noted that the terms "first", "second" and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0164] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0165] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0166] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0167] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0168] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0169] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

[0170] In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

Claims

1. A frequency measurement method for cardiopulmonary resuscitation, characterized in that: include: Acquire image measurement data when the target object performs cardiopulmonary resuscitation; Performing a compression cycle analysis on the shoulder information of the target object using the image measurement data to obtain a target compression time of the target object; A compression frequency measurement result when the target object performs a cardiopulmonary resuscitation operation is determined according to the target compression time.

2. The method according to claim 1, characterized in that The step of obtaining image measurement data when the target object performs a cardiopulmonary resuscitation operation includes: Acquire video stream data collected when the target object performs cardiopulmonary resuscitation operation; Using a human body posture model, the video stream data is split to obtain a start frame position and an end frame position corresponding to each pressing cycle of the target object; The video stream data is divided into image measurement data corresponding to each pressing cycle of the target object according to the start frame position and the end frame position.

3. The method according to claim 2, characterized in that Each CPR test should include at least five cycles of compressions.

4. The method according to claim 1, characterized in that: The step of performing compression cycle analysis on the shoulder information of the target object by using the image measurement data to obtain the target compression time of the target object includes: Recognize the posture information of the target object in the image measurement data to obtain the target posture information corresponding to the target object in the image measurement data; Acquire the shoulder height corresponding to the target object and the shoulder pressing time corresponding to the shoulder height from the target posture information; The target pressing time corresponding to the target object is determined according to the shoulder height and the shoulder pressing time.

5. The method according to claim 4, characterized in that The target posture information at least includes a joint serial number and joint frame image information corresponding to the joint serial number; The step of acquiring the shoulder height corresponding to the target object and the shoulder pressing time corresponding to the shoulder height from the target posture information includes: Filtering the target posture information according to the target joint serial number to obtain the shoulder frame image information corresponding to the target object; According to the shoulder frame image information, obtaining a first vertical coordinate corresponding to the left shoulder and a second vertical coordinate corresponding to the right shoulder of the target object; A mean value is calculated according to the first vertical coordinate and the second vertical coordinate to obtain a shoulder height corresponding to the target object, and a shoulder pressing time corresponding to the shoulder height is obtained.

6. The method according to claim 5, characterized in that The step of determining the target pressing time corresponding to the target object according to the shoulder height and the shoulder pressing time includes: Calculating the mean of the shoulder heights to obtain a shoulder mean; Compare the shoulder height with the shoulder mean, and if the shoulder height is less than the shoulder mean, use the shoulder pressing time corresponding to the shoulder height as the pressing low point time corresponding to the target object; The target pressing time is obtained by calculating the time interval according to the pressing low point time.

7. The method according to claim 6, characterized in that The shoulder height is the shoulder height value sequence; each shoulder height value sequence at least includes: all shoulder height values ​​in each round of cardiopulmonary resuscitation stage; The step of comparing the shoulder height with the shoulder mean, and if the shoulder height is less than the shoulder mean, taking the shoulder pressing time corresponding to the shoulder height as the pressing low point time corresponding to the target object, comprises: Traversing each shoulder height value sequence, and comparing the shoulder height values ​​in each shoulder height value sequence with the shoulder mean value one by one; If the currently traversed shoulder height value is less than the shoulder average value, the shoulder pressing time corresponding to the currently traversed shoulder height value is used as the pressing low point time of the target object in the current round; If the current shoulder height value is greater than or equal to the shoulder mean value, the method further includes: Continue to compare the next shoulder height value in the shoulder height value sequence with the shoulder height mean value until all shoulder height values ​​of the shoulder height value sequence in the current round are traversed.

8. The method according to claim 1, characterized in that The step of determining the compression frequency measurement result when the target object performs a cardiopulmonary resuscitation operation according to the target compression time includes: Calculating an initial pressing frequency corresponding to the target object according to the target pressing time; The initial pressing frequency is subjected to noise reduction screening to obtain a pressing frequency measurement result corresponding to the target object.

9. The method according to claim 8, characterized in that The calculating the initial pressing frequency corresponding to the target object according to the target pressing time includes: The reciprocal of the target pressing time is used as the initial pressing frequency corresponding to the target object; The performing noise reduction screening on the initial pressing frequency to obtain the pressing frequency measurement result corresponding to the target object includes: According to the preset minimum preset pressing frequency and maximum preset pressing frequency, the abnormal pressing frequency in the initial pressing frequency that exceeds the minimum preset pressing frequency or the maximum preset pressing frequency is deleted to obtain the pressing frequency measurement result corresponding to the target object.

10. A frequency measuring device for cardiopulmonary resuscitation, characterized in that: The device comprises: An acquisition unit, used for acquiring image measurement data when a target object performs a cardiopulmonary resuscitation operation; an analyzing unit, configured to perform a compression cycle analysis on the shoulder information of the target object using the image measurement data to obtain a target compression time of the target object; A determination unit is used to determine a compression frequency measurement result when the target object performs a cardiopulmonary resuscitation operation according to the target compression time.

Images