Kinect-based human joint comfort degree calculation method, program, equipment and storage medium

Abstract

The invention discloses a Kinect-based human joint comfort degree calculation method, program and equipment and a storage medium, belongs to the field of motion capture and man-machine engineering, and is used for solving the problem that the working comfort degree of an operator is difficult to evaluate. According to the method, firstly, Kinect is used for carrying out human motion capture, then angles of target joints in the motion process are analyzed, coronal plane, sagittal plane and cross section projection is carried out on the human joints to obtain component vector data, the angles of the target joints of different projections are calculated, and then the comfort degree of the target joints is calculated according to a target joint comfort degree calculation formula. And calculating the joint comfort degree of the target joint when the target joint acts. And superposing the target joint comfort levels to obtain the total human joint comfort level. The method is simple and reliable, and can be applied to human body comfort evaluation in human-computer interaction evaluation. According to the method, the evaluation of the operation comfort of the operator is quantified, so that the evaluation is more objective and more reasonable, and the subsequent improvement on the operation process is facilitated.

Description

Technical Field

[0001] The invention belongs to the field of motion capture and ergonomics, and in particular relates to a method, program, device and storage medium for calculating the comfort of human joints based on Kinect. Background Art

[0002] At present, when evaluating the comfort of human work, most evaluators use subjective feelings as evaluation indicators. This subjective evaluation is difficult to quantify. If actual measurements are taken on the human body, it is also difficult to ensure the accuracy and consistency of the measurements. Therefore, Kinect is used to capture the work process of the workers, convert it into data records, and then decompose and calculate the joint angles, so that quantitative analysis can be performed. Summary of the invention

[0003] In view of the above problems, the present invention proposes a method for calculating human joint comfort based on Kinect to solve the problem that subjective evaluation is difficult to quantify and actual measurement is not accurate enough.

[0004] The present invention provides a method for calculating the comfort of human joints based on Kinect, comprising the following steps:

[0005] Step 1: Build the Kinect plug-in usage environment in Unreal Engine and construct a human skeleton motion model;

[0006] Step 2: Obtain the image of the operator, convert it into a depth image, identify the distribution of body parts through the Kinect plug-in, obtain the three-dimensional coordinates of each joint point in the human skeleton motion model, and present the human skeleton state in real time; obtain the current workload of the operator;

[0007] Step 3: Establish the coronal plane, sagittal plane and transverse section of the human body, decompose and project the action angles of each joint of the human body to the coronal plane, sagittal plane and transverse section, and analyze them, and calculate the angles of the target joints;

[0008] Step 4: Calculate the comfort level of the target joints of the human body; if the total comfort level is within the comfort range, it is determined that the operator is in a comfortable state.

[0009] Furthermore, the three-dimensional coordinates of each joint point are:

[0010]

[0011] In the formula, (x i ,y i ,z i ) is the three-dimensional coordinate of the i-th joint of the human body; (x i ',y i ',z i') is the three-dimensional coordinate information of the i-th joint of the human body in the Kinect device space coordinate system O'X'Y'Z'; Indicates the rotation angle of the human body relative to the XOY plane of the device space coordinate system, (x 12 ,y 12 ,z 12 ) and (x 16 ,y 16 ,z 16 ) are the three-dimensional coordinates of the left hip joint and the right hip joint respectively; (x0, y0, z0) are the three-dimensional coordinates of the spine base joint.

[0012] Furthermore, the step 3 is specifically as follows:

[0013] Step 3.1: Construct the target human body forward vector, select the middle joint point of the spine, the left shoulder joint point and the right shoulder joint point as base points, determine a plane D, and calculate the vector perpendicular to the plane D based on the middle joint point of the spine;

[0014] Step 3.2: Establish the coronal, sagittal and transverse planes of the target human body. The coronal plane is plane D, the sagittal plane is the plane formed by the "human body forward vector" and the "middle spine-subcervical spine joint point vector", and the transverse plane is the plane based on the middle spine joint point perpendicular to the "middle spine-subcervical spine joint point vector". Project the joints of the human body onto the three planes respectively.

[0015] Furthermore, the projection point coordinates (x i1 ,y i1 ,z i1 ) is (x i +Mt1,y i +Nt1,z i +Rt1);

[0016]

[0017] In the formula, (x1, y1, z1) are the three-dimensional coordinates of the middle joint of the spine; (x4, y4, z4) are the three-dimensional coordinates of the left shoulder joint; (x8, y8, z8) are the three-dimensional coordinates of the right shoulder joint;

[0018] The coordinates of the projection point of the i-th joint of the human body to the sagittal plane (x i2 ,y i2 ,z i2 )for

[0019]

[0020] In the formula, (x 20 ,y20 ,z 20 ) are the three-dimensional coordinates of the subcervical spine joints;

[0021] The projection point of the human body's i-th joint to the cross section is (x i3 ,y i3 ,z i3 ) is (x i +(x 20 -x1)t3,y i +(y 20 -y1)t3,z i +(z 20 -z1)t3);

[0022]

[0023] Furthermore, the human target joint angle θ BG :

[0024]

[0025] In the formula, (x BG ,y BG ,z BG ) is the projection point coordinate of the target joint point B of the human body, G=1,2,3; (x AG ,y AG ,z AG ) and (x CG ,y CG ,z CG ) are the projection point coordinates of the adjacent joint points A and C of the target joint point B of the human body;

[0026] For all target joint angles θ BG To standardize:

[0027]

[0028] Calculate the comfort of the target joint point B in the coronal, sagittal and transverse planes

[0029]

[0030] Where M BG is the current actual joint torque of the target joint point B of the human body, F is the operator's current workload; M Bmax Indicates the maximum torque of the target joint B of the human body, that is, the torque at the maximum activity angle;

[0031] Calculate the total comfort of the target joint point B of the human body

[0032]

[0033] In the formula, ω 1G Represents the target joint comfort weights for the coronal, sagittal, and transverse planes.

[0034] Furthermore, all target joint points are superimposed to obtain the total comfort of human joints φ 总 :

[0035]

[0036] In the formula, ω B Represents the comfort weight of the target joint point B of the human body.

[0037] The present invention further provides a computer device / equipment / system, comprising a memory, a processor and a computer program stored in the memory, wherein the processor implements any of the steps of the above-mentioned method for calculating human joint comfort based on Kinect when executing the computer program.

[0038] The present invention further provides a computer-readable storage medium having a computer program / instruction stored thereon, which, when executed by a processor, implements the steps of any one of the above-mentioned methods for calculating human joint comfort based on Kinect.

[0039] The present invention further provides a computer program product, comprising a computer program / instruction, which, when executed by a processor, implements the steps of any one of the above-mentioned methods for calculating human joint comfort based on Kinect.

[0040] Beneficial effects of the present invention:

[0041] The present invention proposes a method for calculating human joint comfort based on Kinect. It only requires a work process demonstration in front of a motion capture device, and Kinect can automatically record human joint data and export it. Then, a custom program is used to calculate joint angle components and joint comfort, which are used as one of the indicators for comfort evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flow chart of a method for calculating human joint comfort based on Kinect of the present invention;

[0043] Figure 2 It is the human skeleton model constructed in the present invention;

[0044] Figure 3 is a schematic diagram of using Kinect to perform motion capture in the present invention;

[0045] Figure 4This is a sample document of human joint angle decomposition;

[0046] Figure 5 is a sample of weighted coefficients of joint comfort;

[0047] Figure 6 It is the equation for calculating joint comfort when the shoulder is under stress;

[0048] Figure 7 It is the equation for calculating the comfort of the joint when the wrist is under stress;

[0049] Figure 8 is the joint comfort evaluation matrix;

[0050] Fig. 9 This is an output sample of the joint comfort evaluation curve. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0052] The present invention may be better understood by referring to the following description given in conjunction with the accompanying drawings, wherein the same or similar reference numerals are used throughout the drawings to represent the same or similar components. The accompanying drawings, together with the following detailed description, are incorporated in and form a part of this specification and are used to further illustrate the preferred embodiments of the present invention and to explain the principles and advantages of the present invention.

[0053] The present invention is further described below in conjunction with the accompanying drawings.

[0054] Example

[0055] This embodiment discloses a specific implementation process of a method for acquiring human joint angles and a method for calculating human joint comfort based on Kinect.

[0056] Initialize the Kinect v2 sensor in UE4 software, such as Figure 2As shown, a human skeleton kinematic model containing 25 main joints is constructed, including the 0th node spinal base joint, the 1st node spinal middle joint, the 2nd node neck joint, the 3rd node head joint, the 4th node left shoulder joint, the 5th node left elbow joint, the 6th node left wrist joint, the 7th node left palm joint, the 8th node right shoulder joint, the 9th node right elbow joint, the 10th node right wrist joint, the 11th node right palm joint, the 12th node left hip joint, the 13th node left knee joint, the 14th node left ankle joint, the 15th node left foot joint, the 16th node right hip joint, the 17th node right knee joint, the 18th node right ankle joint, the 19th node right foot joint, the 20th node cervical spine joint, the 21st node left middle finger joint, the 22nd node left thumb joint, the 23rd node right middle finger joint, and the 24th node right thumb joint. Each joint point information contains three-dimensional coordinate information and tracking status. The spatial coordinate positions of the 25 joint points are represented by (x, y, z). The tracking status of the joint refers to the state when the depth camera tracks and captures the joint point. There are three tracking states, including tracking failure, predicted and tracking success. The state values ​​are represented by 0, 1, and 2.

[0057] The comfort levels of 18 joints among the above-mentioned joints are calculated, including the 0th node spinal base joint, the 1st node middle spine joint, the 2nd node neck joint, the 4th node left shoulder joint, the 5th node left elbow joint, the 6th node left wrist joint, the 7th node left palm joint, the 8th node right shoulder joint, the 9th node right elbow joint, the 10th node right wrist joint, the 11th node right palm joint, the 12th node left hip joint, the 13th node left knee joint, the 14th node left ankle joint, the 16th node right hip joint, the 17th node right knee joint, the 18th node right ankle joint and the 20th node cervical spine joint.

[0058] Among them, the 0th node spinal base joint is connected to the 12th node left hip joint and the 16th node right hip joint on the left and right, the 0th node spinal base joint is connected to the 1st node spinal middle joint upward, the 1st node spinal middle joint is connected to the 20th node subcervical spine joint, the 20th node subcervical spine joint is connected to the 4th node left shoulder joint and the 8th node right shoulder joint on the left and right, the 20th node subcervical spine joint is connected to the 2nd node neck joint upward, the 2nd node neck joint is connected to the 3rd node head joint, the 4th joint left shoulder joint is connected to the 5th node Node left elbow joint, the 5th node left elbow joint is connected to the 6th node left wrist joint, the 6th node left wrist joint is connected to the 7th node left palm joint and the 22nd node left thumb joint, the 7th node left palm joint is connected to the 21st node left middle finger joint, the 8th node right shoulder joint is connected to the 9th node right elbow joint, the 9th node right elbow joint is connected to the 10th node right wrist joint, the 10th node right wrist joint is connected to the 11th node right palm joint and the 24th node right thumb joint, the 11th node right palm joint is connected to the 23rd node right middle finger joint.

[0059] The Kinect v2 sensor is used to obtain human image data and depth data, and the skeleton tracking in Kinect is used to extract the movements of the motion capture personnel when performing the work, and present them in real time in the viewport, recording the angle data of the skeleton points.

[0060] First, map the human skeleton coordinates to the Kinect space coordinate system. Assume that the coordinates of a joint point are represented as (x i ,y i ,z i ), where i = the 0th joint, the 1st joint, the 2nd joint ... the 24th joint, the three-dimensional coordinate information of the joints in the human body space coordinate system OXYZ (where O refers to the origin of the Kinect camera space, located at the center of the Kinect infrared camera, the X-axis direction is the left direction along the Kinect's irradiation direction, the Y-axis direction is the upward direction along the Kinect's irradiation direction, and the Z-axis direction is along the Kinect's irradiation direction); R'(x i ',y i ',z i ') is the three-dimensional coordinate information of the human joint in the Kinect V2 device space coordinate system O'X'Y'Z', R' is R(x i ,y i ,z i ) is mapped to the three-dimensional coordinate information under O'X'Y'Z', and the mapping process is performed according to the following formula:

[0061]

[0062] get:

[0063]

[0064] Where x0', y0', z0' represent the three-dimensional position information of the "0th node spine base joint (Spine Base)" node in the Kinect V2 spatial coordinate system; α(α∈[-70,70]) represents the rotation angle of the human body relative to the XOY plane of the device space coordinate system. It is common to all joints in the calculation process. The positions of the two joints, "12th node left hip joint point (12.Hip Left)" and "16th node right hip joint point (16.HipRight)", are symmetrical relative to the Y axis. The coordinates of these two joints in the device space coordinate system are (x 12 ',y 12 ',z 12 ') and (x 16 ',y 16 ',z 16 '), so α is calculated through the coordinate information of the left and right hip joints of the human body.

[0065] Establish the coronal, sagittal and transverse planes of the target human body, and project the target joints onto the planes respectively; first construct the forward vector of the human body: select the three joint points of "1.spinemiddle", "4.leftshoulder" and "8.rightshoulder" as the base points, determine a plane D, and calculate the vector perpendicular to the plane D based on the point "1.spinemiddle" as the forward vector of the human body. In this way, the coronal, sagittal and transverse planes of the human body can be obtained. Coronal plane: plane D is the coronal plane. Sagittal plane: the plane formed by the "forward vector of the human body" and "1.spinemiddle-20.spineshoulder" is the sagittal plane. Transverse plane: the plane perpendicular to the "1.spinemiddle-20.spineshoulder vector" based on the point "1.spinemiddle" is the transverse plane.

[0066] Assume that the three-dimensional coordinates of "1.spinemiddle", "4.leftshoulder" and "8.rightshoulder" are (x1,y1,z1), (x4,y4,z4) and (x8,y8,z8) respectively, then the equation of the coronal plane is:

[0067]

[0068] The forward vector of the human body is:

[0069]

[0070] Suppose the three-dimensional coordinates of "20.spine shoulder" are (x 20 ,y 20 ,z 20 ), then the equation of the sagittal plane is:

[0071]

[0072] Will Denoted as A, Denoted as B, Let C be the equation of the sagittal plane, then it can be simplified as:

[0073]

[0074] The normal vector of the cross section is (x 20 -x1,y 20 -y1,z 20 -z1), so the equation of the cross section is:

[0075] (x 20 -x1)(x-x1)+(y 20 -y1)(y-y1)+(z 20 -z1)(z-z1)=0

[0076] Then perform vertex projection: project each joint point onto three surfaces to obtain the "projected human skeleton" based on these three surfaces. Suppose the three-dimensional coordinates of a joint point are (x i ,y i ,z i ), then the coordinates of the projection point of the joint point to the coronal plane (x i1 ,y i1 ,z i1 ), (x i1 ,y i1 ,z i1 ) is (x i +At1,y i +Bt1,z i +Ct1), where t1 is the parameter of the straight line equation that passes through the joint point and is perpendicular to the coronal plane. Substituting the coordinates of the projection point into the plane equation, we get:

[0077]

[0078] Similarly, the coordinates of the projection point of the joint point to the sagittal plane (x i2 ,y i2 ,z i2 ), (x i2 ,y i2,z i2 )for Where t2 is the parameter of the straight line equation that passes through the joint and is perpendicular to the sagittal plane. Substituting the coordinates of the projection point into the plane equation, we get:

[0079]

[0080] The coordinates of the projection point from the joint point to the cross section (x i3 ,y i3 ,z i3 ), (x i3 ,y i3 ,z i3 ) is (x i +(x 20 -x1)t3,y i +(y 20 -y1)t3,z i +(z 20 -z1)t3), where t3 is the parameter of the straight line equation that passes through the joint point and is perpendicular to the coronal plane. Substituting the coordinates of the projection point into the plane equation, we get:

[0081]

[0082] After obtaining the projection points of all joints, for each surface, the line connecting two adjacent joint points is regarded as a space vector. According to the cosine theorem, the vector angle, i.e., the joint angle, can be calculated. This joint angle is the component of human joint motion. The component vectors are used as evaluation sub-criteria in the evaluation process, occupying different proportions. After calculating the comfort of different projection surfaces of the target joint, the comfort of the target joint B is evaluated, such as Figure 5 shown.

[0083] Here, we take the bending angle of any target joint B (whose adjacent joints are joints A and C) as an example. The following formula is the bending angle θ of the projection component vector of joint B in space: BG In the process of obtaining θ, at this time, the obtained θ is in radians, which is converted into an angle value by the following formula for subsequent calculation of the joint torque.

[0084]

[0085] In the formula, (x BG ,y BG ,z BG ) is the projection point coordinate of the target joint point B of the human body, G=1,2,3; (x AG ,y AG ,z AG ) and (x CG ,y CG ,z CG) are the projection point coordinates of the adjacent joint points A and C of the target joint point B of the human body;

[0086] The target joint bending angle θ on different projection planes BG To standardize:

[0087]

[0088] The Body Basics module source code in Kinect SDK is redeveloped to output 30 frames of skeleton posture per second, each frame contains the angle data of each joint. The recognized frame-by-frame human motion joint coordinate sequence is output as a ".xlsx" file, such as Figure 4 The following is an output document sample, where each row is a frame of human body posture data, and each column represents the angle value of a joint (θ' BG ), and use red and blue shading to distinguish the left and right joint data respectively.

[0089] Then, the comfort of each target joint B on different projection surfaces is calculated using the comfort calculation formula: This is a method that uses relative joint torque to represent the comfort level of the joint. Relative joint torque refers to the ratio of the current actual joint torque to the maximum joint torque. The concept of relative joint torque can eliminate the influence of different maximum torques generated by different individuals and postures. The formula is defined as follows:

[0090]

[0091] In the formula, represents the comfort level of the target joint B on different projection surfaces, M BG ( α) Indicates the current actual joint torque of the target joint B. Where F is the operator's current workload (e.g., if the operator is carrying objects, F is the weight of the objects being carried); M Bmax ( α) Represents the maximum moment of the joint, which is a constant (M B(α) The maximum value of the function), that is, the torque of the joint when it is at the maximum activity angle.

[0092] Then follow Figure 5 The weighted coefficients obtained by the analytic hierarchy process (AHP for short, is one of the more basic models in the modeling competition. It mainly solves evaluation problems. The sum of each sub-weight coefficient is 1) are shown to calculate the comfort of the target joint B.

[0093]

[0094] In the formula, ω 1GRepresents the target joint comfort weights for the coronal, sagittal, and transverse planes.

[0095] The comfort of all target joints in the human body is superimposed to obtain the total comfort of the human body joints φ 总 :

[0096]

[0097] In the formula, Is the comfort of each joint; B It is the comfort weight of each joint, which is obtained through expert scoring hierarchical analysis method.

[0098] This is the result of the target joint comfort calculation, which is then used by the Unreal Engine and Kinect plug-in according to Figure 6 and Figure 7 The equations shown and Figure 8 The evaluation matrix shown in the figure is used to evaluate, calculate and output the comfort curve, and obtain the comfort of human joints. The output result is as follows Fig. 9 shown.

[0099] In particular, in some preferred embodiments of the present invention, a computer device is also provided, including a memory and a processor and a computer program stored in the memory, and when the processor executes the computer program, the steps of the human joint comfort calculation method based on Kinect in any of the above embodiments are implemented.

[0100] In some other preferred embodiments of the present invention, a computer-readable storage medium is provided, on which a computer program / instructions are stored. When the computer program is executed by a processor, the steps of the human joint comfort calculation method based on Kinect in any of the above embodiments are implemented.

[0101] Therefore, a new method for evaluating work comfort is proposed, which can provide data reference for improving standard operating procedures, reducing operator discomfort and alleviating the risk of work-related musculoskeletal diseases.

[0102] The above embodiments are preferred implementation modes of the present invention, but the implementation modes of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present invention should be equivalent replacement methods and are included in the protection scope of the present invention.

Claims

1. A method for calculating human joint comfort based on Kinect, characterized in that: The following steps are involved: Step 1: Build the Kinect plug-in usage environment in Unreal Engine and construct a human skeleton motion model; Step 2: Obtain the image of the operator, convert it into a depth image, identify the distribution of body parts through the Kinect plug-in, obtain the three-dimensional coordinates of each joint point in the human skeleton motion model, and present the human skeleton state in real time; obtain the current workload of the operator; Step 3: Establish the coronal plane, sagittal plane and transverse section of the human body, decompose and project the action angles of each joint of the human body to the coronal plane, sagittal plane and transverse section, and analyze them, and calculate the angles of the target joints; Step 4: Calculate the comfort level of the target joints of the human body; if the total comfort level is within the comfort range, it is determined that the operator is in a comfortable state.

2. The method for calculating human joint comfort based on Kinect according to claim 1, characterized in that: The three-dimensional coordinates of each joint point: In the formula, (x i ,y i ,z i ) is the three-dimensional coordinate of the i-th joint of the human body; (x' i ,y' i ,z' i ) is the three-dimensional coordinate information of the i-th joint of the human body in the Kinect device space coordinate system O'X'Y'Z'; Indicates the rotation angle of the human body relative to the XOY plane of the device space coordinate system, (x 12 ,y 12 ,z 12 ) and (x 16 ,y 16 ,z 16 ) are the three-dimensional coordinates of the left hip joint and the right hip joint respectively; (x0, y0, z0) are the three-dimensional coordinates of the spine base joint.

3. The method for calculating human joint comfort based on Kinect according to claim 1, characterized in that: The step 3 is specifically as follows: Step 3.1: Construct the target human body forward vector, select the middle joint point of the spine, the left shoulder joint point and the right shoulder joint point as base points, determine a plane D, and calculate the vector perpendicular to the plane D based on the middle joint point of the spine; Step 3.2: Establish the coronal, sagittal and transverse planes of the target human body. The coronal plane is plane D, the sagittal plane is the plane formed by the "human body forward vector" and the "middle spine-subcervical spine joint point vector", and the transverse plane is the plane based on the middle spine joint point perpendicular to the "middle spine-subcervical spine joint point vector". Project the joints of the human body onto the three planes respectively.

4. The method for calculating human joint comfort based on Kinect according to claim 1, characterized in that: The coordinates of the projection point (x i1 ,y i1 ,z i1 ) is (x i +Mt1,y i +Nt1,z i +Rt1); In the formula, (x1, y1, z1) are the three-dimensional coordinates of the middle joint of the spine; (x4, y4, z4) are the three-dimensional coordinates of the left shoulder joint; (x8, y8, z8) are the three-dimensional coordinates of the right shoulder joint; The coordinates of the projection point of the i-th joint of the human body to the sagittal plane (x i2 ,y i2 ,z i2 )for In the formula, (x 20 ,y 20 ,z 20 ) are the three-dimensional coordinates of the subcervical spine joints; The projection point of the human body's i-th joint to the cross section is (x i3 ,y i3 ,z i3 ) is (x i +(x 20 -x1)t3,y i +(y 20 -y1)t3,z i +(z 20 -z1)t3); 5. The method for calculating human joint comfort based on Kinect according to claim 4, characterized in that: The human target joint angle θ BG : In the formula, (x BG ,y BG ,z BG ) is the projection point coordinate of the target joint point B of the human body, G=1,2,3; (x AG ,y AG ,z AG ) and (x CG ,y CG ,z CG ) are the projection point coordinates of the adjacent joint points A and C of the target joint point B of the human body; For all target joint angles θ BG To standardize: Calculate the comfort of the target joint point B in the coronal, sagittal and transverse planes Where M BG is the current actual joint torque of the target joint point B of the human body, F is the operator’s current workload; M Bmax It represents the maximum torque of the target joint point B of the human body, that is, the torque at the maximum activity angle.

6. The method for calculating human joint comfort based on Kinect according to claim 5, characterized in that: Calculate the total comfort of the target joint point B In the formula, ω 1G Represents the target joint comfort weights for the coronal, sagittal, and transverse planes.

7. The method for calculating human joint comfort based on Kinect according to claim 6, characterized in that: Superimpose all target joint points to obtain the total comfort of human joints φ 总 : In the formula, ω B Represents the comfort weight of the target joint point B of the human body.

8. A computer device / equipment / system comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method for calculating human joint comfort based on Kinect according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instruction is executed by a processor, the steps of the method for calculating human joint comfort based on Kinect described in any one of claims 1 to 7 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that: When the computer program / instruction is executed by a processor, the steps of the method for calculating human joint comfort based on Kinect described in any one of claims 1 to 7 are implemented.

Images