Simulators for children's rehabilitation training and teaching

Abstract

The present invention discloses a manikin for children's rehabilitation training and teaching, and relates to the technical field of rehabilitation training. The invention comprises obtaining a healthy human body model, collecting patient body data, determining the patient's skeletal points and corresponding data, making the patient's skeletal points correspond to the healthy human body model, obtaining the healthy human body skeletal points, obtaining the joint forces corresponding to the healthy human body skeletal points, obtaining the corresponding muscle force data, comparing the patient's skeletal point data with the muscle force data, determining the muscle strength deficiency site, and formulating a training plan according to the strength deficiency site. The present invention can provide guidance data for children in rehabilitation training.

Description

Technical Field

[0001] The invention relates to the technical field of rehabilitation training, in particular to a manikin for children's rehabilitation training and teaching. Background Art

[0003] Providing manikins for children's rehabilitation training and teaching, which visually display children's physiological data through three-dimensional simulation technology and effectively solve the communication barriers between doctors and patients, is an issue that technical personnel in this field urgently need to solve. Summary of the invention

[0004] In view of this, the present invention provides a manikin for children's rehabilitation training and teaching, which can provide guidance data for children's rehabilitation training, training and teaching.

[0005] In order to achieve the above object, the present invention adopts the following technical solution:

[0006] A manikin for children's rehabilitation training and teaching includes the following steps:

[0007] S1. Obtain a healthy human model;

[0008] S2. Collect the patient's body data, determine the patient's skeletal point data, the muscle position corresponding to the skeletal point, and the corresponding data;

[0009] S3, aligning the patient's skeletal points with the healthy human body model, and obtaining the healthy human body's skeletal points and the muscle positions corresponding to the skeletal points;

[0010] S4, obtaining the joint force corresponding to the healthy human skeleton point, and obtaining the muscle force data corresponding to the healthy human skeleton point;

[0011] S5, comparing the muscle data corresponding to the patient's skeletal points with the muscle force data corresponding to the skeletal points of a healthy human body to determine the location of muscle strength deficiency;

[0012] S6. Develop a training plan based on the areas of strength loss; the patient performs physical training according to the training plan.

[0013] In the above method, optionally, determining the skeleton points in S2 includes the following steps:

[0014] S21, setting a camera connected to the computer to collect patient motion images;

[0015] S22, pre-processing the image and inputting it into the skeleton point detection network to detect and obtain the two-dimensional coordinates of the human body skeleton points;

[0016] S23, obtaining the camera projection matrix;

[0017] S24, obtaining the three-dimensional coordinates of the human skeleton points based on the camera projection matrix and the two-dimensional skeleton point coordinates.

[0018] In the above method, optionally, the skeleton point detection network in S22 is obtained using an AlphaPose network.

[0019] In the above method, optionally, in S23, the camera projection matrix includes: obtaining a camera calibration algorithm, calculating an intrinsic parameter matrix and an extrinsic parameter matrix of the camera according to the calibration algorithm, and obtaining a projection matrix based on the intrinsic parameter matrix and the extrinsic parameter matrix.

[0020] The above method, optionally, includes in S24: establishing a projection relationship equation between the two-dimensional coordinates and the three-dimensional coordinates of the skeleton point according to the projection matrix;

[0021] Eliminate the projective relationship equation to obtain a homogeneous linear equation system of two-dimensional coordinates and three-dimensional coordinates;

[0022] The sublinear equations are iteratively calculated according to a preset inverse iteration algorithm to obtain the solution of the equations, and then the three-dimensional coordinates of the bone points are determined.

[0023] In the above method, optionally, collecting the patient's body data in S2 further includes manually inputting the patient's skeletal point data, the muscle positions corresponding to the skeletal points, and the corresponding data.

[0024] In the above method, optionally, S4 comprises the following steps:

[0025] S41, obtaining the force of interaction between human body parts and the environment;

[0026] S42, based on the multi-rigid body kinematic function and the force of the interaction between the human body parts and the environment, obtain the external output force of each skeletal point involved in the force generation when the human body parts interact with the environment, and the torque rotating around the corresponding human body skeletal point, and record them in the healthy human body model;

[0027] S43. Obtain muscle force data of each muscle corresponding to the bone point based on the musculoskeletal dynamics function, the external output force of each bone point, and the torque rotating around the corresponding bone point.

[0028] It can be seen from the above technical solutions that, compared with the prior art, the present invention provides a simulator for children's rehabilitation training and teaching, which has the following beneficial effects: 1) The present invention uses an iterative algorithm to quickly converge to the estimated value of the three-dimensional coordinates with the smallest error, thereby improving the accuracy of the three-dimensional coordinates of the bone points; 2) The present invention obtains the corresponding torque based on the multi-rigid body kinematic function, effectively simulating the actual movement of the human body; 3) The present invention can provide guidance data for children in rehabilitation training. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0030] Figure 1 Constructing a flow chart for the child rehabilitation training and teaching manikin disclosed in the present invention;

[0031] Figure 2 A flowchart for determining the coordinates of skeleton points disclosed in the present invention;

[0032] Figure 3 The muscle data acquisition flow chart disclosed in the present invention;

[0033] Figure 4 A flow chart for executing the training program disclosed in the present invention is formulated. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] In this application, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprise one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0036] Reference Figure 1 As shown, the present invention discloses a manikin for children's rehabilitation training and teaching, comprising the following steps:

[0037] S1. Obtain a healthy human model;

[0038] S2. Collect the patient's body data, determine the patient's skeletal point data, the muscle position corresponding to the skeletal point, and the corresponding data;

[0039] S3, aligning the patient's skeletal points with the healthy human body model, and obtaining the healthy human body's skeletal points and muscle positions corresponding to the skeletal points;

[0040] S4, obtaining the joint force corresponding to the healthy human skeleton point, and obtaining the muscle force data corresponding to the healthy human skeleton point;

[0041] S5, comparing the muscle data corresponding to the patient's skeletal points with the muscle force data corresponding to the skeletal points of a healthy human body to determine the location of muscle strength deficiency;

[0042] S6. Develop a training plan based on the areas of strength loss; the patient performs physical training according to the training plan.

[0043] Further, see Figure 2 As shown, determining the skeleton points in S2 includes the following steps:

[0044] S21, setting a camera connected to the computer to collect patient action images;

[0045] S22, pre-processing the image and inputting it into the skeleton point detection network to detect and obtain the two-dimensional coordinates of the human body skeleton points;

[0046] S23, obtaining the camera projection matrix;

[0047] S24, obtaining the three-dimensional coordinates of the human skeleton points based on the camera projection matrix and the two-dimensional skeleton point coordinates.

[0048] Furthermore, the number of cameras in S21 is at least two, and the camera is a monocular grayscale camera.

[0049] Furthermore, the skeleton point detection network in S22 is obtained using the AlphaPose network.

[0050] Furthermore, in S23, the camera projection matrix includes: obtaining a camera calibration algorithm, calculating an intrinsic parameter matrix and an extrinsic parameter matrix of the camera according to the calibration algorithm, and obtaining a projection matrix based on the intrinsic parameter matrix and the extrinsic parameter matrix.

[0051] Further, S24 includes: establishing a projection relationship equation between the two-dimensional coordinates and the three-dimensional coordinates of the skeleton point according to the projection matrix;

[0052] Eliminate the projective relationship equation to obtain a homogeneous linear equation system of two-dimensional coordinates and three-dimensional coordinates;

[0053] The sublinear equations are iteratively calculated according to a preset inverse iteration algorithm to obtain the solution of the equations, and then the three-dimensional coordinates of the bone points are determined.

[0054] Specifically, the projection relationship is a relationship in which light emitted from a point light source is mapped to a three-dimensional coordinate system after passing through a two-dimensional skeleton point.

[0055] Furthermore, the homogeneous linear equations are iteratively calculated according to a preset inverse iteration algorithm; a first result of the current iterative calculation is obtained; a second result of the previous iterative calculation is obtained; if the difference between the first result and the second result is less than a preset value, the first result is used as the solution to the homogeneous linear equations, and the result obtained from each iterative calculation is compared with the result obtained from the previous iterative calculation. When the difference between the first result and the second result is less than a preset value, it is determined that the iteration has converged, and then the first result is used as the solution to the homogeneous linear equations, thereby determining the convergence conditions in different scenarios and improving the accuracy of convergence judgment.

[0056] Furthermore, in S2, obtaining the corresponding data of the patient's bone points includes: collecting sEMG signals, filtering the sEMG signals through a 50-500 Hz bandpass filter, rectifying, and normalizing them to obtain muscle activation signals, establishing a muscle-tendon model relationship, determining the muscle force-length relationship, determining the feathering angle, and determining the muscle-tendon unit length and muscle-tendon unit force based on the feathering angle to obtain the bone point torque.

[0057] Furthermore, in S2, the human body is divided into different areas according to the positions of the bone points, and the muscle information corresponding to the different bone points is obtained. For example, the bone points can be roughly divided into shoulders, neck, elbows, wrists, torso, hips, knees and ankles, and the muscle groups corresponding to the shoulder bone points are the anterior deltoid, the middle deltoid and the posterior deltoid.

[0058] Furthermore, collecting the patient's body data in S2 also includes manually inputting the patient's skeletal point data, the muscle positions corresponding to the skeletal points, and the corresponding data.

[0059] Specifically, some children with early physical movement disorders are unable to cooperate with data collection. In this case, a manual team assessment is performed to obtain the children's corresponding physical data.

[0060] Further, see Figure 3 As shown, S4 includes the following steps:

[0061] S41, obtaining the force of interaction between human body parts and the environment;

[0062] S42, based on the multi-rigid body kinematic function and the force of the interaction between the human body parts and the environment, obtain the external output force of each skeletal point involved in the force generation when the human body parts interact with the environment, and the torque rotating around the corresponding human body skeletal point, and record them in the healthy human body model;

[0063] S43. Obtain muscle force data of each muscle corresponding to the bone point based on the musculoskeletal dynamics function, the external output force of each bone point, and the torque rotating around the corresponding bone point.

[0064] Specifically, the first musculoskeletal dynamics function is the external output force F of the bone point and the external output force of each muscle corresponding to the bone point; the second musculoskeletal dynamics function is the torque T rotating around the bone point and the external output force of each muscle corresponding to the bone point, and the distance data between the connection point between the tendon corresponding to the muscle and the bone and the corresponding bone point, wherein the distance data l between the connection point between the tendon of the muscle and the bone and the corresponding bone point is known.

[0065] The first musculoskeletal dynamics function can be expressed as: F = F 1 +F 2 +…+F n , where F 1 ,F 2 ,…,F n is the muscle output force of each muscle corresponding to the skeleton point, and n is the three-dimensional corresponding quantity; the second musculoskeletal dynamics function can be expressed as: T = F 1 × 1 +F 2 × 2 +…+F n × n , where l 1 ,l 2 ,…,l n It is the distance data between the connection point between the tendon and the bone corresponding to the muscle and the corresponding bone point.

[0066] Further, see Figure 4 As shown, formulating a training plan in S6 includes: determining the muscle atrophy of the muscle strength deficiency site, setting a training plan for activating atrophied muscles, calculating the corresponding joint force based on the training plan, determining the joint force after training using the training plan, and judging whether the joint force after training is consistent with the joint force of a healthy person. When the joint force is inconsistent, it is determined that the corresponding muscle strength site is deficient or overflowed and a prompt is given, and the trainee modifies the training plan according to the prompt; patient training includes: setting a camera connected to a computer to capture patient action images; then comparing the patient action images with the required actions in the training plan, playing the next action when the requirements are met, and giving voice prompts based on the action problems when the requirements are not met.

[0067] Specifically, when it is determined that the patient's bone point force data is inconsistent with the healthy human body data, the defective bone point is first determined, the muscle group around the bone point is determined based on the defective bone point, and a training plan for resuscitating the corresponding muscle group is set.

[0068] Furthermore, it also includes cloud storage data, storing patient physical data and corresponding disease labels. When users need to obtain data on corresponding diseases, they can directly query according to the labels.

[0069] Specifically, users can download training plans for common diseases, and if they have a common disease, they can import it directly.

[0070] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0071] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A manikin for children's rehabilitation training and teaching, characterized in that: The following steps are involved: S1. Obtain a healthy human model; S2. Collect the patient's body data, determine the patient's skeletal point data, the muscle position corresponding to the skeletal point, and the corresponding data; S3, aligning the patient's skeletal points with the healthy human body model, and obtaining the healthy human body's skeletal points and muscle positions corresponding to the skeletal points; S4, obtaining the joint force corresponding to the healthy human skeleton point, and obtaining the muscle force data corresponding to the healthy human skeleton point; S5, comparing the muscle data corresponding to the patient's skeletal points with the muscle force data corresponding to the skeletal points of a healthy human body to determine the location of muscle strength deficiency; S6. Develop a training plan based on the areas of strength loss; Patients perform physical training according to the training plan.

2. A child rehabilitation training and teaching manikin according to claim 1, characterized in that: Determining the skeleton points in S2 includes the following steps: S21, setting a camera connected to the computer to collect patient motion images; S22, pre-processing the image and inputting it into the skeleton point detection network to detect and obtain the two-dimensional coordinates of the human body skeleton points; S23, obtaining the camera projection matrix; S24, obtaining the three-dimensional coordinates of the human skeleton points based on the camera projection matrix and the two-dimensional skeleton point coordinates.

3. A child rehabilitation training and teaching manikin according to claim 2, characterized in that: The skeleton point detection network in S22 is obtained using the AlphaPose network.

4. A child rehabilitation training and teaching manikin according to claim 2, characterized in that: In S23, the camera projection matrix includes: obtaining a camera calibration algorithm, calculating an intrinsic parameter matrix and an extrinsic parameter matrix of the camera according to the calibration algorithm, and obtaining a projection matrix based on the intrinsic parameter matrix and the extrinsic parameter matrix.

5. A child rehabilitation training and teaching manikin according to claim 2, characterized in that: S24 includes: According to the projection matrix, the projection relationship equation between the two-dimensional coordinates and the three-dimensional coordinates of the bone points is established; Eliminate the projective relationship equation to obtain a homogeneous linear equation system of two-dimensional coordinates and three-dimensional coordinates; The sublinear equations are iteratively calculated according to a preset inverse iteration algorithm to obtain the solution of the equations, and then the three-dimensional coordinates of the bone points are determined.

6. A child rehabilitation training and teaching manikin according to claim 1, characterized in that: Collecting the patient's body data in S2 also includes manually inputting the patient's skeletal point data, the muscle positions corresponding to the skeletal points, and the corresponding data.

7. A child rehabilitation training and teaching manikin according to claim 1, characterized in that: S4 includes the following steps: S41, obtaining the force of interaction between human body parts and the environment; S42, based on the multi-rigid body kinematic function and the force of the interaction between the human body parts and the environment, obtain the external output force of each skeletal point involved in the force generation when the human body parts interact with the environment, and the torque rotating around the corresponding human body skeletal point, and record them in the healthy human body model; S43. Obtain muscle force data of each muscle corresponding to the bone point based on the musculoskeletal dynamics function, the external output resultant force of each bone point, and the torque rotating around the corresponding bone point.

Images