Human body scanning system and health assessment method

Abstract

The embodiment of the invention provides a human body scanning system and a health assessment method, and belongs to the technical field of health detection. The system comprises a box body; the plantar scanning force table is arranged on the bottom surface of the box body, and the plantar scanning force table is used for bearing a human body; the plurality of first depth cameras are distributed on each surface of the box body and are connected with the box body through a frame; and a plurality of second depth cameras, wherein the plurality of first depth cameras are distributed on the plantar scanning force table. According to the embodiment of the invention, the whole-body muscle-bone system can be quickly examined, so that the health state of the muscle-bone system can be quickly and comprehensively evaluated.

Description

Technical Field

[0001] The present application relates to the field of health detection technology, and in particular to a human body scanning system and a health assessment method. Background Art

[0002] The human body's muscle and skeletal system (musculoskeletal system) supports the body and drives the movement of various parts of the body. The health of the musculoskeletal system plays an extremely important role in achieving the normal function of the human body. With the change of modern lifestyle, problems such as long-term sitting, poor posture and lack of exercise are common, resulting in a high incidence of musculoskeletal system diseases. Common ones include forward neck, hunchback, uneven shoulders, trunk imbalance, scoliosis, abnormal lumbar lordosis (excessive lumbar lordosis / flatback), pelvic tilt, X / O-shaped legs, knee valgus / valgus, knee hyperextension, inward / outward toe, hallux valgus, flat feet and inward / outward foot problems. These diseases are often progressive and related. For example, spinal abnormalities may trigger a chain reaction, leading to biomechanical imbalance of the lower limbs, while foot problems may in turn aggravate compensatory spinal deformity.

[0003] At present, the clinical diagnosis of musculoskeletal diseases mainly relies on doctors' empirical observation and imaging examinations, but traditional physical examinations require the evaluation of each joint and part one by one, which is time-consuming; a single examination is difficult to simultaneously capture abnormalities in multiple parts, which can easily lead to missed diagnoses; subjective visual inspection or simple tool measurements cannot obtain accurate biomechanical parameters. Although there are some musculoskeletal testing devices on the market, their functions are usually limited to a single part, resulting in fragmented test results and difficulty in supporting overall health assessment. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a human body scanning system and a health assessment method, which are intended to quickly check the musculoskeletal system of the whole body to achieve a rapid and comprehensive assessment of the health status of the musculoskeletal system.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application provides a human body scanning system, the system comprising: Box; A plantar scanning force platform, the plantar scanning force platform is arranged on the bottom surface of the box body, and the plantar scanning force platform is used to support a human body; A plurality of first depth cameras, which are distributed on each surface of the box and connected to the box through a frame; A plurality of second depth cameras and a plurality of the first depth cameras are distributed on the sole scanning force platform.

[0006] In some embodiments, the plantar scanning force platform comprises: A housing and a transparent plate covering the housing. The housing is disposed on the bottom surface of the box body. The transparent plate is rectangular and is used to carry a human body. Four three-dimensional force sensors are disposed between the transparent plate and the housing.

[0007] In some embodiments, the first depth cameras on the opposite two surfaces of the box body are symmetrically disposed and are oriented to photograph towards the center of the box body.

[0008] In some embodiments, a plurality of the second depth cameras are symmetrically disposed in the housing and are oriented to photograph towards the transparent plate.

[0009] To achieve the above object, a second aspect of the embodiments of the present application proposes a health assessment method, and the method includes: Obtain the depth image information of the human body collected by the human body scanning system and the force information of the sole scanning force platform. The depth image information of the human body includes the depth image information of the human body except the sole photographed by a plurality of the first depth cameras and the depth image information of the sole photographed by the second depth cameras. Calculate the force information of the sole scanning force platform to obtain the weight of the human body and the center of gravity line when the human body stands. Stitch the depth image information of the human body to obtain a three-dimensional model of the human body. Analyze the three-dimensional model to obtain the musculoskeletal system parameters of the human body. Perform a health assessment on the weight of the human body, the center of gravity line when the human body stands, and the musculoskeletal system parameters of the human body to obtain a health assessment result.

[0010] In some embodiments, the calculating the force information of the sole scanning force platform to obtain the weight of the human body and the center of gravity line when the human body stands includes: Add the vertical component forces obtained by the four three-dimensional force sensors to obtain the gravity received by the human body. Calculate according to the gravity to obtain the weight of the human body. Calculate the sum of the front-back component forces and the sum of the left-right component forces in the standing direction of the human body obtained by the four three-dimensional force sensors, and perform vector synthesis on the gravity, the sum of the front-back component forces, and the sum of the left-right component forces to obtain the resultant force exerted by the human body on the sole scanning force platform. Calculate the acting point of the force exerted by the human body on the sole scanning force platform based on the resultant force. Calculate according to the acting point of the force and the resultant force to obtain the center of gravity line when the human body stands.

[0011] In some embodiments, stitching the depth image information of the human body to obtain the three-dimensional model of the human body includes: Obtaining three-dimensional point cloud data in the depth image information of the human body; Projecting the three-dimensional point cloud data according to the corresponding internal parameters and external parameters of each of the first depth cameras and each of the second depth cameras to obtain a three-dimensional point cloud model of the human body, where the internal parameters and the external parameters are obtained after calibration of each of the first depth cameras and each of the second depth cameras through a preset calibration board; Rendering the three-dimensional point cloud model into a three-dimensional triangular mesh model to obtain the three-dimensional model of the human body.

[0012] In some embodiments, the calibration board includes a black and white checkerboard and colored dot matrices arranged on both sides of the black and white checkerboard; The calibration process of the first depth camera and the second depth camera is as follows: Obtaining multiple images taken by the multiple first depth cameras and the multiple second depth cameras to be calibrated of the calibration board, where each of the first depth cameras takes at least one image and each of the second depth cameras takes at least one image; Performing the following operations for each depth camera among the multiple first depth cameras and the multiple second depth cameras: Calibrating the depth camera according to the position of the black and white checkerboard in the image taken by the depth camera to obtain the initial external parameters and the internal parameters of the depth camera; Registering the initial external parameters according to the colored dot matrices in the image taken by the depth camera to obtain the external parameters of the depth camera.

[0013] In some embodiments, analyzing the three-dimensional model to obtain the musculoskeletal system parameters of the human body includes: Obtaining the coordinates of the bony landmark points of the human body according to the three-dimensional model; Calculating based on the coordinates of the bony landmark points to obtain the musculoskeletal system parameters of the human body.

[0014] In some embodiments, the musculoskeletal system parameters include: the volume, chest circumference, waist circumference, and hip circumference of the human body; Performing a health assessment on the body weight of the human body, the center of gravity line when the human body stands, and the musculoskeletal system parameters of the human body to obtain a health assessment result, including: Evaluating the health status of the spinal system of the human body according to the bony landmark points and the musculoskeletal system parameters to obtain a first evaluation result; Evaluating the symmetry of the human body according to the position and direction of the center of gravity line to obtain a second evaluation result; Evaluating the obesity degree and obesity type of the human body according to the body weight, the volume, the chest circumference, the waist circumference and the hip circumference to obtain a third evaluation result; Taking the first evaluation result, the second evaluation result and the third evaluation result as the health evaluation result.

[0015] To achieve the above object, a third aspect of the embodiments of the present application provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the method described in the second aspect above is implemented.

[0016] To achieve the above object, a fourth aspect of the embodiments of the present application provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the second aspect above is implemented.

[0017] The embodiments of the present application have the following beneficial effects: The present application provides a human body scanning system, including: a box body; a sole scanning force platform, the sole scanning force platform is arranged on the bottom surface of the box body, and the sole scanning force platform is used to carry a human body; a plurality of first depth cameras, the plurality of first depth cameras are distributed on each surface of the box body and are connected to the box body through a frame; a plurality of second depth cameras, the plurality of first depth cameras are distributed on the sole scanning force platform. The fast human body scanning method based on depth cameras in the present application, combined with the measurement of the human body center of gravity by a three-dimensional force sensor, realizes the fast, accurate and comprehensive evaluation of the health of the whole body musculoskeletal system. Description of the Drawings

[0018] Figure 1 is a schematic structural diagram of the human body scanning system provided by the embodiments of the present application; Figure 2 is a schematic structural diagram of the sole scanning force platform provided by the embodiments of the present application; Figure 3 is a schematic flowchart of the health evaluation method provided by the embodiments of the present application; Figure 4 is a schematic structural diagram of the calibration board provided by the embodiments of the present application; Figure 5 is a schematic hardware structure diagram of the electronic device provided by the embodiments of the present application.

[0019] Icons: 10 - Human body scanning system; 201 - 220 - Multiple first depth cameras; 221 - 222 - Multiple second depth cameras; 223 - Plantar scanning force platform; 224 - Box body; 301 - 304 - Four three - dimensional force sensors; 305 - Transparent plate; 306 - Frame body. Detailed implementation manners

[0020] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0021] Generally, the components of the embodiments of the present application described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application claimed, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0022] Hereinafter, the terms "including", "having" and their cognates that can be used in various embodiments of the present application are only intended to represent specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be construed as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or increasing the possibility of one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items. In addition, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0023] Unless otherwise defined, all terms (including technical terms and scientific terms) used here have the same meaning as those commonly understood by those of ordinary skill in the art to which the various embodiments of the present application belong. The terms (such as those defined in a commonly used dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or being overly formal, unless clearly defined in the various embodiments of the present application.

[0024] Next, some implementation manners of the present application will be described in detail in conjunction with the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0025] The muscular and skeletal system (musculoskeletal system) of the human body plays the functions of supporting the body and driving the movement of various body parts. The health of the musculoskeletal system is extremely important for the realization of the normal functions of the human body. In modern society, due to high work pressure and long working hours, most people have unhealthy living habits such as sitting for long periods, incorrect sitting postures, and lack of exercise. Over time, health problems will occur in the musculoskeletal system, and common ones include forward head posture, hunchback, uneven shoulders, trunk imbalance, scoliosis, abnormal lumbar lordosis (excessive lumbar lordosis / flat back syndrome), pelvic tilt, X / O-shaped legs, genu varum / valgum, knee hyperextension, intoeing / outtoeing, hallux valgus, flat feet, and pes varus / valgus, etc. Since there are many joints and parts involved, it is difficult for doctors to detect all problems at once during medical treatment, which is likely to cause missed detection and treatment delays, aggravating the condition.

[0026] Current clinical diagnosis mainly relies on doctors' experience combined with imaging examinations such as X-rays and CTs, which have obvious limitations: Traditional physical examinations require manual measurement of each joint parameter item by item, with low efficiency and poor repeatability; two-dimensional images are difficult to comprehensively reflect structural abnormalities in three-dimensional space; decentralized detection devices cannot synchronously obtain whole-body mechanical data and morphological features, resulting in a lack of systematicness in evaluation results. Although some three-dimensional scanning devices on the market can obtain body surface morphological data, they lack a plantar mechanics detection module and cannot establish a correlation analysis between posture and force; while independent force platforms cannot synchronously capture the three-dimensional posture information of the human body. This data fragmentation phenomenon makes it difficult for clinics to accurately judge the mechanical root causes of abnormal postures, restricting the formulation of early intervention and personalized rehabilitation programs.

[0027] To solve the above problems, the R & D personnel focused on how to construct an integrated system that can synchronously collect whole-body three-dimensional morphology and plantar mechanics data. Traditional split-type detection devices have technical bottlenecks such as large space occupation and difficult data integration. By analyzing the biomechanical characteristics of the human standing posture, it was found that there is a strong correlation between plantar pressure distribution and spinal alignment, which provides a theoretical basis for the design of a unified detection platform. Further considering the importance of multi-angle three-dimensional imaging for posture analysis and the need to achieve blind-free data collection in a limited space, a solution was proposed to integrate the depth vision sensor and the mechanics detection module.

[0028] Based on this, the embodiments of this application provide a human body scanning system and a health assessment method, aiming to quickly examine the whole-body musculoskeletal system to achieve a rapid and comprehensive assessment of the health status of the musculoskeletal system.

[0029] The human body scanning system and health assessment method provided by the embodiments of this application are specifically described through the following embodiments. First, the human body scanning system in the embodiments of this application is described.

[0030] Figure 1The human body scanning system 10 according to the embodiment of the present application includes: a box body 224, a sole scanning force platform 223 for carrying the human body, a plurality of first depth cameras 201-220 distributed on the surfaces of the box body, and a plurality of second depth cameras 221-222 arranged on the sole scanning force platform. The box body serves as a support frame to carry each detection component. The sole scanning force platform integrates a mechanical sensing function. The first depth camera group is connected to the box body through a fixed frame, and the second depth camera group is deployed in the sole detection area.

[0031] Among them, the box body 224 serves as a rigid support structure for fixing the spatial positions of the depth cameras and defining the range of the detection area, and can be constructed by combining a metal frame and a composite plate. The sole scanning force platform 223 refers to a load-bearing platform with mechanical detection functions, and realizes the measurement of the sole pressure distribution through the combination of a transparent plate and a three-dimensional force sensor. The plurality of first depth cameras 201-220 refer to a visual sensor array covering each perspective of the human body standing space, and can realize three-dimensional point cloud acquisition. The plurality of second depth cameras 221-222 refer to visual sensors arranged facing the sole area, and are used to supplement the sole shape data missing from the perspective of the bottom of the box body. Specifically, the box body 224 forms a cubic detection space, and the subject standing on the sole scanning force platform 223 is synchronously captured from multiple angles by the surrounding depth cameras. The spatial layout of the plurality of first depth cameras 201-220 ensures the complete acquisition of the three-dimensional contour information of the front, side, and back of the human body, and the plurality of second depth cameras 221-222 collect the sole curved surface shape from below.

[0032] Specifically, the human body scanning system includes N depth cameras, where N should be no less than 20 and can be increased according to specific requirements. Among them, N - 2 (multiple first depth cameras) are arranged on the four side surfaces of the box body 224. The box body 224 forms a cuboid measurement space, and the depth cameras are directed towards the center position of the measurement space for shooting. The area near the center line of the measurement space is the human body contour scanning area. The structure of the box body 224 and the placement positions of the depth cameras on the system framework can be adjusted accordingly according to the installation environment. The basic principle is that they should be symmetrically and evenly distributed around the scanning area, and after the optimal shooting areas of all cameras overlap, they can cover all parts from the head to the feet (excluding the soles) of the scanned person, ensuring that all parts of the scanned person except the soles can be captured with high quality. A sole scanning force platform 223 is placed at the center position of the measurement space. The sole scanning force platform 223 mainly consists of a frame body 306, four three-dimensional force sensors 301 - 304, and a transparent plate 305. The material of the transparent plate 305 can be plexiglass. The transparent plate 305 is rectangular (or square). The four three-dimensional force sensors 301 - 304 are placed below the four vertices of the transparent plate 305 and can collect the acting forces exerted on the sole scanning force platform 223 when the test subject stands on the sole scanning force platform 223. The transparent plate 305 and the frame body 306 are fixedly connected through the four three-dimensional force sensors 301 - 304 at the vertices. Two second depth cameras are fixedly placed on the frame body 306 and shoot towards the direction of the transparent plate 305, and can collect the depth image information of the soles when the test subject stands on the sole scanning force platform.

[0033] Compared with the prior art, traditional split-type detection devices require the examinee to move between different detection positions, resulting in asynchronous data collection and difficult spatial registration. In this embodiment, a multi-sensor spatial position is fixed through an integrated box structure to ensure that the data from each perspective has a unified coordinate system. Conventional sole pressure detection devices lack the ability to synchronously collect the three-dimensional shape of the sole. This system combines a transparent force platform with a bottom depth camera to obtain the three-dimensional shape characteristics of the sole while measuring mechanical parameters.

[0034] Through the above technical solutions, this embodiment realizes the synchronous collection of the three-dimensional shape of the whole human body and the sole mechanics in the standing posture, and solves the problem of fragmented data in traditional detection methods. The multi-angle depth camera group eliminates the visual blind area of single-perspective detection and provides complete three-dimensional data for postural analysis. The spatio-temporal alignment characteristics of the mechanical and visual data support the correlation analysis of biomechanical parameters and establish a multi-dimensional data basis for the health assessment of the musculoskeletal system. The integrated design simplifies the detection process and avoids measurement errors caused by multiple body position adjustments of the examinee.

[0035] Figure 2The plantar scanning force platform 223 according to the embodiment of the present application includes: a frame body 306 and a transparent plate 305 covering the frame body 306. The frame body 306 is arranged on the bottom surface of the box body 224. The transparent plate 305 is rectangular and is used to carry a human body. Four three-dimensional force sensors 301-304 are arranged between the transparent plate 305 and the frame body 306.

[0036] Among them, the frame body 306 refers to a rigid structure that constitutes the bottom support of the plantar scanning force platform 223. Specifically, high-strength metals (such as aluminum alloy or steel structure) can be used, and its internal space is used to accommodate the three-dimensional force sensors 301-304. The transparent plate 305 refers to a planar component with high light transmittance and load-bearing strength. Specifically, tempered glass or polycarbonate plates can be used to implement it. The three-dimensional force sensors 301-304 refer to detection units that can detect mechanical data in the vertical direction, front-back direction, and left-right direction. Specifically, composite sensors based on the piezoelectric ceramic or strain gauge principle can be used. Each sensor is fixed between the frame body and the transparent plate by threads.

[0037] Specifically, the transparent plate 305, as the bearing surface, directly contacts the human plantar surface and transmits the three-dimensional mechanics generated during standing to the three-dimensional force sensor array inside the frame body. Multiple sensors are evenly distributed in space below the transparent plate 305. By synchronously collecting the normal pressure in the vertical direction, the shear force in the front-back direction, and the shear force in the left-right direction, a plantar pressure distribution model is established. The frame body 306, as a rigid base, ensures the installation accuracy of the sensors and avoids measurement errors caused by bearing deformation. The sensor data is transmitted to the electronic device by wired or wireless means and is used to calculate the human body center of gravity trajectory and postural stability parameters.

[0038] Compared with the prior art, traditional plantar pressure detection devices mostly use single-direction force sensors or contact thin film sensors, which cannot synchronously obtain three-dimensional mechanical data, and the sensors are easily damaged by external impacts. In this embodiment, through the combined structure of the rigid frame body and the transparent plate, multi-dimensional mechanical detection is realized while ensuring the bearing capacity, and the sensors are built into a closed space to avoid external environmental interference.

[0039] Through the above technical solutions, this embodiment can accurately capture the three-dimensional mechanical distribution characteristics of the plantar surface when a human body stands, providing multi-dimensional biomechanical data for gait analysis and postural assessment. The cooperative design of the transparent plate and the sensor array solves the technical defects of the traditional device with a single measurement dimension and poor anti-interference ability, and the built-in sensor structure effectively extends the service life of the device.

[0040] The present application further proposes that the first depth cameras on the opposite two surfaces of the box body 224 are symmetrically arranged and face the center direction of the box body 224 for shooting.

[0041] Among them, the symmetric setting means that the first depth cameras are arranged on the left and right sides or the front and back sides at the same height in a mirror image manner. Specifically, a bracket can be used to fix the device at symmetric positions on both sides of the box body 224 to ensure that the spatial coordinate relationship of the devices on both sides is consistent. Shooting towards the center direction of the box body 224 means that the optical axis direction of the device converges on the internal geometric center point of the box body 224. Specifically, the pitch angle of the camera can be adjusted so that its lens is aligned with the center point area to ensure that all parts of the human body are within the common field of view of multiple devices when standing.

[0042] Specifically, when a human body stands inside the box body 224, the symmetrically arranged devices synchronously collect the side contour data of the human body from the left and right sides or the front and back sides. After the point cloud data of all the first depth cameras are fused, the three-dimensional morphological characteristics of the front, back, and side of the human body can be completely restored, avoiding the loss of key anatomical landmark points due to insufficient device viewing angles.

[0043] Compared with the prior art, traditional musculoskeletal detection devices usually use unidirectional or asymmetrically distributed acquisition devices, resulting in the lack of human body side and back data and making it difficult to construct a complete three-dimensional model. In this embodiment, through the shooting methods of symmetric layout and central convergence, the fields of view of multiple devices form continuous coverage around the human body, significantly improving the integrity and spatial resolution of data acquisition.

[0044] Through the above technical solutions, this embodiment solves the problem of abnormal missed detection of correlation caused by limited viewing angles of traditional detection devices, and realizes the full-round reconstruction of the three-dimensional shape of the human body through multi-angle synchronous acquisition, providing high-precision data support for scenarios such as symmetry evaluation of the musculoskeletal system and scoliosis detection that require overall analysis.

[0045] This application further proposes that a plurality of second depth cameras 221-222 are symmetrically arranged in the frame body 306, and the plurality of second depth cameras 221-222 are oriented to shoot at the transparent plate 305.

[0046] Among them, the symmetric setting means that a plurality of second depth cameras are distributed inside the frame body 306 in a geometrically symmetric form, which can be specifically realized by mirror distribution or central symmetry distribution, so that the optical signals in different areas of the sole can be synchronously captured. The frame body 306 refers to a structural component for carrying the transparent plate, which can be specifically made of a metal frame or a composite material, providing fixed support for the second depth camera and avoiding interference from external light.

[0047] Specifically, multiple second depth cameras 221-222 are integrated inside the housing 306 of the plantar scanning force platform 223, covering the bearing area of the transparent plate 305 in a symmetric arrangement. When a person stands, the pressure distribution area formed by the plantar contacting the transparent plate 305 is synchronously scanned by the second depth cameras. After the optical signal penetrates the transparent plate 305, it is received by the second depth cameras, and complementary to the top view data of the first depth cameras, three-dimensional plantar shape data is constructed.

[0048] Compared with the prior art, traditional plantar scanning devices usually adopt a single-view or asymmetrically distributed sensor layout, resulting in data missing in the arch depression area. The multiple symmetrically arranged second depth cameras eliminate the blind area of a single camera through field of view superposition.

[0049] Through the above technical solution, this embodiment realizes the full-coverage acquisition of the three-dimensional plantar morphology, solves the problem of missed detection of signs such as arch collapse and abnormal plantar pressure distribution caused by perspective limitations in traditional foot detection, and provides a complete foot biomechanical data basis for subsequent musculoskeletal system health assessment.

[0050] This application further proposes a health assessment method. The health assessment method provided by the embodiments of this application relates to the technical field of health detection. The health assessment method provided by the embodiments of this application can be applied to a terminal, can also be applied to a server side, or can also be software running on a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc.; the server side can be configured as an independent physical server, can also be configured as a server cluster or a distributed system composed of multiple physical servers, or can also be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the health assessment method, etc., but is not limited to the above forms.

[0051] This application can be used in numerous general or specific computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0052] It should be noted that in each specific embodiment of this application, when it comes to relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first. Moreover, the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when this application embodiment needs to obtain the user's sensitive personal information, the user's separate permission or separate consent will be obtained through methods such as pop-up windows or redirecting to a confirmation page. After clearly obtaining the user's separate permission or separate consent, the necessary user-related data for the normal operation of this application embodiment will be obtained.

[0053] Figure 3 It is an optional flowchart of the health assessment method provided by an embodiment of this application. The health assessment method is applied to an electronic device, and the electronic device is communicatively connected to a human body scanning system. The health assessment method may include, but is not limited to, steps S100 to S500.

[0054] Step S100, obtain the depth image information of the human body collected by the human body scanning system and the force information of the plantar scanning force platform. The depth image information of the human body includes the depth image information of the human body except the sole captured by multiple first depth cameras and the depth image information of the sole captured by the second depth camera; Step S200, calculate the force information of the plantar scanning force platform to obtain the weight of the human body and the center of gravity line when the human body stands; Step S300, splice the depth image information of the human body to obtain a three-dimensional model of the human body; Step S400, analyze the three-dimensional model to obtain the musculoskeletal system parameters of the human body; Step S500: Conduct a health assessment on the weight of the human body, the center of gravity line when the human body stands, and the parameters of the human musculoskeletal system to obtain a health assessment result.

[0055] In this embodiment, the depth image information refers to the three-dimensional coordinate data of the human body surface collected by multiple depth cameras, which is used to construct a three-dimensional point cloud covering the whole body. The force information refers to the mechanical data in the vertical and horizontal directions captured by the plantar scanning force platform, which is used to calculate the center of gravity distribution and support stability. The three-dimensional model refers to the human body surface mesh generated by multi-viewpoint cloud fusion, which can be specifically implemented by the iterative closest point algorithm or feature matching, and is used to extract anatomical feature parameters. The musculoskeletal system parameters refer to the body shape and bone features analyzed based on the three-dimensional model, which can be specifically implemented by key point detection or morphological analysis, and are used to evaluate spinal curvature, joint alignment, and postural symmetry. The health assessment refers to the comprehensive analysis combining biomechanical data and body shape parameters, which can be specifically implemented by a machine learning model or a rule engine, and is used to output multi-dimensional health indicators.

[0056] In this embodiment, the plantar mechanical data and the full-body depth image are synchronously collected by the human body scanning system. The plantar mechanical data is used to calculate the weight and the center of gravity trajectory through vector synthesis, and the depth image is used to generate a complete three-dimensional model through multi-camera calibration and point cloud stitching. After the anatomical features of the three-dimensional model are extracted, parameters such as chest circumference and waist circumference are obtained, and the postural symmetry and support stability are analyzed in combination with the center of gravity trajectory. Finally, by fusing biomechanical parameters and body shape parameters, a comprehensive assessment of human obesity, spinal health, and motor function is realized.

[0057] Specifically, the three-dimensional point cloud data of the human body can be obtained by using depth cameras placed distributively, including the depth image information of all parts of the human body except the soles collected by multiple first depth cameras, and the depth image information of the soles of the human body collected by multiple first depth cameras. Through the collaborative work of multiple first depth cameras and multiple second depth cameras, complete three-dimensional data of the human body is jointly obtained.

[0058] The body weight and the center of gravity force line during standing of the human body are obtained by using a three-dimensional force sensor. The plantar scanning force platform detects the force exerted by the subject through the three-dimensional force sensors under its four corners. Each force sensor can detect the forces in three directions: vertical, front-back, and left-right, so as to obtain the interaction force between the sole of the subject's foot and the force platform when standing. The sum of the vertical component forces of the four force sensors is the gravity force received by the subject. Dividing it by the gravitational acceleration g can obtain the body weight of the subject. By calculating the sum of the front-back direction and left-right direction component forces of the four force sensors and combining with the sum of the vertical direction component forces, the resultant force (including the force magnitude and direction) exerted by the human body on the force platform can be obtained. Then, by making the resultant moment received by the force platform equal to zero, the acting point of the force exerted by the human body on the force platform can be calculated. Through the acting point and the resultant force calculated above, the center of gravity force line of the subject during standing can be obtained.

[0059] Using the point cloud data of all depth cameras, the point cloud data of each depth camera is aligned by using the iterative closest point algorithm to eliminate the parallax and overlap between different cameras, and finally a complete and accurate three-dimensional human body model is obtained. From the stitched whole-body external shape point cloud data, the coordinates of the bony landmark points of the main joints of the human body are obtained through a deep learning model, including the left and right frontal vertexes, the left and right posterior vertexes of the head, the left and right ear centers, the 7th cervical vertebra (i.e., the most prominent point at the back of the neck), the left and right acromion points, the clavicle notch points, the xiphoid process points of the sternum, the 10th thoracic vertebra, the left and right lateral points of the elbow joint, the left and right posterior points of the elbow joint, the left and right radial processes of the thumb ends of the wrist joint, the left and right ulnar processes of the little finger ends of the wrist joint, the left and right middle finger vertexes, the left and right anterior superior iliac spines, the left and right posterior superior iliac spines, the left and right lateral epicondyles of the knee, the left and right medial epicondyles of the knee, the left and right lateral malleoli of the ankle, the left and right medial malleoli of the ankle, the left and right heels, the left and right thumb vertexes, the left and right first metatarsophalangeal joint points, and the left and right second metatarsophalangeal joint points, etc. Based on these bony landmark points, the main musculoskeletal system parameters of the human body are calculated, including: height, left and right leg lengths, left and right arm lengths, chest circumference, waist circumference, hip circumference, plantar contact area, standing arch height, and the total volume of the scanned human body, etc.

[0060] Based on data such as the body weight, center of gravity force line, and main musculoskeletal system parameters of the subject, a comprehensive assessment is carried out on aspects such as the obesity degree, spinal health, and motor function of the human body. The results of the health assessment, exemplarily, may include physical indicators such as body weight, BMI, body fat percentage, the assessment of the health status of the spinal system (such as whether there are problems such as forward head carriage, hunchback, etc.), the assessment of plantar health (such as whether there are problems such as flat feet, foot varus / valgus, etc.), the assessment of the obesity degree and type, and health suggestions and improvement plans, etc.

[0061] In this embodiment, by integrating multi-dimensional data sources, the collaborative analysis of mechanical parameters and anatomical parameters is realized, and multiple problems such as postural imbalance, obesity distribution, and spinal abnormalities can be detected simultaneously, improving the comprehensiveness of evaluation. Through the above technical solutions, this embodiment can complete the synchronous acquisition and correlation analysis of whole-body biomechanical and anatomical data at one time, solving the problems of low detection efficiency and limited coverage of traditional methods. The evaluation model based on multi-parameter fusion can identify the correlation between postural imbalance and obesity types, providing a quantitative basis for the early detection of musculoskeletal diseases and reducing the risk of missed diagnosis. The automated processing flow reduces the dependence on manual experience and improves the consistency and repeatability of evaluation results.

[0062] In some embodiments, step S200 may include but is not limited to steps S210 to S250: Step S210, adding the vertical component forces obtained by the four three-dimensional force sensors to obtain the gravity received by the human body; Step S220, calculating based on the gravity to obtain the weight of the human body; Step S230, calculating the sum of the front-back component forces and the sum of the left-right component forces of the human body standing direction obtained by the four three-dimensional force sensors, and performing vector synthesis on the gravity, the sum of the front-back component forces, and the sum of the left-right component forces to obtain the resultant force exerted by the human body on the sole scanning force platform; Step S240, calculating the acting point of the force exerted by the human body on the sole scanning force platform based on the resultant force; Step S250, calculating based on the acting point of the force and the resultant force to obtain the center of gravity line of the human body when standing.

[0063] In this embodiment, adding the vertical component forces means accumulating the component forces perpendicular to the sole scanning force platform detected by each three-dimensional force sensor, which can be specifically implemented by a numerical accumulation algorithm to reflect the total gravity of the human body. Vector synthesis means integrating the component forces in different directions into a spatial resultant force according to the vector superposition principle, which can be specifically implemented by a vector coordinate decomposition and synthesis method to determine the overall direction of the sole force distribution. The acting point of the force refers to the equivalent acting position of the resultant force on the sole scanning force platform, which can be specifically calculated by the moment balance equation to characterize the projection position of the human body's center of gravity. The center of gravity line refers to the spatial action line of the human body's center of gravity relative to the sole support surface, which can be specifically calculated by the acting point coordinates and the resultant force direction to reflect the balance state of the human body when standing.

[0064] Specifically, during the data calculation process, first, the vertical component forces collected by the three-dimensional force sensor are accumulated and summed to directly obtain the total force value corresponding to the human body gravity, and then the body weight is obtained through conversion using the acceleration due to gravity. Subsequently, the component forces of each sensor in the front-back direction and the left-right direction are summed respectively, and combined with the total gravity force for three-dimensional vector synthesis to obtain the overall force direction and magnitude of the plantar scan force platform. Based on the resultant force after synthesis, the position of the action point of the resultant force is calculated using the principle of moment balance, that is, by the condition that the sum of the moments of each component force relative to the reference point of the force platform is equal to the moment of the resultant force, the coordinates of the action point are solved. Finally, according to the coordinates of the action point and the spatial direction of the resultant force, a straight line passing through the action point and extending along the direction of the resultant force is determined as the center of gravity force line, which is used to describe the projection trajectory of the center of gravity when the human body stands.

[0065] In this embodiment, through multi-sensor data fusion and three-dimensional vector synthesis, the spatial distribution of the plantar force can be accurately calculated, and the action point can be dynamically determined in combination with the moment balance equation, significantly improving the calculation accuracy and reliability of the center of gravity force line. This embodiment can automatically obtain accurate body weight data and biomechanical parameters when the human body stands, solve the error problem caused by the traditional method relying on subjective judgment, provide high-precision basic data support for subsequent musculoskeletal health assessment, and at the same time avoid the risk of misdiagnosis or missed diagnosis caused by inaccurate data.

[0066] In some embodiments, step S300 may include but is not limited to steps S310 to S330: Step S310, obtaining the three-dimensional point cloud data in the depth image information of the human body; Step S320, projecting the three-dimensional point cloud data according to the corresponding internal parameters and external parameters of each of the first depth cameras and each of the second depth cameras to obtain the three-dimensional point cloud model of the human body, where the internal parameters and the external parameters are obtained after calibration of each of the first depth cameras and each of the second depth cameras using a preset calibration board; Step S330, rendering the three-dimensional point cloud model into a three-dimensional triangular mesh model to obtain the three-dimensional model of the human body.

[0067] In this embodiment, the three-dimensional point cloud data refers to a set of discrete points containing the three-dimensional coordinate information of the object surface collected by a depth camera, and each point includes spatial coordinates and depth information. The internal parameters and external parameters refer to a set of parameters that describe the imaging characteristics of the depth camera. The internal parameters include the focal length, the coordinates of the principal point, and the lens distortion coefficients, and the external parameters include the position and orientation of the camera in space. Projection refers to the process of converting the point cloud data of multiple cameras into a unified coordinate system. The three-dimensional point cloud model refers to a complete three-dimensional model of the human body surface formed by multi-viewpoint cloud fusion. Specifically, the iterative closest point algorithm can be used to register the overlapping areas to achieve seamless splicing of multi-source data. The calibration board refers to a device for camera parameter calibration, which can specifically consist of a 9×6 black-and-white checkerboard in the middle and color dot matrices on both sides. The depth camera obtains calibration parameters by photographing the calibration board from different angles. The triangular mesh model refers to a geometric model that converts point cloud data into a continuous surface representation.

[0068] Specifically, the multi-viewpoint cloud data collected by the depth camera is subjected to coordinate transformation through the parameter matrix obtained by calibration to eliminate the spatial pose differences brought about by different camera viewpoints. All point clouds are registered and fused in a unified coordinate system to form a three-dimensional point cloud data set that completely covers the human body surface. This point cloud data set is processed by a surface reconstruction algorithm and converted into a triangular mesh model with a topological structure, providing an accurate geometric basis for subsequent morphological analysis. The calibration process accurately calibrates the internal and external parameters of each camera through the extraction of calibration board feature points and optimization calculations to ensure the spatial consistency of multi-camera data.

[0069] In this embodiment, the calibration method of the depth camera is as follows: As Figure 4 shown, a color calibration board for a depth camera includes: a black-and-white checkerboard, and color dot matrices arranged on both sides of the black-and-white checkerboard.

[0070] The calibration processes of the first depth camera and the second depth camera are as follows: Obtain multiple images taken by the multiple first depth cameras and the multiple second depth cameras to be calibrated of the calibration board, where each of the first depth cameras takes at least one image, and each of the second depth cameras takes at least one image; For each depth camera among the multiple first depth cameras and the multiple second depth cameras: Calibrate the depth camera according to the position of the black-and-white checkerboard in the image taken by the depth camera to obtain the initial external parameters and the internal parameters of the depth camera; Register the initial external parameters according to the color dot matrices in the image taken by the depth camera to obtain the external parameters of the depth camera.

[0071] Among them, the black-and-white checkerboard refers to a planar pattern composed of alternately arranged black and white squares, which is used to calculate the initial external parameters and internal parameters of the depth camera through the checkerboard corner point detection algorithm. The color dot matrix refers to an array composed of regularly arranged color circular markers, which is used to perform spatial registration on the initial external parameters through color recognition and spatial matching algorithms.

[0072] Specifically, during the calibration process of the external parameters, the calibration board is fixed at a preset position inside the box of the human body scanning system. The preset position can be the position at the center of the box. Multiple depth cameras simultaneously capture images of the calibration board from different angles. The calibration board is fixed in position during one capture. The number of calibrations can be customized according to the actual calibration accuracy and is not limited here. During the calibration process of the internal parameters, the calibration board is sequentially shown to each depth camera in a pre-set order. Each depth camera captures a set of images of the calibration board for internal parameter calibration. Among them, the calibration board captured by each depth camera should occupy at least 20% or more of the area of the picture. In a set of captured photos, the position of the calibration board in the picture should be able to cover the entire picture. Exemplarily, for internal parameter calibration, 4 photos are captured, namely a, b, c, and d. In photo a, the calibration board is in the upper left corner of the picture, occupying 25% of the picture; in photo b, the calibration board is in the upper right corner of the picture, occupying 25% of the picture; in photo c, the calibration board is in the lower left corner of the picture, occupying 25% of the picture; in photo d, the calibration board is in the lower right corner of the picture, occupying 25% of the picture, and the positions of the calibration board in the four images a, b, c, and d can cover the entire picture. In the specific practice process, the calibration board can be moved within the shooting range of each depth camera, and the depth camera can obtain a set of pictures as calibration images by shooting a video and intercepting some of the pictures.

[0073] The image processing process of each depth camera is divided into two stages: In the first stage, by identifying the corner coordinates of the black-and-white checkerboard, the mapping relationship between the camera coordinate system and the checkerboard coordinate system is established, and the initial external parameters and internal parameters are calculated; in the second stage, by identifying the pixel coordinates of the center of each circle in the color dot matrix, spatial matching is performed with the pre-stored three-dimensional coordinates of the color dot matrix, and the least squares method is used to optimize the spatial pose of the initial external parameters, and finally the accurate external parameters are obtained.

[0074] Specifically, the steps of color point cloud registration and external parameter optimization are as follows: By selecting one camera as the reference camera (reference point), the initial transformation matrix of other cameras relative to the reference camera is calculated using the initial external parameters. This initial transformation matrix describes the position and orientation of other cameras relative to the reference camera. Then, the Color Iterative Closest Point (C-ICP) registration algorithm is used for registration. When the C-ICP algorithm iteratively searches for corresponding point pairs, it not only utilizes the rich geometric features provided by the combined calibration board but also focuses on the different colors provided by the circular pattern areas on both sides to enhance the accuracy of corresponding point judgment. The C-ICP algorithm minimizes a cost function that simultaneously includes geometric error and color error. Geometric error refers to the distance error between corresponding points, and color error refers to the color difference between corresponding points. By minimizing this cost function, the optimal corresponding point pairs can be found, thereby optimizing the initial external parameters of the cameras and obtaining the accurate external parameters of each camera relative to the reference camera. These accurate external parameters describe the position and orientation of each camera in three-dimensional space, ensuring that the data collected by all cameras can be correctly stitched and fused.

[0075] Compared with existing methods, the combined calibration board provides rich geometric and color features. The initial calibration using checkerboard corners ensures the basic accuracy, and the subsequent optimization using the color and geometric information of the circular patterns on both sides provides stronger constraints, improving the robustness of point cloud registration under different lighting conditions or viewpoints and enabling more accurate stereo camera external parameters to be obtained than a single-feature calibration board.

[0076] In this embodiment, the checkerboard pattern at the center of the calibration board provides rich geometric features such as corners and edges, which are used for preliminary corresponding point matching; the circular pattern areas on both sides of the calibration board provide different color information, which is used to enhance the accuracy of corresponding point matching, especially in cases where geometric features are not obvious. By combining geometric features and color features, the C-ICP algorithm can more accurately find corresponding point pairs, thereby optimizing the initial external parameters of the cameras and obtaining more accurate camera external parameters. These accurate external parameters are crucial for subsequent 3D reconstruction and point cloud stitching, ensuring that the data collected by all cameras can be correctly stitched and fused, and finally obtaining a complete and accurate 3D human body model. By establishing an accurate spatial correspondence through multi-camera joint calibration and using the calibration parameters to achieve accurate projection and registration of multi-viewpoint point cloud data, the stitching error can be effectively eliminated. This embodiment realizes the accurate fusion of multi-view depth data, generates a complete and topologically correct 3D human body model, and provides high-precision geometric data support for subsequent musculoskeletal parameter calculation.

[0077] In some embodiments, step S400 may include but is not limited to steps S410 to S420: Step S410, obtaining the coordinates of the osseous landmark points of the human body according to the three-dimensional model; Step S420, calculating based on the coordinates of the osseous landmark points to obtain the musculoskeletal system parameters of the human body.

[0078] In this embodiment, the three-dimensional model refers to a three-dimensional human body model formed by stitching depth image information collected by multiple depth cameras. Specifically, it can be implemented by projecting three-dimensional point cloud data to generate a triangular mesh model, which is used to completely present the surface morphology of the human body. Among them, the coordinates of the osseous landmark points refer to the position data of key points with anatomical features in the human skeletal system. Specifically, it can be achieved by analyzing the surface curvature of the three-dimensional model or automatically identifying landmark points such as the acromion, anterior superior iliac spine, and greater trochanter of the femur through a preset deep learning model, which is used to locate the skeletal structure features. Among them, the musculoskeletal system parameters refer to quantitative indicators reflecting the morphological characteristics of the musculoskeletal system. Specifically, it can be achieved by calculating the distance, angle, or perimeter data between osseous landmark points. The main musculoskeletal system parameters of the human body include: height, left and right leg lengths, left and right arm lengths, chest circumference, waist circumference, hip circumference, sole contact area, standing arch height, and the total volume of the scanned human body, etc.

[0079] Specifically, the three-dimensional model is constructed by fusing multi-viewpoint cloud data collected by an array of depth cameras to form a three-dimensional mesh containing complete geometric information of the human body surface. During the process of identifying osseous landmark points, a deep learning model can be used to extract features from the vertex distribution of the three-dimensional mesh and match a predefined anatomical feature template to achieve key point positioning. In the stage of calculating musculoskeletal system parameters, geometric operations are performed based on the spatial coordinate relationship of key points. For example: height can be calculated by the vertical distance from the highest point of the head to the lowest point of the foot; the left and right leg lengths can be obtained by the length of the line connecting the anterior superior iliac spine osseous landmark points on the left and right to the center point of the heel; the waist circumference can be calculated by the outer perimeter length of the cross-sectional shape of the three-dimensional human body model at the horizontal plane where the anterior superior iliac spines are located on the left and right; the sole contact area and arch height can be calculated from the images captured by the depth camera under the foot.

[0080] In some specific embodiments, the identification of osseous landmark points can adopt an algorithm based on curvature extreme value detection. By calculating the Gaussian curvature distribution at the vertices of the three-dimensional mesh, feature points corresponding to skeletal protrusions such as the acromion and iliac crest are screened out. The calculation of musculoskeletal system parameters can be combined with a biomechanical model. For example, the offset of the lower limb biomechanical axis is deduced according to the spatial relationship between the greater trochanter of the femur and the center of the knee joint.

[0081] This embodiment automatically extracts the coordinates of osseous landmark points through a three-dimensional model, realizes the objective calculation of multi-dimensional space parameters, provides objective data support for the quantitative evaluation of musculoskeletal system diseases such as scoliosis and pelvic tilt, solves the problem of missed diagnosis caused by the traditional method relying on empirical judgment, and improves the evaluation efficiency through automated calculation.

[0082] In some embodiments, step S500 may include, but is not limited to, steps S510 to S540: Step S510, evaluate the health status of the human spinal system based on the bony landmark points and musculoskeletal system parameters to obtain a first evaluation result; Step S520, evaluate the symmetry of the human body based on the position and direction of the center of gravity line to obtain a second evaluation result; Step S530, evaluate the obesity degree and obesity type of the human body based on the body weight, volume, chest circumference, waist circumference, and hip circumference to obtain a third evaluation result; Step S540, use the first evaluation result, the second evaluation result, and the third evaluation result as the health evaluation result.

[0083] In this embodiment, the bony landmark points refer to the position points with anatomical features in the human skeletal system, such as the acromion, anterior superior iliac spine, and greater trochanter of the femur. Specifically, three-dimensional model surface curvature analysis or machine learning algorithms can be used to identify the spatial coordinates of these points for constructing the spatial relationship of the human skeletal structure. The center of gravity line refers to the projection of the gravity action line on the sole plane when the human body stands. Specifically, it can be calculated through the resultant force vector and the acting point coordinates obtained by a three-dimensional force sensor for analyzing the balance of the human standing posture. The volume refers to the space size occupied by the human three-dimensional model. Specifically, voxelization methods or integral algorithms can be used for calculation to evaluate the fat distribution in combination with the body weight. The chest circumference, waist circumference, and hip circumference refer to the circumferences of specific parts of the human body. Specifically, the cross-sectional contours at corresponding heights can be intercepted along the coronal plane in the three-dimensional model and their circumferences can be calculated for quantifying body shape characteristics.

[0084] In this embodiment, by using the human joint landmark points and musculoskeletal system parameters, the joint alignment of each major joint can be further obtained to comprehensively evaluate the health status of the spinal system of the user, including but not limited to problems of the spinal system such as forward head carriage, kyphosis, uneven shoulders, trunk imbalance, scoliosis, abnormal lumbar lordosis (hyperlordosis / flat back), pelvic tilt, X / O-shaped legs, genu varum / valgum, knee hyperextension, intoeing / outtoeing, hallux valgus, flat feet, and pes cavus / valgus.

[0085] In this embodiment, by analyzing the position and direction of the center of gravity line when the human body stands, the symmetry of the left and right sides of the human body is evaluated. Specifically, if the center of gravity line passes through the center point of the human body shape, it indicates that the body is symmetric left and right. If the center of gravity line deviates to one side, it indicates that the body is asymmetric left and right, and there may be problems such as overweight and uneven muscle strength.

[0086] In this embodiment, by analyzing parameters such as body weight, volume, chest circumference, waist circumference, and hip circumference, the degree and type of obesity of the human body are evaluated. By dividing the body weight by the acceleration due to gravity g, the total body mass of the human body can be obtained. Then, by dividing this mass by the calculated total body volume of the human body, the body density of the human body can be obtained, and this parameter can be used to quantitatively evaluate the body fat percentage and obesity degree of the subject, etc. Through parameters such as chest circumference, waist circumference, and hip circumference, the obesity degree and type of the subject can be preliminarily judged, such as central obesity, peripheral obesity, general obesity, etc. Exemplarily, if the waist circumference of a male is greater than 94 cm and that of a female is greater than 88 cm, there is a risk of abdominal obesity; if the waist-to-hip ratio of a male is greater than or equal to 0.90 and that of a female is greater than or equal to 0.85, the risk of central obesity is high.

[0087] Specifically, bony landmark points are located on the surface of the three-dimensional model through curvature extreme value detection or key point matching algorithms. For example, the coordinates of the acromion vertex are identified in the shoulder region, and the coordinates of the anterior superior iliac spine are located in the pelvic region. According to these coordinates, parameters such as shoulder tilt angle and spinal curvature are calculated as quantitative indicators of the health status of the spinal system. The center of gravity line is determined by the vector synthesis of the plantar pressure distribution data. When the line of force deviates from the central region of the sole, it can be judged that there is a left-right pressure imbalance or a forward-backward center of gravity shift. The volume calculation is achieved by dividing the three-dimensional model into voxel units and counting the number of valid voxels. The chest circumference, waist circumference, and hip circumference are respectively measured as the circumferences on the cross-sections at the axillary level, the upper edge of the umbilicus, and the most prominent position of the buttocks. The obesity type is evaluated by comparing the waist-to-hip ratio with a preset threshold to judge the fat distribution pattern. For example, when the waist-to-hip ratio is greater than 0.9, it is judged as central obesity.

[0088] In this embodiment, by synchronously acquiring three-dimensional body shape data, plantar mechanics data, and body weight data, an association model between body shape characteristics and mechanical load is established. For example, by combining an increase in waist circumference and a forward shift of the center of gravity to judge the risk of lumbar lordosis. Compared with the prior art, it can detect multi-site collaborative abnormalities. This embodiment solves the problem of missed detection of associated abnormalities caused by scattered data in traditional detections and realizes the comprehensive analysis of body shape parameters, mechanical parameters, and skeletal posture parameters. For example, when it is detected that the hip circumference is asymmetric and the center of gravity line shifts to the left, it can be suggested that there is pelvic tilt accompanied by abnormal lower limb load; when the chest circumference decreases and the scoliosis angle exceeds the standard, it can be jointly judged that there is a risk of thoracic compensatory deformation. This multi-dimensional cross-validation mechanism reduces the possibility of misjudgment of a single parameter and provides a quantitative basis for the detection of musculoskeletal system diseases.

[0089] In the embodiment of the present application, a box body is provided as the support framework of the entire system, and a plantar scan force platform is provided to carry the human body and measure the plantar pressure; multiple depth cameras distributed on the box body are used to capture the omnidirectional depth image information of the human body, and four three-dimensional force sensors arranged on the plantar scan force platform are used to measure the force exerted by the human body on the plantar scan force platform, so as to obtain key indicators such as body weight, center of gravity line, and musculoskeletal system parameters for detecting the human muscle and bone system, and then comprehensively evaluate the health of the human musculoskeletal system. By integrating multi-dimensional data sources, the embodiment of the present application realizes the collaborative analysis of mechanical parameters and anatomical parameters, can simultaneously detect multiple problems such as postural imbalance, obesity distribution, and spinal abnormalities, and improves the comprehensiveness of the evaluation.

[0090] The embodiment of the present application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the above-mentioned health assessment method is realized. The electronic device can be any intelligent terminal including a tablet computer, an in-vehicle computer, etc.

[0091] Please refer to Figure 5 , Figure 5 which schematically shows the hardware structure of an electronic device in another embodiment. The electronic device includes: A processor 501, which can be implemented by using a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided by the embodiments of the present application; A memory 502, which can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 502 can store an operating system and other application programs. When implementing the technical solutions provided by the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 502, and the processor 501 is used to call and execute the health assessment method of the embodiments of the present application; An input / output interface 503, which is used to realize information input and output; A communication interface 504, which is used to realize the communication interaction between this device and other devices, and can communicate through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.); A bus 505, which transmits information between various components of the device (such as the processor 501, the memory 502, the input / output interface 503, and the communication interface 504); Among them, the processor 501, the memory 502, the input / output interface 503, and the communication interface 504 are communicatively connected to each other inside the device through the bus 505.

[0092] The embodiment of the present application also provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the above-mentioned health assessment method.

[0093] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0094] The human body scanning system provided by the embodiment of the present application includes: a box body; a plantar scanning force platform disposed on the bottom surface of the box body for carrying a human body; a plurality of first depth cameras distributed on each surface of the box body and connected to the box body through a frame; and a plurality of second depth cameras distributed on the plantar scanning force platform. The fast human body scanning method based on depth cameras in the present application, combined with the measurement of the human body center of gravity by a three-dimensional force sensor, realizes a fast, accurate, and comprehensive assessment of the health of the whole body musculoskeletal system. The health assessment method provided by the embodiment of the present application includes: obtaining the depth image information of the human body and the force information of the plantar scanning force platform collected by the human body scanning system, calculating the weight and the center of gravity line of the subject using the force information of the plantar scanning force platform, stitching the depth image information to obtain a three-dimensional human body model, and obtaining the musculoskeletal system parameters of the human body from the three-dimensional human body model; finally, comprehensively evaluating the health status of the musculoskeletal system of the subject based on data such as weight, center of gravity line, and musculoskeletal system parameters, and providing personalized health suggestions and improvement plans according to the evaluation results. The embodiment of the present application realizes the comprehensive analysis of body shape parameters, mechanical parameters, and bone posture parameters by synchronously obtaining three-dimensional body shape data, plantar mechanics data, and weight data. This multi-dimensional cross-validation mechanism reduces the possibility of misjudgment of a single parameter and provides a quantitative basis for the detection of musculoskeletal system diseases.

[0095] The embodiments described in the embodiments of the present application are to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art will know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0096] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than those shown, or combine certain steps, or different steps.

[0097] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0098] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware and their appropriate combinations.

[0099] It should be understood that in the present application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally means that the associated objects before and after are in an "or" relationship. "At least one (one) of the following" or a similar expression means any combination of these items, including any combination of single items (ones) or plural items (ones). For example, at least one (one) of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0100] In several embodiments provided by the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the above division of units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms.

[0101] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0102] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0103] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. The foregoing storage medium includes: various media that can store programs such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0104] The preferred embodiments of the embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of rights of the embodiments of the present application. Any modification, equivalent replacement, and improvement made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of rights of the embodiments of the present application.

Claims

1. A human body scanning system, characterized in that, The system includes: a box body; a plantar scanning force platform, which is arranged on the bottom surface of the box body and is used to carry a human body; a plurality of first depth cameras, which are distributed on each surface of the box body and are connected to the box body through a frame; a plurality of second depth cameras, which are distributed on the plantar scanning force platform.

2. The system according to claim 1, wherein The plantar scanning force platform includes: a frame body and a transparent plate covering the frame body, the frame body is arranged on the bottom surface of the box body, the transparent plate is rectangular and is used to carry a human body; four three-dimensional force sensors, which are arranged between the transparent plate and the frame body.

3. The system according to claim 1, wherein The first depth cameras on the opposite two surfaces of the box body are symmetrically arranged and shoot towards the center direction of the box body.

4. The system according to claim 2, wherein A plurality of the second depth cameras are symmetrically arranged in the frame body and shoot towards the transparent plate.

5. A health assessment method is applied to an electronic device, and the electronic device is communicatively connected to a human body scanning system. It is characterized in that, The method includes: acquiring the depth image information of the human body and the force information of the plantar scanning force platform collected by the human body scanning system according to any one of claims 1-4, wherein the depth image information of the human body includes the depth image information of the human body except the sole shot by a plurality of the first depth cameras and the depth image information of the sole shot by the second depth cameras; calculating the force information of the plantar scanning force platform to obtain the weight of the human body and the center of gravity line when the human body stands; stitching the depth image information of the human body to obtain a three-dimensional model of the human body; analyzing the three-dimensional model to obtain the musculoskeletal system parameters of the human body; performing a health assessment on the weight of the human body, the center of gravity line when the human body stands, and the musculoskeletal system parameters of the human body to obtain a health assessment result.

6. The method according to claim 5, wherein The calculating the force information of the plantar scanning force platform to obtain the weight of the human body and the center of gravity line when the human body stands includes: adding the vertical component forces obtained by the four three-dimensional force sensors to obtain the gravity received by the human body; calculating according to the gravity to obtain the weight of the human body; calculating the sum of the front-back component forces and the sum of the left-right component forces in the standing direction of the human body obtained by the four three-dimensional force sensors, and performing vector synthesis on the gravity, the sum of the front-back component forces, and the sum of the left-right component forces to obtain the resultant force applied by the human body to the plantar scanning force platform; calculating the acting point of the force applied by the human body to the plantar scanning force platform based on the resultant force; calculating according to the acting point of the force and the resultant force to obtain the center of gravity line when the human body stands.

7. The method according to claim 5, wherein The stitching the depth image information of the human body to obtain a three-dimensional model of the human body includes: acquiring the three-dimensional point cloud data in the depth image information of the human body; Project the three-dimensional point cloud data according to the corresponding internal and external parameters of each of the first depth cameras and each of the second depth cameras to obtain a three-dimensional point cloud model of the human body, where the internal parameters and the external parameters are obtained after calibration of each of the first depth cameras and each of the second depth cameras using a preset calibration board; Render the three-dimensional point cloud model into a three-dimensional triangular mesh model to obtain the three-dimensional model of the human body.

8. The method according to claim 7, wherein The calibration board includes a black and white chessboard grid, and color dot matrices arranged on both sides of the black and white chessboard grid; The calibration process of the first depth camera and the second depth camera is as follows: Obtain multiple images taken by the multiple first depth cameras and multiple second depth cameras to be calibrated of the calibration board, where each of the first depth cameras takes at least one image, and each of the second depth cameras takes at least one image; For each depth camera among the multiple first depth cameras and multiple second depth cameras: Calibrate the depth camera according to the position of the black and white chessboard grid in the image taken by the depth camera to obtain the initial external parameters and the internal parameters of the depth camera; Register the initial external parameters according to the color dot matrices in the image taken by the depth camera to obtain the external parameters of the depth camera.

9. The method according to claim 5, characterized in that, Analyze the three-dimensional model to obtain the musculoskeletal system parameters of the human body, including: Obtain the coordinates of the bony landmark points of the human body according to the three-dimensional model; Perform calculations based on the coordinates of the bony landmark points to obtain the musculoskeletal system parameters of the human body.

10. The method according to claim 9, characterized in that, The musculoskeletal system parameters include: the volume, chest circumference, waist circumference, and hip circumference of the human body; Perform a health assessment on the weight of the human body, the center of gravity line when the human body stands, and the musculoskeletal system parameters of the human body to obtain a health assessment result, including: Evaluate the health status of the spinal system of the human body according to the bony landmark points and the musculoskeletal system parameters to obtain a first evaluation result; Evaluate the symmetry of the human body according to the position and direction of the center of gravity line to obtain a second evaluation result; Evaluate the obesity degree and obesity type of the human body according to the weight, volume, chest circumference, waist circumference, and hip circumference to obtain a third evaluation result; Use the first evaluation result, the second evaluation result, and the third evaluation result as the health assessment result.

Images