Attitude processing method and intelligent wearing system

Abstract

The invention discloses a posture processing method and an intelligent wearing system, and relates to the technical field of intelligent wearing equipment, the posture processing method is applied to intelligent clothing, the intelligent clothing comprises a plurality of fiber-based stretching sensors, and the fiber-based stretching sensors are woven into areas, corresponding to human joints, of the intelligent clothing; the attitude processing method comprises the following steps: acquiring a stretching detection value of the fiber-based stretching sensor; determining a corresponding angle value according to the stretching detection value; and mapping the angle value to a coordinate axis of a three-dimensional coordinate system of each human body joint to obtain a three-dimensional posture. The technical problem that the accuracy of the user posture recognized by an existing posture recognition scheme is low is solved.

Description

Technical Field

[0001] This application relates to the technical field of intelligent wearable devices, and particularly to a posture processing method and an intelligent wearable system. Background Art

[0002] In the fields of human-computer interaction, virtual reality, health monitoring, and sports science, the research and application of human posture estimation technology have increasingly become the focus.

[0003] Existing posture recognition methods usually adopt inertial motion capture or optical motion capture. In inertial motion capture, inertial measurement units are embedded at key positions (such as joints and torso) of the motion capture suit, and the posture angles of each part of the human body are calculated by integrating the sensor data of the inertial measurement units. However, long-term use may cause "drift" due to integration calculation errors. Optical motion capture is motion capture realized by relying on computer vision after collecting images, which is easily affected by occlusion or light interference. As a result, the accuracy of the recognized user postures is relatively low.

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

[0005] The main purpose of this application is to provide a posture processing method and an intelligent wearable system, aiming to solve the technical problem of relatively low accuracy of the user postures recognized by existing posture recognition solutions.

[0006] To achieve the above purpose, this application proposes a posture processing method applied to intelligent clothing, where the intelligent clothing includes a plurality of fiber-based stretch sensors woven into the areas corresponding to each human joint of the intelligent clothing; The posture processing method includes: Obtain the stretch detection value of the fiber-based stretch sensor; Determine the corresponding angle value according to the stretch detection value; Map the angle value to the coordinate axes of the three-dimensional coordinate system of each human joint to obtain a three-dimensional posture.

[0007] In one embodiment, the step of determining the corresponding angle value according to the stretch detection value includes: Obtain the initial stretch value of the fiber-based stretch sensor, where the initial stretch value is the stretch value of the fiber-based stretch sensor in the initial standard state; Calculate the stretch change value between the stretch detection value and the initial stretch value; Based on the stretching change value and the angle mapping relationship corresponding to the fiber-based stretching sensor, an angle value corresponding to the stretching detection value is obtained, where the angle mapping relationship describes the mapping relationship between the stretching change value and the angle value of the fiber-based stretching sensor.

[0008] In one embodiment, the step of mapping the angle value to the coordinate axes of the three-dimensional coordinate system of each human joint to obtain a three-dimensional posture includes: Determine the coordinate axes of the three-dimensional coordinate system of the human joint corresponding to the fiber-based stretching sensor according to the installation position of the fiber-based stretching sensor; Map the angle value of the fiber-based stretching sensor to the corresponding coordinate axes of the three-dimensional coordinate system to obtain a local joint angle; According to the transformation relationship between the three-dimensional coordinate systems of each human joint, concatenate each local joint angle to obtain a global human posture as the three-dimensional posture.

[0009] In one embodiment, the step of concatenating each local joint angle according to the transformation relationship between the three-dimensional coordinate systems of each human joint to obtain a global human posture includes: Obtain a specified human body area and determine the local joint angles of each human joint within the specified human body area; According to the transformation relationship between the three-dimensional coordinate systems of each human joint, concatenate the local joint angles of each human joint within the specified human body area to obtain a global human posture.

[0010] In one embodiment, each human joint within the specified human body area includes an ankle joint, a knee joint, and a hip joint; After the step of obtaining a specified human body area and determining the local joint angles of each human joint within the specified human body area, it includes: In response to a jumping event, obtain a landing acceleration, and based on the landing acceleration, calculate a ground reaction force, where the landing acceleration is determined according to the vertical acceleration during the jumping event; Determine the force thresholds of the ankle joint, the knee joint, and the hip joint according to the local joint angles of the ankle joint, the knee joint, and the hip joint; According to the ground reaction force, perform reverse recursive calculation starting from the ankle joint to obtain the ankle joint force, the knee joint force, and the hip joint force; Compare the ankle joint force, the knee joint force, and the hip joint force with their corresponding force thresholds respectively, and output an injury warning message after any one of the ankle joint force, the knee joint force, and the hip joint force exceeds the corresponding force threshold.

[0011] In one embodiment, the posture processing method further includes: In response to a motion analysis instruction, obtain the joint chain and standard action angle sequence involved in the motion to be analyzed; Generate a current action angle sequence from the local joint angles in the joint chain involved; Align the current action angle sequence and the standard action angle sequence to obtain a motion coordination deviation; Generate pose correction prompt information according to the motion coordination deviation.

[0012] In one embodiment, the step of aligning the current action angle sequence and the standard action angle sequence to obtain a motion coordination deviation includes: Map the current action angle sequence and the standard action angle sequence on the same time axis, and calculate the angular difference and timing difference between the key phase points in the standard action angle sequence and the corresponding mapped phase points in the current action angle sequence; Use the angular difference and the timing difference as the motion coordination deviation.

[0013] In one embodiment, after the step of mapping the angle values to the coordinate axes of the three-dimensional coordinate system of each human joint to obtain a three-dimensional pose, the pose processing method further includes: Import the three-dimensional pose into a standard human model to determine the real-time center of gravity position in the three-dimensional pose; After the horizontal movement speed of the real-time center of gravity position is greater than a predetermined speed threshold, or the relative distance between the real-time center of gravity position and a predetermined human support point is greater than a predetermined distance threshold, output a fall warning message.

[0014] In addition, to achieve the above object, the present application also proposes an intelligent wearable system, which includes an intelligent garment and a control terminal communicatively connected to the intelligent garment; The intelligent garment includes: a base fabric layer and a plurality of fiber-based stretch sensors, and the fiber-based stretch sensors are woven into the regions corresponding to each human joint in the base fabric layer; The control terminal is configured to implement the steps of the pose processing method as described above.

[0015] In one embodiment, the intelligent garment further includes a data acquisition module; The data acquisition module is electrically connected to each of the fiber-based stretch sensors through a wire, and is configured to collect the sensor signals of each of the fiber-based stretch sensors and send them to the control terminal.

[0016] In addition, to achieve the above object, the present application further provides a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the attitude processing method described above are implemented.

[0017] In addition, to achieve the above object, the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the attitude processing method described above are implemented.

[0018] One or more technical solutions proposed by the present application have at least the following technical effects: The present application is applied to smart clothing, which includes a plurality of fiber-based stretch sensors woven into areas corresponding to each human joint of the smart clothing. Since the degree of fiber stretching in the areas of the smart clothing corresponding to each human joint is different when the human joint is at different angles, the present application can obtain the stretch detection value of the fiber-based stretch sensor, and then determine the corresponding angle value according to the stretch detection value. Therefore, the present application can map the angle values to the coordinate axes of the three-dimensional coordinate system of each human joint respectively to obtain a three-dimensional posture. Thus, by means of the fiber-based stretch sensor, the present application accurately identifies the angle values of each human joint in three-dimensional space from the mechanical stretching level and maps them to the three-dimensional coordinate system of each human joint to form a three-dimensional posture. Compared with the existing inertial motion capture and optical motion capture, the posture processing method of the present application not only has stronger adaptability to different scenarios, but also does not have the problem of integral drift because the angle is identified from the mechanical stretching level. Therefore, the accuracy of user posture recognition can be effectively improved. In addition, inertial motion capture and optical motion capture need to fit multiple degrees of freedom (position + posture) of the whole body based on inertial information and image information, resulting in a large amount of operation data and high processing difficulty. However, the present application directly fits the human body posture through the joint angles detected by the fiber-based stretch sensor, with less operation data and low processing difficulty, which can improve the real-time performance of user posture recognition and achieve fast response and feedback. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application.

[0020] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0021] Figure 1 It is a schematic flowchart provided for the first embodiment of the posture processing method of this application; Figure 2 It is a schematic structural diagram of the intelligent clothing involved in the embodiment of this application; Figure 3 It is a scene diagram of the three-dimensional coordinate system of each human joint involved in the embodiment of this application; Figure 4 It is a scene schematic diagram of the axis limits in the three-dimensional coordinate system involved in the embodiment of this application; Figure 5 It is a setting scene diagram of the fiber-based tensile sensor involved in the embodiment of this application; Figure 6 It is a model schematic diagram of the standard human body model involved in the embodiment of this application; Figure 7 It is a schematic flowchart provided for the second embodiment of the posture processing method of this application; Figure 8 It is a schematic flowchart provided for the third embodiment of the posture processing method of this application; Figure 9 It is a system structure diagram of the intelligent wearable system in the embodiment of this application; Figure 10 It is an example diagram of the intelligent clothing involved in the embodiment of this application; Figure 11 It is another example diagram of the intelligent clothing involved in the embodiment of this application.

[0022] The realization of the purpose, functional characteristics and advantages of this application will be further described with reference to the embodiments and the accompanying drawings. Specific embodiments

[0023] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of this application and are not used to limit this application.

[0024] In order to better understand the technical solutions of this application, the following will be described in detail in combination with the accompanying drawings of the specification and the specific embodiments.

[0025] The main solution of the embodiment of this application is: The intelligent clothing includes a plurality of fiber-based tensile sensors, and the fiber-based tensile sensors are woven into the areas corresponding to each human joint of the intelligent clothing; by obtaining the tensile detection values of the fiber-based tensile sensors; according to the tensile detection values, determining the corresponding angle values; mapping the angle values to the coordinate axes of the three-dimensional coordinate system of each human joint to obtain a three-dimensional posture.

[0026] Since the existing posture recognition methods usually adopt inertial motion capture or optical motion capture. In inertial motion capture, inertial measurement units are embedded at key positions of the motion capture suit (such as joints and torso), and by integrating the sensor data of the inertial measurement units, the posture angles of various parts of the human body are calculated. However, long-term use may cause "drift" due to integration calculation errors. Optical motion capture is motion capture realized by relying on computer vision after collecting images, which is easily affected by occlusion or light interference. As a result, the accuracy of the recognized user postures is relatively low.

[0027] This application provides a solution. By means of fiber-based tensile sensors, the angular values of each human joint in three-dimensional space are accurately recognized from the mechanical stretching level, and mapped to the three-dimensional coordinate system of each human joint to form a three-dimensional posture. Compared with the existing inertial motion capture and optical motion capture, the posture processing method of this application not only has stronger adaptability to different scenarios, but also does not have the problem of integration drift because the angle recognition is carried out from the mechanical stretching level. Therefore, the accuracy of user posture recognition can be effectively improved. In addition, inertial motion capture and optical motion capture need to fit multiple degrees of freedom (position + posture) of the whole body based on inertial information and image information, resulting in a large amount of operation data and high processing difficulty. However, this application directly fits the human body posture through the joint angles detected by the fiber-based tensile sensors, with less operation data and low processing difficulty, which can improve the real-time performance of user posture recognition and achieve fast response and feedback.

[0028] Based on this, an embodiment of this application provides a posture processing method, referring to Figure 1 , Figure 1 which is a schematic flowchart of the first embodiment of the posture processing method of this application.

[0029] In this embodiment, the posture processing method is applied to an intelligent garment, and the intelligent garment includes a plurality of fiber-based tensile sensors, and the fiber-based tensile sensors are woven into the areas of the intelligent garment corresponding to each human joint; The posture processing method includes steps S10 to S30: Step S10, obtaining the tensile detection value of the fiber-based tensile sensor; It should be noted that as Figure 2 shown, the intelligent garment can be in the form of clothing such as an upper garment, trousers, gloves, arm sleeves, etc., and the matrix fabric layer of the intelligent garment ( Figure 2The black area (in [description]) is made of elastic fibers (such as spandex, polyester, nylon, polyamide fibers or blended elastic fibers) to fit the user's body surface. In addition, the elastic fibers can be additionally subjected to functional treatments (such as antibacterial treatment, coating with a water-wash resistant coating, coating with a fatigue-resistant coating, etc.). The intelligent clothing includes a plurality of fiber-based stretch sensors woven into the areas of the matrix fabric layer of the intelligent clothing corresponding to each human joint ( Figure 2 the green area in [description]), to detect the stretching amplitude of the areas corresponding to each human joint and represent the corresponding angular values. It can be understood that the fiber-based stretch sensors are at least arranged in the areas where stretching occurs when the human joints move. Exemplarily, the fiber-based stretch sensors can be woven into the matrix fabric layer by means of knitting, embroidery or adhesion.

[0030] In addition, it should be noted that the fiber-based stretch sensor is a sensor in the form of a fiber. The fiber-based stretch sensor causes a voltage change as the fiber is stretched. Thus, in this embodiment, the stretching amplitude of the fiber in the area where the fiber-based stretch sensor is located can be determined through the voltage change.

[0031] In this embodiment, a communication connection can be established with each fiber-based stretch sensor through wireless communication or wired communication. Thus, the sensor signals of each fiber-based stretch sensor can be received, and the stretching detection values of the fiber-based stretch sensors can be obtained.

[0032] Step S20: Determine the corresponding angular value according to the stretching detection value; It should be noted that the stretching detection value represents the fiber length. The stretching detection value can be the voltage value directly output by the fiber-based stretch sensor or the length value converted from the voltage value.

[0033] Since the stretching amplitude of the fiber by the human joints at different angles is different, taking the elbow joint as an example, when the elbow joint is flexed, the fibers in the area corresponding to the dorsal side of the elbow joint are stretched. And the deeper the flexion degree of the elbow joint (i.e., the smaller the angle between the humerus and the ulna or radius), the greater the fiber stretching amplitude. The fiber-based stretch sensors are arranged in the areas corresponding to the dorsal side of the elbow joint on the intelligent clothing. Thus, there is a mapping relationship between the fiber stretching amplitude detected by the fiber-based stretch sensors and the angular value in the flexion direction of the elbow joint. Therefore, in this embodiment, the fiber stretching amplitude of the intelligent clothing in the areas corresponding to each human joint can be determined according to the stretching detection value, and then, according to the mapping relationship between the fiber stretching amplitude and the angular value, the angular value of the human joint corresponding to the stretching detection value can be determined.

[0034] In a feasible implementation manner, step S20 may include steps S21 to S23: Step S21, obtain the initial tensile value of the fiber-based tensile sensor, where the initial tensile value is the tensile value of the fiber-based tensile sensor in an initial standard state; Step S22, calculate the tensile change value between the tensile detection value and the initial tensile value; Step S23, according to the tensile change value and the corresponding angle mapping relationship of the fiber-based tensile sensor, obtain the angle value corresponding to the tensile detection value, where the angle mapping relationship describes the mapping relationship between the tensile change value and the angle value of the fiber-based tensile sensor.

[0035] It should be noted that the initial tensile value is the tensile value of the fiber-based tensile sensor in an initial standard state, and the initial standard state is the state of the fiber-based tensile sensor in a specified standard posture (such as a natural standing posture, an outstretched arm standing posture, etc.). Exemplarily, in this embodiment, the smart clothing can be worn on a standard human model in a specified standard posture, and then the tensile detection value of the fiber-based tensile sensor can be used as the initial tensile value. In this embodiment, the user can also be guided to use the tensile detection value of the fiber-based tensile sensor as the initial tensile value after wearing the smart clothing and making a specified standard posture.

[0036] This embodiment can also obtain the initial stretching value of the fiber-based stretching sensor, where the initial stretching value is the stretching value of the fiber-based stretching sensor in the initial standard state. Thus, the stretching change value between the stretching detection value and the initial stretching value can be calculated, where the stretching change value is the difference between the stretching detection value and the initial stretching value. Thus, this embodiment can obtain the angle value corresponding to the stretching detection value according to the stretching change value and the angle mapping relationship corresponding to the fiber-based stretching sensor, where the angle mapping relationship describes the mapping relationship between the stretching change value and the angle value of the fiber-based stretching sensor. The angle mapping relationship can be described in the form of a mapping table, a fitting function, etc. Exemplarily, the partial pressure value is the voltage value output after the fiber-based stretching sensor is stretched. Since the signal directly output by the fiber-based stretching sensor is generally an analog signal, the partial pressure value can be converted to decimal to obtain the current stretching value. Then, the difference between the current stretching value and the initial stretching value is calculated to obtain the stretching change value, and then, according to the stretching change value and the fitting function, the angle value corresponding to the stretching detection value is calculated. Exemplarily, the fitting function corresponding to the fiber-based stretching sensor on the X-axis of the left shoulder is f(x)=11.924x, the current stretching value is 464, and the initial stretching value is 460. Then, the stretching change value is the current stretching value minus the initial stretching value, that is, 464 - 460 = 4, and the angle value f(4)=11.924*4 = 47.70°. The fitting function corresponding to the fiber-based stretching sensor on the Y-axis of the left shoulder is f(x)= -1.8407x + 90, the current stretching value is 985, and the initial stretching value is 953. Then, the stretching change value is the current stretching value minus the initial stretching value, that is, 985 - 953 = 32, and the angle value f(32)=-1.8407*32 + 90 = 31.10°. The fitting function corresponding to the fiber-based stretching sensor on the Z-axis of the left shoulder is f(x)= -1.8058x, the current stretching value is 340, and the initial stretching value is 359. Then, the stretching change value is the current stretching value minus the initial stretching value, that is, 340 - 359 = -19, and the angle value f(-19)=-1.8058*-19 = 34.31°. Further, in order to reduce errors, this embodiment can set multiple fiber-based stretching sensors in each axis direction of the three-dimensional coordinate system corresponding to each human joint. Thus, by fusing the detection values of the multiple fiber-based stretching sensors, the stretching detection value of the fiber-based stretching sensor in each axis direction of the three-dimensional coordinate system corresponding to the human joint is obtained.

[0037] Step S30: Map the angle value to the coordinate axes of the three-dimensional coordinate system of each human joint to obtain a three-dimensional posture.

[0038] It should be noted that the three-dimensional coordinate system of the human joint is a pre-set coordinate system established with the joint of the human joint as the origin. Exemplarily, as Figure 3 shown, the positive direction of the X-axis of the three-dimensional coordinate system is the direction of the bone connected to one end of the human joint, the positive direction of the Y-axis points to a specified direction perpendicular to the positive direction of the X-axis (such as pointing to the front side of the body), and the Z-axis is the direction perpendicular to the plane formed by the X-axis and the Y-axis. In addition, as Figure 4 shown, due to the limitations of the human body structure, the value ranges of the coordinate axes in the three-dimensional coordinate systems corresponding to different human joints are determined according to the range of motion of the human joint.

[0039] It should also be noted that the three-dimensional pose can be the full-body pose of the human body, or the limb pose of some human joints, such as the limb pose of the hand area, the limb pose of the upper body area, etc.

[0040] Since the angle value corresponding to the fiber-based tensile sensor describes the angle on a single degree of freedom (i.e., a certain coordinate axis), in this embodiment, the angle values corresponding to the fiber-based tensile sensors need to be mapped to the coordinate axes of the three-dimensional coordinate system of each human joint respectively to obtain the three-dimensional pose. Exemplarily, in this embodiment, according to the installation position of the fiber-based tensile sensor, the coordinate axis of the three-dimensional coordinate system of the human joint corresponding to the fiber-based tensile sensor is determined. Then, the angle value of the fiber-based tensile sensor can be mapped to the corresponding coordinate axis of the three-dimensional coordinate system to obtain the local joint angle, where the local joint angle is the three-dimensional vector of the human joint in the corresponding three-dimensional coordinate system. Since each three-dimensional coordinate system is established based on the joint of each human joint and the bone direction at one end, and there is a relative position relationship between the joints, in this embodiment, the local joint angles can be concatenated according to the transformation relationship between the three-dimensional coordinate systems of each human joint to obtain the global human pose as the three-dimensional pose. Thus, after importing the three-dimensional pose into the human model in this embodiment, the real-time mapping and visualization of the user's actions are realized. Furthermore, the three-dimensional pose obtained in this embodiment can be used in scenarios such as motion analysis, rehabilitation, human-computer interaction, virtual reality, etc.

[0041] In a feasible implementation manner, step S30 may include steps S31 to S33: Step S31, according to the installation position of the fiber-based tensile sensor, determine the coordinate axis of the three-dimensional coordinate system of the human joint corresponding to the fiber-based tensile sensor; Step S32, map the angle value of the fiber-based tensile sensor to the corresponding coordinate axis of the three-dimensional coordinate system to obtain the local joint angle; Step S33: According to the transformation relationship between the three-dimensional coordinate systems of the human joints, concatenate the local joint angles of each of the human joints to obtain the global human posture as the three-dimensional posture.

[0042] It should be noted that the installation positions of the fiber-based stretch sensors are within the ranges of the human joints, so as to facilitate the detection of the fiber stretch amplitudes of the human joints in the directions of the respective coordinate axes in the three-dimensional coordinate system.

[0043] Such as Figure 5As shown, the red line segments in the figure are fiber-based tensile sensors. For the neck, fiber-based tensile sensors 7 and 13 are used to detect the fiber stretching amplitude in the X-axis direction of the trapezius muscle on the right side of the human body; fiber-based tensile sensors 8 and 14 are used to detect the fiber stretching amplitude in the X-axis direction of the trapezius muscle on the left side of the human body. Fiber-based tensile sensor 1 is used to detect the fiber stretching amplitude in the Y-axis direction of the trapezius muscle on the right side of the human body; fiber-based tensile sensor 2 is used to detect the fiber stretching amplitude in the Y-axis direction of the trapezius muscle on the left side of the human body. Fiber-based tensile sensors 5 and 11 are used to detect the fiber stretching amplitude in the Z-axis direction of the trapezius muscle on the right side of the human body; fiber-based tensile sensors 6 and 12 are used to detect the fiber stretching amplitude in the Z-axis direction of the trapezius muscle on the left side of the human body. For the shoulder, fiber-based tensile sensor 21 is used to detect the fiber stretching amplitude in the X-axis direction of the shoulder on the right side of the human body; fiber-based tensile sensor 22 is used to detect the fiber stretching amplitude in the X-axis direction of the shoulder on the left side of the human body. Fiber-based tensile sensor 3 is used to detect the fiber stretching amplitude in the Y-axis direction of the shoulder on the right side of the human body; fiber-based tensile sensor 4 is used to detect the fiber stretching amplitude in the Y-axis direction of the shoulder on the left side of the human body. Fiber-based tensile sensor 9 is used to detect the fiber stretching amplitude in the Z-axis direction of the shoulder on the right side of the human body; fiber-based tensile sensor 10 is used to detect the fiber stretching amplitude in the Z-axis direction of the shoulder on the left side of the human body. For the chest cavity, fiber-based tensile sensor 15 is used to detect the fiber stretching amplitude in the Z-axis direction of the chest cavity. For the waist, fiber-based tensile sensors 16 and 17 are used to detect the fiber stretching amplitude in the X-axis direction of the waist; fiber-based tensile sensors 18 and 19 are used to detect the fiber stretching amplitude in the Y-axis direction of the waist; fiber-based tensile sensor 20 is used to detect the fiber stretching amplitude in the Z-axis direction of the waist. For the elbow joint, fiber-based tensile sensor 23 is used to detect the fiber stretching amplitude in the X-axis direction of the elbow joint on the right side of the human body; fiber-based tensile sensor 24 is used to detect the fiber stretching amplitude in the X-axis direction of the elbow joint on the left side of the human body; fiber-based tensile sensor 25 is used to detect the fiber stretching amplitude in the Z-axis direction of the elbow joint on the right side of the human body; fiber-based tensile sensor 26 is used to detect the fiber stretching amplitude in the Z-axis direction of the elbow joint on the left side of the human body. Due to the limitation of the human body structure, the elbow joint only has the ability to move in these two degrees of freedom, so there is no need to set up a fiber-based tensile sensor to detect the fiber stretching in the Y-axis direction of the elbow joint. For the hip joint, fiber-based tensile sensors 31 and 32 are used to detect the fiber stretching amplitude in the X-axis direction of the hip joint; fiber-based tensile sensors 29 and 30 are used to detect the fiber stretching amplitude in the Y-axis direction of the hip joint; fiber-based tensile sensors 27 and 28 are used to detect the fiber stretching amplitude in the Z-axis direction of the hip joint.For the knee joint, the fiber-based stretch sensor 33 is used to detect the fiber stretch amplitude in the Z-axis direction of the right knee joint of the human body; the fiber-based stretch sensor 34 is used to detect the fiber stretch amplitude in the Z-axis direction of the left knee joint of the human body. Due to the limitation of the human body structure, the knee joint has the ability to move only in this one degree of freedom. Therefore, there is no need to set fiber-based stretch sensors for detecting the X-axis and Y-axis directions of the knee joint. Thus, in this embodiment, the coordinate axes of the three-dimensional coordinate system of the human joint corresponding to the fiber-based stretch sensor can be determined according to the installation position of the fiber-based stretch sensor. Then, the angle value of the fiber-based stretch sensor is mapped onto the coordinate axes of the corresponding three-dimensional coordinate system to obtain the three-dimensional vector (local joint angle) of the human joint in the corresponding three-dimensional coordinate system, that is, the angle of the human body in the three-dimensional space. And each three-dimensional coordinate system is established with the joint of each human joint as the origin. Therefore, the position and connection relationship between each human joint can be used as the transformation relationship between the three-dimensional coordinate systems of each human joint. Furthermore, in this embodiment, all the local joint angles can be concatenated according to the transformation relationship between the three-dimensional coordinate systems of each human joint to obtain the global human posture corresponding to the entire human body as the three-dimensional posture. Regarding the method of concatenating each local joint angle, in this embodiment, the joint parent-child relationship between each human joint can be determined first. For example: root joint: waist, torso chain: waist → chest → neck, left lower limb chain: waist → left hip → left knee → left ankle, etc. Starting from the root joint in the joint parent-child relationship, each local joint angle is multiplied by the transformation matrix describing the transformation relationship step by step to obtain the global joint angle of each human joint, forming the global human posture. Of course, in this embodiment, some of the local joint angles can also be concatenated according to the transformation relationship between the three-dimensional coordinate systems of each human joint to obtain the global human posture corresponding to a partial human body area as the three-dimensional posture.

[0044] In a feasible implementation manner, step S33 may include steps A10 to A20: Step A10, obtain a specified human body area and determine the local joint angles of each human joint within the specified human body area; Step A20, concatenate the local joint angles of each human joint within the specified human body area according to the transformation relationship between the three-dimensional coordinate systems of each human joint to obtain the global human posture.

[0045] It should be noted that the specified human body area is the specified human body area where the global human posture is expected to be constructed, such as the torso area, the upper body area, the lower body area, etc.

[0046] In this embodiment, it is possible to obtain a specified human body area for which pose construction is desired, then determine the human joints included in the specified human body area and the local joint angles of these human joints. Furthermore, according to the transformation relationship between the three-dimensional coordinate systems of the human joints, the local joint angles of the human joints in the specified human body area are concatenated to obtain the global human pose.

[0047] The embodiment of this application is different from the inertial motion capture solution. The inertial motion capture solution identifies the positions of key points in the global coordinate system (such as the ground coordinate system) through inertial information or optical information to achieve pose recognition. In this way, even if one wants to obtain the global human pose of a specified human body area, due to the interference caused by the overall pose change in the global coordinate system, the recognition error of the local human body area is too large. Exemplarily, when constructing the global human pose of only the hand and elbow areas, when constructing through the key points of the hand and elbow areas in the global coordinate system, it is usually difficult to avoid the interference caused by the overall pose change. For example, when the upper body rotates, even if the hand and elbow do not change, the inertial information of the hand and elbow will change, so that the constructed global human pose cannot actually be decoupled from the overall pose, achieving the accuracy of pose description for the specified human body area.

[0048] In a feasible implementation manner, after step S30, steps S40 - S50 may be included: Step S40: Import the three-dimensional pose into a standard human model to determine the real-time center of gravity position in the three-dimensional pose; Step S50: After the horizontal movement speed of the real-time center of gravity position is greater than a predetermined speed threshold, or the relative distance between the real-time center of gravity position and a predetermined human body support point is greater than a predetermined distance threshold, output a fall warning message.

[0049] It should be noted that as Figure 6 shown, the standard human model is a three-dimensional model of the human body under a specified standard body type.

[0050] Since existing inertial motion capture and optical motion capture require a large amount of data processing based on inertial information or optical information, it is difficult to ensure the real-time output of three-dimensional postures. In this embodiment, the three-dimensional posture is imported into the standard human model to bind each global joint angle in the three-dimensional posture to each model joint in the standard human model, so that the standard human model presents the three-dimensional posture. Furthermore, in this embodiment, based on the standard human model imported with the three-dimensional posture, the real-time center-of-gravity position under the three-dimensional posture can be calculated. Exemplarily, in this embodiment, the mass ratios of each body part in the standard human model can be obtained. For example, the mass ratio of the torso part is 50%, the mass ratio of the head and neck is 8%, the mass ratio of each arm part is 5%, and the mass ratio of each leg is 16%. Next, the center-of-gravity position of each part needs to be determined. And determine the center-of-gravity positions of each body part in the standard human model imported with the three-dimensional posture (such as close to the geometric center of the body part, or the corresponding proportional position). For example, the center of gravity of the thigh is at the middle position between the hip joint and the knee joint, or closer to the hip joint. The center of gravity of the upper arm is at a certain proportional position near the proximal end (close to the shoulder joint), such as the 43% position. Then, the sum is obtained by multiplying the mass ratio of each body part by its center-of-gravity position, and then divided by the total mass, and the real-time center-of-gravity position under the three-dimensional posture can be obtained. Thus, the relative distance in the horizontal direction between the real-time center-of-gravity position at the previous moment and the real-time center-of-gravity position at the current moment and the time difference between the real-time center-of-gravity position at the previous moment and the real-time center-of-gravity position at the current moment can be calculated, and the horizontal movement speed of the real-time center-of-gravity position can be calculated according to the relative distance in the horizontal direction and the time difference. In this embodiment, it can be determined whether the horizontal movement speed of the real-time center-of-gravity position is greater than a predetermined speed threshold, and whether the relative distance between the real-time center-of-gravity position and the predetermined human support point is greater than a predetermined distance threshold, where the predetermined human support point is the center-of-gravity position of the human body in a preset stable posture. Thus, in this embodiment, after the horizontal movement speed of the real-time center-of-gravity position is greater than the predetermined speed threshold, or the relative distance between the real-time center-of-gravity position and the predetermined human support point is greater than the predetermined distance threshold, it indicates that the real-time center-of-gravity position has changed rapidly, or is no longer in a stable posture. At this time, the user is at risk of falling, and a fall warning message can be output. The fall warning message is information used to warn of the risk of falling and can be output in the form of text, images, voice, etc. If the horizontal movement speed of the real-time center-of-gravity position is not greater than the predetermined speed threshold, and the relative distance between the real-time center-of-gravity position and the predetermined human support point is not greater than the predetermined distance threshold, it can be determined that there is no risk of falling. This embodiment realizes the timely warning of the risk of falling with high-accuracy joint angles and high real-time performance.

[0051] The first embodiment of the present application provides a posture processing method, which is applied to intelligent clothing. The intelligent clothing includes a plurality of fiber-based stretch sensors woven into areas corresponding to each human joint of the intelligent clothing. Since the degree of fiber stretching in the areas corresponding to each human joint of the intelligent clothing is different when the human joints are at different angles, in this embodiment, the stretching detection value of the fiber-based stretch sensor can be obtained, and then the corresponding angle value can be determined according to the stretching detection value. And in this embodiment, an independent three-dimensional coordinate system is set for each human joint. Since a single fiber-based stretch sensor can identify the stretching amplitude at different angles of a human joint in a single direction, in this embodiment, the angle value can be mapped to the coordinate axes of the three-dimensional coordinate system of each human joint to obtain a three-dimensional posture. Thus, in this embodiment, with the help of fiber-based stretch sensors, the angle values of each human joint in three-dimensional space are accurately identified from the mechanical stretching level and mapped to the three-dimensional coordinate systems of each human joint to form a three-dimensional posture. Compared with the existing inertial motion capture and optical motion capture, the posture processing method of this embodiment not only has stronger adaptability to different scenarios, but also does not have the problem of integral drift because the angle is identified from the mechanical stretching level. Therefore, the accuracy of user posture recognition can be effectively improved. In addition, inertial motion capture and optical motion capture need to fit multiple degrees of freedom (position + posture) of the whole body based on inertial information and image information, resulting in a large amount of operation data and high processing difficulty. However, in this embodiment, the human body posture is directly fitted through the joint angles detected by fiber-based stretch sensors, with less operation data and low processing difficulty, which can improve the real-time performance of user posture recognition and achieve fast response and feedback.

[0052] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar content as in the above-mentioned first embodiment can be referred to the above introduction and will not be repeated hereinafter. On this basis, please refer to Figure 7 , each human joint in the specified human area includes an ankle joint, a knee joint and a hip joint; After step A10, steps B10 to B40 are included: Step B10, in response to a jumping event, obtain the landing acceleration, and calculate the ground reaction force based on the landing acceleration, where the landing acceleration is determined according to the vertical acceleration at the time of the jumping event; Step B20, determine the force thresholds of the ankle joint, the knee joint and the hip joint according to the local joint angles of the ankle joint, the knee joint and the hip joint; Step B30, perform reverse recursive calculation starting from the ankle joint according to the ground reaction force to obtain the ankle joint force, the knee joint force and the hip joint force; Step B40, comparing the ankle joint force, knee joint force and hip joint force with the corresponding force thresholds respectively, and outputting injury warning information when any one of the ankle joint force, knee joint force and hip joint force exceeds the corresponding force threshold.

[0053] It should be noted that for jumping scenarios (such as shooting, long jump, etc.), if the angles of the ankle, knee and hip joints are different when the user lands, the support force that can be provided is also different. For example, when the local joint angle of the ankle joint is 0°, that is, when the calf is perpendicular to the ground, the support force provided is the largest. The greater the angle difference between the local joint angle and 0°, the smaller the support force that can be provided. Therefore, this embodiment can set a corresponding force threshold for the local joint angle of each human joint, where the force threshold is the support force of the human joint at the local joint angle. The jumping event is an event in which the user performs a jumping action.

[0054] This embodiment can obtain the vertical acceleration of the user in the direction perpendicular to the ground. If the vertical acceleration has an acceleration that first decreases (pre-squat stage) and then rises sharply (at the moment of leaving the ground), it can be determined that there is a jumping event. This embodiment can respond to the jumping event and obtain the landing acceleration, wherein the landing acceleration is determined according to the vertical acceleration at the time of the jumping event, and the landing acceleration can be the sum of the absolute values of the gravity acceleration and the vertical acceleration. This embodiment can also take into account the air resistance during the jumping and falling process, and the landing acceleration can also be a correction value of the sum of the absolute values of the gravity acceleration and the vertical acceleration, that is, the product of the sum of the absolute values of the gravity acceleration and the vertical acceleration and a predetermined correction coefficient. Therefore, the ground reaction force can be calculated by the landing acceleration with the help of Newton's second law, that is, the ground reaction force is the product of the landing acceleration and the mass of the human body. This embodiment can query the mapping relationship between the joint angle of the human body joint and the force threshold according to the local joint angles of the ankle joint, knee joint and hip joint, and obtain the force threshold corresponding to the ankle joint, knee joint and hip joint at their respective local joint angles. Furthermore, this embodiment can calculate the ankle joint force, knee joint force and hip joint force at the moment of landing by reverse recursive calculation based on the ground reaction force and taking the ankle joint as the starting point. For example, ankle joint force Fankle: Fankle=m foot *g−F GRF , where m foot is the mass of the foot, g is the acceleration due to gravity, F GRF is the ground reaction force. ankle Knee joint force Fknee transmitted to the knee joint: Fknee=Fankle+m shank *g, where m foot is the mass of the calf, and the knee joint force Fankle The hip joint force Fhip after being transmitted to the hip joint: Fhip = Fknee + m thigh *g, where m thigh is the mass of the thigh. Thus, the ankle joint force, knee joint force, and hip joint force can be respectively compared with the corresponding force thresholds, and after any one of the ankle joint force, knee joint force, and hip joint force exceeds the corresponding force threshold, an injury warning message is output. The injury warning message is information used to warn of the injury risk and can be output in the form of text, images, voices, etc.

[0055] In the second embodiment of the present application, by responding to the jumping event, the landing acceleration is obtained, and based on the landing acceleration, the ground reaction force is calculated, where the landing acceleration is determined according to the vertical acceleration at the time of the jumping event; according to the local joint angles of the ankle joint, knee joint, and hip joint, the force thresholds of the ankle joint, knee joint, and hip joint are determined; according to the ground reaction force, starting from the ankle joint and recursively calculating backward, the ankle joint force, knee joint force, and hip joint force are obtained; the ankle joint force, knee joint force, and hip joint force are respectively compared with the corresponding force thresholds, and after any one of the ankle joint force, knee joint force, and hip joint force exceeds the corresponding force threshold, an injury warning message is output. In this embodiment, the corresponding landing acceleration is estimated through the vertical acceleration, the ground reaction force at the moment of jumping and landing is calculated, and then the joint forces are recursively calculated backward starting from the ankle joint, accurately decomposing the transmission path of the impact force in the joint chain (ankle - knee - hip), and determining the force thresholds adapted to the current posture according to the real - time local joint angles. Thus, after any joint force exceeds the limit, there may be risks such as joint sprains and dislocations, and an injury warning message is immediately output, realizing the monitoring and warning of possible injuries after the jumping event.

[0056] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar content as in the above - mentioned first embodiment can be referred to the above introduction and will not be repeated hereinafter. On this basis, please refer to Figure 8 wherein the posture processing method further includes steps C10 to C40: Step C10, in response to the motion analysis instruction, obtain the joint chain involved in the motion to be analyzed and the standard action angle sequence; Step C20, generate the current action angle sequence from the local joint angles in the involved joint chain; Step C30, align the current action angle sequence and the standard action angle sequence to obtain the motion coordination deviation; Step C40, generate the posture correction prompt information according to the motion coordination deviation.

[0057] It should be noted that the motion analysis instruction is a command for indicating the analysis of motion behaviors, such as the analysis of motion behaviors like push-ups, yoga poses, sit-ups, etc. The joint chain involved in the motion to be analyzed is the joint chain composed of each human joint involved in the motion to be analyzed. The standard action angle sequence is a time sequence composed of the local joint angles of each human joint in the joint chain involved in the standard action to be analyzed.

[0058] In this embodiment, in response to the motion analysis instruction, the joint chain involved in the motion to be analyzed and the standard action angle sequence can be obtained. Then, the local joint angles in the joint chain involved can be arranged in chronological order to generate the current action angle sequence. Furthermore, the current action angle sequence and the standard action angle sequence are aligned on the time axis. Then, the angle difference and time sequence difference between the key phase points in the standard action angle sequence and the corresponding mapped phase points in the current action angle sequence can be calculated. The key phase points are the phase points of the landmark nodes of the motion to be analyzed in the standard action angle sequence. Exemplarily, taking the sit-up as the motion to be analyzed, the landmark nodes are the four nodes of "lying back", "lying flat", "sitting up", and "sitting down". The mapped phase points are the phase points in the current action angle sequence corresponding to the key phase points in the standard action angle sequence. Then, this embodiment can calculate the difference information (such as angle difference, time sequence difference) between the key phase points and the mapped phase points as the motion coordination deviation. Thus, according to the motion coordination deviation, this embodiment generates posture correction prompt information. For example, when the angle difference is large, it prompts the local joint angle of the human joint that needs to be corrected and the angle value that needs to be adjusted; when the time sequence difference is large, it prompts the coordination between the human joints that need to be corrected and the time points of the key phase points that need to be adjusted (such as advancing the execution time point of the landmark node in the motion to be analyzed, delaying the execution time point of the landmark node in the motion to be analyzed, etc.).

[0059] In some embodiments, after step C30, steps D10 to D20 may be included: Step D10, map the current action angle sequence and the standard action angle sequence on the same time axis, and calculate the angle difference and time sequence difference between the key phase points in the standard action angle sequence and the corresponding mapped phase points in the current action angle sequence; Step D20, use the angle difference and the time sequence difference as the motion coordination deviation.

[0060] In this embodiment, the current action angle sequence and the standard action angle sequence can be mapped on the same time axis, and then the key phase points in the standard action angle sequence can be matched with the current action angle sequence to obtain the mapped phase points corresponding to the key phase points in the current action angle sequence. Furthermore, in this embodiment, the angle difference and the timing difference between the key phase points in the standard action angle sequence and the mapped phase points corresponding to the current action angle sequence can be calculated, and the angle difference and the timing difference are used as the motion coordination deviation. Thus, the action standard degree of the motion to be analyzed can be determined by means of the angle difference in the motion coordination deviation, and the action coordination degree can be determined by means of the timing difference in the motion coordination deviation.

[0061] In the third embodiment of the present application, by responding to a motion analysis instruction, the joint chain involved in the motion to be analyzed and the standard action angle sequence are obtained, and the local joint angles in the joint chain involved are used to generate the current action angle sequence. The current action angle sequence and the standard action angle sequence are aligned to obtain a motion coordination deviation, and according to the motion coordination deviation, posture correction prompt information is generated. In this embodiment, by performing non-linear alignment on the current action angle sequence and the standard action angle sequence, multi-joint collaborative analysis on the time axis is realized, the motion coordination deviation is located, and the deviation in the angle and coordination of the motion to be analyzed can be realized for posture correction prompt.

[0062] The present application provides an intelligent wearable system, such as Figure 9 shown, the intelligent wearable system includes an intelligent garment 201 and a control terminal 202 communicatively connected to the intelligent garment 201; The intelligent garment 201 includes: a base fabric layer and a plurality of fiber-based stretch sensors, and the fiber-based stretch sensors are woven into the regions corresponding to each human joint in the base fabric layer; The control terminal 202 is configured to implement the steps of the posture processing method as in the above embodiment.

[0063] It should be noted that the intelligent garment 201 can be in the form of clothing such as a coat, trousers, gloves, arm sleeves, etc. The base fabric layer of the intelligent garment 201 ( Figure 9 the black area in) is made of elastic fibers (fibers such as spandex, polyester fiber, nylon, polyamide fiber or blended elastic fibers) to fit the user's body surface. In addition, the elastic fibers can be additionally subjected to functional treatments (such as antibacterial treatment, coating with a water-washable coating, coating with a fatigue-resistant coating, etc.). The intelligent garment 201 includes a plurality of fiber-based stretch sensors, and the fiber-based stretch sensors are woven into the regions corresponding to each human joint in the base fabric layer of the intelligent garment 201 ( Figure 9The green area in it) is used to detect the stretching amplitude of the area corresponding to each human joint and represent the corresponding angle value. It can be understood that the fiber-based stretch sensor is at least arranged in the area where stretching occurs during the movement of the human joint. Exemplarily, the fiber-based stretch sensor can be woven, embroidered or adhered into the matrix fabric layer.

[0064] The control terminal 202 can be a terminal device independent of the smart clothing, or the control terminal can also be a control unit integrated in the smart clothing. The control terminal 202 can include: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the posture processing method in the first embodiment above. The control terminal of the smart wearable system in the embodiment of the present application can include, but is not limited to, terminal devices such as smart phones, smart watches, head-mounted display devices, laptop computers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions: tablet computers), desktop computers, etc.

[0065] In some embodiments, the smart clothing 201 further includes a data acquisition module; The data acquisition module is electrically connected to each of the fiber-based stretch sensors through a wire, and is configured to collect the sensor signals of each of the fiber-based stretch sensors and send them to the control terminal 202.

[0066] As Figure 10 shown, taking the smart clothing as an example of clothes, Figure 10 the thick black line segments in it are fiber-based stretch sensors, and the light red thin lines are wires. As Figure 11 shown, taking the smart clothing as an example of gloves, Figure 11 the thick black line segments in it are fiber-based stretch sensors, and the light red thin lines are wires. Thus, the smart clothing 201 further includes a data acquisition module, and the data acquisition module is electrically connected to each of the fiber-based stretch sensors through a wire, and is configured to collect the sensor signals of each of the fiber-based stretch sensors and send them to the control terminal 202.

[0067] Figure 9 The smart wearable system shown is only an example, and should not bring any limitations to the functions and usage scopes of the embodiments of the present application.

[0068] The intelligent wearable system provided by the present application adopts the posture processing method in the above-mentioned embodiment, which can solve the technical problem of low accuracy of the user posture recognized by the existing posture recognition scheme. Compared with the prior art, the beneficial effects of the intelligent wearable system provided by the present application are the same as those of the posture processing method provided by the above-mentioned embodiment, and other technical features in the intelligent wearable system are the same as those disclosed in the method of the previous embodiment, which will not be elaborated here.

[0069] It should be understood that each part disclosed in the present application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0070] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0071] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the posture processing method in the above-mentioned embodiment.

[0072] The computer-readable storage medium provided by the present application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or combined with an instruction execution system or device. The program code contained on the computer-readable storage medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0073] The above computer-readable storage medium may be included in the control terminal; or it may exist independently without being assembled into the control terminal.

[0074] The above computer-readable storage medium carries one or more programs. When the one or more programs are executed by the control terminal, the control terminal is caused to: obtain the tensile detection value of the fiber-based tensile sensor; determine the corresponding angle value according to the tensile detection value; map the angle value onto the coordinate axes of the three-dimensional coordinate system of each human joint to obtain a three-dimensional posture.

[0075] Computer program code for performing the operations of the present application may be written in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it may be connected to an external computer (for example, by connecting through an Internet service provider using the Internet).

[0076] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0077] The modules described in the embodiments of the present application may be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation to the unit itself in some cases.

[0078] The readable storage medium provided by this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned attitude processing method, which can solve the technical problem that the accuracy of the user attitude recognized by the existing attitude recognition scheme is relatively low. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by this application are the same as those of the attitude processing method provided by the above embodiment, and will not be elaborated here.

[0079] This application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the steps of the attitude processing method as described above.

[0080] The computer program product provided by this application can solve the technical problem that the accuracy of the user attitude recognized by the existing attitude recognition scheme is relatively low. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as those of the attitude processing method provided by the above embodiment, and will not be elaborated here.

[0081] The above are only some embodiments of this application, and thus do not limit the patent scope of this application. Any equivalent structural transformation made under the technical concept of this application by using the content of the specification and drawings of this application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of this application.

Claims

1. A posture processing method, characterized in that, Applied to smart clothing, the smart clothing includes a plurality of fiber-based stretch sensors which are woven into areas corresponding to each human joint of the smart clothing; The posture processing method includes: Obtaining the stretch detection value of the fiber-based stretch sensor; Determining a corresponding angle value according to the stretch detection value; Mapping the angle value onto the coordinate axes of the three-dimensional coordinate system of each human joint to obtain a three-dimensional posture.

2. The attitude processing method according to claim 1, wherein The step of determining a corresponding angle value according to the stretch detection value includes: Obtaining the initial stretch value of the fiber-based stretch sensor, where the initial stretch value is the stretch value when the fiber-based stretch sensor is in an initial standard state; Calculating the stretch change value between the stretch detection value and the initial stretch value; Obtaining the angle value corresponding to the stretch detection value according to the stretch change value and the angle mapping relationship corresponding to the fiber-based stretch sensor, where the angle mapping relationship describes the mapping relationship between the stretch change value and the angle value of the fiber-based stretch sensor.

3. The attitude processing method according to claim 1, characterized in that The step of mapping the angle value onto the coordinate axes of the three-dimensional coordinate system of each human joint to obtain a three-dimensional posture includes: Determining the coordinate axes of the three-dimensional coordinate system of the human joint corresponding to the fiber-based stretch sensor according to the installation position of the fiber-based stretch sensor; Mapping the angle value of the fiber-based stretch sensor onto the corresponding coordinate axes of the three-dimensional coordinate system to obtain a local joint angle; Connecting in series each local joint angle according to the transformation relationship between the three-dimensional coordinate systems of each human joint to obtain a global human posture as the three-dimensional posture.

4. The attitude processing method according to claim 3, wherein The step of connecting in series each local joint angle according to the transformation relationship between the three-dimensional coordinate systems of each human joint to obtain a global human posture includes: Obtaining a specified human area and determining the local joint angles of each human joint within the specified human area; Connecting in series the local joint angles of each human joint within the specified human area according to the transformation relationship between the three-dimensional coordinate systems of each human joint to obtain a global human posture.

5. The attitude processing method according to claim 4, wherein Each human joint within the specified human area includes an ankle joint, a knee joint and a hip joint; After the step of obtaining a specified human area and determining the local joint angles of each human joint within the specified human area, it includes: In response to a jumping-up event, obtaining the landing acceleration and calculating the ground reaction force based on the landing acceleration, where the landing acceleration is determined according to the vertical acceleration during the jumping-up event; Determining the force thresholds of the ankle joint, the knee joint and the hip joint according to the local joint angles of the ankle joint, the knee joint and the hip joint; Calculating recursively backward starting from the ankle joint according to the ground reaction force to obtain the ankle joint force, the knee joint force and the hip joint force; Comparing the ankle joint force, the knee joint force and the hip joint force with the corresponding force thresholds respectively, and outputting an injury warning message after any one of the ankle joint force, the knee joint force and the hip joint force exceeds the corresponding force threshold.

6. The attitude processing method according to claim 3, characterized in that The posture processing method further includes: In response to a motion analysis instruction, obtaining the involved joint chain and the standard action angle sequence of the motion to be analyzed; Generate the current motion angle sequence from the local joint angles involved in the joint chain; Align the current motion angle sequence with the standard motion angle sequence to obtain the motion coordination deviation; Generate posture correction prompt information based on the motion coordination deviation.

7. The attitude processing method according to claim 6, characterized in that, The step of aligning the current motion angle sequence with the standard motion angle sequence to obtain the motion coordination deviation includes: Map the current motion angle sequence and the standard motion angle sequence on the same time axis, and calculate the angular difference and timing difference between the key phase points in the standard motion angle sequence and the corresponding mapped phase points in the current motion angle sequence; Use the angular difference and the timing difference as the motion coordination deviation.

8. The attitude processing method according to any one of claims 1 to 7, characterized in that After the step of mapping the angular values to the coordinate axes of the three-dimensional coordinate system of each human joint to obtain the three-dimensional posture, the posture processing method further includes: Import the three-dimensional posture into a standard human model to determine the real-time center of gravity position in the three-dimensional posture; After the horizontal movement speed of the real-time center of gravity position is greater than a predetermined speed threshold, or the relative distance between the real-time center of gravity position and a predetermined human support point is greater than a predetermined distance threshold, output a fall warning message.

9. An intelligent wearable system, characterized in that, The intelligent wearable system includes intelligent clothing and a control terminal communicatively connected to the intelligent clothing; The intelligent clothing includes: a matrix fabric layer and a plurality of fiber-based stretch sensors, and the fiber-based stretch sensors are woven into the matrix fabric layer in areas corresponding to each human joint; The control terminal is configured to implement the steps of the posture processing method according to any one of claims 1 to 8.

10. The intelligent wearable system according to claim 9, wherein, The intelligent clothing further includes a data acquisition module; The data acquisition module is electrically connected to each of the fiber-based stretch sensors through wires, and is configured to collect the sensor signals of each of the fiber-based stretch sensors and send them to the control terminal.

Images