Human body biomechanical line detection method and system

Abstract

The present invention discloses a method for detecting human bioforce lines, which comprises the following steps: S1, continuously detecting plantar pressure changes to generate pressure data; continuously collecting depth images of the human body, and obtaining displacement data of key points in the human body movement process according to the continuous depth images; S2, associating the pressure data and displacement data of each frame; detecting the bioforce lines in the human body movement process; and a detection system thereof. Through the technical scheme of the present invention, the bioforce lines of the human body are quickly detected by running, and the lower limb parts of the human body with abnormalities are found frame by frame through the bioforce lines, and the parts are quickly and accurately locked, and corresponding rehabilitation treatment is carried out in time. The implementation cost is low, and it is convenient for wide application in society, and the problems of rough detection and high detection cost of existing bioforce line detection are solved.

Description

Technical Field

[0001] The present invention relates to the field of sports biomechanics, and in particular to a method and system for detecting human biomechanics. Background Art

[0002] Muscles, connective tissue, joints, bones, nerves and gravity work together to create an exquisite system that works effectively under ideal conditions. This system consists of a series of "moving parts" and is called the "kinetic chain". The nervous system controls muscles that are affected by gravity. Muscles help move our bones and joints. Each movement activates the adjacent nerves that control the adjacent muscles. The adjacent muscles then activate the adjacent bone marrow, allowing the adjacent joints to move. Every small movement in the body will cause ripples throughout the entire kinetic chain. Biomechanical alignment is a term used to describe how the kinetic chain works. Healthy biomechanical alignment allows us to move our bodies efficiently by correctly supporting all elements of the kinetic chain. Abnormal biomechanical alignment causes the body to "overcompensate" for the "weak links" in the kinetic chain, resulting in increasing energy consumption, muscle fatigue and pain. What's more, even if there is a temporary problem in one link of the kinetic chain, it will affect and change the brain's record of "how to complete certain movements correctly", which will cause the formation of "bad habits" and lead to persistent biomechanical abnormalities.

[0003] According to statistics, 75% of people in the world have abnormal biomechanical alignment of the lower limbs, which manifests itself in the human body as flat feet, scoliosis, meniscus wear, X / O legs and other posture problems. There are many reasons for the above-mentioned posture problems, including congenital factors and acquired bad behavior habits. As time goes by, we find that the proportion of lower limb biomechanical alignment abnormalities is also increasing year by year. It is closely related to people's long-term work. More and more people suffer from various occupational "diseases". In the early stages of posture problems, they often do not attract people's attention until the posture problems are serious enough to be visible to the naked eye or have affected their lives. Only then will people pay attention. With existing medical technology, long-term and expensive rehabilitation methods are required for correction, and even only improvement can be achieved, and complete recovery cannot be achieved.

[0004] Timely early detection and early treatment have become the top priority for dealing with abnormal biomechanical lines. The existing technology monitors the body posture of the test subject through several sensor electrodes in the laboratory, collects data of relevant parts during exercise, and dynamically visualizes the human figure simulated by the data to judge whether the test subject has posture problems and the severity of the posture problems. Since the existing technology only judges the result data with long-lasting abnormalities and large fluctuations in the test result data, it leads to the neglect of many minor abnormalities in the biomechanical line detection of human body movement, and it is impossible to detect the existing but mild abnormal biomechanical lines in time; at the same time, the implementation cost of this method of detecting posture is very high, and it cannot be widely popularized.

[0005] How to fully and carefully detect the biomechanical lines of the lower limbs of the human body to avoid the gradual aggravation of abnormal posture and at the same time popularize it widely is an issue that urgently needs to be solved in modern society. Summary of the invention

[0006] In view of the problem that the above-mentioned prior art cannot detect abnormal bioforce lines that already exist but are mild in nature in a timely manner and the cost is high, the present invention provides a human bioforce line detection method and system, which can conduct a comprehensive detection of key parts of the human body during exercise, analyze and find abnormal bioforce lines in exercise frame by frame, and has low implementation cost, which is conducive to popularization.

[0007] The method for detecting human biomechanical lines comprises the following steps:

[0008] S1, continuously detect the change of plantar pressure to generate pressure data; continuously collect depth images of the human body, and obtain the displacement data of key points during the movement of the human body according to the continuous depth images;

[0009] S2. Correlate the pressure data and displacement data of each frame; and detect the bioforce lines during human movement through key points.

[0010] Furthermore, the detection method further comprises, before executing step S1:

[0011] Identify the plantar pressure detection areas of the left and right feet respectively;

[0012] Collect the displacement range of the human body;

[0013] Correcting the acquisition angle of the depth image;

[0014] Set the body movement speed.

[0015] Furthermore, in step S1, the depth image of the front side and the back below the knee of the human body is continuously collected, and the depth image within a preset number of frames is analyzed to obtain the displacement data of each key point;

[0016] Each of the key points corresponds to a certain part of the human body, the key points in the depth image are locked, the depth image within a preset number of frames is analyzed frame by frame, and the displacement data of each key point is obtained.

[0017] Furthermore, in step S2, the pressure data and displacement data acquired in the same frame are associated to form motion parameters; bioforce line detection is performed using the motion parameters, and key points where abnormalities exist are determined based on frame values ​​corresponding to abnormal detection results.

[0018] Furthermore, in step S2, the bioforce line detection includes:

[0019] Key point stability detection: Determine the parts of the left and right feet that need to be detected. Based on the displacement data of each key point, calculate the standard deviation of the angle between the two key points corresponding to the part in each frame, from the time frame when the pressure data appears to the time frame when the pressure data disappears, and average all standard deviations to obtain the average pressure value. The average pressure value is used to compare with the preset pressure stability threshold to determine whether there is a stability problem;

[0020] Sports posture detection: Based on the pressure data, the center point coordinates and the maximum pressure range of the pressure area of ​​each frame of the sole are calculated, and the sports posture is judged by the maximum pressure range; the center of gravity transition ratio is calculated by the center of gravity distance and the maximum pressure range, and the center of gravity transition ratio is compared with the preset ratio threshold to judge the foot landing mode;

[0021] The coordinates of the center points of each frame are connected to form the center of gravity of the entire sole, and the center of gravity distance is determined by the center of gravity of the sole of the foot in the first frame when the sole touches the ground and the center of gravity of the sole of the foot in the frame before leaving the ground.

[0022] Human body biomechanical line detection system, including:

[0023] A plantar detection subsystem, the plantar detection subsystem comprising: a treadmill and a pressure acquisition module arranged at the lower end of the treadmill belt, for continuously detecting plantar pressure changes, generating and sending pressure data;

[0024] A human body depth image acquisition subsystem, the human body depth image acquisition subsystem comprising at least two camera devices with RGB-D image acquisition function, for acquiring and sending depth images;

[0025] The back-end control center is used to send work instructions to the sole detection subsystem and the human body depth image acquisition subsystem; to receive pressure data and depth images; to obtain displacement data based on continuous depth images; to associate the pressure data and displacement data of each frame; and to detect the bioforce lines during human body movement.

[0026] Furthermore, the camera device is arranged on the front side and the back of the human body, and is used to continuously collect depth images of the front side and the back of the human body below the knee;

[0027] Each of the key points corresponds to a certain part of the human body. The back-end control center locks the key points in the depth image, analyzes the depth image within a preset number of frames frame by frame, and obtains the displacement data of each key point.

[0028] Furthermore, the back-end control center associates the pressure data and displacement data acquired in the same frame to form motion parameters; the back-end control center performs bio-force line detection through the motion parameters, and determines the key points where the abnormalities exist according to the frame values ​​corresponding to the abnormal detection results.

[0029] Furthermore, the biomechanical line detection includes:

[0030] Key point stability detection: Determine the parts of the left and right feet that need to be detected. Based on the displacement data of each key point, calculate the standard deviation of the angle between the two key points corresponding to the part in each frame, from the time frame when the pressure data appears to the time frame when the pressure data disappears, and average all standard deviations to obtain the average pressure value. The average pressure value is used to compare with the preset pressure stability threshold to determine whether there is a stability problem;

[0031] Sports posture detection: Based on the pressure data, the center point coordinates and the maximum pressure range of the pressure area of ​​each frame of the sole are calculated, and the sports posture is judged by the maximum pressure range; the center of gravity transition ratio is calculated by the center of gravity distance and the maximum pressure range, and the center of gravity transition ratio is compared with the preset ratio threshold to judge the foot landing mode;

[0032] The coordinates of the center points of each frame are connected to form the center of gravity of the entire sole, and the center of gravity distance is determined by the center of gravity of the sole of the foot in the first frame when the sole touches the ground and the center of gravity of the sole of the foot in the frame before leaving the ground.

[0033] Compared with the prior art, the advantages and beneficial effects of the present invention are as follows: through the technical solution of the present invention, the bioforce lines of the human body can be quickly detected through running, and the abnormal lower limb parts of the human body can be found frame by frame through the bioforce lines, and they can be quickly and accurately locked, and corresponding rehabilitation treatment can be carried out in time. Moreover, the implementation cost is low, and it is convenient for widespread application in society, which solves the problems of rough bioforce line detection and high detection cost in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the process of the present invention;

[0035] Figure 2 It is a structural block diagram of the system of the present invention;

[0036] Figure 3 It is a schematic diagram of key points of the lower limbs behind the back in the present invention;

[0037] Figure 4 A schematic diagram of key points collected by the depth image in the present invention;

[0038] Figure 5 This is a schematic diagram of the pressure area collected by the sole detection subsystem of the present invention. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below through specific implementation methods in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0040] The method for detecting human biomechanical lines comprises the following steps:

[0041] S1, continuously detect the change of plantar pressure to generate pressure data; continuously collect depth images of the human body, and obtain the displacement data of key points during the movement of the human body according to the continuous depth images;

[0042] S2. Correlate the pressure data and displacement data of each frame; and detect the bioforce lines during human movement through key points.

[0043] The present invention detects the process of the subject running at a constant speed on a treadmill, detects the key points corresponding to the lower limbs of the human body frame by frame, and detects the plantar pressure. The plantar pressure data and the displacement data of the key points are correlated through AI, and finally the abnormal bioforce lines and the abnormal lower limb parts are determined frame by frame.

[0044] Specifically, the detection method further includes, before executing step S1:

[0045] Identify the plantar pressure detection areas of the left and right feet respectively;

[0046] Collect the displacement range of the human body;

[0047] Correcting the acquisition angle of the depth image;

[0048] Set the body movement speed.

[0049] Specifically, Figure 4 As shown, in step S1, depth images of the front side and the back below the knee of the human body are continuously collected, the depth images within a preset number of frames are analyzed, and the displacement data of each key point is obtained; each key point corresponds to a certain part of the lower limbs of the human body, the key point in the depth image is locked, the depth images within a preset number of frames are analyzed frame by frame, and the displacement data of each key point is obtained.

[0050] In actual application, the person being tested is asked to walk on the device for 5 seconds. The pressure change on the sole of the foot divides the left / right foot of the person being tested into areas to distinguish whether the pressure data detected during the test comes from the left foot or the right foot. Because the body will sway left and right when walking forward, the range where the human body appears is collected. In subsequent calculations, only this area will be calculated to improve the collection efficiency, and the same is true for the part below the knee behind the body.

[0051] At the beginning, you need to stand still for 3 seconds before entering the actual detection phase.

[0052] like Figure 3 As shown, the purpose of static standing is to calibrate the camera device. The camera device set below the knees behind the body is positioned according to the LB / RB key points of the left and right feet, and the slope of the two key points is calculated. When the inclination of the two points is greater than 8°, the image needs to be rotated and corrected. After correction, the inclination of the two points is 0°. The same is true for the front and side camera devices. If the absolute value |(current angle - 90°)|>10°, the camera device needs to be rotated and corrected so that the angle of the straight line between the two points is 90°.

[0053] After completing the above preparation process, the person being tested stands on the treadmill with his feet apart on both sides, starts the treadmill, sets the speed to, for example, 3km / h, and keeps running quickly. When pressure changes on the soles of the feet are detected, the depth image collection begins synchronously.

[0054] Through the depth image, the position distance data of various parts of the human body are obtained. By continuously locking the position distance data of the key points in the current depth image, the key position distance data is identified in the subsequent depth image. The distance difference between the two is the displacement distance of the key point. In the process of identifying multiple consecutive depth images, the key point position information data of the last two depth images are subtracted to obtain the corresponding displacement distance.

[0055] Specifically, in step S2, the pressure data and displacement data acquired in the same frame are associated to form motion parameters; the bioforce line detection is performed using the motion parameters, and the key points where the abnormalities exist are determined based on the frame values ​​corresponding to the abnormal detection results.

[0056] In practical applications, all data are in "step" units during the detection process. A "step" refers to the same foot of the person being detected going from the back of the foot touching the ground -> the entire sole of the foot touching the ground -> the sole of the foot pushing off the previous frame. Each step contains the pressure data of the relevant frames, the depth image, and the position information data of the key points in the depth image. For example, if the "step" process has 30 frames, then all relevant data of the person being detected for 30 frames will also be included.

[0057] Specifically, in step S2, the bioforce line detection includes:

[0058] Key point stability detection: Determine the parts of the left and right feet that need to be detected. Based on the displacement data of each key point, calculate the standard deviation of the angle between the two key points corresponding to the part in each frame, from the time frame when the pressure data appears to the time frame when the pressure data disappears, and average all standard deviations to obtain the average pressure value. The average pressure value is used to compare with the preset pressure stability threshold to determine whether there is a stability problem;

[0059] Sports posture detection: Based on the pressure data, the center point coordinates and the maximum pressure range of the pressure area of ​​each frame of the sole are calculated, and the sports posture is judged by the maximum pressure range; the center of gravity transition ratio is calculated by the center of gravity distance and the maximum pressure range, and the center of gravity transition ratio is compared with the preset ratio threshold to judge the foot landing mode;

[0060] The coordinates of the center points of each frame are connected to form the center of gravity of the entire sole, and the center of gravity distance is determined by the center of gravity of the sole of the foot in the first frame when the sole touches the ground and the center of gravity of the sole of the foot in the frame before leaving the ground.

[0061] Embodiment 1: Take the key point data frame of the heel during the support period of each step (from the instantaneous frame when pressure is detected to the frame before the pressure disappears), calculate the angle between the two lines TZ and ZB in each frame, calculate the standard deviation of the angle between the two lines during the support period, collect the standard deviation of the angle between the two lines within the time range from the frame number when pressure appears to the frame number when pressure disappears, and average all the standard deviations to obtain the average pressure value, and obtain the stability of the detection period. The smaller the average pressure value, the better the stability of the heel during the entire support period, and the larger the value, the worse the stability. The stability of the heel during the support period can provide a certain reference for whether it is easy to sprain the ankle during running.

[0062] Example 2:

[0063] like Figure 5 As shown, the landing posture is closely related to running. The posture is mainly judged by the pressure of each step. The coordinates of the center point of the pressure area of ​​each frame should be calculated (the current pressure resolution is 128*64). The pressure center points of each frame are connected to form the transition direction and distance of the center of gravity of the entire sole (the center of gravity distance is determined by the center of gravity of the sole of the first frame of the sole landing and the center of gravity of the sole of the previous frame before leaving the ground, and the number of pressure points detected by the sole detection subsystem is collected). At the same time, the maximum range of pressure should be obtained (the pressure values ​​of each frame are superimposed and binary differentiated, with pressure / no pressure, and the area with pressure points is the maximum pressure area). First, if the aspect ratio of the maximum pressure range is less than 1.5, it can be judged that the forefoot is used for running. If not, the center of gravity distance / length of the maximum pressure range = the center of gravity transition ratio. The larger the value, the more obvious the way of landing with the back of the foot, and the smaller the value, the more obvious the way of landing with the middle of the foot. Theoretically, this value will not be less than 0.2.

[0064] It should be noted that the above embodiments are only part of the test items of the present invention in practical application, and do not represent the test content of all biomechanical lines. By associating the pressure data and displacement data obtained in the same frame, the key points corresponding to the knee joint, hip joint, etc. can be tested. When there is a problem with the biomechanical line during human movement, the displacement data of a certain key point is abnormal, which does not mean that the part of the human body corresponding to the key point must have a problem. There may also be problems with other key points, but the human body should compensate for long-term incorrect behavior patterns to make the key points of the part with problems seem to be normal. Correspondingly, the key points of the compensated part will definitely have abnormalities. By associating the pressure data with the displacement data, based on the human body structure, a deep-level judgment of the possibility of compensation can be made, and then the key point location with problems can be determined.

[0065] Human body biomechanical line detection system, including:

[0066] The plantar detection subsystem includes: a treadmill and a pressure collection module arranged at the lower end of the treadmill belt, which is used to continuously detect the plantar pressure changes, generate and send pressure data;

[0067] A human body depth image acquisition subsystem, which includes at least two camera devices with RGB-D image acquisition function, used to acquire and send depth images;

[0068] The back-end control center is used to send work instructions to the sole detection subsystem and the human body depth image acquisition subsystem; to receive pressure data and depth images; to obtain displacement data based on continuous depth images; to associate the pressure data and displacement data of each frame; and to detect the bioforce lines during human body movement through key points.

[0069] Specifically, the camera device is arranged on the front side and the back of the human body, and is used to continuously collect the depth image of the front side and the back of the human body below the knee;

[0070] Among them, each key point corresponds to a certain part of the lower limbs of the human body. The back-end control center locks the key points in the depth image, analyzes the depth image within the preset frame number frame by frame, and obtains the displacement data of each key point.

[0071] Specifically, the back-end control center associates the pressure data and displacement data obtained in the same frame to form motion parameters; the back-end control center performs bioforce line detection through the motion parameters, and determines the key points where the abnormalities exist based on the frame values ​​corresponding to the abnormal detection results.

[0072] The biomechanical line detection includes:

[0073] Key point stability detection: Determine the parts of the left and right feet that need to be detected. Based on the displacement data of each key point, calculate the standard deviation of the angle between the two key points corresponding to the part in each frame, from the time frame when the pressure data appears to the time frame when the pressure data disappears, and average all standard deviations to obtain the average pressure value. The average pressure value is used to compare with the preset pressure stability threshold to determine whether there is a stability problem;

[0074] Sports posture detection: Based on the pressure data, the center point coordinates and the maximum pressure range of the pressure area of ​​each frame of the sole are calculated, and the sports posture is judged by the maximum pressure range; the center of gravity transition ratio is calculated by the center of gravity distance and the maximum pressure range, and the center of gravity transition ratio is compared with the preset ratio threshold to judge the foot landing mode;

[0075] The coordinates of the center points of each frame are connected to form the center of gravity of the entire sole, and the center of gravity distance is determined by the center of gravity of the sole of the foot in the first frame when the sole touches the ground and the center of gravity of the sole of the foot in the frame before leaving the ground.

[0076] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0077] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0078] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0080] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0081] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0082] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0083] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0084] The above contents are further detailed descriptions of the present invention in combination with specific implementation methods, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For ordinary technical personnel in the technical field to which the present invention belongs, several simple deductions or substitutions can be made without departing from the concept of the present invention, which should be regarded as belonging to the protection scope of the present invention.

Claims

1. A method for detecting human biomechanical lines, characterized in that: The following steps are involved: S1, continuously detect the changes in plantar pressure and generate pressure data; Continuously collect depth images of the human body and obtain the displacement data of key points during the movement of the human body based on the continuous depth images; S2, associating the pressure data and displacement data of each frame; Detect the bio-force lines during human movement through key points; In step S2, the bio-force line detection includes: Key point stability detection: Determine the parts of the left and right feet that need to be detected. Based on the displacement data of each key point, calculate the standard deviation of the angle between the two key points corresponding to the part in each frame, from the time frame when the pressure data appears to the time frame when the pressure data disappears, and average all standard deviations to obtain the average pressure value. The average pressure value is used to compare with the preset pressure stability threshold to determine whether there is a stability problem; Sports posture detection: Based on the pressure data, the center point coordinates and the maximum pressure range of the pressure area of ​​each frame of the sole are calculated, and the sports posture is judged by the maximum pressure range; the center of gravity transition ratio is calculated by the center of gravity distance and the maximum pressure range, and the center of gravity transition ratio is compared with the preset ratio threshold to judge the foot landing mode; The coordinates of the center points of each frame are connected to form the center of gravity of the entire sole, and the center of gravity distance is determined by the center of gravity of the sole of the foot in the first frame when the sole touches the ground and the center of gravity of the sole of the foot in the frame before leaving the ground.

2. The human body bioforce line detection method according to claim 1, characterized in that: The detection method further comprises, before executing step S1: Identify the plantar pressure detection areas of the left and right feet respectively; Collect the displacement range of the human body; Correcting the acquisition angle of the depth image; Set the body movement speed.

3. The human body bioforce line detection method according to claim 1, characterized in that: In the step S1, the depth image of the front side and the back below the knee of the human body is continuously collected, and the depth image within a preset number of frames is analyzed to obtain the displacement data of each key point; Each of the key points corresponds to a certain part of the human body, the key points in the depth image are locked, the depth image within a preset number of frames is analyzed frame by frame, and the displacement data of each key point is obtained.

4. The human body bioforce line detection method according to claim 1, characterized in that: In step S2, the pressure data and displacement data acquired in the same frame are associated to form motion parameters; the bioforce line detection is performed using the motion parameters, and the key points where the abnormality exists are determined based on the frame values ​​corresponding to the abnormal detection results.

5. Human body bio-force line detection system, characterized in that: include: A plantar detection subsystem, the plantar detection subsystem comprising: a treadmill and a pressure acquisition module arranged at the lower end of the treadmill belt, for continuously detecting plantar pressure changes, generating and sending pressure data; A human body depth image acquisition subsystem, the human body depth image acquisition subsystem comprising at least two camera devices with RGB-D image acquisition function, for acquiring and sending depth images; A back-end control center, which is used to send work instructions to the sole detection subsystem and the human body depth image acquisition subsystem; to receive pressure data and depth images; to obtain displacement data based on continuous depth images; to associate the pressure data and displacement data of each frame; and to detect the bio-force lines during human body movement through key points; The biomechanical line detection includes: Key point stability detection: Determine the parts of the left and right feet that need to be detected. Based on the displacement data of each key point, calculate the standard deviation of the angle between the two key points corresponding to the part in each frame, from the time frame when the pressure data appears to the time frame when the pressure data disappears, and average all standard deviations to obtain the average pressure value. The average pressure value is used to compare with the preset pressure stability threshold to determine whether there is a stability problem; Sports posture detection: Based on the pressure data, the center point coordinates and the maximum pressure range of the pressure area of ​​each frame of the sole are calculated, and the sports posture is judged by the maximum pressure range; the center of gravity transition ratio is calculated by the center of gravity distance and the maximum pressure range, and the center of gravity transition ratio is compared with the preset ratio threshold to judge the foot landing mode; The coordinates of the center points of each frame are connected to form the center of gravity of the entire sole, and the center of gravity distance is determined by the center of gravity of the sole of the foot in the first frame when the sole touches the ground and the center of gravity of the sole of the foot in the frame before leaving the ground.

6. The human body bio-force line detection system according to claim 5, characterized in that: The camera device is arranged on the front side and the back of the human body, and is used to continuously collect depth images of the front side and the back of the human body below the knee; Each of the key points corresponds to a certain part of the human body. The back-end control center locks the key points in the depth image, analyzes the depth image within a preset number of frames frame by frame, and obtains the displacement data of each key point.

7. The human body bio-force line detection system according to claim 5, characterized in that: The back-end control center associates the pressure data and displacement data acquired in the same frame to form motion parameters; the back-end control center performs bio-force line detection through the motion parameters, and determines the key points where the abnormalities exist according to the frame values ​​corresponding to the abnormal detection results.

Images