Elderly state analysis method based on image recognition

Abstract

The invention relates to the technical field of old person state monitoring, in particular to an old person state analysis method based on image recognition, comprising the following steps: S1, acquiring first image data of an old person and old person physiological data including stature data, heart rate record and blood pressure record in real time from multiple angles; s2, identifying the identity of the elderly, extracting an initial key point in the first image data, and judging whether an error occurs or not; if yes, entering the step S3; if not, marking the initial key point as a determined key point, marking the first image data as second image data, and entering the step S4; s3, correcting the initial key point in the first image data to generate second image data; according to the method, the situation that the heart rate and the blood pressure may be changed when the old fall down is considered, so that the calculation precision of the comprehensive risk degree value is further improved, and medical staff can take corresponding treatment measures in time according to the comprehensive risk degree value.

Description

Technical Field

[0001] The present invention relates to the technical field of elderly status monitoring, and in particular to an elderly status analysis method based on image recognition. Background Art

[0002] The main responsibility of a nursing home is to provide comprehensive care and services to the elderly and ensure their quality of life, health and safety. However, the medical staff in a nursing home is limited and often cannot take care of everything. Therefore, it is necessary to set up multiple monitoring devices in the nursing home to take real-time photos of the elderly and analyze the elderly's condition based on the photos taken.

[0003] However, a common analysis method is to directly use the openpose algorithm to extract key points, and then directly predict whether the elderly have fallen based on the changes in key points and the elderly's physiological data. This method does not take into account the impact of the elderly's fall on physiological data, so there are errors in the calculation of the elderly's actual condition and risk level, which is not conducive to medical staff to take accurate countermeasures based on it. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides a method for analyzing the status of the elderly based on image recognition, which solves the technical problem that the prior art does not take into account the impact of the elderly's fall on physiological data, resulting in errors in the analysis of the elderly's actual status.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for analyzing the state of an elderly person based on image recognition comprises the following steps:

[0007] S1, acquiring first image data of the elderly and physiological data of the elderly including body data, heart rate record and blood pressure record in real time from multiple angles;

[0008] S2, identifying the identity of the elderly and extracting initial key points in the first image data, and determining whether errors occur;

[0009] If yes, proceed to step S3;

[0010] If not, the initial key point is marked as a determined key point, and the first image data is marked as the second image data and the process proceeds to step S4;

[0011] S3, correcting the initial key points in the first image data to generate second image data;

[0012] S4, analyzing the current state of the elderly according to the continuous second image data and the elderly's physiological data;

[0013] S5. The comprehensive risk value Provide real-time feedback to staff.

[0014] Furthermore, in step S2, the following steps are specifically included:

[0015] S21, constructing initial key edges for representing the skeleton and torso of the elderly according to the initial key points;

[0016] S22, obtaining the monitoring device calibration parameters including the focal length, principal point coordinates, rotation matrix and translation vector of the monitoring device;

[0017] S23, constructing a world coordinate system with one of the monitoring devices as the origin, selecting two first image data, and calculating the three-dimensional coordinates of each initial key point according to the calibration parameters ;

[0018] S24. Calculate the length of each initial key edge , and its calculation formula is:

[0019]

[0020] In the formula, represents the length of the i-th initial key edge; Represents the three-dimensional coordinates of one of the initial key points of the i-th initial key edge; Represents the three-dimensional coordinates of another initial key point of the i-th initial key edge;

[0021] S25, preset tolerance range , whose expression is:

[0022]

[0023] In the formula, Represents the tolerance range of the i-th initial key edge; represents the actual length of the limb corresponding to the i-th initial key edge; Indicates the tolerance percentage;

[0024] S26, determine the length Is it in middle;

[0025] If yes, it means that there is no error in the initial key point;

[0026] If not, it means that there is an error in the initial key point.

[0027] Furthermore, in step S23, the following steps are specifically included:

[0028] S231, select an initial key point and obtain its position in the two first image data and ;

[0029] S232, according to and Construct the first linear equation system, whose expressions are:

[0030]

[0031]

[0032] Simplifying it to:

[0033]

[0034]

[0035] in, ;

[0036] S233. Define normalized coordinates , whose expression is:

[0037]

[0038]

[0039] S234, according to the normalized coordinates Construct the second linear equation system, which is expressed as:

[0040]

[0041]

[0042] Expanding this to:

[0043]

[0044]

[0045] S235, Merger and , we get the third linear equation system, which is expressed as:

[0046]

[0047] in,

[0048]

[0049]

[0050]

[0051] S236, solving the third linear equation group by the least square method to obtain the three-dimensional coordinates of the initial key point .

[0052] Furthermore, in step S3, the following steps are specifically included:

[0053] S31, dividing the initial key point into a first initial key point and a second initial key point;

[0054] S32. Use edge detection algorithm to extract the actual limb direction vector of the elderly , ;

[0055] S33. Calculate the estimated direction vector of the initial key edge , and its calculation formula is:

[0056]

[0057] In the formula, Represents the estimated direction vector of the initial key edge between the i-th and j-th initial key points; and Represent the three-dimensional coordinates of the i-th and j-th initial key points respectively;

[0058] S34. Calculate the actual limb direction vector and the estimated direction vector Angle , and its calculation formula is:

[0059]

[0060]

[0061] S35, calculating the offset influence of the key point in each direction, and the calculation formula is:

[0062]

[0063]

[0064]

[0065] In the formula, , and Respectively represent the offset influence of the i-th key point on the x, y and z axes; represents the length of the initial key edge between the i-th and j-th initial key points; represents the actual length of the old man’s limb corresponding to the initial key edge between the i-th and j-th initial key points;

[0066] S36, correcting the three-dimensional coordinates of the second initial key point according to the offset influence ( ), the calculation formula is:

[0067]

[0068]

[0069]

[0070] S37, repeat the above steps until all the second initial key points are corrected, all the key points are recorded as determined key points, the corrected initial key edges are recorded as determined key edges and the second image data is constructed based on them.

[0071] Furthermore, in step S4, the following steps are specifically included:

[0072] S41. Calculate the limb angle change score of the elderly , and its calculation formula is:

[0073]

[0074] In the formula, The limb angle change score represents the degree of change in the angles of all key edges determined by the elderly; Indicates the total number of key edges determined; Indicates about The weight coefficient of represents the angle between the i-th critical edge and the vertical direction at time t; Indicates that the i-th critical edge is determined at time The angle between the time and the vertical direction; Represents the time interval between two adjacent frames of first image data;

[0075] S42. Calculate the speed change score of the elderly , and its calculation formula is:

[0076]

[0077] In the formula, A speed change score representing the degree of speed change of all determined key points of the elderly; represents the velocity of the i-th key point at time t; Indicates that the i-th critical edge is determined at time speed at 1000 s; Indicates about The weight coefficient of

[0078] S43. Scoring based on limb angle changes and speed change score Calculate the risk of falling ;

[0079] S44. Assess the current physical health of the elderly based on their heart rate and blood pressure records ;

[0080] S45. According to the fall risk value and physical health Calculate the comprehensive risk value .

[0081] Further, in step S43, the fall risk value The calculation formula is:

[0082]

[0083] In the formula, Indicates the likelihood of the elderly falling; , and They represent the first, second and third weight parameters for the fall risk value respectively.

[0084] Furthermore, in step S44, the following steps are specifically included:

[0085] S441, obtaining blood pressure records and heart rate records of several test elderly people in a time period T as training samples;

[0086] S442. Calculate the physical condition score of each tested elderly person one day after time T , and use this as the sample label;

[0087] S443, training a physical condition assessment model using training samples and sample labels to obtain a target model;

[0088] S444. Input heart rate and blood pressure records, and output the health status of the elderly .

[0089] Furthermore, in step S442, the following steps are specifically included:

[0090] S4421, calculate heart rate deviation score , and its calculation formula is:

[0091]

[0092] In the formula, Represents the weight coefficient about heart rate; It means testing the heart rate of the elderly one day after T; Indicates normal heart rate level; is the standard deviation of heart rate;

[0093] S4422, Calculate systolic blood pressure deviation score and diastolic blood pressure deviation score , and its calculation formula is:

[0094]

[0095]

[0096] In the formula, and Respectively represent the weight coefficients for systolic and diastolic blood pressure; and Respectively represent the systolic and diastolic blood pressure of the elderly tested one day after T; and Respectively represent normal systolic and diastolic blood pressure levels; and standard deviation of systolic and diastolic blood pressure;

[0097] S4423, scoring based on heart rate deviation , Systolic blood pressure deviation score and diastolic blood pressure deviation score Calculating physical condition score , and its calculation formula is:

[0098]

[0099] In the formula, It indicates the physical condition score of the tested elderly one day after T.

[0100] Furthermore, in step S45, the following steps are specifically included:

[0101] S451. Calculate the average heart rate deviation score of the elderly after falling , and its calculation formula is:

[0102]

[0103] In the formula, It indicates the average heart rate of the elderly after falling; represents the weight parameter for the average heart rate deviation score;

[0104] S452. Calculate the average systolic blood pressure deviation score of the elderly after a fall , and its calculation formula is:

[0105]

[0106] In the formula, It represents the average systolic blood pressure of the elderly after falling; represents the weight parameter regarding the mean systolic blood pressure deviation score;

[0107] S453. Calculate the average diastolic blood pressure deviation score of the elderly after falling , and its calculation formula is:

[0108]

[0109] In the formula, It represents the average diastolic blood pressure of the elderly after falling; represents the weight parameter regarding the mean diastolic blood pressure deviation score;

[0110] S454. Calculate the comprehensive risk value .

[0111] Further, in step S454, the comprehensive risk value The calculation formula is:

[0112]

[0113] In the formula, , , , and Respectively represent the first, second, third, fourth and fifth weight parameters regarding the comprehensive risk value.

[0114] Compared with the prior art, the present invention provides an elderly status analysis method based on image recognition, which has the following beneficial effects:

[0115] 1. The present invention takes into account that when an elderly person falls, not only the angle of the limbs will change significantly, but also the speed of movement will change suddenly. Therefore, the calculation of the fall risk value is more accurate than other calculation methods. In addition, when calculating the comprehensive risk value, the change in heart rate and blood pressure may be caused when the elderly person falls. Therefore, the calculation accuracy of the comprehensive risk value is further improved, so that medical staff can take corresponding treatment measures in time according to the comprehensive risk value.

[0116] 2. When detecting the limb position and movement of the elderly, the present invention takes into account that heavy clothing will affect the detection accuracy of the openpose algorithm, thereby affecting the subsequent judgment of the elderly's state. Therefore, by introducing image processing technology to extract the actual limb direction and considering the angle difference for correction, the actual posture of the human body can be more accurately reflected. This method not only utilizes the length information provided by the three-dimensional coordinates, but also combines the direction information in the two-dimensional image, thereby providing a more comprehensive posture estimation.

[0117] 3. The present invention obtains the first image data from the monitoring device at two angles, and then calculates the three-dimensional coordinates of each initial key point in the world coordinate system, so as to calculate the distance between the initial key points later and thereby evaluate whether there is any deviation in the initial key points. BRIEF DESCRIPTION OF THE DRAWINGS

[0118] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0119] Figure 1 It is a flow chart of the elderly status analysis method based on image recognition of the present invention;

[0120] Figure 2 It is a schematic diagram of the initial key points of the present invention. DETAILED DESCRIPTION

[0121] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific implementation methods, so that the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0122] Those skilled in the art can understand that all or part of the steps in the following embodiments can be completed by instructing the relevant hardware through a program, so the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0123] Nursing homes are equipped with professional medical staff and caregivers who can provide comprehensive care services for the elderly, including daily life care, health monitoring, and drug management. This is especially important for those elderly people who need special medical attention. However, the nursing staff in nursing homes is limited. When the elderly move freely in the nursing home, it is impossible to ensure that the status of each elderly person is known in real time. Therefore, if an elderly person suddenly falls ill or trips and falls in the nursing home, the elderly person cannot receive timely care and treatment. For this reason, Figure 1 As shown, the present invention proposes a method for analyzing the state of an elderly person based on image recognition, comprising the following steps:

[0124] S1. Acquire the first image data of the elderly and the elderly's physiological data including body shape data, heart rate records and blood pressure records in real time from multiple angles; specifically, a plurality of monitoring devices are generally set up in a nursing home to obtain multi-angle (at least two angles) photos of each elderly person in real time, and the image data that can identify the elderly can be extracted through a convolutional neural network model. In addition, the body shape data, heart rate records and blood pressure records can be obtained through daily measurements. It should be noted that the convolutional neural network is a common existing technology and will not be elaborated here.

[0125] S2, identifying the identity of the elderly and extracting initial key points in the first image data, and determining whether errors occur;

[0126] If yes, proceed to step S3;

[0127] If not, the initial key point is marked as a determined key point, and the first image data is marked as the second image data and the process proceeds to step S4; specifically, the openpose algorithm and the facial recognition algorithm are used. The facial recognition algorithm can directly identify the identity of the elderly, so as to match the corresponding physiological data of the elderly according to the facial recognition algorithm. The openpose algorithm can extract the initial key point in the first image data. In the present invention, each initial key point is as follows: Figure 2 As shown, there are 13 initial key points, including the head initial key point, the neck initial key point, the left shoulder initial key point, the right shoulder initial key point, the left elbow initial key point, the right elbow initial key point, the left wrist initial key point, the right wrist initial key point, the hip initial key point, the left knee initial key point, the right knee initial key point, the left ankle initial key point and the right ankle initial key point. Since the elderly are more afraid of cold than young people, they generally wear more and heavier clothes in winter, which will affect the detection accuracy of the initial key points, and then affect the later analysis of the elderly's state. It should be noted that the openpose algorithm and the facial recognition algorithm are both existing technologies and will not be repeated here. For this reason, in step S2, the following steps are specifically included:

[0128] S21, constructing initial key edges for representing the skeleton and torso of the elderly according to the initial key points; specifically, the initial key edges are combined with Figure 2 As shown, it includes the head and neck initial key edge, the left shoulder and neck initial key edge, the right shoulder and neck initial key edge, the left shoulder and upper arm key edge, the right shoulder and upper arm key edge, the left forearm initial key edge, the right forearm initial key edge, the trunk initial key edge, the left thigh initial key edge, the right thigh initial key edge, the left calf initial key edge and the right calf initial key edge, a total of 12 initial key edges;

[0129] S22, obtaining the monitoring device calibration parameters including the focal length, principal point coordinates, rotation matrix and translation vector of the monitoring device; specifically, the expression of the projection equation of the monitoring device is:

[0130]

[0131] in, represents the two-dimensional coordinates of the i-th initial key point in an image data; Represents the three-dimensional coordinates of the i-th initial key point; Represents the internal parameter matrix of the monitoring device; Represents the rotation matrix of the monitoring device; Represents the translation vector of the monitoring device;

[0132]

[0133] in, and Respectively represent the focal length of the monitoring device on the x-axis and y-axis; and Respectively represent the coordinates of the principal point of the monitoring device in the x-axis and y-axis directions;

[0134]

[0135] in, Indicates the rotation of the monitoring device relative to the world coordinate system; Represents the translation component of the monitoring device relative to the world coordinate system.

[0136] S23, constructing a world coordinate system with one of the monitoring devices as the origin, selecting two first image data, and calculating the three-dimensional coordinates of each initial key point according to the calibration parameters Specifically, since there is an angle between different monitoring devices, the actual coordinates of each initial key point can be calculated by triangulation. It should be noted that the acquisition time point of the two first image data is the same. Therefore, in step S23, the following steps are specifically included:

[0137] S231, select an initial key point and obtain its position in the two first image data and ;

[0138] S232, according to and Construct the first linear equation system, whose expressions are:

[0139]

[0140]

[0141] Simplifying it to:

[0142]

[0143]

[0144] in, ;

[0145] S233. Define normalized coordinates , whose expression is:

[0146]

[0147]

[0148] S234, according to the normalized coordinates Construct the second linear equation system, which is expressed as:

[0149]

[0150]

[0151] Expanding this to:

[0152]

[0153]

[0154] S235, Merger and , we get the third linear equation system, which is expressed as:

[0155]

[0156] in,

[0157]

[0158]

[0159]

[0160] S236, solving the third linear equation group by the least square method to obtain the three-dimensional coordinates of the initial key point .

[0161] In step S23 of the present invention, the three-dimensional coordinates of each initial key point in the world coordinate system are calculated based on the first image data obtained by the monitoring device at two angles, so as to facilitate the subsequent calculation of the distance between the initial key points and thereby evaluate whether there is any deviation in the initial key points.

[0162] S24. Calculate the length of each initial key edge , and its calculation formula is:

[0163]

[0164] In the formula, represents the length of the i-th initial key edge; Represents the three-dimensional coordinates of one of the initial key points of the i-th initial key edge; Represents the three-dimensional coordinates of another initial key point of the i-th initial key edge;

[0165] S25, preset tolerance range , whose expression is:

[0166]

[0167] In the formula, Represents the tolerance range of the i-th initial key edge; represents the actual length of the limb corresponding to the i-th initial key edge; Indicates the tolerance percentage; in the present invention, 5%;

[0168] S26, determine the length Is it in middle;

[0169] If yes, it means that there is no error in the initial key point;

[0170] If not, it means that there is an error in the initial key point.

[0171] It should be noted that if there is no error in the initial key point, the initial key edge is also marked as a determined key edge.

[0172] S3, correcting the initial key points in the first image data to generate the second image data; specifically, if the position of the initial key points has a large error, then the length and angle of the initial key sides constructed according to the initial key points will also have a large error, so that the movements and postures of the elderly cannot be accurately obtained, affecting the accuracy of the subsequent analysis of the elderly's state. Therefore, in step S3, the following steps are specifically included:

[0173] S31, dividing the initial key points into first initial key points and second initial key points; specifically, since some initial key points are not easily blocked, the monitoring equipment can directly capture them, and the error is often small, such as the head, wrists and ankles, so the initial key points corresponding to these parts can be used as the first initial key points, and the other initial key points can be used as the second initial key points. Therefore, the first initial key points include the head initial key points, the left wrist initial key points, the right wrist initial key points, the left ankle initial key points and the right ankle initial key points, and the other initial key points are the initial key points to be corrected;

[0174] S32. Use edge detection algorithm to extract the actual limb direction vector of the elderly , ; Wherein, i and j represent the i-th and j-th initial key points respectively, and there is an initial key edge between the i-th and j-th key points; Specifically, although the openpose algorithm will be affected by clothing and cause deviation, its calculation of the approximate direction of the limbs is still relatively accurate, so the approximate position of the elderly limbs can be determined according to the direction of the initial key edge, and then the actual limb direction of this position can be determined according to the edge detection algorithm, so as to facilitate the subsequent correction of the position of each initial key point. It should be noted that the edge detection algorithm belongs to the existing technology and will not be described in detail here;

[0175] S33. Calculate the estimated direction vector of the initial key edge , and its calculation formula is:

[0176]

[0177] In the formula, Represents the estimated direction vector of the initial key edge between the i-th and j-th initial key points; and Represent the three-dimensional coordinates of the i-th and j-th initial key points respectively;

[0178] S34. Calculate the actual limb direction vector and the estimated direction vector Angle , and its calculation formula is:

[0179]

[0180]

[0181] S35, calculating the offset influence of the key point in each direction, and the calculation formula is:

[0182]

[0183]

[0184]

[0185] In the formula, , and Respectively represent the offset influence of the i-th key point on the x, y and z axes; represents the length of the initial key edge between the i-th and j-th initial key points; represents the actual length of the old man’s limb corresponding to the initial key edge between the i-th and j-th initial key points;

[0186] S36, correcting the three-dimensional coordinates of the second initial key point according to the offset influence ( ), the calculation formula is:

[0187]

[0188]

[0189]

[0190] Specifically, the second initial key point can be corrected by the first initial key point. For example, the neck initial key point is corrected according to the head initial key point, and then the left shoulder initial key point and the right shoulder initial key point are corrected according to the neck initial key point. In order to avoid the reduction of accuracy, the first initial key point is preferentially used to calculate the adjacent second initial key point. Figure 2 It can be seen from the content that only the left shoulder initial key point, the right shoulder initial key point and the hip initial key point are not adjacent to the first initial key point, so these three initial key points are calculated last.

[0191] S37, repeat the above steps until all the second initial key points are corrected, all the key points are recorded as determined key points, the corrected initial key edges are recorded as determined key edges and the second image data is constructed based on them.

[0192] In the present invention, when detecting the limb position and movement of the elderly, it is considered that heavy clothing will affect the detection accuracy of the openpose algorithm, thereby affecting the later judgment of the elderly's state. Therefore, by introducing image processing technology to extract the actual limb direction and considering the angle difference for correction, the actual posture of the human body can be more accurately reflected. This method not only utilizes the length information provided by the three-dimensional coordinates, but also combines the direction information in the two-dimensional image, thereby providing a more comprehensive posture estimation.

[0193] S4, analyzing the current state of the elderly according to the continuous second image data and the elderly's physiological data; specifically, the elderly's daily movements are slower than those of young people, so the acceleration of their limbs is generally smaller, and when the elderly have a sudden illness or are tripped, the acceleration of their limbs will increase significantly, and this change will start from the legs and spread to the whole body. The basic physical condition of each elderly is different, so when different elderly people have the same fall situation, their conditions may be different. Therefore, in step S4, the following steps are specifically included:

[0194] S41. Calculate the limb angle change score of the elderly , and its calculation formula is:

[0195]

[0196] In the formula, The limb angle change score represents the degree of change in the angles of all key edges determined by the elderly; Indicates the total number of key edges determined; Indicates about The weight coefficient of represents the angle between the i-th critical edge and the vertical direction at time t; Indicates that the i-th critical edge is determined at time The angle between the time and the vertical direction; represents the time interval between two adjacent frames of first image data; in the present invention, According to different limb positions, the key edges are determined by the head and neck, the left shoulder and neck, the right shoulder and neck, the left shoulder and upper arm, the right shoulder and upper arm, the left forearm and the right forearm. Both are 0.1; the torso determines the key edge is 0.3; the left thigh determines the key edge and the right thigh determines the key edge Both are 0.5; the left calf determines the key edge and the right calf determines the key edge Both are 0.6;

[0197] S42. Calculate the speed change score of the elderly , and its calculation formula is:

[0198]

[0199] In the formula, A speed change score representing the degree of speed change of all determined key points of the elderly; represents the velocity of the i-th key point at time t; Indicates that the i-th critical edge is determined at time speed at 1000 s; Indicates about The weight coefficient of ; where

[0200] ;

[0201] in, represents the three-dimensional coordinates of the i-th determined key point at time t; Indicates the i-th determined key point at time The three-dimensional coordinates of

[0202] It should be noted that According to different positions, the initial key points of the head, neck, left shoulder, right shoulder, left elbow, right elbow, left wrist and right wrist are determined. All are 0.1; the initial key point of the hip is 0.3; the initial key point of the left knee and the initial key point of the right knee Both are 0.5; the initial key points of the left ankle and the right ankle Both are 0.6;

[0203] S43. Scoring based on limb angle changes and speed change score Calculate the risk of falling Specifically, when an elderly person falls, not only the angle of the limbs will change significantly, but also the speed of movement will change suddenly. Therefore, considering the angle change and speed change comprehensively can more effectively identify potential falls. For example, in the early stage of a fall, the speed change of the legs will appear before the angle change of the upper body, and then the angle change of the whole body will increase sharply. Therefore, in step S43, the fall risk value The calculation formula is:

[0204]

[0205] In the formula, Indicates the likelihood of the elderly falling; , and Respectively represent the first, second and third weight parameters about the fall risk value; In the present invention, , and They are 0.4, 0.5 and 0.1 respectively;

[0206] S44. Assess the current physical health of the elderly based on their heart rate and blood pressure records Specifically, since the heart rate record and blood pressure record can reflect the physical condition of the elderly, the common method for calculating the physical health of the elderly is to calculate directly based on the heart rate record and blood pressure record, and this method does not take into account the complex interactive relationship between the heart rate record and the blood pressure record. For example, under normal circumstances, an increase in heart rate will lead to an increase in cardiac output, which in turn leads to an increase in systolic blood pressure. However, under certain pathological conditions (such as heart failure), an increase in heart rate may not be accompanied by a significant increase in systolic blood pressure. Therefore, in step S44, the following steps are specifically included:

[0207] S441, obtaining blood pressure records and heart rate records of several test elderly people in a time period T as training samples;

[0208] S442. Calculate the physical condition score of each tested elderly person one day after time T , and use this as a sample label; specifically, in step S442, the following steps are specifically included:

[0209] S4421, calculate heart rate deviation score , and its calculation formula is:

[0210]

[0211] In the formula, Represents the weight coefficient about heart rate; It means testing the heart rate of the elderly one day after T; Indicates normal heart rate level; is the heart rate standard deviation; in the present invention, is 10; is 80; is 0.8;

[0212] S4422, Calculate systolic blood pressure deviation score and diastolic blood pressure deviation score , and its calculation formula is:

[0213]

[0214]

[0215] In the formula, and Respectively represent the weight coefficients for systolic and diastolic blood pressure; and Respectively represent the systolic and diastolic blood pressure of the elderly tested one day after T; and Respectively represent normal systolic and diastolic blood pressure levels; and The standard deviation of systolic and diastolic blood pressure; in the present invention, and 0.7 and 0.6 respectively; and 115 and 70 respectively; and 15 and 10 respectively;

[0216] S4423, scoring based on heart rate deviation , Systolic blood pressure deviation score and diastolic blood pressure deviation score Calculating physical condition score , and its calculation formula is:

[0217]

[0218] In the formula, It indicates the physical condition score of the tested elderly one day after T.

[0219] S443, using the training samples and sample labels to train a physical condition assessment model to obtain a target model; specifically, the physical condition assessment model is constructed based on LSTM, which belongs to the prior art and will not be described in detail here;

[0220] S444. Input heart rate and blood pressure records, and output the health status of the elderly .

[0221] S45. According to the fall risk value and physical health Calculate the comprehensive risk value Specifically, when an elderly person falls, heart rate and blood pressure may change. For example, falling may cause pain, anxiety or physical stress reactions, which may affect heart rate and blood pressure. Therefore, when assessing the overall health risk of the elderly, it is very important to consider the impact of falling on physiological parameters (such as heart rate and blood pressure). This interactive impact can more accurately reflect the actual health status of the elderly and help to take necessary medical measures in a timely manner. To this end, in step S45, the following steps are specifically included:

[0222] S451. Calculate the average heart rate deviation score of the elderly after falling , and its calculation formula is:

[0223]

[0224] In the formula, It indicates the average heart rate of the elderly after falling; represents a weight parameter for the average heart rate deviation score; in the present invention, ; is 0.8;

[0225] S452. Calculate the average systolic blood pressure deviation score of the elderly after a fall , and its calculation formula is:

[0226]

[0227] In the formula, It represents the average systolic blood pressure of the elderly after falling; represents a weight parameter for the mean systolic blood pressure deviation score; in the present invention, ; is 0.75;

[0228] S453. Calculate the average diastolic blood pressure deviation score of the elderly after falling , and its calculation formula is:

[0229]

[0230] In the formula, It represents the average diastolic blood pressure of the elderly after falling; represents a weight parameter for the mean diastolic pressure deviation score; in the present invention, ; is 0.73;

[0231] S454. Calculate the comprehensive risk value Specifically, in step S454, the comprehensive risk value The calculation formula is:

[0232]

[0233] In the formula, , , , and Respectively represent the first, second, third, fourth and fifth weight parameters about the comprehensive risk value; in the present invention, , , , and They are 0.4, 0.3, 0.1, 0.1 and 0.1 respectively.

[0234] In the present invention, when the elderly is about to fall, the limb angle change score is first calculated. and speed change score , and then calculate the fall risk value based on it , and calculate the fall risk value When the elderly fall, not only the angle of their limbs will change significantly, but also their movement speed will change suddenly, so the fall risk value Compared with other calculation methods, it has higher accuracy and then calculates the comprehensive risk value. Considering that falling may cause changes in heart rate and blood pressure, the comprehensive risk value The calculation accuracy is further improved.

[0235] S5. The comprehensive risk value Real-time feedback to staff; specifically, when staff obtain the comprehensive risk value of the elderly When the comprehensive risk value is To formulate a response plan, for example, if the comprehensive risk value When the value is high, call the emergency number directly and have special personnel carry emergency first aid equipment to help the elderly.

[0236] The above implementation methods have been described in detail. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for analyzing the state of an elderly person based on image recognition, characterized in that: The following steps are involved: S1, acquiring first image data of the elderly and physiological data of the elderly including body data, heart rate record and blood pressure record in real time from multiple angles; S2, identifying the identity of the elderly and extracting initial key points in the first image data, and determining whether errors occur; If yes, proceed to step S3; If not, the first image data is marked as the second image data and the process goes to step S4; S3, correcting the initial key points in the first image data to generate second image data; S4, analyzing the current state of the elderly according to the continuous second image data and the elderly's physiological data; S5. The comprehensive risk value Provide real-time feedback to staff.

2. The method for analyzing the state of the elderly based on image recognition according to claim 1, characterized in that: In step S2, the following steps are specifically included: S21, constructing initial key edges for representing the skeleton and torso of the elderly according to the initial key points; S22, obtaining the monitoring device calibration parameters including the focal length, principal point coordinates, rotation matrix and translation vector of the monitoring device; S23, constructing a world coordinate system with one of the monitoring devices as the origin, selecting two first image data, and calculating the three-dimensional coordinates of each initial key point according to the calibration parameters ; S24. Calculate the length of each initial key edge , and its calculation formula is: In the formula, represents the length of the i-th initial key edge; Represents the three-dimensional coordinates of one of the initial key points of the i-th initial key edge; Represents the three-dimensional coordinates of another initial key point of the i-th initial key edge; S25, preset tolerance range , whose expression is: In the formula, Represents the tolerance range of the i-th initial key edge; represents the actual length of the limb corresponding to the i-th initial key edge; Indicates the tolerance percentage; S26, determine the length Is it in middle; If yes, it means that there is no error in the initial key point; If not, it means that there is an error in the initial key point.

3. The method for analyzing the state of the elderly based on image recognition according to claim 2, characterized in that: In step S23, the following steps are specifically included: S231, select an initial key point and obtain its position in the two first image data and ； S232, according to and Construct the first linear equation system, whose expressions are: Simplifying it to: in, ; S233. Define normalized coordinates , whose expression is: S234, according to the normalized coordinates Construct the second linear equation system, which is expressed as: Expanding this to: S235, Merger and , we get the third linear equation system, which is expressed as: in, S236, solving the third linear equation group by the least square method to obtain the three-dimensional coordinates of the initial key point .

4. The method for analyzing the state of the elderly based on image recognition according to claim 1, characterized in that: In step S3, the following steps are specifically included: S31, dividing the initial key point into a first initial key point and a second initial key point; S32. Use edge detection algorithm to extract the actual limb direction vector of the elderly , ； S33. Calculate the estimated direction vector of the initial key edge , and its calculation formula is: In the formula, Represents the estimated direction vector of the initial key edge between the i-th and j-th initial key points; and Represent the three-dimensional coordinates of the i-th and j-th initial key points respectively; S34. Calculate the actual limb direction vector and the estimated direction vector Angle , and its calculation formula is: S35, calculating the offset influence of the key point in each direction, and the calculation formula is: In the formula, , and Respectively represent the offset influence of the i-th key point on the x, y and z axes; represents the length of the initial key edge between the i-th and j-th initial key points; represents the actual length of the old man’s limb corresponding to the initial key edge between the i-th and j-th initial key points; S36, correcting the three-dimensional coordinates of the second initial key point according to the offset influence ( ), the calculation formula is: S37, repeat the above steps until all the second initial key points are corrected, all the key points are recorded as determined key points, the corrected initial key edges are recorded as determined key edges and the second image data is constructed based on them.

5. The method for analyzing the state of the elderly based on image recognition according to claim 4 is characterized in that: In step S4, the following steps are specifically included: S41. Calculate the limb angle change score of the elderly , and its calculation formula is: In the formula, The limb angle change score represents the degree of change in the angles of all key edges determined by the elderly; Indicates the total number of key edges determined; Indicates about The weight coefficient of represents the angle between the i-th critical edge and the vertical direction at time t; Indicates that the i-th critical edge is determined at time The angle between the time and the vertical direction; Represents the time interval between two adjacent frames of first image data; S42. Calculate the speed change score of the elderly , and its calculation formula is: In the formula, A speed change score representing the degree of speed change of all determined key points of the elderly; represents the velocity of the i-th key point at time t; Indicates that the i-th critical edge is determined at time speed at 1000 s; Indicates about The weight coefficient of S43. Scoring based on limb angle changes and speed change score Calculate the risk of falling ; S44. Assess the current health status of the elderly based on their heart rate and blood pressure records ; S45. According to the fall risk value and physical health Calculate the comprehensive risk value .

6. The method for analyzing the state of the elderly based on image recognition according to claim 5, characterized in that: In step S43, the fall risk value The calculation formula is: In the formula, Indicates the likelihood of the elderly falling; , and They represent the first, second and third weight parameters for the fall risk value respectively.

7. The method for analyzing the state of the elderly based on image recognition according to claim 5, characterized in that: In step S44, the following steps are specifically included: S441, obtaining blood pressure records and heart rate records of several test elderly people in a time period T as training samples; S442. Calculate the physical condition score of each tested elderly person one day after time T , and use this as the sample label; S443, training a physical condition assessment model using training samples and sample labels to obtain a target model; S444. Input heart rate and blood pressure records, and output the health status of the elderly .

8. The method for analyzing the state of the elderly based on image recognition according to claim 7, characterized in that: In step S442, the following steps are specifically included: S4421, calculate heart rate deviation score , and its calculation formula is: In the formula, Represents the weight coefficient about heart rate; It means testing the heart rate of the elderly one day after T; Indicates normal heart rate level; is the standard deviation of heart rate; S4422, Calculate systolic blood pressure deviation score and diastolic blood pressure deviation score , and its calculation formula is: In the formula, and Respectively represent the weight coefficients for systolic and diastolic blood pressure; and Respectively represent the systolic and diastolic blood pressure of the elderly tested one day after T; and Respectively represent normal systolic and diastolic blood pressure levels; and standard deviation of systolic and diastolic blood pressure; S4423, scoring based on heart rate deviation , Systolic blood pressure deviation score and diastolic blood pressure deviation score Calculating physical condition score , and its calculation formula is: In the formula, It indicates the physical condition score of the tested elderly one day after T.

9. The method for analyzing the state of the elderly based on image recognition according to claim 5, characterized in that: In step S45, the following steps are specifically included: S451. Calculate the average heart rate deviation score of the elderly after falling , and its calculation formula is: In the formula, It indicates the average heart rate of the elderly after falling; represents the weight parameter for the average heart rate deviation score; S452. Calculate the average systolic blood pressure deviation score of the elderly after a fall , and its calculation formula is: In the formula, It represents the average systolic blood pressure of the elderly after falling; represents the weight parameter regarding the mean systolic blood pressure deviation score; S453. Calculate the average diastolic blood pressure deviation score of the elderly after falling , and its calculation formula is: In the formula, It represents the average diastolic blood pressure of the elderly after falling; represents the weight parameter regarding the mean diastolic blood pressure deviation score; S454. Calculate the comprehensive risk value .

10. The method for analyzing the state of the elderly based on image recognition according to claim 9, characterized in that: In step S454, the comprehensive risk value The calculation formula is: In the formula, , , , and Respectively represent the first, second, third, fourth and fifth weight parameters regarding the comprehensive risk value.

Images