Symmetric modeling method and device for human skeleton model, medium and equipment

Abstract

The invention provides a symmetric modeling method and device for a human skeleton model, a medium and equipment. The method comprises the following steps: constructing a curved surface image of a human skeleton based on a three-dimensional model image; recognizing a symmetric center point cloud in the curved surface image to obtain a median sagittal plane of the curved surface image; the vertex point clouds of the triangular patches are symmetrical to the other side with respect to the median sagittal plane, and symmetrical point clouds are obtained; based on the vertex point cloud and the symmetric point cloud, calculating to obtain a target point cloud; constructing a human skeleton model based on the target point cloud; a curved surface image is constructed based on a three-dimensional model image, vertex point clouds of triangular patches in the curved surface image are symmetrical to the other side about a median sagittal plane to obtain symmetrical point clouds, target point clouds are obtained according to the vertex point clouds and the symmetrical point clouds, and therefore a human body skeleton model is constructed. The real human skeleton structure can be guaranteed to the maximum extent, the workload of skeleton finite element model construction can be reduced, and the stability and reliability of finite element simulation are improved.

Description

Technical Field

[0001] The present application relates to the technical field of constructing a human skeleton model, and in particular to a symmetric modeling method, device, medium and equipment for a human skeleton model. Background Art

[0002] The human body geometric model is usually a three-dimensional model generated by processing high-precision human medical images. The data of existing digital models are all collected from real human bodies. However, although the human body's skeletal structure is symmetrically distributed along the mid-sagittal plane as a whole, it is not strictly symmetrical and has a large number of personalized features. When performing finite element modeling on the geometric model, one side of the bone is usually selected for modeling, and the human body skeletal model is formed by mirror symmetry, which lacks authenticity and theoretical basis. Therefore, it is necessary to build a model that can truly reflect the human body's skeletal structure. Summary of the invention

[0003] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a symmetric modeling method, device, medium and equipment for a human skeleton model.

[0004] According to one aspect of the present application, a symmetric modeling method for a human skeleton model is provided, comprising: acquiring a three-dimensional model image of a human skeleton; constructing a curved surface image of the human skeleton based on the three-dimensional model image; wherein the curved surface image comprises a plurality of triangular facets; identifying a symmetry center point cloud in the curved surface image, and generating a mid-sagittal plane of the curved surface image based on the symmetry center point cloud; symmetricizing the vertex point cloud of the triangular facet to the other side about the mid-sagittal plane to obtain a symmetric point cloud; calculating a target point cloud based on the vertex point cloud and the symmetric point cloud; and constructing a human skeleton model based on the target point cloud.

[0005] In one embodiment, the step of symmetrically adjusting the vertex point cloud of the triangular facet about the midsagittal plane to the other side to obtain a symmetrical point cloud includes: symmetrically adjusting the left vertex point cloud of the triangular facet on the left side of the midsagittal plane to the right side of the midsagittal plane to obtain a left symmetrical point cloud; symmetrically adjusting the right vertex point cloud of the triangular facet on the right side of the midsagittal plane to the left side of the midsagittal plane to obtain a right symmetrical point cloud; the step of calculating the target point cloud based on the vertex point cloud and the symmetrical point cloud includes: calculating the right target point cloud based on the right vertex point cloud and the left symmetrical point cloud; calculating the left target point cloud based on the left vertex point cloud and the right symmetrical point cloud.

[0006] In one embodiment, the calculation of the right target point cloud based on the right vertex point cloud and the left symmetrical point cloud includes: calculating the average value of the right vertex point cloud and the left symmetrical point cloud to obtain the right target point cloud; the calculation of the left target point cloud based on the left vertex point cloud and the right symmetrical point cloud includes: calculating the average value of the left vertex point cloud and the right symmetrical point cloud to obtain the left target point cloud.

[0007] In one embodiment, the calculating the average value of the right vertex point cloud and the left symmetrical point cloud to obtain the right target point cloud includes: calculating the right difference between the right vertex point cloud and the left symmetrical point cloud; if the right difference is greater than a preset difference threshold, calculating the average value of the right vertex point cloud and the left symmetrical point cloud to obtain the right target point cloud; the calculating the average value of the left vertex point cloud and the right symmetrical point cloud to obtain the left target point cloud includes: calculating the left difference between the left vertex point cloud and the right symmetrical point cloud; if the left difference is greater than the difference threshold, calculating the average value of the left vertex point cloud and the right symmetrical point cloud to obtain the left target point cloud.

[0008] In one embodiment, the calculation of the average value of the right vertex point cloud and the left symmetrical point cloud to obtain the right target point cloud includes: symmetric the left target point cloud about the mid-sagittal plane to the right side of the mid-sagittal plane to obtain a modified left symmetrical point cloud; calculating the modified left difference between the right target point cloud and the modified left symmetrical point cloud; if the modified left difference is greater than the difference threshold, updating the right target point cloud again based on the right target point cloud and the modified left symmetrical point cloud; the calculation of the average value of the left vertex point cloud and the right symmetrical point cloud to obtain the left target point cloud includes: symmetric the right target point cloud about the mid-sagittal plane to the left side of the mid-sagittal plane to obtain a modified right symmetrical point cloud; calculating the modified right difference between the left target point cloud and the modified right symmetrical point cloud; if the modified right difference is greater than the difference threshold, updating the left target point cloud again based on the left target point cloud and the modified right symmetrical point cloud.

[0009] In one embodiment, the target point cloud is calculated based on the vertex point cloud and the symmetric point cloud, including: calculating an average point cloud based on the vertex point cloud and the symmetric point cloud; constructing a loss function of the vertex point cloud based on the vertex point cloud and the average point cloud; wherein the loss function represents the difference between the registered vertex point cloud and the average point cloud; calculating the registration function of the vertex point cloud so that the loss function is less than a preset value; wherein the registration function represents the correspondence between the vertex point cloud and the registered vertex point cloud; and calculating the target point cloud based on the vertex point cloud and the registration function.

[0010] In one embodiment, the calculation of the target point cloud based on the vertex point cloud and the symmetric point cloud also includes: calculating multiple spatial angles formed between each vertex point cloud and multiple surrounding point clouds; if the sum of the multiple spatial angles is less than a preset angle threshold, deleting the vertex point cloud.

[0011] According to another aspect of the present application, a symmetric modeling device for a human skeleton model is provided, comprising: a three-dimensional image acquisition module for acquiring a three-dimensional model image of a human skeleton; a surface image construction module for constructing a surface image of the human skeleton based on the three-dimensional model image; wherein the surface image comprises a plurality of triangular facets; a mid-sagittal plane recognition module for identifying a symmetry center point cloud in the surface image, and generating a mid-sagittal plane of the surface image based on the symmetry center point cloud; a symmetry point cloud computing module for symmetrically arranging the vertex point cloud of the triangular facet to the other side about the mid-sagittal plane to obtain a symmetric point cloud; a target point cloud computing module for calculating a target point cloud based on the vertex point cloud and the symmetry point cloud; and a skeleton model construction module for constructing a human skeleton model based on the target point cloud.

[0012] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute any of the above methods.

[0013] According to another aspect of the present application, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; and the processor is used to execute any of the above-described methods.

[0014] The present application provides a symmetric modeling method, device, medium and equipment for a human skeleton model, which obtain a three-dimensional model image of a human skeleton; construct a curved surface image of the human skeleton based on the three-dimensional model image; wherein the curved surface image includes multiple triangular facets; identify a symmetry center point cloud in the curved surface image, and generate a mid-sagittal plane of the curved surface image based on the symmetry center point cloud; symmetric point cloud of the vertex point cloud of the triangular facet is made symmetrical to the other side about the mid-sagittal plane to obtain a symmetric point cloud; based on the vertex point cloud and the symmetric point cloud, a target point cloud is calculated; based on the target point cloud, a human skeleton model is constructed; that is, a curved surface image is constructed based on the three-dimensional model image, and the vertex point cloud of the triangular facet in the curved surface image is made symmetrical to the other side about the mid-sagittal plane to obtain a symmetric point cloud, and a target point cloud is obtained based on the vertex point cloud and the symmetric point cloud, thereby constructing a human skeleton model, and by symmetrically processing the bone tissue, not only can the real human skeleton structure be guaranteed to the maximum extent, but also the workload of constructing a bone finite element model can be reduced, and the stability and reliability of finite element simulation can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0016] Figure 1 It is a flowchart of a method for symmetric modeling of a human skeleton model provided by an exemplary embodiment of the present application.

[0017] Figure 2 It is a structural schematic diagram of the sagittal plane in the human skeleton model provided by an exemplary embodiment of the present application.

[0018] Figure 3 It is a structural schematic diagram of a method for deleting a vertex point cloud of a human skeleton model provided by an exemplary embodiment of the present application.

[0019] Figure 4 It is a structural schematic diagram of a symmetric modeling device for a human skeleton model provided by an exemplary embodiment of the present application.

[0020] Figure 5 It is a structural diagram of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0021] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0022] Figure 1 FIG. 1 is a flow chart of a method for symmetric modeling of a human skeleton model provided by an exemplary embodiment of the present application. Figure 1 As shown, the symmetric modeling method of the human skeleton model includes the following steps: Step 110: Acquire a three-dimensional model image of a human skeleton.

[0023] This application can use a Micro-CT instrument to scan the human body, and obtain a CT tomographic image according to the required clarity. The different grayscales in the tomographic image express the boundaries of different tissues in the human body. The three-dimensional model images of different tissues in the human body can be obtained through three-dimensional image processing software. This application uses three-dimensional image processing software to perform grayscale segmentation on CT tomographic images. The accuracy of the segmentation depends on the resolution during scanning. The CT tomographic image is displayed as square units of different grayscales in the three-dimensional image processing software. The three-dimensional model of a single tissue or organ can be obtained by selecting and extracting the squares of the same grayscale. If only a part of the boundary of the tissue or organ falls within the square unit, an error will occur. At this time, it is necessary to rely on manual adjustment for preprocessing, and the generated three-dimensional model image is preliminarily checked for surface smoothness and repaired.

[0024] Step 120: constructing a surface image of the human skeleton based on the three-dimensional model image.

[0025] Among them, the surface image includes multiple triangular facets. The present application uses 3D image processing software to output the segmented 3D model image into STL format and import it into the geometric surface reconstruction software, converting the 3D model image into a NURBS surface to convert the surface features of the polygonal 3D model into a limited number of triangular facets. The outer contour surface of the human skeleton model is composed of a series of triangular facets. The number and size of the triangular facets depend on the accuracy required by the human skeleton model. The data formed by each vertex of the triangular facet is the vertex point cloud, which represents the spatial coordinate values ​​of all triangular facets. The present application can also perform secondary corrections on the 3D reverse reconstruction software NURBS surface to remove or redistribute unreasonable triangular facets and output the final surface image.

[0026] Step 130: Identify the symmetry center point cloud in the curved surface image, and generate the mid-sagittal plane of the curved surface image based on the symmetry center point cloud.

[0027] The bones in the surface image usually obtained are asymmetrical, so it is necessary to select a symmetry plane to straighten the model. The present application selects multiple symmetry center point clouds in the surface image, such as the front surface center point of each cone of the human spine, the rear tail process point, the surface projection point of the pelvic geometric center point, and the upper and lower vertices of the skull as the symmetry center point cloud, and obtains the human body mid-axis plane from the skull to the sacrum in the human skeleton model based on the multiple symmetry center point clouds, that is, the mid-sagittal plane (such as Figure 2 As shown in the figure). Since the human skeleton model in the curved image is composed of triangular facets, the selected symmetric center point cloud is the vertex of the triangular facets. In the process of registering to the mid-sagittal plane, the shape of the triangular facets contained in the symmetric center point cloud will change, but the arrangement of the triangular facets will not change. The registration algorithm iterates the symmetric midline point cloud to continuously approach the mid-sagittal plane.

[0028] Step 140: Symmetrically align the vertex point cloud of the triangular patch to the other side about the mid-sagittal plane to obtain a symmetrical point cloud.

[0029] After determining the mid-sagittal plane of the curved image, the present application symmetrizes the triangular facets on one side to the other side based on the mid-sagittal plane to obtain a symmetrical point cloud, so as to determine whether the triangular facets on both sides of the mid-sagittal plane are symmetrical, and to make corrections if they are asymmetrical to achieve a symmetrical result.

[0030] Step 150: Calculate and obtain a target point cloud based on the vertex point cloud and the symmetric point cloud.

[0031] When the difference between the symmetrical point cloud and the corresponding vertex point cloud is large, the target point cloud is obtained by comprehensive calculation based on the vertex point cloud and the symmetrical point cloud to correct the original vertex point cloud, thereby obtaining vertex point cloud data symmetrical about the mid-sagittal plane.

[0032] Step 160: Construct a human skeleton model based on the target point cloud.

[0033] After calculating the target point cloud, the present application constructs a symmetrical human skeleton model based on the target point cloud to improve the stability and authenticity of the model.

[0034] The present application provides a symmetric modeling method for a human skeleton model, which comprises the following steps: obtaining a three-dimensional model image of a human skeleton; constructing a curved surface image of the human skeleton based on the three-dimensional model image; wherein the curved surface image comprises a plurality of triangular facets; identifying a symmetry center point cloud in the curved surface image, and generating a mid-sagittal plane of the curved surface image based on the symmetry center point cloud; symmetricizing the vertex point cloud of the triangular facets about the mid-sagittal plane to the other side to obtain a symmetric point cloud; calculating a target point cloud based on the vertex point cloud and the symmetric point cloud; and constructing a human skeleton model based on the target point cloud; namely, constructing a curved surface image based on the three-dimensional model image, and symmetricizing the vertex point cloud of the triangular facets in the curved surface image to the other side to obtain a symmetric point cloud, and obtaining a target point cloud based on the vertex point cloud and the symmetric point cloud, thereby constructing a human skeleton model. By symmetrically processing the bone tissue, not only can the real human skeleton structure be guaranteed to the greatest extent, but also the workload of constructing a bone finite element model can be reduced, thereby improving the stability and reliability of finite element simulation.

[0035] In one embodiment, the specific implementation method of the above step 140 can be: the left vertex point cloud of the triangular facet on the left side of the midsagittal plane is symmetrical about the midsagittal plane to the right side of the midsagittal plane to obtain a left symmetrical point cloud; the right vertex point cloud of the triangular facet on the right side of the midsagittal plane is symmetrical about the midsagittal plane to the left side of the midsagittal plane to obtain a right symmetrical point cloud; the specific implementation method of the above step 150 can be: based on the right vertex point cloud and the left symmetrical point cloud, calculate the right target point cloud; based on the left vertex point cloud and the right symmetrical point cloud, calculate the left target point cloud.

[0036] The present application respectively symmetrizes the left vertex point cloud of the left triangular patch of the midsagittal plane to the right side and the right vertex point cloud of the right triangular patch of the midsagittal plane to the left side to obtain a left-side symmetrical point cloud and a right-side symmetrical point cloud, and combines the right vertex point cloud and the left-side symmetrical point cloud to calculate the right-side target point cloud, and combines the left vertex point cloud and the right-side symmetrical point cloud to calculate the left-side target point cloud, so as to realize the correction of the left vertex point cloud and the right vertex point cloud, thereby realizing the symmetry of the left target point cloud and the right target point cloud.

[0037] In one embodiment, the specific implementation method of the above step 150 can be: calculate the average value of the right vertex point cloud and the left symmetrical point cloud to obtain the right target point cloud; calculate the average value of the left vertex point cloud and the right symmetrical point cloud to obtain the left target point cloud.

[0038] The present application can respectively calculate the average value of the right vertex point cloud and the left symmetrical point cloud, and the average value of the left vertex point cloud and the right symmetrical point cloud, to obtain the right target point cloud and the left target point cloud, that is, to correct the current vertex point cloud with the average value of the current vertex point cloud and the symmetrical point cloud obtained symmetrically on the other side, so as to reduce the symmetric deviation between the left vertex point cloud and the right vertex point cloud. Preferably, the present application can adopt the average value correction and then symmetry again, and then combine the corrected vertex point cloud calculation average value, and continuously reduce the symmetric deviation between the left vertex point cloud and the right vertex point cloud through multiple iterative corrections, until the symmetric deviation between the left vertex point cloud and the right vertex point cloud is close to zero, that is, the symmetry between the left vertex point cloud and the right vertex point cloud is achieved.

[0039] In one embodiment, the specific implementation method of the above step 150 can be: calculate the right side difference between the right vertex point cloud and the left symmetrical point cloud; if the right side difference is greater than a preset difference threshold, calculate the average value of the right vertex point cloud and the left symmetrical point cloud to obtain the right side target point cloud; calculate the left side difference between the left vertex point cloud and the right symmetrical point cloud; if the left side difference is greater than the difference threshold, calculate the average value of the left vertex point cloud and the right symmetrical point cloud to obtain the left side target point cloud.

[0040] The present application calculates the right side difference between the right vertex point cloud and the left side symmetrical point cloud. If the right side difference is greater than the preset difference threshold, it means that the symmetry deviation between the left vertex point cloud and the right vertex point cloud is large. Then the average value of the right vertex point cloud and the left side symmetrical point cloud is calculated, and the average value is used as the new right side target point cloud; if the right side difference is less than or equal to the difference threshold, it means that the symmetry deviation between the left vertex point cloud and the right vertex point cloud is small, and there is no need to correct the right vertex point cloud. Similarly, the left side difference between the left vertex point cloud and the right side symmetrical point cloud is calculated. If the left side difference is greater than the difference threshold, it means that the symmetry deviation between the right vertex point cloud and the left vertex point cloud is large. Then the average value of the left vertex point cloud and the right side symmetrical point cloud is calculated to obtain the left side target point cloud; if the left side difference is less than or equal to the difference threshold, it means that the symmetry deviation between the right vertex point cloud and the left vertex point cloud is small, and there is no need to correct the left vertex point cloud.

[0041] In one embodiment, the specific implementation method of the above step 150 can be: symmetric the left target point cloud about the midsagittal plane to the right side of the midsagittal plane to obtain a corrected left symmetrical point cloud; calculate the corrected left difference between the right target point cloud and the corrected left symmetrical point cloud; if the corrected left difference is greater than the difference threshold, then update the right target point cloud based on the right target point cloud and the corrected left symmetrical point cloud again; symmetric the right target point cloud about the midsagittal plane to the left side of the midsagittal plane to obtain a corrected right symmetrical point cloud; calculate the corrected right difference between the left target point cloud and the corrected right symmetrical point cloud; if the corrected right difference is greater than the difference threshold, then update the left target point cloud based on the left target point cloud and the corrected right symmetrical point cloud again.

[0042] After calculating the left target point cloud, the present application again symmetrizes the left target point cloud about the mid-sagittal plane to the right side of the mid-sagittal plane to obtain a corrected left symmetrical point cloud, and calculates the corrected left difference between the right target point cloud and the corrected left symmetrical point cloud; if the corrected left difference is greater than the difference threshold, the right target point cloud is again updated based on the right target point cloud and the corrected left symmetrical point cloud. Similarly, after calculating the right target point cloud, the right target point cloud is again symmetrized about the mid-sagittal plane to the left side of the mid-sagittal plane to obtain a corrected right symmetrical point cloud; calculates the corrected right difference between the left target point cloud and the corrected right symmetrical point cloud; if the corrected right difference is greater than the difference threshold, the left target point cloud is again updated based on the left target point cloud and the corrected right symmetrical point cloud. Through multiple iterative corrections, the symmetry deviation between the left vertex point cloud and the right vertex point cloud is continuously reduced until the symmetry deviation between the left vertex point cloud and the right vertex point cloud is close to zero, that is, the symmetry between the left vertex point cloud and the right vertex point cloud is achieved.

[0043] In one embodiment, the specific implementation method of the above step 150 may be: based on the vertex point cloud and the symmetric point cloud, an average point cloud is calculated; based on the vertex point cloud and the average point cloud, a loss function of the vertex point cloud is constructed; wherein the loss function represents the difference between the registered vertex point cloud and the average point cloud; the registration function of the vertex point cloud is calculated so that the loss function is less than a preset value; wherein the registration function represents the correspondence between the vertex point cloud and the registered vertex point cloud; based on the vertex point cloud and the registration function, a target point cloud is calculated.

[0044] Specifically, the present application can divide the vertex point cloud of the human skeleton into several parts according to the structure, including the head, upper limbs, pelvis, lower limbs, etc. Taking one of the parts as an example, the vertex point cloud set of the part (the vertex point cloud on one side of the mid-sagittal plane) is recorded as , the symmetrical point cloud set obtained by symmetrically converting the vertex point cloud on the other side of the midsagittal plane is , where X contains N points and V contains K points. The number of N and K can be the same or different. When N=K, the number of triangles formed by the vertex point cloud and the target point cloud is the same, and the spatial arrangement of the triangles in a certain area is also highly similar. When N≠K, the number of triangles formed by the vertex point cloud and the target point cloud is different, and the spatial arrangement of the triangles in a certain area is also different, but the geometric similarity of the surface formed by the triangles will not be greatly affected. The purpose of point cloud registration is to find an optimal three-dimensional coordinate space transformation function f , so that the following loss function value is minimized, that is, the spatial distance between each vertex point cloud in the set and the target point is minimized, and the bones on both sides are transformed through coordinates and iterative calculations to achieve the purpose of symmetry of the vertex point clouds on both sides. The constructed loss function is as follows: ; in, v a Represents any point in V, 1≤ a ≤K, f ( v a ) is the point cloud after the vertex point cloud is transformed, y a For v a The corresponding target point cloud, Represents the target point cloud X and f ( v a ), and are the set constants, T is the temperature coefficient, It is a spatial transformation f Smoothness constraint.

[0045] in, y a The calculation formula is as follows: ; in, ; T is the temperature coefficient, which is used to control the accuracy of point cloud registration. T The smaller the value, the higher the registration accuracy; represent x i and f(v a ) The greater the distance, m ai The smaller.

[0046] Preferably, the present application adds a filter coefficientq , in order to filter out the points with large distortion, so that the triangular face of the human skeleton model is as smooth as possible, and add the filtering coefficient q The loss function after is: .

[0047] In one embodiment, the specific implementation method of the above step 150 may be: calculating multiple spatial angles formed between each vertex point cloud and multiple surrounding point clouds; if the sum of the multiple spatial angles is less than a preset angle threshold, deleting the vertex point cloud.

[0048] In the process of point cloud registration, this application adds a filter coefficient q , in order to filter out the points with large distortion, so that the triangular facets of the human skeleton model are as smooth as possible. Specifically, Figure 3 As shown, the present application calculates multiple spatial angles formed between each vertex point cloud and multiple surrounding point clouds. If the sum of the multiple spatial angles is less than a preset angle threshold, for example α+β +γ< 240 ° , it is considered that the vertex point cloud is severely distorted and the vertex point cloud is deleted.

[0049] Figure 4 Schematic diagram of the structure of a symmetric modeling device for a human skeleton model provided by an exemplary embodiment of the present application. Figure 4 As shown, the symmetric modeling device 40 of the human skeleton model includes: a three-dimensional image acquisition module 41, which is used to acquire a three-dimensional model image of the human skeleton; a surface image construction module 42, which is used to construct a surface image of the human skeleton based on the three-dimensional model image; wherein the surface image includes a plurality of triangular facets; a mid-sagittal plane recognition module 43, which is used to recognize the symmetry center point cloud in the surface image, and generate the mid-sagittal plane of the surface image based on the symmetry center point cloud; a symmetry point cloud computing module 44, which is used to symmetric the vertex point cloud of the triangular facet to the other side about the mid-sagittal plane to obtain a symmetric point cloud; a target point cloud computing module 45, which is used to calculate a target point cloud based on the vertex point cloud and the symmetry point cloud; a skeleton model construction module 46, which is used to construct a human skeleton model based on the target point cloud.

[0050] The present application provides a symmetric modeling device for a human skeleton model, wherein a three-dimensional image acquisition module 41 acquires a three-dimensional model image of a human skeleton; a curved surface image construction module 42 constructs a curved surface image of a human skeleton based on the three-dimensional model image; wherein the curved surface image includes a plurality of triangular facets; a mid-sagittal plane recognition module 43 recognizes a symmetric center point cloud in the curved surface image, and generates a mid-sagittal plane of the curved surface image based on the symmetric center point cloud; a symmetric point cloud computing module 44 calculates a symmetric point cloud by symmetrically transferring the vertex point cloud of the triangular facet to the other side about the mid-sagittal plane; and a target point cloud computing module 45 calculates a symmetric point cloud based on the vertex point cloud of the triangular facet. Point point cloud and symmetrical point cloud are used to calculate the target point cloud; the skeleton model construction module 46 constructs a human skeleton model based on the target point cloud; that is, a curved surface image is constructed based on the three-dimensional model image, and the vertex point cloud of the triangular facets in the curved surface image is symmetrical to the other side about the mid-sagittal plane to obtain a symmetrical point cloud, and the target point cloud is obtained according to the vertex point cloud and the symmetrical point cloud, so as to construct a human skeleton model. By symmetrically processing the bone tissue, it can not only maximize the real human skeleton structure, but also reduce the workload of constructing the bone finite element model, thereby improving the stability and reliability of the finite element simulation.

[0051] In one embodiment, the above-mentioned symmetrical point cloud computing module 44 can be further configured as: the left vertex point cloud of the triangular facet on the left side of the midsagittal plane is symmetrical about the midsagittal plane to the right side of the midsagittal plane, so as to obtain a left-side symmetrical point cloud; the right vertex point cloud of the triangular facet on the right side of the midsagittal plane is symmetrical about the midsagittal plane to the left side of the midsagittal plane, so as to obtain a right-side symmetrical point cloud; the above-mentioned target point cloud computing module 45 can be further configured as: based on the right vertex point cloud and the left symmetrical point cloud, the right target point cloud is calculated; based on the left vertex point cloud and the right symmetrical point cloud, the left target point cloud is calculated.

[0052] In one embodiment, the target point cloud computing module 45 can be further configured to: calculate the average value of the right vertex point cloud and the left symmetrical point cloud to obtain the right target point cloud; calculate the average value of the left vertex point cloud and the right symmetrical point cloud to obtain the left target point cloud.

[0053] In one embodiment, the target point cloud computing module 45 can be further configured as follows: calculating the right difference between the right vertex point cloud and the left symmetrical point cloud; if the right difference is greater than a preset difference threshold, calculating the average of the right vertex point cloud and the left symmetrical point cloud to obtain the right target point cloud; calculating the left difference between the left vertex point cloud and the right symmetrical point cloud; if the left difference is greater than the difference threshold, calculating the average of the left vertex point cloud and the right symmetrical point cloud to obtain the left target point cloud.

[0054] In one embodiment, the target point cloud computing module 45 can be further configured as follows: the left target point cloud is symmetrical about the midsagittal plane to the right side of the midsagittal plane to obtain a modified left symmetrical point cloud; the modified left difference between the right target point cloud and the modified left symmetrical point cloud is calculated; if the modified left difference is greater than the difference threshold, the right target point cloud is updated again based on the right target point cloud and the modified left symmetrical point cloud; the right target point cloud is symmetrical about the midsagittal plane to the left side of the midsagittal plane to obtain a modified right symmetrical point cloud; the modified right difference between the left target point cloud and the modified right symmetrical point cloud is calculated; if the modified right difference is greater than the difference threshold, the left target point cloud is updated again based on the left target point cloud and the modified right symmetrical point cloud.

[0055] In one embodiment, the target point cloud computing module 45 can be further configured as follows: based on the vertex point cloud and the symmetric point cloud, an average point cloud is calculated; based on the vertex point cloud and the average point cloud, a loss function of the vertex point cloud is constructed; wherein the loss function represents the difference between the registered vertex point cloud and the average point cloud; the registration function of the vertex point cloud is calculated so that the loss function is less than a preset value; wherein the registration function represents the correspondence between the vertex point cloud and the registered vertex point cloud; based on the vertex point cloud and the registration function, a target point cloud is calculated.

[0056] In one embodiment, the target point cloud computing module 45 can be further configured to: calculate multiple spatial angles formed between each vertex point cloud and multiple surrounding point clouds; if the sum of the multiple spatial angles is less than a preset angle threshold, delete the vertex point cloud.

[0057] Below, reference Figure 5 The electronic device according to the embodiment of the present application is described. The electronic device may be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device may communicate with the first device and the second device to receive the collected input signal from them.

[0058] Figure 5 A block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0059] like Figure 5 As shown, the electronic device 10 includes one or more processors 11 and a memory 12 .

[0060] The processor 11 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0061] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the methods of the various embodiments of the present application described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0062] In one example, the electronic device 10 may further include: an input device 13 and an output device 14 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0063] When the electronic device is a stand-alone device, the input device 13 may be a communication network connector, which is used to receive the collected input signals from the first device and the second device.

[0064] In addition, the input device 13 may also include, for example, a keyboard, a mouse, and the like.

[0065] The output device 14 can output various information to the outside, including the determined distance information, direction information, etc. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0066] Of course, to simplify, Figure 5 Only some of the components related to the present application in the electronic device 10 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 10 may also include any other appropriate components.

[0067] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

[0068] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0069] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the method according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0070] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0071] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0072] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0073] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0074] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0075] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A symmetric modeling method for a human skeleton model, characterized in that: include: Obtain a three-dimensional model image of a human skeleton; Based on the three-dimensional model image, construct a curved surface image of the human skeleton; wherein the curved surface image includes a plurality of triangular facets; Identifying a symmetric center point cloud in the curved surface image, and generating a mid-sagittal plane of the curved surface image based on the symmetric center point cloud; Symmetrically distribute the vertex point cloud of the triangular facet to the other side about the mid-sagittal plane to obtain a symmetrical point cloud; Based on the vertex point cloud and the symmetric point cloud, a target point cloud is calculated; Based on the target point cloud, a human skeleton model is constructed.

2. The symmetric modeling method of a human skeleton model according to claim 1, characterized in that: The step of symmetrically arranging the vertex point cloud of the triangular facet to the other side about the mid-sagittal plane to obtain a symmetrical point cloud comprises: The left vertex point cloud of the left triangular facet on the mid-sagittal plane is symmetrical about the mid-sagittal plane to the right side of the mid-sagittal plane to obtain a left symmetrical point cloud; The right vertex point cloud of the right triangular facet of the mid-sagittal plane is symmetrical about the mid-sagittal plane to the left side of the mid-sagittal plane to obtain a right symmetrical point cloud; The calculating the target point cloud based on the vertex point cloud and the symmetric point cloud comprises: Based on the right vertex point cloud and the left symmetric point cloud, a right target point cloud is calculated; Based on the left vertex point cloud and the right symmetric point cloud, a left target point cloud is calculated.

3. The symmetric modeling method of a human skeleton model according to claim 2, characterized in that: The calculating the right target point cloud based on the right vertex point cloud and the left symmetric point cloud comprises: Calculate the average value of the right vertex point cloud and the left symmetric point cloud to obtain the right target point cloud; The calculating the left target point cloud based on the left vertex point cloud and the right symmetric point cloud comprises: The average value of the left vertex point cloud and the right symmetric point cloud is calculated to obtain the left target point cloud.

4. The symmetric modeling method of a human skeleton model according to claim 3, characterized in that: The calculating the average value of the right vertex point cloud and the left symmetric point cloud to obtain the right target point cloud comprises: Calculating a right difference between the right vertex point cloud and the left symmetric point cloud; If the right side difference is greater than a preset difference threshold, then the average value of the right side vertex point cloud and the left side symmetric point cloud is calculated to obtain the right side target point cloud; The calculating the average value of the left vertex point cloud and the right symmetric point cloud to obtain the left target point cloud comprises: Calculating the left difference between the left vertex point cloud and the right symmetric point cloud; If the left difference is greater than the difference threshold, the average value of the left vertex point cloud and the right symmetric point cloud is calculated to obtain the left target point cloud.

5. The symmetric modeling method of a human skeleton model according to claim 4, characterized in that: The calculating the average value of the right vertex point cloud and the left symmetric point cloud to obtain the right target point cloud comprises: Symmetrically aligning the left target point cloud with respect to the mid-sagittal plane to the right side of the mid-sagittal plane to obtain a modified left symmetrical point cloud; Calculating a corrected left difference between the right target point cloud and the corrected left symmetric point cloud; If the corrected left difference is greater than the difference threshold, updating the right target point cloud again based on the right target point cloud and the corrected left symmetrical point cloud; The calculating the average value of the left vertex point cloud and the right symmetric point cloud to obtain the left target point cloud comprises: Symmetrically aligning the right target point cloud with respect to the mid-sagittal plane to the left side of the mid-sagittal plane, to obtain a modified right symmetrical point cloud; Calculating a corrected right side difference between the left side target point cloud and the corrected right side symmetric point cloud; If the modified right side difference is greater than the difference threshold, the left side target point cloud is updated again based on the left side target point cloud and the modified right side symmetric point cloud.

6. The symmetric modeling method of a human skeleton model according to claim 1, characterized in that: The calculating the target point cloud based on the vertex point cloud and the symmetric point cloud comprises: Based on the vertex point cloud and the symmetric point cloud, an average point cloud is calculated; Based on the vertex point cloud and the average point cloud, construct a loss function of the vertex point cloud; wherein the loss function represents the difference between the registered vertex point cloud and the average point cloud; Calculating a registration function of the vertex point cloud so that the loss function is less than a preset value; wherein the registration function represents a corresponding relationship between the vertex point cloud and the registered vertex point cloud; The target point cloud is obtained by calculation based on the vertex point cloud and the registration function.

7. The symmetric modeling method of a human skeleton model according to claim 6, characterized in that: The step of calculating the target point cloud based on the vertex point cloud and the symmetric point cloud further comprises: Calculate multiple spatial angles formed between each vertex point cloud and multiple surrounding point clouds; If the sum of the multiple spatial angles is less than a preset angle threshold, the vertex point cloud is deleted.

8. A symmetric modeling device for a human skeleton model, characterized in that: include: A three-dimensional image acquisition module, used to acquire a three-dimensional model image of a human skeleton; A curved surface image construction module, used to construct a curved surface image of the human skeleton based on the three-dimensional model image; wherein the curved surface image includes a plurality of triangular facets; A mid-sagittal plane recognition module, used to recognize a symmetric center point cloud in the curved surface image, and generate a mid-sagittal plane of the curved surface image based on the symmetric center point cloud; A symmetric point cloud computing module, used to symmetric the vertex point cloud of the triangular facet to the other side about the mid-sagittal plane to obtain a symmetric point cloud; A target point cloud computing module, used for computing a target point cloud based on the vertex point cloud and the symmetric point cloud; The skeleton model building module is used to build a human skeleton model based on the target point cloud.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is used to execute the method described in any one of claims 1 to 7.

Images