Human body balance evaluation equipment, human body balance evaluation method and human body balance evaluation device

Abstract

The invention relates to the technical field of rehabilitation medical equipment, in particular to human body balance assessment equipment, a human body balance assessment method and a human body balance assessment device. Acquiring pressure information on the standing platform through a three-dimensional force sensor, and calculating human body pressure data based on the pressure information; acquiring a human body contour image and a human eye image through a pose acquisition device, and acquiring a plantar image through a plantar image acquisition device; human body balance state evaluation is carried out according to at least one of the human body pressure data, the plantar image, the human body contour image and the human eye image, the human body balance state is analyzed through multi-dimensional balance evaluation, comprehensive dynamic balance evaluation is achieved, the precision is higher, meanwhile, a mechanical part and a processing part are flexibly combined, and the dynamic balance evaluation efficiency is improved. And the applicability is wider.

Description

Technical Field

[0001] The present invention relates to the technical field of rehabilitation medical equipment, and in particular to human body balance assessment equipment, a human body balance assessment method and a device. Background Art

[0002] Maintaining the body's balance function depends on the coordinated action of the vestibular system, visual system, and proprioceptive system. These sensory systems may become dysfunctional due to degenerative changes, infection, or trauma, thereby increasing the risk of falls and potentially leading to serious consequences such as hip fractures, back injuries, and even life-threatening situations. In order to reduce the occurrence of the above situations, a balance function assessment can be conducted on the user in advance to detect the risk of falls as early as possible and intervene in time, providing scientific guidance for subsequent targeted inspections and interventions.

[0003] However, in traditional technologies, the equipment used for balance function assessment at home and abroad is large in size and fixed in position. When measuring human balance, the effect of dynamic balance test is poor, and the measurement effect of human balance is general. It cannot provide high-precision human balance data and auxiliary opinions for rehabilitation diagnosis and treatment.

[0004] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of the present invention is to provide a human balance assessment device, a human balance assessment method and an apparatus, aiming to solve the technical problems in the prior art of human balance assessment devices, such as poor assessment effect and low accuracy when performing balance tests.

[0006] To achieve the above-mentioned object, the present invention provides a human balance assessment device, comprising: a main frame, a three-dimensional force platform, a posture acquisition device, and a control unit; The main frame is set on the ground and is used to install the three-dimensional force platform and the posture acquisition device; The three-dimensional force platform includes a base and a balance force platform. Two guide rails are provided in parallel on the base. The balance force platform is slidably connected to the guide rails. The balance force platform includes at least a light source, a three-dimensional force sensor, a motor, an AF-N actuator, a plantar image acquisition device, and a standing platform. The three-dimensional force platform adjusts the balance of a user standing on the three-dimensional force platform by moving the standing platform on the guide rails and / or adjusting the horizontal state of the standing platform; The three-dimensional force platform is further used to collect sole images and body pressure data of a user standing on the three-dimensional force platform; The posture acquisition device is used to acquire an eye image and a body contour image of a user standing on the three-dimensional force platform; The control unit is used to evaluate the balance state of the human body according to the human body pressure data, the sole image, the human body contour image and the human eye image.

[0007] Optionally, the human body balance assessment device further includes a projection device; The main frame is provided with a movable mounting cross bar; The projection device is arranged on the mounting crossbar; The posture acquisition device is used to acquire a human eye image of a user when viewing the target image when the projection device projects the target image.

[0008] Optionally, the human body balance assessment device further includes: The human body protection device is suspended on the installation cross bar and is used to protect the user's balance state when the three-dimensional force platform is started.

[0009] The present invention also provides a method for evaluating human body balance, the method comprising the following steps: activating a projection device and a three-dimensional force platform in the human body balance assessment device; Acquire pressure information on the standing platform through a three-dimensional force sensor, and calculate human body pressure data based on the pressure information; The body contour image and the human eye image are collected by the posture acquisition device, and the sole image is collected by the sole image acquisition device; The human body balance state is assessed according to at least one of the human body pressure data, the sole image, the human body contour image, and the human eye image.

[0010] Optionally, the performing of the human body balance state assessment based on at least one of the human body pressure data, the sole image, the human body contour image, and the human eye image further includes: Obtaining data timestamps of the human body pressure data, the sole image, the human body contour image, and the human eye image; Time-aligning the human body pressure data, the plantar image, the human body contour image, and the human eye image according to the data timestamp; The human body balance state is assessed according to at least one of the aligned human body pressure data, the sole image, the human body contour image, and the human eye image.

[0011] Optionally, the performing the human body balance state assessment based on at least one of the aligned human body pressure data, the plantar image, the human body contour image, and the human eye image includes: Preprocessing the sole image to obtain a footprint image; Obtaining the pixel value and image weighted grayscale centroid of each pixel in the footprint image; Calculating plantar pressure distribution data based on the pixel value of each pixel point and the weighted grayscale center of gravity of the image; Calculating the arch index, plantar support area, and pressure center offset according to the plantar pressure distribution data; The human body balance state is evaluated based on the arch index, the plantar support area and the pressure center offset to obtain a first evaluation result.

[0012] Optionally, calculating the arch index, the plantar support area, and the pressure center offset according to the plantar pressure distribution data includes: Dividing the footprint image into a forefoot region, a midfoot region, and a rearfoot region; Calculating a forefoot support area corresponding to the forefoot region, a midfoot support area corresponding to the midfoot region, and a rearfoot support area corresponding to the rearfoot region according to the plantar pressure distribution data; Determine the plantar support area according to the sum of the forefoot support area, the midfoot support area, and the rearfoot support area; Calculating the area ratio between the midfoot support area and the plantar support area to obtain an arch index; The pressure center offset is calculated according to the plantar pressure distribution data and historical plantar pressure distribution data.

[0013] Optionally, the performing the human body balance state assessment based on at least one of the aligned human body pressure data, the plantar image, the human body contour image, and the human eye image further includes: Identify the skeleton key points in each human body contour image and mark them according to their types; Perform one-dimensional vector concatenation according to each marked skeleton key point to generate multiple skeleton RGB images, wherein the coordinates of each skeleton key point in the skeleton RGB image correspond to the RGB pixel value; Normalizing the pixels of the multiple skeleton RGB images to obtain multiple target skeleton RGB images; The target skeleton RGB image is input into a trained neural network model for analysis to obtain a second evaluation result, which includes at least one of the skeleton point trajectory, joint angle and trunk-limb coordination.

[0014] Optionally, the performing the human body balance state assessment based on at least one of the aligned human body pressure data, the plantar image, the human body contour image, and the human eye image further includes: Obtaining a pressure center coordinate set corresponding to the human body pressure data set; Marking the pressure center for preprocessing to obtain a target pressure center coordinate set; Calculate time domain measurement indicators and frequency domain measurement indicators based on the target pressure center coordinate set, the time domain measurement indicators at least including: time domain average distance, time domain root mean square distance, time domain sway path, time domain average speed and human body inclination angle, and the frequency domain measurement indicators at least including: power spectrum density and power spectrum moment; Determine the time domain fluctuation and frequency domain offset of the human body pressure data according to the time domain measurement index and the frequency domain measurement index; A third evaluation result is obtained according to the time domain fluctuation and the frequency domain offset.

[0015] In addition, to achieve the above-mentioned purpose, the present invention further provides a human body balance assessment device, the human body balance assessment device comprising: A starting module, used to start the projection device and the three-dimensional force platform in the human body balance assessment device; a calculation module, configured to obtain pressure information on the standing platform through a three-dimensional force sensor and calculate human body pressure data based on the pressure information; An acquisition module, configured to acquire a human body contour image and a human eye image through a posture acquisition device, and to acquire a plantar image through a plantar image acquisition device; An evaluation module is used to evaluate the balance state of the human body according to at least one of the human body pressure data, the sole image, the human body contour image, and the human eye image.

[0016] In addition, to achieve the above-mentioned purpose, the present invention also proposes a human body balance assessment device, which includes: a memory, a processor, and a human body balance assessment program stored on the memory and executable on the processor, wherein the human body balance assessment program is configured to implement the steps of the human body balance assessment method described above.

[0017] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a human body balance assessment program is stored. When the human body balance assessment program is executed by a processor, the steps of the human body balance assessment method described above are implemented.

[0018] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the human body balance assessment method as described above.

[0019] The present invention starts the projection device and the three-dimensional force platform in the human body balance assessment device; obtains pressure information on the standing platform through a three-dimensional force sensor, and calculates human body pressure data based on the pressure information; collects human body contour images and human eye images through a posture acquisition device, and collects plantar images through a plantar image acquisition device; assesses the human body balance state according to at least one of the human body pressure data, the plantar image, the human body contour image and the human eye image, analyzes the human body balance state through multi-dimensional balance assessment, and realizes comprehensive dynamic balance assessment with higher accuracy. At the same time, the mechanical part and the processing part are flexibly combined, and the applicability is wider, avoiding the technical problems of poor assessment effect and low accuracy when the human body balance assessment equipment in the prior art performs balance test. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] Figure 1 Schematic diagram of the structure of the human body balance assessment device of the present invention; Figure 2 Schematic diagram of the structure of the three-dimensional force platform in the human body balance assessment device of the present invention; Figure 3 Schematic diagram of the flow chart of the first embodiment of the human body balance assessment method of the present invention; Figure 4 A schematic diagram of the user's posture when the three-dimensional force platform is running in accordance with an embodiment of the human body balance assessment method of the present invention; Figure 5 A schematic diagram of segmenting a footprint image using a minimum circumscribed rectangle method according to an embodiment of a method for assessing human balance of the present invention; Figure 6 A schematic diagram of the position of the camera device installed on the crossbar in accordance with an embodiment of the human body balance assessment method of the present invention; Figure 7 A schematic diagram of the motion modeling stage of an embodiment of a human balance assessment method according to the present invention; Figure 8 A schematic diagram of the coordinate axes of the pressure center on a three-dimensional force platform according to an embodiment of a method for evaluating human balance of the present invention; Figure 9 This is a structural block diagram of a first embodiment of a human body balance assessment device according to the present invention; Figure 10 It is a structural diagram of a human body balance assessment device in a hardware operating environment involved in an embodiment of the present invention.

[0023] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0024] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0025] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0026] The embodiment of the present invention provides a human body balance assessment device, referring to Figure 1 and Figure 2 , Figure 1 is a schematic diagram of the structure of the human body balance assessment device in this embodiment, Figure 2 Schematic diagram of the structure of the three-dimensional force platform in this embodiment, wherein the human balance assessment device includes: a main frame 1, a three-dimensional force platform 5, a posture acquisition device 4 and a control unit 7.

[0027] A main frame 1 is provided on the ground and is used for installing the three-dimensional force platform 5 and the position acquisition device 4; The three-dimensional force platform 5 includes a base 56 and a balance force platform. Two guide rails 55 are provided in parallel on the base. The balance force platform is slidably connected to the guide rails 55. The balance force platform includes at least a light source 51, a three-dimensional force sensor 52, a motor 53, an AF-N actuator 54, a plantar image acquisition device 57, and a standing platform. A three-dimensional force platform, which adjusts the balance of a user standing on the three-dimensional force platform by moving the platform on the guide rails and / or adjusting the horizontal state of the platform; The three-dimensional force platform is further used to collect sole images and body pressure data of a user standing on the three-dimensional force platform; A posture acquisition device for acquiring an eye image and a body contour image of a user standing on the three-dimensional force platform; A control unit is used to evaluate the balance state of the human body according to the human body pressure data, the sole image, the human body contour image and the human eye image.

[0028] It should be noted that in recent years, with the prevalence of intelligent monitoring, some research has begun exploring the use of image analysis techniques (such as deep learning algorithms and posture estimation) to detect human posture and motion state, particularly in areas such as gait analysis and fall risk assessment. These studies utilize cameras and video analysis to monitor posture and balance. However, relying solely on image analysis may struggle to achieve the same accuracy as traditional sensors (such as force platforms). This is especially true when detecting subtle posture adjustments and center of gravity shifts. Image analysis is easily affected by factors such as ambient light, viewing angle, and resolution, resulting in low reliability of measurement data. Planar image analysis calculates center of gravity information based on the patient's outline captured in a video. If the patient has a limb disability and is obscured by clothing, the error in calculating the center of gravity will be significant. Therefore, two-dimensional images lack the ability to accurately capture depth information, making image analysis less effective than force platforms or inertial sensors, thus affecting the accuracy of balance assessment.

[0029] Compared with traditional balance assessment equipment, in this embodiment, the human balance assessment equipment includes: a main frame, a three-dimensional force platform, a posture acquisition device and a control unit, wherein the three-dimensional force platform base and the balance force platform are provided with two guide rails on the base, and the balance force platform is slidably connected to the base through the guide rails. When the user stands on the balance force platform, the balance force platform can adjust the user's balance state by sliding on the guide rails, thereby observing the user's limb control ability when in an unstable state, and realizing the dynamic balance test of the human body.

[0030] At the same time, the balancing force platform includes at least a light source, a three-dimensional force sensor, a motor, an AF-N actuator, a plantar image acquisition device and a standing platform. The motor and the AF-N actuator can control the horizontal state of the platform surface of the balancing force platform to tilt to adjust the user's balance state. The three-dimensional force sensor can also be used to collect pressure data on the standing platform during the balance test of the user, and combined with the plantar image collected by the plantar image acquisition device to realize dynamic balance testing when the user is dealing with an unstable state.

[0031] In a feasible embodiment, the human body balance assessment device further includes a projection device; The main frame is provided with a movable mounting cross bar; The projection device is arranged on the mounting crossbar; The posture acquisition device is used to acquire a human eye image of a user when viewing the target image when the projection device projects the target image.

[0032] It should be noted that the projection device can be a device with image mapping function such as a projector and a mobile terminal. This embodiment does not impose any specific restrictions on this. In addition, in order to facilitate the installation and movement of the equipment, a movable mounting cross bar can be provided on the main frame in this embodiment to avoid operations such as drilling during the installation process, and the projection device and the posture acquisition device can both be installed on the mounting cross bar.

[0033] The posture acquisition device can be a matrix of multiple image acquisition devices, such as a camera matrix, which can realize human posture detection by acquiring user images from multiple angles. At the same time, it can also acquire human eye images to facilitate balance testing in combination with the orientation of the mapping image of the projection device.

[0034] In a feasible embodiment, the human body balance assessment device further includes: The human body protection device is suspended on the installation cross bar and is used to protect the user's balance state when the three-dimensional force platform is started.

[0035] In the specific implementation, the structure of the human balance assessment equipment is 2 meters high and 1 meter long and wide. A hook is provided on the beam of the crossbar for hanging human protection devices (safety clothing) to ensure the safety of the subjects. The connection mechanism between the crossbar and the fixed frame is a spring lock set at both ends of the crossbar. The lock has a built-in spring buffer structure to reduce vibration transmission during equipment operation. A groove lock hole is designed at the corresponding position of the frame to complete the rapid installation and removal of the crossbar and the fixed frame. At the same time, the contact surface between the crossbar and the frame is embedded with a neodymium iron boron magnet (suction force ≥ 5kg) to assist in rapid alignment. A silicone shock-absorbing pad (damping coefficient 0.3) is installed between the crossbar and the frame to achieve an anti-vibration effect. The connection mechanism between the projector and the crossbar is: a slide rail is set at the top of the crossbar, and the projector is connected through a universal ball head with an adjustment range of ±30° pitch angle and 360° horizontal rotation. In addition, the detachable punch-free installation crossbar can be removed from the fixed frame and combined with the projector and camera on it for rehabilitation training at the patient's home.

[0036] Based on this, the embodiment of the present invention provides a method for evaluating human balance, referring to Figure 3 , Figure 3 FIG1 is a flow chart of a first embodiment of a method for assessing human balance according to the present invention.

[0037] In this embodiment, the human body balance assessment method includes: Step S10: starting the projection device and the three-dimensional force platform in the human body balance assessment device.

[0038] Step S20: Obtaining pressure information on the standing platform through a three-dimensional force sensor, and calculating human body pressure data based on the pressure information.

[0039] Step S30: The body contour image and the eye image are collected by the posture collection device, and the sole image is collected by the sole image collection device.

[0040] Step S40: performing a human body balance state assessment based on at least one of the human body pressure data, the sole image, the human body contour image, and the human eye image.

[0041] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device, control chip, or control computer capable of implementing the above functions. The following describes this embodiment and the following embodiments using a control computer as an example.

[0042] refer to Figure 4 , Figure 4 This is a schematic diagram of the user's posture when the three-dimensional force platform of this embodiment is in operation. Starting the projection device and the three-dimensional force platform in the human balance assessment device means controlling the projection device to start projection to project a specific image onto a preset plane, and controlling the movement of the balance force platform on the guide rail and / or controlling the tilt degree of the balance force platform to control the tilt of the human body, thereby collecting the dynamic posture of the human body during the tilting process and other data that affect the balance of the human body, thereby realizing the assessment of the human body's balance posture and providing auxiliary opinions for subsequent disease diagnosis or rehabilitation.

[0043] It is understandable that the three-dimensional force sensors on the balance force platform can be evenly arranged below the standing platform, for example Figure 2 The four corners of the body are not specifically restricted in this embodiment. The human body pressure data refers to the time domain measurement indicators and frequency domain measurement indicators of the human body pressure center. The time domain measurement indicators include at least: time domain average distance, time domain root mean square distance, time domain swing path, time domain average speed and human body inclination angle. The frequency domain measurement indicators include at least: power spectrum density and power spectrum moment. This embodiment does not specifically restrict this.

[0044] Specifically, due to the activation of the projection device and the three-dimensional force platform, healthy users are in an unbalanced state, and the body inclination angle, dynamic posture control, plantar pressure distribution and overall coordination of human limbs are all different from those of patients with otogenic vertigo. Therefore, in this embodiment, the body pressure data, the plantar image, the body contour image and the human eye image can be compared to determine whether the user has related symptoms of otogenic vertigo.

[0045] In a specific implementation, since the data collected in this embodiment comes from different devices, it may be necessary to combine multi-dimensional data for comprehensive judgment in the subsequent judgment process. After the data collection is completed, the human body pressure data, the plantar image, the human body contour image and the human eye image can be time-aligned to improve the credibility of the data and the reliability of subsequent judgments.

[0046] In a feasible embodiment, the performing of the human body balance state assessment based on at least one of the human body pressure data, the sole image, the human body contour image, and the human eye image further includes: Obtaining data timestamps of the human body pressure data, the sole image, the human body contour image, and the human eye image; Time-aligning the human body pressure data, the plantar image, the human body contour image, and the human eye image according to the data timestamp; The human body balance state is assessed according to at least one of the aligned human body pressure data, the sole image, the human body contour image, and the human eye image.

[0047] Specifically, due to the different speeds of tilt or movement of the three-dimensional force platform, when collecting data such as human body pressure data, plantar images, human body contour images, and human eye images, it is necessary to collect continuous and large amounts of image frames or pressure data sets. The pressure data or images at the same moment represent the user's body balance state at that moment. Therefore, in order to improve the credibility of the user's balance state, time alignment is performed through the timestamps of each data or image, that is, the pressure data or images with the same timestamp are regarded as a group of data to participate in subsequent image processing or data feature calculation.

[0048] In a feasible embodiment, the performing of the human body balance state assessment based on at least one of the aligned human body pressure data, the plantar image, the human body contour image, and the human eye image includes: Preprocessing the sole image to obtain a footprint image; Obtaining the pixel value and image weighted grayscale centroid of each pixel in the footprint image; Calculating plantar pressure distribution data based on the pixel value of each pixel point and the weighted grayscale center of gravity of the image; Calculating the arch index, plantar support area, and pressure center offset according to the plantar pressure distribution data; The human body balance state is evaluated based on the arch index, the plantar support area and the pressure center offset to obtain a first evaluation result.

[0049] In this embodiment, different evaluation methods are used for data of different dimensions, and data of different dimensions can be combined to improve the reliability of the evaluation results. The plantar image is used as an example for explanation. Since the plantar image can be used to calculate or characterize the user's gait parameters or whether the body is disordered, for example: patients with otogenic vertigo may have abnormal foot pressure distribution due to vestibular-proprioceptive integration disorder. Therefore, this embodiment can calculate parameters such as arch index, plantar support area and pressure center offset based on the plantar image to determine whether the user has related symptoms of otogenic vertigo.

[0050] In the specific implementation, the plantar image is obtained, then converted from the BGR color space to the HSV color space, and the green threshold range is set, and the image is eroded and expanded to improve the image quality, remove noise, and make the edge of the footprint clearer, which is convenient for subsequent processing and accurate extraction of the footprint image.

[0051] In order to analyze the pressure distribution on the sole of the foot in detail, the image was converted into a grayscale image, and the pressure value information in the image was mapped using the color interval of Colormap Jet. The sum of all pixel values in the grayscale image and the weighted grayscale center of gravity of the image were calculated to identify the area of pressure concentration, so as to further calculate the foot length FL, maximum foot width MFW, big toe distance BTD, ankle distance IMD, effective foot length EFL, support area BoS and foot angle α.

[0052] By analyzing the deviation between the above-mentioned plantar data and the plantar data of a normal user on the three-dimensional force platform, it is possible to determine whether the current user has problems such as deformity, limb incoordination, etc.

[0053] In a feasible embodiment, the calculating of the arch index, the plantar support area, and the pressure center offset according to the plantar pressure distribution data includes: Dividing the footprint image into a forefoot region, a midfoot region, and a rearfoot region; Calculating the forefoot support area corresponding to the forefoot region, the midfoot support area corresponding to the midfoot region, and the rearfoot support area corresponding to the rearfoot region according to the plantar pressure distribution data; Determine the plantar support area according to the sum of the forefoot support area, the midfoot support area, and the rearfoot support area; Calculating the area ratio between the midfoot support area and the plantar support area to obtain an arch index; The pressure center offset is calculated according to the plantar pressure distribution data and historical plantar pressure distribution data.

[0054] It should be understood that in order to perform a more detailed analysis of different areas of the sole, this embodiment uses the minimum bounding rectangle method to segment the footprint image. Figure 5 , Figure 5 The figure is a schematic diagram of segmenting a footprint image using the minimum circumscribed rectangle method in this embodiment. The sole area is divided into three equal parts: front (A), middle (B), and back (C) along the height of the rectangle. The contours of each part of the sole can be extracted separately, and the areas of these areas can be calculated. Finally, the arch index AI can be calculated by comparing the ratio of the area of the midfoot area (B) to the area of the entire sole. The arch index AI is an important numerical indicator for judging foot abnormalities such as flat feet or high arches. Generally, a low arch index indicates flat feet, and a high arch index indicates high arches.

[0055] In addition, a joint analysis can be performed in combination with the arch index and the pressure center offset to identify whether the current user has a compensatory gait, so as to provide auxiliary advice for subsequent patient rehabilitation diagnosis and treatment. Compensatory gait refers to when the human body is injured or functionally impaired and affects the normal gait, the body uses other parts or methods to replace and compensate, thereby forming an abnormal gait pattern, such as hemiplegic gait, abnormal gait caused by hip abductor muscle weakness, etc. This embodiment does not impose specific restrictions on this.

[0056] In a feasible embodiment, the performing of the human body balance state assessment based on at least one of the aligned human body pressure data, the plantar image, the human body contour image, and the human eye image further includes: Identify the skeleton key points in each human body contour image and mark them according to their types; Perform one-dimensional vector concatenation according to each marked skeleton key point to generate multiple skeleton RGB images, wherein the coordinates of each skeleton key point in the skeleton RGB image correspond to the RGB pixel value; Normalizing the pixels of the multiple skeleton RGB images to obtain multiple target skeleton RGB images; The target skeleton RGB image is input into a trained neural network model for analysis to obtain a second evaluation result, which includes at least one of the skeleton point trajectory, joint angle and trunk-limb coordination.

[0057] It should be noted that, in this embodiment, the human body contour image is collected by synchronously collecting the four image acquisition devices installed on the crossbar. Figure 6 , Figure 6 This is a schematic diagram of the position of the camera device installed on the crossbar in this embodiment. The crossbar is preset with four standard interfaces (spacing 200mm). The cameras are fixed via threaded interfaces. Four high-definition cameras are respectively arranged in the front, back, left and right of the subject. The left and right cameras are tilted 15°, and the front and rear cameras are pointed vertically downward to ensure there are no blind spots and provide multi-angle patient posture and gait information.

[0058] In the specific implementation, refer to Figure 7 , Figure 7 This is a schematic diagram of the stages of motion modeling in this embodiment. Multi-angle cameras capture videos of the patient and convert them into frame-by-frame human image data. The image data is then processed for contour recognition to obtain model data of the main limbs of the human body. Finally, after processing through the CNN algorithm, the motion model parameters of the human body are obtained. Specifically, the key points of the human skeleton are regarded as a sequence of dynamic trajectories in the time domain. Through the solution of models such as Hidden Markov Model (HMM), Conditional Random Field (CRFs), and Time Domain Pyramid, the joint position histogram distribution of the time domain key points of the skeleton and the rotation and displacement characteristics of the 3D position of the key points are obtained.

[0059] The skeleton points in each image are divided into five parts, namely the left and right arm skeleton points, the left and right leg skeleton points, and the torso skeleton points, and are distinguished by different colors. In the order of representation, the skeleton points of each frame are pulled into a one-dimensional vector. Then, the vectors of each frame in a complete video posture sequence are cascaded to form an RGB image. The (R, G, B) channels correspond to the (x, y, z) coordinates of each skeleton point, respectively, thus completing the mapping of the key points of the human body video posture to an image.

[0060] Specifically, a row of a human pose image is defined as: Ri = [xi1; xi2; :::; xiN], Gi = [yi1; yi2; :::; yiN], Bi = [zi1; zi2; :::; ziN], where i is the index of the keypoint and N is the total number of frames in the video sequence. The final pose image is then obtained by concatenating the vectors in each frame in the coordinate system pixel-wise. This is expressed as N×M×3, where M is the number of skeleton points in each frame (which remains constant).

[0061] Then, the pixels of each image are normalized:

[0062] Where Cmax and Cmin are the maximum and minimum coordinate values in the training dataset, and 255 is normalized to the pixel range (0-255) of the image representation.

[0063] In a feasible embodiment, the performing of the human body balance state assessment based on at least one of the aligned human body pressure data, the plantar image, the human body contour image, and the human eye image further includes: Obtaining a pressure center coordinate set corresponding to the human body pressure data set; Marking the pressure center for preprocessing to obtain a target pressure center coordinate set; Calculate time domain measurement indicators and frequency domain measurement indicators based on the target pressure center coordinate set, the time domain measurement indicators at least including: time domain average distance, time domain root mean square distance, time domain sway path, time domain average speed and human body inclination angle, and the frequency domain measurement indicators at least including: power spectrum density and power spectrum moment; Determine the time domain fluctuation and frequency domain offset of the human body pressure data according to the time domain measurement index and the frequency domain measurement index; A third evaluation result is obtained according to the time domain fluctuation and the frequency domain offset.

[0064] It should be noted that the pressure center refers to the theoretical center point of the human body standing on the three-dimensional force platform. Figure 8 , Figure 8 This is a schematic diagram of the coordinate axes for calculating the pressure center on the three-dimensional force platform in this embodiment. By processing the sensor data, the human body pressure center CoP (Center of Pressure) is calculated according to the principle of conservation of torque. The center of the force platform is set as the coordinate origin, the distance between two adjacent sensors is 520mm, and the plane positions of the four sensors are A ( , )、B( , )、C( , )、D( , ),in, = = = =L=260, = = = =L=260. The outputs of the four sensors on the Z axis are: 、 、 、 The projection of the center of gravity of the human body on the force platform is point G, and its coordinates are (x, y). From the formula:

[0065]

[0066] Substituting the coordinate values into the above formula, we can get:

[0067]

[0068] The coordinates (x, y) of the human body's center of pressure CoP are obtained, where x represents the left-right (ML) direction and y represents the front-back (AP) direction. Based on the CoP, time-domain measurement indicators can be calculated, including: CoP mean distance (MDIST), root mean square distance (RDIST), total sway path (LNG), average velocity (MVEL), human body inclination angle, and 95% power frequency.

[0069] The coordinates of the average CoP ( , ), calculated as follows:

[0070]

[0071] Where: N is the total number of CoP sampling points, that is, the number of CoP position data collected during the test time, T is the sampling time (unit: seconds), and f is the sampling frequency (unit: Hz), satisfying N = T × f.

[0072] Subtract the average CoP from the initial CoP to eliminate bias or noise in the data. The calculation formula is as follows:

[0073] Time domain measurement indicators include: CoP average distance (MDIST), root mean square distance (RDIST), total sway path (LNG), average speed (MVEL), and human body inclination. Specifically, the average distance (MDIST) is the average distance to the average CoP, and its calculation formula is:

[0074] The calculation formula of root mean square distance (RDIST) is:

[0075] The total swing path (LNG) is calculated as:

[0076] The average velocity (MVEL) is the total swing distance / sampling time, and its calculation formula is:

[0077] The height of the center of gravity, Gh, is estimated by biomechanical methods. Gh = 0.55h, where h is the height of the subject. GL_ap_plat is the projection of the center of gravity on the sagittal plane of the platform, which is approximately estimated by the displacement of the CoP. Accordingly, the inclination angle of the user in a standing position is calculated as follows:

[0078] The power spectral density given in the frequency domain measurement index is calculated based on the Fourier transform. The specific formula is:

[0079] Where Y(f) is the Fourier transform of the signal.

[0080] The calculation formula of spectral moment is:

[0081] in is the frequency resolution, the inverse of the sampling duration, i.e. =1 / T Hz. The power spectral density is calculated over a frequency range of 1 / T to 5 Hz. Due to the influence of the DC component and the fundamental frequency component, the first two frequency points are excluded. In the above formula, i ranges from 3 to 100, and m is the frequency point number. 95% power frequency is v , where v is the smallest integer calculated by the following formula:

[0082] Among them, u0 is the zero-order spectral moment, that is, the sum of the power spectral density of all frequency points.

[0083] In one embodiment, to accurately capture eye images, facial images can be captured first, and then the eyes can be separated from the image. This can be accomplished in three stages: image preprocessing, face detection, and eye location. Specifically, image preprocessing involves using median filtering and low-pass Gaussian filtering to remove image noise. This operation can also blur image edges. Using a high-quality camera can reduce image noise at the source.

[0084] Face detection refers to skin color detection technology. First, the face area in the image is initially extracted using skin color detection technology. Then, morphological processing is used to fill holes in the face area and smooth edges. Finally, the outline of the face area is extracted and the circumscribed rectangle of the outline is used as the face location. After the face area is detected, in order to further determine the face location, the facial outline is extracted. The face location is determined by the circumscribed rectangle of the outline. When extracting the facial outline in the area obtained by skin color detection, many outlines are often obtained. Therefore, this embodiment also sets two constraints: 1. The extracted outline must be the outer outline of the outline to eliminate the inner outline of the eyebrows and eye areas; 2. The area enclosed by the outline must be greater than 20% of the image area. This can effectively eliminate objects in the background.

[0085] Eye positioning refers to extracting the image of the human eye, that is, determining the size of the eye and the coordinates of the eye center, which is achieved using the integral projection algorithm. The integral projection algorithm first uses the prior knowledge of facial area distribution, and uses the facial grayscale integral projection curve to further determine the position of the human eye and remove the interference of the eyebrows. The essence of grayscale integration is to obtain grayscale distribution information by projecting the image in the vertical and horizontal directions, that is, the peaks and troughs of the grayscale, so as to achieve the purpose of detecting the target. The integral projection results of the facial image in the horizontal and vertical directions are shown in the figure. The vertical coordinate range [60, 240] is the prior knowledge and experience of the human eye. Within this range, the eyebrows and eyes are darker, so there are obvious troughs on the integral projection function, that is, local extreme values. Therefore, the features can be used to complete the positioning of the human eyes and eyebrows in the horizontal direction.

[0086] After obtaining the eye coordinates through the above positioning method, combined with the eye size calculated from the facial region, the eye image can be segmented. The segmentation result is shown in the figure, with the black area of the eye marked in green, the center of the eye marked in red, and the eye area selected with a green box, thus obtaining the human eye image.

[0087] This embodiment starts the projection device and the three-dimensional force platform in the human balance assessment device; obtains pressure information on the standing platform through a three-dimensional force sensor, and calculates human body pressure data based on the pressure information; collects human body contour images and human eye images through a posture acquisition device, and collects plantar images through a plantar image acquisition device; assesses the human body balance state based on at least one of the human body pressure data, the plantar image, the human body contour image, and the human eye image, analyzes the human body balance state through multi-dimensional balance assessment, and realizes a comprehensive dynamic balance assessment with higher accuracy. At the same time, the mechanical part and the processing part are flexibly combined, and the applicability is wider.

[0088] This application also provides a human body balance assessment device, please refer to Figure 9 , the human body balance assessment device comprises: The starting module 10 is used to start the projection device and the three-dimensional force platform in the human body balance assessment device.

[0089] The calculation module 20 is used to obtain pressure information on the standing platform through a three-dimensional force sensor and calculate human body pressure data based on the pressure information.

[0090] The acquisition module 30 is used to acquire a human body contour image and a human eye image through a posture acquisition device, and to acquire a plantar image through a plantar image acquisition device.

[0091] The evaluation module 40 is configured to evaluate the balance state of the human body according to at least one of the human body pressure data, the sole image, the human body contour image, and the human eye image.

[0092] This embodiment starts the projection device and the three-dimensional force platform in the human balance assessment device; obtains pressure information on the standing platform through a three-dimensional force sensor, and calculates human body pressure data based on the pressure information; collects human body contour images and human eye images through a posture acquisition device, and collects plantar images through a plantar image acquisition device; assesses the human body balance state based on at least one of the human body pressure data, the plantar image, the human body contour image, and the human eye image, analyzes the human body balance state through multi-dimensional balance assessment, and realizes a comprehensive dynamic balance assessment with higher accuracy. At the same time, the mechanical part and the processing part are flexibly combined, and the applicability is wider.

[0093] In one embodiment, the evaluation module 40 is further used to obtain data timestamps of the human body pressure data, the plantar image, the human body contour image, and the human eye image; time-align the human body pressure data, the plantar image, the human body contour image, and the human eye image according to the data timestamps; and evaluate the human body balance state based on at least one of the aligned human body pressure data, the plantar image, the human body contour image, and the human eye image.

[0094] In one embodiment, the evaluation module 40 is further used to preprocess the plantar image to obtain a footprint image; obtain the pixel value of each pixel point in the footprint image and the image weighted grayscale center of gravity; calculate the plantar pressure distribution data based on the pixel value of each pixel point and the image weighted grayscale center of gravity; calculate the arch index, plantar support area and pressure center offset according to the plantar pressure distribution data; evaluate the human body balance state according to the arch index, plantar support area and pressure center offset to obtain a first evaluation result.

[0095] In one embodiment, the evaluation module 40 is further used to divide the footprint image to obtain a forefoot area, a midfoot area, and a rearfoot area; calculate the forefoot support area corresponding to the forefoot area, the midfoot support area corresponding to the midfoot area, and the rearfoot support area corresponding to the rearfoot area based on the plantar pressure distribution data; determine the plantar support area based on the sum of the forefoot support area, the midfoot support area, and the rearfoot support area; calculate the area ratio between the midfoot support area and the plantar support area to obtain an arch index; and calculate the pressure center offset based on the plantar pressure distribution data and historical plantar pressure distribution data.

[0096] In one embodiment, the evaluation module 40 is further used to identify the skeletal key points in each human body contour image and mark them according to the type of each skeletal key point; perform one-dimensional vector cascade based on each marked skeletal key point to generate multiple skeletal RGB images, and the coordinates of each skeletal key point in the skeletal RGB image correspond to the RGB pixel value; perform pixel normalization on the multiple skeletal RGB images to obtain multiple target skeletal RGB images; input the target skeletal RGB images into a trained neural network model for analysis to obtain a second evaluation result, which includes at least one of the skeletal point trajectory, joint angle, and trunk-limb coordination.

[0097] In one embodiment, the evaluation module 40 is also used to obtain the pressure center coordinate set corresponding to the human body pressure data set; mark the pressure center and perform preprocessing to obtain a target pressure center coordinate set; calculate time domain measurement indicators and frequency domain measurement indicators based on the target pressure center coordinate set, the time domain measurement indicators at least include: time domain average distance, time domain root mean square distance, time domain swing path, time domain average speed and human body inclination angle, and the frequency domain measurement indicators at least include: power spectrum density and power spectrum spectral moment; determine the time domain fluctuation and frequency domain offset of the human body pressure data based on the time domain measurement indicators and frequency domain measurement indicators; and obtain a third evaluation result based on the time domain fluctuation and frequency domain offset.

[0098] The present application provides a human balance assessment device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the human balance assessment method in the above-mentioned embodiment one.

[0099] Reference below Figure 10 , which shows a schematic diagram of the structure of a human balance assessment device suitable for implementing embodiments of the present application. The human balance assessment device in embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 10 The human body balance assessment device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0100] like Figure 10 As shown, the human balance assessment device may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the human balance assessment device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to I / O interface 1006: input devices 1007, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008, such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003, such as a magnetic tape or hard disk; and communication device 1009. The communication device 1009 can allow the human balance assessment device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a human balance assessment device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have alternatively.

[0101] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0102] The human balance assessment device provided in this application utilizes the human balance assessment method described in the aforementioned embodiment to address the technical challenges of human balance assessment. Compared to the prior art, the beneficial effects of the human balance assessment device provided in this application are the same as those of the human balance assessment method described in the aforementioned embodiment. Other technical features of the human balance assessment device are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0103] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0104] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0105] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, wherein the computer-readable program instructions are used to execute the human body balance assessment method in the above-mentioned embodiment.

[0106] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0107] The computer-readable storage medium may be included in the human body balance assessment device, or may exist independently without being assembled into the human body balance assessment device.

[0108] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the human body balance assessment device, the human body balance assessment device can perform human body balance assessment.

[0109] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0110] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0111] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0112] The computer-readable storage medium provided in this application is a computer-readable storage medium storing computer-readable program instructions (i.e., a computer program) for executing the aforementioned human balance assessment method, thereby solving the technical problem of human balance assessment. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the human balance assessment method provided in the aforementioned embodiments, and are not further elaborated here.

[0113] The present application also provides a computer program product, comprising a computer program, which implements the steps of the above-mentioned human body balance assessment method when executed by a processor.

[0114] The computer program product provided in this application can solve the technical problem of human balance assessment. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the human balance assessment method provided in the above embodiment, and will not be repeated here.

[0115] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A human body balance assessment device, characterized in that: The human balance assessment device includes: a main frame, a three-dimensional force platform, a posture acquisition device and a control unit; The main frame is set on the ground and is used to install the three-dimensional force platform and the posture acquisition device; The three-dimensional force platform includes a base and a balance force platform. Two guide rails are provided in parallel on the base. The balance force platform is slidably connected to the guide rails. The balance force platform includes at least a light source, a three-dimensional force sensor, a motor, an AF-N actuator, a plantar image acquisition device, and a standing platform. The three-dimensional force platform adjusts the balance of a user standing on the three-dimensional force platform by moving the standing platform on the guide rails and / or adjusting the horizontal state of the standing platform; The three-dimensional force platform is further used to collect sole images and body pressure data of a user standing on the three-dimensional force platform; The posture acquisition device is used to acquire an eye image and a body contour image of a user standing on the three-dimensional force platform; The control unit is used to evaluate the balance state of the human body according to the human body pressure data, the sole image, the human body contour image and the human eye image.

2. The human body balance assessment device according to claim 1, wherein: The human body balance assessment device further includes a projection device; The main frame is provided with a movable mounting cross bar; The projection device is arranged on the mounting crossbar; The posture acquisition device is used to acquire a human eye image of a user when viewing the target image when the projection device projects the target image.

3. The human body balance assessment device according to claim 1, wherein: The human body balance assessment device also includes: The human body protection device is suspended on the installation cross bar and is used to protect the user's balance state when the three-dimensional force platform is started.

4. A method for assessing human balance, characterized in that: The human body balance assessment method is applied to the human body balance assessment device according to any one of claims 1 to 3; The human body balance assessment method comprises: activating a projection device and a three-dimensional force platform in the human body balance assessment device; Acquire pressure information on the standing platform through a three-dimensional force sensor, and calculate human body pressure data based on the pressure information; The body contour image and the human eye image are collected by the posture acquisition device, and the sole image is collected by the sole image acquisition device; The human body balance state is assessed according to at least one of the human body pressure data, the sole image, the human body contour image, and the human eye image.

5. The human body balance assessment method according to claim 4, wherein: The performing of the human body balance state assessment based on at least one of the human body pressure data, the sole image, the human body contour image, and the human eye image further includes: Obtaining data timestamps of the human body pressure data, the sole image, the human body contour image, and the human eye image; Time-aligning the human body pressure data, the plantar image, the human body contour image, and the human eye image according to the data timestamp; The human body balance state is assessed according to at least one of the aligned human body pressure data, the sole image, the human body contour image, and the human eye image.

6. The human body balance assessment method according to claim 5, wherein: The performing of a human body balance state assessment based on at least one of the aligned human body pressure data, the plantar image, the human body contour image, and the human eye image includes: Preprocessing the sole image to obtain a footprint image; Obtaining the pixel value and image weighted grayscale centroid of each pixel in the footprint image; Calculating plantar pressure distribution data based on the pixel value of each pixel point and the weighted grayscale center of gravity of the image; Calculating the arch index, plantar support area, and pressure center offset according to the plantar pressure distribution data; The human body balance state is evaluated based on the arch index, the plantar support area and the pressure center offset to obtain a first evaluation result.

7. The human body balance assessment method according to claim 6, wherein: Calculating the arch index, the plantar support area, and the pressure center offset according to the plantar pressure distribution data includes: Dividing the footprint image into a forefoot region, a midfoot region, and a rearfoot region; Calculating the forefoot support area corresponding to the forefoot region, the midfoot support area corresponding to the midfoot region, and the rearfoot support area corresponding to the rearfoot region according to the plantar pressure distribution data; Determine the plantar support area according to the sum of the forefoot support area, the midfoot support area, and the rearfoot support area; Calculating the area ratio between the midfoot support area and the plantar support area to obtain an arch index; The pressure center offset is calculated according to the plantar pressure distribution data and historical plantar pressure distribution data.

8. The human body balance assessment method according to claim 7, wherein: The performing of a human body balance state assessment based on at least one of the aligned human body pressure data, the plantar image, the human body contour image, and the human eye image further includes: Identify the skeleton key points in each human body contour image and mark them according to their types; Perform one-dimensional vector concatenation according to each marked skeleton key point to generate multiple skeleton RGB images, wherein the coordinates of each skeleton key point in the skeleton RGB image correspond to the RGB pixel value; Normalizing the pixels of the multiple skeleton RGB images to obtain multiple target skeleton RGB images; The target skeleton RGB image is input into a trained neural network model for analysis to obtain a second evaluation result, which includes at least one of the skeleton point trajectory, joint angle and trunk-limb coordination.

9. The human body balance assessment method according to claim 4, wherein: The performing of a human body balance state assessment based on at least one of the aligned human body pressure data, the plantar image, the human body contour image, and the human eye image further includes: Obtaining a pressure center coordinate set corresponding to the human body pressure data set; Marking the pressure center for preprocessing to obtain a target pressure center coordinate set; Calculate time domain measurement indicators and frequency domain measurement indicators based on the target pressure center coordinate set, the time domain measurement indicators at least including: time domain average distance, time domain root mean square distance, time domain sway path, time domain average speed and human body inclination angle, and the frequency domain measurement indicators at least including: power spectrum density and power spectrum moment; Determine the time domain fluctuation and frequency domain offset of the human body pressure data according to the time domain measurement index and the frequency domain measurement index; A third evaluation result is obtained according to the time domain fluctuation and the frequency domain offset.

10. A human body balance assessment device, characterized in that: The human body balance assessment device comprises: A starting module, used to start the projection device and the three-dimensional force platform in the human body balance assessment device; a calculation module, configured to obtain pressure information on the standing platform through a three-dimensional force sensor and calculate human body pressure data based on the pressure information; An acquisition module, configured to acquire a human body contour image and a human eye image through a posture acquisition device, and to acquire a plantar image through a plantar image acquisition device; An evaluation module is used to evaluate the balance state of the human body according to at least one of the human body pressure data, the sole image, the human body contour image, and the human eye image.

Images