A non-contact cardiopulmonary resuscitation compression action monitoring method and system

Abstract

A non-contact cardiopulmonary resuscitation pressing action monitoring method, the method comprising: acquiring a monitoring area image; acquiring geodetic coordinates of a pressing key point in the monitoring area image; tracking and detecting the Z-axis value Z of the geodetic coordinates of the pressing key point w , thereby obtaining a pressing curve of the pressing action; and monitoring the cardiopulmonary resuscitation pressing action based on one or more pressing parameters of the pressing curve. In the present application, the cardiopulmonary resuscitation pressing action quality monitoring method is a non-contact monitoring method, which does not require direct contact with the personnel when monitoring the pressing quality and does not cause external injury to the user, thereby having the characteristic of good comfort. Furthermore, the cardiopulmonary resuscitation pressing action quality monitoring method of the present application has high user acceptance and is suitable for wide use in clinical rescue scenes, thereby having the characteristic of strong applicability.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and in particular to a non-contact cardiopulmonary resuscitation (CPR) compression action monitoring method and system. Background Technology

[0002] Cardiac arrest is the most critical clinical condition, with more than 7 million cases occurring globally each year, and a survival rate of less than 10%. In my country, approximately 1.4 million people experience cardiac arrest annually, with a cure rate of only 1%. The most important rescue measure for cardiac arrest is cardiopulmonary resuscitation (CPR), and clinical studies have confirmed that the quality of CPR can significantly affect survival outcomes.

[0003] However, existing cardiopulmonary resuscitation (CPR) chest compression quality monitoring devices are contact monitoring devices. When monitoring compression quality, the monitoring device needs to be placed on the chest. Its high rigidity leads to poor comfort and may cause external injury. Patients and their families have low acceptance of it, so it cannot be widely used and its use is limited in real clinical rescue scenarios.

[0004] Therefore, how to solve the above problems has become a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of this invention is to provide a non-contact cardiopulmonary resuscitation (CPR) compression monitoring method and system.

[0006] To address the aforementioned problems, according to a first aspect of the present invention, the present invention provides a non-contact cardiopulmonary resuscitation (CPR) compression action monitoring method, comprising: acquiring an image of the monitoring area;

[0007] Obtain the geodetic coordinates of the key points of pressure in the image of the monitoring area;

[0008] Track and detect the Z-axis value of the key pressing point in geodetic coordinates. w Based on this, the pressing curve of the pressing action is obtained;

[0009] Cardiopulmonary resuscitation (CPR) compression actions are monitored based on one or more compression parameters of the compression curve.

[0010] In some embodiments, the monitoring of cardiopulmonary resuscitation (CPR) compression actions based on one or more compression parameters according to compression curves includes:

[0011] Obtain the compression frequency and compression depth parameters of the compression curve;

[0012] The system monitors whether the pressing action is standardized by comparing the pressing frequency and pressing depth parameters with preset thresholds.

[0013] In some embodiments, the monitoring of cardiopulmonary resuscitation (CPR) compression actions based on one or more compression parameters according to compression curves includes:

[0014] Obtain the compression retention parameters of the compression curve;

[0015] Based on the comparison between the press retention parameter and the preset threshold, it monitors whether press retention occurs during the pressing action.

[0016] In some embodiments, the step of obtaining the geodetic coordinates of the key points pressed in the monitoring area image includes:

[0017] Obtain the pixel coordinates of the key pressure points in the image of the monitored area;

[0018] The pixel coordinates of the key points are transformed using a transformation function to obtain the camera coordinates of the key points.

[0019] The geodetic coordinates of the key points are obtained based on the camera coordinates and camera pitch angle of the key points.

[0020] In some embodiments, the method for obtaining the compression parameters of the compression curve includes:

[0021] Extract the most recent compression waveform with a certain duration from the compression curve;

[0022] The maximum and minimum points of the press waveform are detected, where the maximum and minimum points are defined as points that are larger or smaller than all of the nearby preset extreme points.

[0023] Obtain the time and amplitude of the maximum and minimum points; where the time and amplitude of the maximum point are ((t) max_m y max_m The time and magnitude of the minimum point are ((t) min_k y min_k ));t max_m Let y represent the time corresponding to the m-th maximum point. max_m t represents the height value corresponding to the m-th maximum point; min_k Let y represent the time corresponding to the k-th local minimum. min_k This represents the height value corresponding to the k-th local minimum point;

[0024] Based on the time difference between the maxima, the compression frequency is calculated using the following formula:

[0025]

[0026] The compression depth is calculated using the following formula:

[0027]

[0028] Where y max_i Table y max_i Let y represent the value of the i-th maximum point. min_iTable y min_i This represents the value of the i-th local minimum point.

[0029] In some embodiments, whether press retention occurs is determined based on whether the maximum value in one press cycle is less than the maximum value in the previous press cycle; where y max_m Less than It is assumed that pressure retention occurred at that time, where y max_m y is the maximum value during a single pressing cycle. max_i This is the maximum value in the previous pressing cycle.

[0030] In some embodiments, the step of acquiring the image of the monitoring area includes:

[0031] Control the camera's pitch angle to perform a step search;

[0032] At each step angle, key points of the human body are identified until a human body is identified and located in the center of the camera's field of view; among them, a rectangle formed by four key points—left shoulder, right shoulder, lower left abdomen, and lower right abdomen—is selected as the monitoring area.

[0033] In some embodiments, the monitoring area image includes a compression image and a compression depth image;

[0034] Using a key pressure point detection algorithm, the horizontal coordinates of the pixels of the key pressure points are obtained from the pressure image; the pressure depth values ​​of the pixels of the key pressure points are obtained from the pressure depth image; where the horizontal coordinates include X and Y axis coordinates, and the depth value is the Z axis coordinate value Z. w .

[0035] In some embodiments, it also includes:

[0036] Based on the comparison between the pressing parameters and the preset threshold, an audible and visual alarm is triggered if the comparison result is greater than or less than the preset threshold.

[0037] In some embodiments, the monitoring area is redefined based on the detected movement of the person undergoing CPR;

[0038] Key points on the human body include the left shoulder (x0, y0), the right shoulder (x1, y1), the left lower abdomen (x2, y2), and the right lower abdomen (x3, y3);

[0039] Detecting whether the person undergoing CPR has moved, including:

[0040] The coordinates of the left shoulder, right shoulder, lower left abdomen, and lower right abdomen at time t are respectively... The average distance between each keypoint and the initial stored keypoint is calculated as follows:

[0041] When this value is greater than the preset pixel value, it is determined that the position of the person undergoing cardiac resuscitation has moved;

[0042] The monitoring area has been redefined, including:

[0043] At each step angle, the human key point detection algorithm is executed until a human body is detected and located in the center of the camera's field of view. A rectangle formed by four key points—left shoulder, right shoulder, lower left abdomen, and lower right abdomen—is selected as the monitoring area, and the data of the four initial key points are stored.

[0044] According to a second aspect of the present invention, a non-contact cardiopulmonary resuscitation (CPR) compression action monitoring system is provided, applied to the aforementioned system, comprising:

[0045] An acquisition unit, connected to the camera unit, is used to acquire the geodetic coordinates of the key points pressed in the image of the monitoring area;

[0046] The analysis unit, connected to the acquisition unit, is used to track and detect the Z-axis value of the geodetic coordinates of the pressing key point. w Based on this, the pressing curve of the pressing action is obtained;

[0047] A monitoring unit, connected to the analysis unit, monitors cardiopulmonary resuscitation (CPR) compression actions based on one or more compression parameters of the compression curve.

[0048] In some embodiments, the monitoring unit includes an acquisition module and a monitoring module; the acquisition module is used to acquire the compression frequency and compression depth parameters of the compression curve; the monitoring module monitors whether the compression action is standardized based on the comparison of the compression frequency and compression depth parameters with preset thresholds.

[0049] In some embodiments, the monitoring unit includes an acquisition module and a monitoring module; the acquisition module is used to acquire the press retention parameter of the press curve; the monitoring module monitors whether press retention occurs during the press action based on the comparison of the press retention parameter with a preset threshold.

[0050] In some embodiments, the monitoring unit includes an interception module, a detection module, a parameter acquisition module, and a calculation module;

[0051] The capture module is used to capture the most recent press waveform over a certain period of time from the press curve;

[0052] The detection module is used to detect the maximum and minimum points of the press waveform, where the maximum and minimum points are defined as the point being larger or smaller than all of the nearby preset extreme points;

[0053] The parameter acquisition module is used to obtain the time and amplitude of the maximum and minimum points; where the time and amplitude of the maximum point are ((t) max_m y max_mThe time and magnitude of the minimum point are ((t) min_k y min_k ));t max_m Let y represent the time corresponding to the m-th maximum point. max_m t represents the height value corresponding to the m-th maximum point; min_k Let y represent the time corresponding to the k-th local minimum. min_k This represents the height value corresponding to the k-th local minimum point;

[0054] The calculation module calculates the compression frequency based on the time difference between the maxima, using the following formula:

[0055]

[0056] The compression depth is calculated using the following formula:

[0057]

[0058] Where y max_i Let y represent the height value of the i-th maximum point. min_i This represents the height value of the i-th local minimum point.

[0059] In some embodiments, the monitoring module determines whether press retention has occurred based on whether the maximum value in one press cycle is less than the maximum value in the previous press cycle; wherein, y max_m Less than It is assumed that pressure retention occurred at that time, where y max_m y is the maximum value during a single pressing cycle. max_i This is the maximum value in the previous pressing cycle.

[0060] The above-described technical solution of the present invention has the following beneficial technical effects:

[0061] In this application, a method for monitoring the quality of cardiopulmonary resuscitation (CPR) compression movements involves detecting key compression points in an image of a monitoring area and obtaining the geodetic coordinates of these points. The method then calculates the Z-axis value of the geodetic coordinates of these key points and obtains a compression curve. Furthermore, it calculates the compression parameters of the compression curve and monitors the CPR compression movements based on a comparison of these parameters with preset thresholds. Therefore, this method does not require direct contact with personnel, will not cause injury to the user, and is characterized by good comfort. Moreover, this method has high user acceptance and is suitable for widespread use in clinical emergency scenarios, demonstrating strong applicability. Attached Figure Description

[0062] Figure 1 This is a flowchart of a non-contact cardiopulmonary resuscitation (CPR) compression action quality monitoring method provided by one embodiment of the present invention;

[0063] Figure 2 This is a structural diagram of a non-contact cardiopulmonary resuscitation (CPR) compression action quality monitoring system provided in one embodiment of the present invention;

[0064] Figure 3 This is a structural diagram of a non-contact cardiopulmonary resuscitation (CPR) compression action quality monitoring system provided in one embodiment of the present invention;

[0065] Figure 4 This is a schematic diagram illustrating an application scenario of a non-contact cardiopulmonary resuscitation (CPR) compression quality monitoring system provided by one embodiment of the present invention.

[0066] Figure 5 This is a schematic diagram illustrating an application scenario of a non-contact cardiopulmonary resuscitation compression action quality monitoring system provided by another embodiment of the present invention;

[0067] Figure 6 This is a structural schematic diagram of a non-contact cardiopulmonary resuscitation (CPR) compression quality monitoring system provided by one embodiment of the present invention. Detailed Implementation

[0068] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments and the accompanying drawings. It should be understood that these descriptions are merely exemplary and not intended to limit the scope of the invention. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0069] The terminology used in one or more embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the scope of one or more embodiments of this application. The singular forms “a,” “the,” and “the” used in one or more embodiments of this application and in the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” used in one or more embodiments of this application refers to and includes any or all possible combinations of one or more associated listed items.

[0070] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0071] refer to Figure 1 This invention provides a non-contact cardiopulmonary resuscitation (CPR) compression action monitoring method, comprising:

[0072] S101. Acquire images of the monitoring area;

[0073] In some embodiments, a camera unit is used to acquire images of the monitoring area; the monitoring area images include pressure images and pressure depth images.

[0074] In some embodiments, the monitoring area image includes a compression image and a compression depth image; wherein, the monitoring area image is acquired using a camera unit; the camera unit includes a monitoring camera and a depth camera, the monitoring camera is used to acquire the compression image of the monitoring area; and the depth camera is used to acquire the compression depth image of the monitoring area.

[0075] S102. Obtain the geodetic coordinates of the key pressing points in the monitoring area image;

[0076] Step S102 includes: S1021, obtaining the pixel coordinates of the pressing key points in the monitoring area image;

[0077] Furthermore, based on the key point detection algorithm, key points are detected in the image of the monitoring area, and the pixel coordinates of the key points are obtained;

[0078] In some embodiments, based on the press image and press depth image of the monitoring area image, a press key point detection algorithm is used to obtain the horizontal coordinates of the pixels of the press key points on the press image; and the press depth value of the pixels of the press key points is obtained on the press depth image; wherein, the horizontal coordinates include X and Y axis coordinates, and the depth value is the Z axis coordinate value.

[0079] In some embodiments, based on the press image, a press key point detection algorithm is used to obtain the horizontal coordinates of the pixels of the press key points in the press image;

[0080] Based on the pressure depth image, the pressure depth value of the pixels of the pressure key points in the pressure depth image is obtained by using the pressure key point detection algorithm.

[0081] In some embodiments, the method further includes pixel alignment of the press image and the press depth image. Since the press image and the press depth image have been aligned, the depth value of the press key point at that pixel can be obtained by directly reading the same coordinates of the press depth image, that is, the Z-axis value of the press key point in the pixel coordinate system.

[0082] In some embodiments, the monitoring camera is an RGB camera.

[0083] In some embodiments, the key point of compression includes the palm joint of the hand performing the CPR compression within the monitoring area.

[0084] In some embodiments, the key point of pressure is the metacarpophalangeal joint of the middle finger.

[0085] In a specific example provided in this application, the key point of pressure is the metacarpophalangeal joint of the middle finger, whose horizontal coordinates in the RGB pixel coordinate system are (u, v). Since the RGB image and the pressure depth image have been aligned, the depth value d (Z-axis coordinate) of the pixel can be obtained by directly reading the same coordinates of the pressure depth image, thus obtaining the pixel coordinates (u, v, d) of the key point of pressure.

[0086] S1022. Use a transformation function to transform the pixel coordinates of the key points and obtain the camera coordinates of the key points.

[0087] The pixel coordinates of the key points are transformed using a transformation function to obtain the camera coordinates of the key points in the camera unit coordinate system;

[0088] In a specific example provided in this application, the transformation function is F, and the three-dimensional coordinates of the press key point in the pixel coordinate system are F(u, v, d). Therefore, the camera coordinates of the press key point in the camera unit coordinate system are: (X... c Y c Z c ) = F(u, v, d).

[0089] S1023. Based on the camera coordinates and camera pitch angle of the pressing key point, obtain the geodetic coordinates of the pressing key point.

[0090] In some embodiments, the geodetic coordinates of the key point are obtained based on the camera coordinates and camera pitch angle of the key point, including:

[0091] (X c Y c Z c ) = F(u, v, d).

[0092] S10232. Calculate the pitch angle transformation based on the coordinates of the key points pressed in the camera unit coordinate system.

[0093] In some embodiments, conditional expressions are used:

[0094] Perform pitch angle conversion calculations to obtain the geodetic coordinates of the key pressing point; where θ x For θ x The pitch angle of the camera unit; (X) w Y w Z w ) represents the geodetic coordinates of the key pressing point.

[0095] S103, Track and detect the Z-axis value of the key pressing point's geodetic coordinates. w Based on this, the pressing curve of the pressing action is obtained;

[0096] In some embodiments, the Z-axis value of the geodetic coordinates of the key point is calculated for each frame within a preset period, and the pressing curve is obtained based on each Z-axis value within the period and the pressing parameters of the pressing curve are calculated.

[0097] Furthermore, referring to the above conditional formula, the Z-axis value of the key point's geodetic coordinates is Z in the formula. w Value; Z w The value represents the vertical height of the rescuer's hand. Because the rescuer's hand is pressed against the patient's chest during chest compressions, Z is calculated on each frame. w The compression curve [Z] can then be obtained. w (0), Z w (1), ..., Z w [(n)], where Z w (n) is the Z-axis value of the nth frame, and the preset frame period is T seconds. w The time corresponding to (n) is n*T.

[0098] In some embodiments, when the hand is not detected in the monitoring area, Z w (n)=Z w (n-1). The shape of the pressure curve depends on the position of the hand, and there will be discontinuities during the pressing. In order to maintain the continuity of the pressure curve, the old value is used as the new value.

[0099] S104. Monitor cardiopulmonary resuscitation compression actions based on one or more compression parameters of the compression curve.

[0100] In some embodiments, the cardiopulmonary resuscitation (CPR) compression actions are monitored based on a comparison of compression parameters with preset thresholds.

[0101] In some embodiments, monitoring CPR compression actions based on one or more compression parameters of the compression curve further includes: acquiring compression frequency and compression depth parameters of the compression curve; and monitoring whether the compression actions are standardized based on a comparison of the compression frequency and compression depth parameters with preset thresholds.

[0102] In some embodiments, monitoring CPR compression actions based on one or more compression parameters of the compression curve further includes: acquiring compression retention parameters of the compression curve; and monitoring whether compression retention occurs based on a comparison of the compression retention parameters with a preset threshold.

[0103] In some embodiments, the method for obtaining the compression parameters of the compression curve includes:

[0104] Extract the most recent compression waveform with a certain duration from the compression curve;

[0105] The maximum and minimum points of the press waveform are detected, where the maximum and minimum points are defined as points that are larger or smaller than all of the nearby preset extreme points.

[0106] Obtain the time and amplitude of the maximum and minimum points; where the time and amplitude of the maximum point are ((t) max_m y max_m The time and magnitude of the minimum point are ((t) min_k y min_k ));t max_m Let y represent the time corresponding to the m-th maximum point. max_m t represents the height value corresponding to the m-th maximum point; min_k Let y represent the time corresponding to the k-th local minimum. min_k This represents the height value corresponding to the k-th local minimum point;

[0107] Based on the time difference between the maxima, the compression frequency is calculated using the following formula:

[0108] In the formula, t max_m Let t represent the time corresponding to the m-th maximum point. max_1 This represents the time corresponding to the first maximum point.

[0109] In some embodiments, the formula for calculating the pressing depth is:

[0110] In the formula, y max_i y represents the height value corresponding to the i-th maximum point; min_i This represents the height value corresponding to the i-th local minimum point. The difference between m and k is either 0 or 1.

[0111] In some embodiments, whether press retention occurs is determined based on whether the maximum value in one press cycle is less than the maximum value in the previous press cycle; where y max_m Less than It is assumed that pressure retention occurred at that time, where y max_m y is the maximum value during a single pressing cycle. max_i This is the maximum value in the previous pressing cycle.

[0112] In a specific example provided in this application, the compression curve data of the most recent 5 seconds is extracted, and the maximum and minimum points of the compression waveform are detected. The extreme point is defined as a point that is greater than or less than all of its five nearest neighbors. The time and amplitude of these points are recorded, resulting in m maximum points [(t...]. max_1 y max_1 ), (t max_2 y max_2 ), ..., (t max_m ymax_m ))] and k local minima [(t min_1 y min_1 ), (t min_2 y min_2 ), ..., (t min_k y min_k ))],t max_m Let y represent the time corresponding to the m-th maximum point. max_m t represents the height value corresponding to the m-th maximum point. min_k Let y represent the time corresponding to the k-th local minimum. min_k This represents the height value corresponding to the k-th local minimum point; based on y max_m Is it less than Determine if pressure retention has occurred.

[0113] In some embodiments, the step of acquiring the image of the monitoring area in step S101 includes: controlling the camera pitch angle to perform a step search;

[0114] At each step angle, key human body points are identified until a human body is detected and located at the center of the camera's field of view; wherein, the camera pitch angle is obtained as θ. x The rectangle formed by four key points—left shoulder, right shoulder, lower left abdomen, and lower right abdomen—was selected as the monitoring area.

[0115] In some embodiments, human key points in the monitoring area image are detected according to a human key point detection algorithm, and the monitoring area is determined based on the key points.

[0116] In some embodiments, key points on the human body include the left shoulder, right shoulder, lower left abdomen, and lower right abdomen; wherein, a rectangular monitoring area is determined based on the left shoulder, right shoulder, lower left abdomen, and lower right abdomen.

[0117] In a specific example provided in this application, the camera pitch angle is controlled to search in 1° increments from -30° to -60°. At each increment, a human keypoint detection algorithm is executed until a human body is detected and located at the center of the camera's field of view, thus obtaining the camera pitch angle as θ. x The rectangle formed by four key points—left shoulder (x0, y0), right shoulder (x1, y0), lower left abdomen (x0, y1), and lower right abdomen (x1, y1)—was selected as the monitoring area.

[0118] In this application, this design can eliminate interference from the hands of the person undergoing cardiac resuscitation and other unrelated persons within the field of view, thus preventing false tracking.

[0119] In some embodiments, the method further includes: S105, based on the comparison between the pressing parameter and a preset threshold, triggering an audible and visual alarm based on whether the comparison result is greater than or less than the preset threshold.

[0120] In some embodiments, the acquired compression frequency and depth are compared with preset thresholds to determine whether the compression parameters meet the specifications. When the compression parameters do not meet the specifications, the difference between the current parameters and the preset parameters is calculated, and the rescuer is alerted using lights and voice prompts. Light and voice alarms should also be issued to the rescuer when compression stops.

[0121] In some embodiments, the pressing parameter is the pressing depth; the preset threshold of the pressing depth includes an upper threshold of pressing depth and a lower threshold of pressing depth; based on the comparison between the pressing depth and the upper and lower thresholds of pressing depth, an audible and visual alarm is triggered.

[0122] In some embodiments, the pressing parameters include pressing frequency; the preset threshold of pressing frequency includes an upper threshold and a lower threshold of pressing frequency; and an audible and visual alarm is triggered based on a comparison of the pressing frequency with the upper and lower thresholds of pressing frequency.

[0123] In a specific example provided in this application, the preset lower threshold for compression depth is 5cm, and the upper threshold is 6cm; the preset lower threshold for compression frequency is 100 times / minute, and the upper threshold is 120 times / minute. Every 5 seconds, the compression depth and frequency are compared with the corresponding upper and lower thresholds. When both the compression depth and frequency are within the upper and lower threshold ranges, audio-visual feedback is provided; specifically, a green light illuminates and a prompt is played via the audio feedback device. When the compression depth and frequency exceed the upper and lower threshold ranges, audio-visual feedback is provided; specifically, a red light illuminates and a corresponding prompt is played via the audio feedback device. The prompt is as follows:

[0124] 1. The pressing depth is too large. Please reduce the pressing depth.

[0125] 2. The pressing depth is too shallow; please increase the pressing depth.

[0126] 3. The pressing frequency is too high. Please reduce the pressing frequency.

[0127] 4. The pressing frequency is too low; please increase the pressing frequency.

[0128] Furthermore, when pressure retention is detected, a prompt is played via an audible feedback device: "Pressure retention detected. Please allow your chest to fully recoil."

[0129] In some embodiments, the monitoring area is redefined based on the detected movement of the person undergoing CPR.

[0130] In this application, a camera unit is used to detect key compression points in the image of the monitoring area and obtain the geodetic coordinates of these key points. The Z-axis value of the geodetic coordinates of the key points is calculated to obtain the compression curve. Furthermore, the compression parameters of the compression curve are calculated, and the cardiopulmonary resuscitation (CPR) compression actions are monitored based on a comparison of the compression parameters with a preset threshold. Therefore, this application provides a non-contact method for monitoring the quality of CPR compression actions. It utilizes images of the monitoring area for compression quality monitoring, eliminating the need for direct contact with personnel and preventing external injury to the user, thus offering good comfort. Furthermore, this non-contact CPR compression action quality monitoring method has high user acceptance and is suitable for widespread use in clinical emergency scenarios, demonstrating strong applicability.

[0131] In some embodiments, the monitoring area is redefined based on the detected movement of the person undergoing CPR;

[0132] Key points on the human body include the left shoulder (x0, y0), the right shoulder (x1, y1), the left lower abdomen (x2, y2), and the right lower abdomen (x3, y3);

[0133] Detecting whether the person undergoing CPR has moved, including:

[0134] The coordinates of the left shoulder, right shoulder, lower left abdomen, and lower right abdomen at time t are respectively... The average distance between each keypoint and the initial stored keypoint is calculated as follows:

[0135] When this value is greater than the preset pixel value, it is determined that the position of the person undergoing cardiac resuscitation has moved;

[0136] The monitoring area has been redefined, including:

[0137] At each step angle, the human key point detection algorithm is executed until a human body is detected and located in the center of the camera's field of view. A rectangle formed by four key points—left shoulder, right shoulder, lower left abdomen, and lower right abdomen—is selected as the monitoring area, and the data of the four initial key points are stored.

[0138] In a specific example provided in this application, the detection of whether the position of the person undergoing cardiac resuscitation has moved involves continuously monitoring changes at four key points during the measurement process: left shoulder (x0, y0), right shoulder (x1, y1), lower left abdomen (x2, y2), and lower right abdomen (x3, y3). Assume the key point detected at time t is... The average distance between the initial keypoints for calculation and storage is When this value is greater than 50 pixels, it is determined that the location of the person undergoing cardiac resuscitation has moved, and the monitoring area needs to be redefined.

[0139] Furthermore, the camera's pitch angle is controlled by a servo motor to perform a 1° step search from -30° to -60°. At each step angle, a human keypoint detection algorithm is executed until a human body is detected and located at the center of the camera's field of view, thus obtaining the camera pitch angle as θ. x A quadrilateral formed by four key points—left shoulder (x0, y0), right shoulder (x1, y1), lower left abdomen (x2, y2), and lower right abdomen (x3, y3)—was selected as the monitoring area, and the data of the four key points were stored. The system detects and tracks hand movements only within this area. This design eliminates interference from the hands of people undergoing cardiac resuscitation and other unrelated individuals within the field of view, preventing false tracking.

[0140] In one embodiment, such as Figure 6 As shown, the present invention provides a non-contact cardiopulmonary resuscitation compression action monitoring system, comprising:

[0141] The camera unit acquires images of the monitored area;

[0142] An acquisition unit, connected to the camera unit, is used to acquire the geodetic coordinates of the key points pressed in the image of the monitoring area;

[0143] The analysis unit, connected to the acquisition unit, is used to track and detect the Z-axis value of the geodetic coordinates of the pressing key point. w Based on this, the pressing curve of the pressing action is obtained;

[0144] A monitoring unit, connected to the analysis unit, monitors cardiopulmonary resuscitation (CPR) compression actions based on one or more compression parameters of the compression curve.

[0145] In this application, the cardiopulmonary resuscitation (CPR) compression quality monitoring system is a non-contact device. It detects key compression points in an image of the monitoring area and obtains the geodetic coordinates of these points. It then calculates the Z-axis value of the geodetic coordinates of the key compression points and obtains a compression curve. Furthermore, it calculates the compression parameters of the compression curve and monitors CPR compression movements based on a comparison of these parameters with preset thresholds. Therefore, this CPR compression quality monitoring system does not require direct contact with personnel. Its non-contact compression monitoring method prevents external injury to the user and offers good comfort. Moreover, this CPR compression quality monitoring system has high user acceptance and is suitable for widespread use in clinical emergency scenarios, demonstrating strong applicability.

[0146] Specifically, in some embodiments, a camera unit is used to acquire images of the monitoring area; the monitoring area images include pressure images and pressure depth images. Further, the camera unit includes a monitoring camera and a depth camera, with the monitoring camera used to acquire pressure images of the monitoring area and the depth camera used to acquire pressure depth images of the monitoring area.

[0147] Furthermore, the main control unit includes an acquisition unit and an analysis unit; using the key point detection algorithm of the acquisition unit, the horizontal coordinates of the pixels of the key points are acquired on the key point image; the key point depth value of the pixels of the key points is acquired on the key point depth image; wherein, the horizontal coordinates include X and Y axis coordinates, and the depth value is the Z axis coordinate value Z. w This involves obtaining the pixel coordinates. Further, using a transformation function provided by the camera unit, the pixel coordinates of the pressing key point are transformed to obtain the camera coordinates of the pressing key point. The acquisition unit then obtains the geodetic coordinates of the pressing key point based on the camera coordinates and the camera pitch angle. Finally, the analysis unit tracks and detects the Z-axis value Z of the geodetic coordinates of the pressing key point. w Based on this, the pressing curve of the pressing action is obtained.

[0148] In some embodiments, the monitoring unit includes an acquisition module and a monitoring module; the acquisition module is used to acquire the compression frequency and compression depth parameters of the compression curve; the monitoring module monitors whether the compression action is standardized based on the comparison of the compression frequency and compression depth parameters with preset thresholds.

[0149] In some embodiments, the monitoring unit includes an acquisition module and a monitoring module; the acquisition module is used to acquire the press retention parameter of the press curve; the monitoring module monitors whether press retention occurs during the press action based on the comparison of the press retention parameter with a preset threshold.

[0150] In some embodiments, the monitoring unit includes an interception module, a detection module, a parameter acquisition module, and a calculation module;

[0151] The capture module is used to capture the most recent press waveform over a certain period of time from the press curve;

[0152] The detection module is used to detect the maximum and minimum points of the press waveform, where the maximum and minimum points are defined as the point being larger or smaller than all of the nearby preset extreme points;

[0153] The parameter acquisition module is used to obtain the time and amplitude of the maximum and minimum points; where the time and amplitude of the maximum point are ((t) max_m y max_m The time and magnitude of the minimum point are ((t) min_k y min_k ));t max_m Let y represent the time corresponding to the m-th maximum point. max_m t represents the height value corresponding to the m-th maximum point; min_k Let y represent the time corresponding to the k-th local minimum. min_k This represents the height value corresponding to the k-th local minimum point;

[0154] The calculation module calculates the compression frequency based on the time difference between the maxima, using the following formula:

[0155]

[0156] The compression depth is calculated using the following formula:

[0157]

[0158] Where y max_i Let y represent the height value of the i-th maximum point. min_i This represents the height value of the i-th local minimum point.

[0159] In some embodiments, the monitoring module determines whether press retention has occurred based on whether the maximum value in one press cycle is less than the maximum value in the previous press cycle; wherein, y max_m Less than It is assumed that pressure retention occurred at that time, where y max_m y is the maximum value during a single pressing cycle. max_i This is the maximum value in the previous pressing cycle.

[0160] In some embodiments, the acquisition unit redetermines the monitoring area based on the detected movement of the person undergoing cardiac resuscitation; the acquisition unit includes a human detection module and a control module;

[0161] Key points on the human body include the left shoulder (x0, y0), the right shoulder (x1, y1), the left lower abdomen (x2, y2), and the right lower abdomen (x3, y3);

[0162] The human detection module detects whether the person undergoing cardiac resuscitation has moved, including:

[0163] The coordinates of the left shoulder, right shoulder, lower left abdomen, and lower right abdomen at time t are respectively... The average distance between each keypoint and the initial stored keypoint is calculated as follows: When this value is greater than the preset pixel value, it is determined that the position of the person undergoing cardiac resuscitation has moved;

[0164] The control module redefines the monitoring area, including:

[0165] At each step angle, the human key point detection algorithm is executed until a human body is detected and located in the center of the camera's field of view. A rectangle formed by four key points—left shoulder, right shoulder, lower left abdomen, and lower right abdomen—is selected as the monitoring area, and the data of the four initial key points are stored.

[0166] In some embodiments, the system further includes an alarm unit connected to the monitoring unit, which triggers an audible and visual alarm based on a comparison of the pressing parameters with a preset threshold.

[0167] In one specific embodiment provided in this application, Figure 2-3 The non-contact CPR compression monitoring system shown includes a main body, and an alarm unit, a camera unit 5, and a main control unit mounted on the main body. The camera unit 5 is connected to the main control unit, and the alarm unit is also connected to the main control unit. The alarm unit includes an audible alarm unit 1 and a visual alarm unit 2. The camera unit 5 includes an RGB camera and a depth camera. The monitoring system also includes a display screen 3, input buttons 4, and a battery and power management unit. The display screen 3 is used to display signals and parameters, the input buttons 4 are used for user interaction, and the battery and power management unit includes a power button 6 and an external power interface 7. Furthermore, the system is mounted on a vertical bracket or wall via threaded holes 8.

[0168] In one embodiment, this application illustrates two use cases of the system, referencing Figure 4-5 , Figure 4 The system described in this application is installed using a vertical bracket for temporary emergency rescue scenarios. Figure 5 The system described in this application is designed for fixed installation on a wall for use in emergency rooms or wards.

[0169] According to a third aspect of the present invention, a computing device is provided, including a memory, a processor, and computer instructions stored in the memory and executable on the processor, wherein the processor executes the instructions to implement the steps of the method described above.

[0170] According to a fourth aspect of the present invention, a computer-readable storage medium is provided that stores computer instructions, characterized in that the instructions, when executed by a processor, implement the steps of the method described above.

[0171] It should be understood that the specific embodiments described above are merely illustrative or explanatory of the principles of the invention and do not constitute a limitation thereof. Therefore, any modifications, equivalent substitutions, improvements, etc., made without departing from the spirit and scope of the invention should be included within the protection scope of the invention. Furthermore, the appended claims are intended to cover all variations and modifications falling within the scope and boundaries of the appended claims, or equivalent forms of such scope and boundaries.

[0172] The above is an illustrative scheme of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium and the technical solution of the cardiopulmonary resuscitation compression quality monitoring method described above belong to the same concept. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the cardiopulmonary resuscitation compression quality monitoring method described above.

[0173] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0174] Computer instructions include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. Computer-readable media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in computer-readable media can be appropriately added to or removed according to the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0175] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0176] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0177] The preferred embodiments disclosed above are merely illustrative of this application. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to specific implementations. Clearly, many modifications and variations can be made based on the content of this application. These embodiments are selected and specifically described in this application to better explain the principles and practical applications of this application, thereby enabling those skilled in the art to better understand and utilize this application. This application is limited only by the claims and their full scope and equivalents.

Claims

1. A non-contact cardiopulmonary resuscitation (CPR) compression monitoring method, characterized in that, include: Acquire images of the monitored area; Obtain the geodetic coordinates of the key points of pressure in the image of the monitoring area; Tracking and detecting the geodetic coordinates of the key pressing points Axis value Based on this, the pressing curve of the pressing action is obtained; Monitor cardiopulmonary resuscitation compression actions based on one or more compression parameters of the compression curve; The monitoring of cardiopulmonary resuscitation (CPR) compression actions based on one or more compression parameters according to the compression curve includes: Obtain the compression frequency and compression depth parameters of the compression curve; The system monitors whether the pressing action is standardized by comparing the pressing frequency and pressing depth parameters with preset thresholds. The monitoring of cardiopulmonary resuscitation (CPR) compression actions based on one or more compression parameters according to the compression curve includes: Obtain the compression retention parameters of the compression curve; Based on the comparison between the press retention parameter and the preset threshold, it monitors whether press retention occurs during the pressing action; The step of obtaining the geodetic coordinates of the key points pressed in the image of the monitoring area further includes: Obtain the pixel coordinates of the key pressure points in the image of the monitored area; The pixel coordinates of the key points are transformed using a transformation function to obtain the camera coordinates of the key points. Based on the camera coordinates and camera pitch angle of the key point of pressure, obtain the geodetic coordinates of the key point of pressure. The method for obtaining the compression parameters of the compression curve includes: Extract the most recent compression waveform with a certain duration from the compression curve; The maximum and minimum points of the press waveform are detected, where the maximum and minimum points are defined as points that are larger or smaller than all of the nearby preset extreme points. Obtain the time and amplitude of the maximum and minimum points; where the time and amplitude of the maximum point are ( The time and magnitude of the minimum point are (). ); Indicates the first The time corresponding to each maximum point Indicates the first The height values ​​corresponding to the maximum points; Indicates the first The time corresponding to each local minimum point Indicates the first The height values ​​corresponding to the minimum points; Based on the time difference between the maxima, the compression frequency is calculated using the following formula: , The compression depth is calculated using the following formula: , in This represents the height value of the i-th maximum point. This represents the height value of the i-th local minimum point.

2. The method according to claim 1, characterized in that, Whether compression retention has occurred is determined by whether the maximum value in one compression cycle is less than the maximum value in the previous compression cycle; where, Less than It is assumed that pressure retention has occurred, where, This is the maximum value within a single compression cycle. This is the maximum value in the previous pressing cycle.

3. The method according to claim 1, characterized in that, The step of acquiring the image of the monitoring area includes: Control the camera's pitch angle to perform a step search; The system identifies key human body points at each step angle until a human body is detected and located at the center of the camera's field of view. The rectangular area formed by four key points—left shoulder, right shoulder, lower left abdomen, and lower right abdomen—is selected as the monitoring area.

4. The method according to claim 3, characterized in that, The images of the monitored area include compression images and compression depth images; Using a key pressure point detection algorithm, the horizontal coordinates of the pixels at the key pressure points are obtained from the key pressure image; the pressure depth values ​​of the pixels at the key pressure points are obtained from the pressure depth image; where the horizontal coordinates include X and Y axis coordinates, and the depth values ​​are... axis coordinates .

5. The method according to claim 1, characterized in that, Also includes: Based on the comparison between the pressing parameters and the preset threshold, an audible and visual alarm is triggered if the comparison result is greater than or less than the preset threshold.

6. The method according to claim 3, characterized in that, The monitoring area was redefined based on the detected movement of the person requiring CPR; Key points of the human body include the left shoulder right shoulder , lower abdomen left and lower abdominal right ; Detecting whether the person undergoing CPR has moved, including: Detection The coordinates of the left shoulder, right shoulder, lower left abdomen, and lower right abdomen at time are respectively , The average distance between each keypoint and the stored initial keypoint is calculated as follows: ; When this value is greater than the preset pixel value, it is determined that the position of the person undergoing cardiac resuscitation has moved; The monitoring area has been redefined, including: At each step angle, the human key point detection algorithm is executed until a human body is detected and located in the center of the camera's field of view. A rectangle formed by four key points—left shoulder, right shoulder, lower left abdomen, and lower right abdomen—is selected as the monitoring area, and the data of the four initial key points are stored.

7. A non-contact cardiopulmonary resuscitation (CPR) compression monitoring system, characterized in that, include: The camera unit acquires images of the monitored area; An acquisition unit, connected to the camera unit, is used to acquire the geodetic coordinates of the key points pressed in the image of the monitoring area; The analysis unit, connected to the acquisition unit, is used to track and detect the geodetic coordinates of the key pressing points. Axis value Based on this, the pressing curve of the pressing action is obtained; A monitoring unit, connected to the analysis unit, monitors cardiopulmonary resuscitation (CPR) compression actions based on one or more compression parameters of the compression curve; The monitoring unit includes an acquisition module and a monitoring module; the acquisition module is used to acquire the compression frequency and compression depth parameters of the compression curve; the monitoring module monitors whether the compression action is standardized based on the comparison of the compression frequency and compression depth parameters with preset thresholds; The monitoring unit includes an acquisition module and a monitoring module; the acquisition module is used to acquire the pressure retention parameter of the pressure curve; the monitoring module monitors whether pressure retention occurs during the pressing action based on the comparison between the pressure retention parameter and a preset threshold. The step of obtaining the geodetic coordinates of the key point in the monitoring area image further includes: obtaining the pixel coordinates of the key point in the monitoring area image; converting the pixel coordinates of the key point using a conversion function to obtain the camera coordinates of the key point; and obtaining the geodetic coordinates of the key point based on the camera coordinates and camera pitch angle of the key point. The monitoring unit includes an interception module, a detection module, a parameter acquisition module, and a calculation module; The capture module is used to capture the most recent press waveform over a certain period of time from the press curve; The detection module is used to detect the maximum and minimum points of the press waveform, where the maximum and minimum points are defined as the point being larger or smaller than all of the nearby preset extreme points; The parameter acquisition module is used to obtain the time and amplitude of the maximum and minimum points; where the time and amplitude of the maximum point are ( The time and magnitude of the minimum point are (). ); Indicates the first The time corresponding to each maximum point Indicates the first The height values ​​corresponding to the maximum points; Indicates the first The time corresponding to each local minimum point Indicates the first The height values ​​corresponding to the minimum points; The calculation module calculates the compression frequency based on the time difference between the maxima, using the following formula: , The compression depth is calculated using the following formula: , in This represents the height value of the i-th maximum point. This represents the height value of the i-th local minimum point.

8. The system according to claim 7, characterized in that, The monitoring module determines whether compression retention has occurred based on whether the maximum value in one compression cycle is less than the maximum value in the previous compression cycle; wherein, Less than It is assumed that pressure retention has occurred, where, This is the maximum value within a single compression cycle. This is the maximum value in the previous pressing cycle.

Images