Modeling method, manufacturing method, electronic device and storage medium of ear-wearable device

Abstract

The application provides a modeling method, a manufacturing method, an electronic device and a storage medium of an ear-wearing device. The modeling method comprises the following steps: obtaining three-dimensional point cloud data of a target region of the ear-wearing device; determining at least one calibration surface based on contour features of the target region; and constructing a three-dimensional curved surface corresponding to each calibration surface based on the three-dimensional point cloud data to obtain a three-dimensional model of the target region. The application obtains the three-dimensional point cloud data of the target region of the ear-wearing device, constructs a three-dimensional digital model matched with the target region based on the three-dimensional point cloud data and the contour features of the target region, increases the matching accuracy of the target region, and improves the user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of three-dimensional printing, and in particular to a modeling method and a manufacturing method of an ear-wearing device, an electronic device, and a storage medium. BACKGROUND

[0002] As a wearable product, earphones have large differences in individual physiological feature surfaces and unique shapes. At present, the earphone industry cannot design and produce a product suitable for all people. At present, in the earphone industry, the shell design data is large and difficult to modify, and there is no systematic digital design method. If the design is simply based on limited feature size data and subjective experience, it often cannot meet the needs. Traditional silicone manual mold turning has a certain failure rate and cannot stack structures, making it difficult to ensure yield. In related solutions, there are three-dimensional point cloud reconstruction methods based on feature templates or measurement and modeling methods for small curved surface parts, but these algorithms are complex and do not fit earphone curves.

[0003] Therefore, the related technology has the problem that the ear-wearing device does not match the individual physiological features of the user. SUMMARY

[0004] To solve the above technical problems or at least partially solve the above technical problems, the present application provides a modeling method and a manufacturing method of an ear-wearing device, an electronic device, and a storage medium.

[0005] In a first aspect, the present application provides a modeling method of an ear-wearing device, the method comprising:

[0006] obtaining three-dimensional point cloud data of a target region of the ear-wearing device;

[0007] determining at least one calibration surface based on contour features of the target region;

[0008] constructing a three-dimensional curved surface corresponding to each calibration surface based on the three-dimensional point cloud data to obtain a three-dimensional model of the target region.

[0009] In a second aspect, the present application provides a manufacturing method of an ear-wearing device, comprising: obtaining a three-dimensional model corresponding to the ear-wearing device, wherein the three-dimensional model is obtained by the method according to any one of the first aspect; and three-dimensionally printing the three-dimensional model to obtain the ear-wearing device.

[0010] In a third aspect, the present application provides an electronic device, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus.

[0011] The memory is used to store a computer program.

[0012] A processor for executing a computer program to implement the method steps of the first aspect or the second aspect.

[0013] In a fourth aspect, the present application provides a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the method steps of the first aspect or the second aspect.

[0014] In a fifth aspect, the embodiments of the present application further provide a computer program product containing instructions, which, when executed on a computer, cause the computer to perform the method steps of the first aspect or the second aspect.

[0015] The above technical solutions provided by the embodiments of the present application have the following advantages compared with related art:

[0016] The modeling method of the ear-wearable device provided by the embodiments of the present application can construct a modeling of the ear-wearable device matched with the individual physiological characteristics of the user by obtaining the three-dimensional point cloud data of the target region of the ear-wearable device, and constructing a three-dimensional digital model matched with the target region according to the three-dimensional point cloud data and the contour feature of the target region, so that the user can wear the ear-wearable device more closely, and the user experience is improved. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings, which are incorporated herein and constitute part of the specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced as follows, and obviously, other drawings can also be obtained by those skilled in the art without any creative labor.

[0019] Figure 1 A flowchart of a modeling method of an ear-wearable device provided by an embodiment of the present application;

[0020] Figure 2 A flowchart of a modeling method of an ear-wearable device provided by an embodiment of the present application;

[0021] Figure 3 A three-dimensional point cloud diagram of an ear contour provided by an embodiment of the present application;

[0022] Figure 4 A point cloud diagram of preprocessed three-dimensional point cloud data provided by an embodiment of the present application;

[0023] Figure 5 A diagram of fitting a calibration surface provided by an embodiment of the present application;

[0024] Figure 6 The outline provided for a specific embodiment of this application;

[0025] Figure 7 A schematic diagram of a three-dimensional model of an ear-worn device provided in a specific embodiment of this application;

[0026] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] Optionally, in this embodiment, the modeling method for the ear-worn device described above can be applied to a hardware environment consisting of a terminal and a server. The server connects to the terminal via a network and can be used to provide services to the terminal or clients installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services to the server.

[0029] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity), Bluetooth. The terminal is not limited to PC, mobile phone, tablet computer, etc.

[0030] The modeling method for the ear-worn device in this application embodiment can be executed by a server, a terminal, or both. Alternatively, the modeling method can be executed by a client installed on the terminal.

[0031] Taking the modeling method of the ear-worn device in this embodiment, executed by the server, as an example, Figure 1 This is a flowchart illustrating a modeling method for an ear-worn device provided in an embodiment of this application. Figure 1 As shown, the method includes the following steps:

[0032] Step S101: Obtain the three-dimensional point cloud data of the target area of ​​the ear-worn device;

[0033] Preferably, the target region of the ear-wearable device is at least a part of the region of the ear-wearable device that needs to be modeled, which can correspond to at least a part of the inner contour of the user's ear, and the three-dimensional point cloud data of the target region can be obtained by scanning the 3D point cloud of the inner contour of the ear, such as by a three-dimensional laser scanner.

[0034] Further, after obtaining the three-dimensional point cloud data, noise points in the three-dimensional point cloud data are filtered out in a bilateral filtering manner. In this embodiment, the obtained three-dimensional point cloud data can contain bad points, such as point clouds outside the range of the model, point clouds with obvious convexities or concavities, and missing points due to scanning angle problems, which can be removed from the point cloud by bilateral filtering. The bilateral filtering used needs to consider both the spatial domain and the value domain.

[0035] In this embodiment, different densities of point clouds can be generated due to scanning and measurement errors, which is not conducive to local point cloud feature extraction and affects point cloud matching accuracy. By removing bad points in the point cloud through bilateral filtering and taking a weighted average of neighboring sampling points to adjust the position of the current sampling point, the weight in the dimension is improved. The weighted average algorithm obtains a value under the spatial domain and the value domain, which needs to traverse all points to make it smoother, and the condition is that the point cloud is limited, which can maximize the preservation of geometric feature information and avoid over-smoothing of the fitted surface while retaining the effective point cloud on both sides of the surface.

[0036] In step S102, at least one calibration plane is determined based on the contour feature of the target region.

[0037] In this embodiment, the target region is divided into multiple contour planes based on the contour feature of the target region, and a calibration plane is set for each contour plane. The more calibration planes are set, the more accurate the shape contour of the model of the target region will be.

[0038] Optionally, the contour feature of the target region is the inner contour of the ear, and based on the physiological shape of the inner contour of the ear and the sudden change of the inner surface of the ear, the inner contour of the ear can be divided into at least three parts, i.e., the region near the helix foot, the region near the concha cavity, and the region near the external auditory canal opening. Based on this, the planes where the helix foot, the concha cavity, and the external auditory canal opening are located are set as calibration planes. In this embodiment, the calibration planes for the helix foot, the concha cavity, and the external auditory canal opening are selected through experimental comparison, which is the minimum calculation on the basis of meeting the model features.

[0039] Of course, in other embodiments, the three calibration surfaces described above are not limited to be used, and the number of calibration surfaces can also be one, two, or more, and the positions of the calibration surfaces are not limited to the three positions of the tragus foot, the concha cavity, and the external auditory canal opening, and the specific selection can be made according to actual needs, which are not limited here.

[0040] In step S103, a three-dimensional surface corresponding to each calibration surface is constructed based on the three-dimensional point cloud data, so as to obtain a three-dimensional model of the target region.

[0041] Optionally, the three-dimensional surface corresponding to each calibration surface is fitted by using the collected three-dimensional point cloud data, and then the surface fitting is performed on the plurality of three-dimensional surfaces corresponding to the plurality of calibration surfaces, so as to obtain the three-dimensional model matched with the target region. It can be understood that the three-dimensional model in the embodiment is a shell model of the ear-wearing device.

[0042] The modeling method of the ear-wearing device provided in the embodiment of the present application can obtain the three-dimensional point cloud data of the target region of the ear-wearing device, construct a three-dimensional digital model matched with the target region according to the three-dimensional point cloud data and the contour feature of the target region, so as to construct a modeling of the ear-wearing device matched with the individual physiological characteristics of the user, and the user can wear it more closely, thereby improving the user experience.

[0043] In the embodiment of the present application, a possible implementation manner is provided, and the above step S103 includes the following steps:

[0044] In step S201, a target contour corresponding to a target calibration surface of the three-dimensional point cloud data is determined, and a boundary constraint of the target contour is determined; wherein the target calibration surface is each of the at least one calibration surface;

[0045] In order to wear comfortably, the contour of the ear-wearing device needs to be slightly smaller than the contour of the human ear, so the contour corresponding to the three-dimensional point cloud data needs to be reduced in size. In the specific implementation, the determination of the target contour of the three-dimensional point cloud data corresponding to the target calibration surface in the above step S201 includes the following steps:

[0046] In step S301, an initial contour of the three-dimensional point cloud data on the target calibration surface is determined.

[0047] Further, the above step S301 includes the following steps: determining an original contour of the three-dimensional point cloud data on the target calibration surface; and performing offset processing on the original contour to obtain the initial contour.

[0048] The original contour, i.e., the contour of the three-dimensional point cloud data on the target calibration surface, is an unprocessed contour. Taking the helix foot as an example, the intersection line (i.e., the original contour) is formed between the helix foot contour of the three-dimensional point cloud data and the calibration surface. A preset distance (for example, 0.5-0.7 mm) offset is performed, i.e., a size reduction is performed, to obtain an offset contour (i.e., the initial contour) after the offset. Through this step, the initial contour corresponding to each calibration surface can be obtained.

[0049] In step S302, a plurality of feature points on the initial contour are extracted; wherein the plurality of feature points are a plurality of curvature feature points.

[0050] According to the above embodiment, after obtaining the initial contour after the offset, the average curvature on the intersection line between the calibration surface and the initial contour is calculated, the point with the smallest average curvature radius is the point with the largest curvature radius of the corresponding region in the target region, i.e., the surface transition point, so as to obtain the plurality of feature points on the initial contour.

[0051] It should be noted that the number of feature points is not limited, and different calibration surfaces can select different numbers of feature points. The more the number is, the more accurate it is, but generally it is sufficient to represent the curvature mutation. If the number of points is too large, the accuracy is not much improved, but the calculation amount is large.

[0052] In step S303, the plurality of feature points are connected to obtain a target contour.

[0053] That is, the plurality of feature points with curvature representation are connected together through the connection processing to obtain the target contour which can reflect the overall trend of the initial contour.

[0054] Through the above steps, the target contour corresponding to each calibration surface can be obtained, so as to realize the purpose that the shape contour of the ear-wearing device is slightly smaller than the contour of the human ear.

[0055] Further, the boundary constraint for determining the target contour in step S201 includes the following steps:

[0056] In step S401, a feature projection distance of the target contour is determined; wherein the feature projection distance has a corresponding relationship with the contour feature corresponding to the target calibration surface.

[0057] The feature projection distance in the embodiment is the maximum projection distance between any two feature points on the target contour, which can be used to determine the ear size in actual application, such as small ear, medium ear, large ear, super large ear, etc., and can be obtained through Gaussian kernel function fitting.

[0058] After the data points are introduced based on the Gaussian kernel function, the Gaussian kernel functions generated in the function space need to be fitted, i.e., the combination coefficients are optimized, and the maximum projection distance can be obtained by directly solving the linear equation set.

[0059] In step S402, the boundary constraint corresponding to each feature point is determined based on the feature projection distance and the plurality of feature points.

[0060] The boundary constraint in this embodiment is used to further define the accurate range of the three-dimensional point cloud data. It can be understood that the number of points in the point cloud is large, and the feature points and the corresponding boundary constraints can be used to accurately simplify the point cloud data, so that the accuracy of the obtained three-dimensional model is higher and the number is controllable.

[0061] Further, the boundary constraint includes a plurality of boundary constraints, and has a one-to-one correspondence with the plurality of feature points.

[0062] The above step S402 includes the following steps:

[0063] In step S501, the size level of the ear-wearable device is determined based on the feature projection distance.

[0064] In this embodiment, the size level of the ear-wearable device corresponds to the ear size, such as small ear, medium ear, large ear, and super large ear.

[0065] In step S502, the boundary constraint corresponding to each feature point is determined based on the association between the size level and the boundary constraint.

[0066] That is, in some application scenarios, the association between the different size levels and the boundary constraints can be pre-stored according to past data calculation, experience, etc., and the boundary constraint can be calculated based on the association when needed.

[0067] In step S202, the three-dimensional point cloud data is simplified based on the target contour and the boundary constraint.

[0068] In this embodiment, the three-dimensional point cloud data is simplified based on the target contour and the determined boundary constraint, so as to retain the point cloud within the target contour and the boundary constraint, and kick out the point cloud outside the range, so as to improve the accuracy of the three-dimensional model of the target region.

[0069] In step S203, the three-dimensional point cloud data after the simplification is reconstructed into a three-dimensional surface corresponding to the target calibration surface, so as to obtain a three-dimensional model of the target region.

[0070] In specific implementation, the above step S203 includes: performing surface reconstruction based on the plurality of feature points to obtain a reconstructed surface corresponding to each feature point; and performing joint processing on the reconstructed surfaces corresponding to the plurality of feature points to obtain a three-dimensional surface corresponding to the target calibration surface.

[0071] Further, taking the target feature point as a center point, a target point cloud is filtered from the three-dimensional point cloud data after simplification based on a boundary constraint corresponding to the target feature point, wherein the target feature point is each of the plurality of feature points; and a three-dimensional surface corresponding to each feature point is fitted by using the target point cloud corresponding to each feature point.

[0072] For example, taking the helix crura contour as an example, after obtaining the target contour corresponding to the helix crura, a mathematical model is established by combining the Greedy Algorithm, taking the target contour of the helix crura as a reference and taking the feature projection maximum distance as a boundary constraint, and the feature points in the point cloud that do not meet the requirements are removed, and the surface is reconstructed and fitted based on the simplified point cloud to obtain a plurality of CAD models. In this embodiment, the boundary constraint refers to a constraint taking each feature point as a center and taking the feature projection distance corresponding to the feature point as a boundary constraint distance. Based on each feature point, a plurality of surfaces can be fitted, the surfaces of different feature points are connected, more combinations are generated, and a plurality of three-dimensional surfaces corresponding to each feature point are fitted.

[0073] In an optional embodiment of the present case, the three-dimensional surface corresponding to the target calibration surface includes a plurality of alternative three-dimensional surfaces, and the step S203 includes the following steps:

[0074] Step S601: reconstructing the three-dimensional point cloud data after simplification into a three-dimensional surface corresponding to the target calibration surface;

[0075] Step S602: determining a plurality of alternative three-dimensional surfaces from the three-dimensional surface corresponding to the target calibration surface according to a first preset quality parameter;

[0076] Since one calibration surface corresponds to a plurality of feature points, and each feature point can correspond to a fitted three-dimensional surface, a plurality of alternative three-dimensional surfaces can be fitted for one calibration surface; further, according to a preset surface quality parameter (i.e., the first preset quality parameter described above), that is, a parameter set according to the requirement for the surface quality, the five three-dimensional surfaces with the best quality are selected from the plurality of alternative three-dimensional surfaces;

[0077] Step S602: determining a plurality of alternative three-dimensional surfaces from the three-dimensional surface corresponding to the target calibration surface according to a first preset quality parameter;

[0078] Step S603: performing surface fitting on the target alternative three-dimensional surface corresponding to the target calibration surface and the alternative three-dimensional surface corresponding to each calibration surface except the target calibration surface in the at least one calibration surface to obtain a plurality of alternative three-dimensional models corresponding to the target region, wherein the target alternative three-dimensional surface is each of the plurality of alternative three-dimensional surfaces;

[0079] For each alternative three-dimensional surface corresponding to each calibration surface, an alternative three-dimensional model can be fitted from the alternative three-dimensional surface corresponding to each calibration surface in the other calibration surface, so that a plurality of alternative three-dimensional surfaces corresponding to the target region are fitted.

[0080] In step S604, a three-dimensional model of the target region is determined from the plurality of candidate three-dimensional models according to a second preset quality parameter.

[0081] According to the preset model quality parameter (i.e., the second preset quality parameter described above), a three-dimensional model with the best quality is selected from the plurality of candidate three-dimensional models as the final three-dimensional model of the target region.

[0082] Preferably, the number of calibration surfaces in the embodiment is at least two, and the step S103 further includes: constructing at least two three-dimensional curved surfaces corresponding to the at least two calibration surfaces based on the three-dimensional point cloud data; and splicing the at least two three-dimensional curved surfaces to obtain the three-dimensional model of the target region.

[0083] Preferably, the number of calibration surfaces in the embodiment is at least two, and the step S103 further includes: constructing at least two three-dimensional curved surfaces corresponding to the at least two calibration surfaces based on the three-dimensional point cloud data; and splicing the at least two three-dimensional curved surfaces to obtain the three-dimensional model of the target region.

[0084] In the embodiment, the curved surface is reconstructed by segment fitting and splicing, and based on the at least two calibration surfaces, a three-dimensional curved surface corresponding to each calibration surface is fitted, and then the three-dimensional model is obtained by fitting the three-dimensional curved surfaces corresponding to all the calibration surfaces, which can improve the efficiency and accuracy of curved surface reconstruction.

[0085] Based on the modeling method of the ear-wearing device provided in the above embodiments and based on the same inventive concept, in the embodiment, a modeling method of an ear-wearing device is further provided.

[0086] A manufacturing method of an ear-wearing device is also provided, which is used to implement the above embodiments and preferred embodiments, and will not be described again.

[0087] The manufacturing method of the ear-wearing device provided in the embodiment includes the following steps:

[0088] According to the modeling method of the ear-wearing device, a three-dimensional model corresponding to the ear-wearing device is obtained.

[0089] The three-dimensional model is subjected to three-dimensional printing to obtain the ear-wearing device. The three-dimensional printing method used can be DLP, SLA, LCD, FDM, etc., which is not limited here.

[0090] Through the manufacturing method of the ear-wearing device provided in the application, the earphone modeling digital design method based on the application of 3D printing can provide a 3D printing earphone modeling digital design method for different individual physiological characteristics, increase the accuracy of curved surface matching, improve the model processing efficiency, reduce the production cycle, and provide better user experience and product advantages.

[0091] The method provided in the application will be further described below in combination with a specific embodiment:

[0092] In the specific embodiment, the modeling curve of the earphone product is matched with the physiological feature curve of the human body, so that the earphone product can be worn more closely. The specific embodiment mainly includes the flowchart as shown in Figure 2 The flowchart includes the following steps.

[0093] S1, collecting source data;

[0094] The 3D point cloud of the inner contour of the ear is obtained by scanning. The point cloud data can be obtained by a three-dimensional laser scanner. As shown in Figure 3 As shown in Figure 3 The 3D point cloud of the inner contour of the ear provided by the specific embodiment of the present application is shown in the figure.

[0095] S2, preprocessing;

[0096] The 3D point cloud data is preprocessed, such as removing bad points, denoising, simplifying, fitting, etc., as shown in Figure 4

[0097] S3, constructing a digital model;

[0098] Based on the physiological shape of the inner contour of the ear, according to the curvature mutation, the inner contour of the ear can be divided into three parts, i.e., the area near the helix foot, the area near the concha cavity, and the area near the external auditory canal. Therefore, the planes where the helix foot, the concha cavity, and the external auditory canal are located are set as calibration planes, three segments of surfaces corresponding to the three areas are fitted based on the three calibration planes, and then the three segments of surfaces are spliced to obtain a complete inner contour surface, as shown in Figure 5

[0099] The fitting method of each calibration plane corresponding to a segment of surface is similar, only the specific features are different, and the helix foot is taken as the calibration plane for detailed description below.

[0100] S701, in order to facilitate wearing, the earphone contour needs to be slightly smaller than the human ear contour, so the boundary contour on the calibration plane can be offset by 0.5-0.7mm, the point with the smallest average curvature radius on the intersection line of the calibration plane and the offset contour is obtained by calculation, which is the maximum point of the curvature radius of the inner surface in the corresponding area, i.e., the transition point of the surface, and the coordinates of the feature points P1, P2, P3, P4, P5, and P6 can be obtained.

[0101] S702, the relative distance between P2 and P5 can obtain the maximum projection distance D of the concha cavity. D can determine the ear size as small ear, medium ear, large ear, and super large ear, and D will be used as the fitting value of the Gaussian kernel function.

[0102] After a certain amount of data points are brought in, the Gaussian kernel functions generated in the function space need to be fitted, and the solution is obtained based on this.

[0103] ​​It should be noted that for the calibration surface corresponding to the antihelix foot and the external auditory canal, the relative distance between the two selected feature points is the point corresponding to the maximum projection distance of the antihelix foot and the point corresponding to the maximum projection distance of the external auditory canal, respectively.

[0104] S703, the spatial coordinates of P1 to P6 are introduced into the CAD software to sequentially connect and construct a first-order spline curve, as shown in Figure 6 The point distance threshold corresponding to each feature point P1 to P6 is obtained according to the above, which can be based on the arithmetic square root of the difference between the vectors of any two feature points, the maximum projection distance D of the concha cavity, the spatial coordinates of the feature points, the spatial coordinates of the points near the feature points, etc.

[0105] S704, taking the first-order spline curve as a reference and the point distance threshold as a boundary constraint, a mathematical model is established by combining GreedyAlgorithm to eliminate feature points in the point cloud that do not meet the requirements, and the surface is reconstructed and fitted based on the simplified point cloud to obtain a plurality of CAD models.

[0106] The boundary constraint in this step refers to the constraint with the corresponding point distance threshold as the boundary distance with the feature point as the center. Specifically, the points in the point cloud within the corresponding point distance threshold of the feature point are retained, and the other points are eliminated.

[0107] In addition, based on each feature point, a plurality of surfaces can be fitted, and more combinations will occur when the surfaces of different feature points are connected.

[0108] The quality of each model surface is analyzed, and the final model is selected, and the physical parameterization modeling is performed to obtain a CAD model that meets the requirements of 3D printing, as shown in Figure 7 .

[0109] In this step, the reconstructed surface can be determined based on the first preset quality parameter, for example, the reconstructed surface can be tested by observing the zebra stripes and measuring the gap between adjacent surfaces, the curvature change, and the rate of change. The quality of the surface can be analyzed and evaluated by observing the zebra stripes of the surface with the naked eye, automatically detecting the radius of curvature by software, etc.

[0110] For the software automatic measurement method, the following steps can be implemented:

[0111] ① Define the standard: set the gap between adjacent surfaces, the rate of change, and the range of curvature change according to the requirements, for example, the gap between adjacent surfaces <0.005mm, the rate of change <0.16°, and the curvature change <0.005° according to the A-level surface requirements;

[0112] ② Compare and calculate the generated model surfaces, delete the surfaces that do not meet the requirements, and sort the surfaces that meet the requirements according to the quality, for example, the top three surfaces (if any) can be retained;

[0113] ③Based on the second preset quality parameter, a final model of the ear-wearable device is determined, specifically, gap analysis is performed on the original human ear model that is not offset in the pre-processed model in step S2, and a model with more uniform gaps is selected as the final model. This is because the final model is obtained by appropriate offset, and compared with the initial point cloud model in step 2 (which can be considered as obtained after scanning the human ear structure, without offset), a model with more uniform offset distance is found to better meet the requirements.

[0114] S4, 3D printing rapid prototyping.

[0115] That is, based on the three-dimensional model obtained by the above steps, 3D printing is performed to obtain a physical earphone shell.

[0116] Through the above implementation steps, the embodiments of the present application can realize analyzing each reconstructed surface, fitting the final model on the surface that meets the requirements, and modeling the physical parameters; the reconstructed surface is tested by observing the zebra pattern and measuring the gap between adjacent surfaces, the curvature change and the rate of change; in this way, the surface matching accuracy can be increased; in addition, in related technologies, if the model surface quality does not meet the requirements after analysis, optimization needs to be performed on the basis of the original model, the segmented surface reconstruction of the present application can directly obtain multiple CAD models, and then the quality is selected, in this way, the model processing efficiency is improved, the production cycle is reduced, and better user experience and product advantages are provided.

[0117] As shown in Figure 8 the embodiments of the present application provide an electronic device, which includes a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112 and the memory 113 complete mutual communication through the communication bus 114,

[0118] the memory 113 is used to store a computer program;

[0119] In an embodiment of the present application, the processor 111 is used to execute the program stored in the memory 113, and realizes the modeling method of the ear-wearable device or the manufacturing method of the ear-wearable device provided by any one of the preceding method embodiments.

[0120] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the steps of the modeling method of the ear-wearable device or the manufacturing method of the ear-wearable device provided by any one of the preceding method embodiments.

[0121] It has to be noted that, in the present document, relational terms are intended only to convey a possible relationship between elements or

[0122] The foregoing is considered as illustrative only of the principles of the application. Numerous modifications and changes will readily occur to those skilled in the art, which modifications and changes are to be understood as intended to be encompassed by the general scope of the application. Accordingly, the application is not to be limited to the above described or illustrated embodiments, but is intended to encompass all embodiments consistent with the principles of the application.

Claims

1. A method of modeling an ear-wearable device, the method comprising: The method comprises: acquiring three-dimensional point cloud data of a target region of the ear-wearable device; determining at least one calibration surface based on contour features of the target region; constructing a three-dimensional curved surface corresponding to each of the calibration surfaces based on the three-dimensional point cloud data to obtain a three-dimensional model of the target region, comprising: determining an initial contour of the three-dimensional point cloud data on a target calibration surface, extracting a plurality of feature points on the initial contour, the plurality of feature points being a plurality of curvature feature points, performing line connection processing on the plurality of feature points to obtain a target contour, and determining boundary constraints of the target contour, the target calibration surface being each of the at least one calibration surface; performing simplification processing on the three-dimensional point cloud data based on the target contour and the boundary constraints; and reconstructing the three-dimensional point cloud data after the simplification processing into a three-dimensional curved surface corresponding to the target calibration surface to obtain a three-dimensional model of the target region. In the step of determining the boundary constraints of the target contour, the method comprises: determining a feature projection distance of the target contour, the feature projection distance having a corresponding relationship with the contour features corresponding to the target calibration surface; obtaining the boundary constraints corresponding to each of the feature points based on the feature projection distance and the plurality of feature points; determining a size level of the ear-wearable device based on the feature projection distance; and determining the boundary constraints corresponding to each of the feature points based on an association relationship between the size level and the boundary constraints, the boundary constraints including a plurality of boundary constraints and having a one-to-one correspondence with the plurality of feature points.

2. The method of claim 1, wherein, After acquiring the three-dimensional point cloud data of the target region associated with the ear-wearable device, the method further comprises: using a bilateral filtering method to filter out noise points in the three-dimensional point cloud data.

3. The method of claim 1, wherein, The step of determining the initial contour of the three-dimensional point cloud data on the target calibration surface comprises: determining an original contour of the three-dimensional point cloud data on the target calibration surface; performing offset processing on the original contour to obtain the initial contour.

4. The method of claim 1, wherein, The step of reconstructing the three-dimensional point cloud data after the simplification processing into a three-dimensional curved surface corresponding to the target calibration surface comprises: performing curved surface reconstruction based on the plurality of feature points to obtain a reconstructed curved surface corresponding to each of the feature points; performing joint processing on the reconstructed curved surfaces corresponding to the plurality of feature points to obtain a three-dimensional curved surface corresponding to the target calibration surface.

5. The method of claim 4, wherein, The step of performing curved surface reconstruction based on the plurality of feature points to obtain a reconstructed curved surface corresponding to each of the feature points comprises: taking a target feature point as a center point, and screening a target point cloud from the three-dimensional point cloud data after the simplification processing based on the boundary constraints corresponding to the target feature point, wherein the target feature point is each of the plurality of feature points; fitting to obtain a three-dimensional curved surface corresponding to each of the feature points using the target point cloud corresponding to each of the feature points.

6. The method of claim 4, wherein, The three-dimensional curved surface corresponding to the target calibration surface comprises a plurality of alternative three-dimensional curved surfaces; and the step of reconstructing the three-dimensional point cloud data after the simplification processing into a three-dimensional curved surface corresponding to the target calibration surface to obtain a three-dimensional model of the target region comprises: reconstruct the three-dimensional point cloud data after the simplification processing into a three-dimensional curved surface corresponding to the target calibration surface; determine a plurality of candidate three-dimensional curved surfaces from the three-dimensional curved surface corresponding to the target calibration surface according to a first preset quality parameter; perform curved surface fitting on the target candidate three-dimensional curved surface corresponding to the target calibration surface and the candidate three-dimensional curved surfaces corresponding to the calibration surfaces other than the target calibration surface among the at least one calibration surface, to obtain a plurality of candidate three-dimensional models corresponding to the target region, wherein the target candidate three-dimensional curved surface is each of the plurality of candidate three-dimensional curved surfaces; determine the three-dimensional model of the target region from the plurality of candidate three-dimensional models according to a second preset quality parameter.

7. The method of claim 1, wherein, The number of calibration surfaces is at least two, and the step of constructing a three-dimensional curved surface corresponding to each calibration surface based on the three-dimensional point cloud data to obtain a three-dimensional model of the target region comprises: constructing at least two three-dimensional curved surfaces corresponding to at least two calibration surfaces based on the three-dimensional point cloud data; splicing the at least two three-dimensional curved surfaces to obtain a three-dimensional model of the target region.

8. The method of any one of claims 1-7, wherein: the contour feature includes at least one of a helix crus, a concha cavity, and an external auditory canal opening, and the at least one calibration surface includes a plane in which at least one of the helix crus, the concha cavity, and the external auditory canal opening is located.

9. A method for manufacturing an ear-worn device, characterized in that, The method comprises: obtaining a three-dimensional model corresponding to the ear-wearing device, wherein the three-dimensional model is obtained by the method according to any one of claims 1-8; three-dimensionally printing the three-dimensional model to obtain the ear-wearing device.

10. An electronic device, comprising: comprise: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory is configured to store a computer program; the processor is configured to execute the computer program to implement the method steps of any one of claims 1-9.

11. A computer readable storage medium, characterized in that, The computer program is stored in the computer readable storage medium, and the computer program is executed by the processor to implement the method steps of any one of claims 1-9. The computer program is stored in the computer readable storage medium, and the computer program is executed by the processor to implement the method steps of any one of claims 1-9.

Images