A personalized mannequin and its manufacturing method, system and device

Abstract

The present invention provides a personalized mannequin and its manufacturing method, system and device, which relates to the technical field of layered mannequins. The method mainly includes: collecting three-dimensional point cloud data of a human body sample; generating a three-dimensional model and extracting the text of the sagittal plane cross-section point cloud data of the human body; dividing the sagittal plane cross-section point cloud data into front and rear parts and writing them into the corresponding contour line data texts respectively; through a BP neural network, respectively fitting and predicting to obtain the optimal contour lines of the front and rear parts; calculating the zero-crossing points through the first derivative to determine the characteristic points of the front and rear parts; segmenting the three-dimensional model to obtain several human body components and corresponding processing data of the front and rear parts; sending the processing data to a sheet cutting device for manufacturing; and sequentially assembling and fixing the sheets on a positioning fixture to obtain a mannequin. This solution can significantly reduce the manufacturing cost while retaining personalized body shape information, and can quickly and accurately manufacture a professional layered mannequin that meets the requirements of clothing design.

Description

Technical Field

[0001] The present invention relates to the technical field of layered mannequins, and in particular, to a personalized mannequin and its manufacturing method, system and device. Background Art

[0002] With the increasing demand for the fit of clothing, the clothing industry has gradually introduced three-dimensional measurement technology to perform refined modeling of the human body. Existing refined human body models are mainly applied in the field of virtual fitting, but are rarely applied in the field of mannequins. The mannequin is a physical model made according to the usual proportions of the human body, which is convenient for clothing design and cutting production. However, it often has only fixed dimensions and cannot meet the personalized needs of consumers with different body types for made-to-measure (MTM) clothing.

[0003] Currently, there are personalized mannequins made by applying 3D printing technology. Although this personalized mannequin can reproduce the body shapes of different humans, the cost of this technology is relatively high, and the material is hard and rough, which is not suitable as a physical model for clothing design.

[0004] Therefore, there is an urgent need to develop a low-cost and high-precision manufacturing method for personalized mannequins to meet the actual needs of individual consumers for made-to-measure clothing and clothing design teaching. Summary of the Invention

[0005] The purpose of the present invention is to provide a personalized mannequin and its manufacturing method, system and device to solve at least one of the above technical problems existing in the prior art.

[0006] In a first aspect, to solve the above technical problems, the present invention provides a manufacturing method for a personalized mannequin, including the following steps:

[0007] Step 1: The client collects three-dimensional point cloud data of a human body sample through a three-dimensional human body scanner and sends it to the server together with the human body sample information; the three-dimensional point cloud data establishes a coordinate system with the axes in human anatomy: the Y-axis is the sagittal axis (referring to the axis from front to back of a standing human body and perpendicular to the vertical axis), the X-axis is the coronal axis (referring to the axis from left to right of a standing human body and perpendicular to both the sagittal axis and the vertical axis at the same time), and the Z-axis is the vertical axis (referring to the axis from head to tail of a standing human body and perpendicular to the ground plane); the human body sample information includes customer ID, name, age, weight, height, skin color, collection date, etc.;

[0008] In a feasible implementation manner, Step 1 specifically includes:

[0009] Step 11: Prepare a human body sample according to the requirements for 3D point cloud acquisition. The requirements for 3D point cloud acquisition include: wearing a white tight-fitting garment, a white swimming cap on the head, and removing accessories; separating the feet by 10 - 20 cm, standing upright with the head held high, parallel, and looking straight ahead; letting the forearms hang naturally, abducting the upper arms by 20° from the body, and making fists with both hands; maintaining normal breathing, etc.

[0010] Step 12: Use a 3D human body scanner to perform 3D scanning on the human body sample to obtain 3D point cloud data.

[0011] Step 13: After encrypting and compressing the 3D point cloud data, send it from the client to the server.

[0012] Through the above steps, in physical stores, experience stores, etc., 3D point cloud data of a customer's human body sample can be collected through a 3D human body scanner and sent to the server through the client, which is conducive to building a data foundation for personalized mannequin manufacturing; and fully protecting the privacy of the customer's body type information, etc.

[0013] Step 2: The server generates a 3D surface model from the 3D point cloud data and extracts the text of the sagittal plane cross-section point cloud data of the human body.

[0014] In a feasible implementation manner, the specific steps of Step 2 include:

[0015] Step 21: The server decompresses and decrypts the 3D point cloud data to generate a 3D surface model of the human body sample.

[0016] Step 22: Extract all the point cloud data with the X-axis coordinate of 0 in the 3D point cloud data, that is, the point cloud data on the reference plane where the center line of the left-right direction of the human body sample is located, as the text of the sagittal plane cross-section point cloud data.

[0017] Step 3: In the text of the sagittal plane cross-section point cloud data, use the point cloud at the minimum value of the Z-axis coordinate as the 3D origin, and take the vertical axis of this 3D origin as the reference to divide the sagittal plane cross-section point cloud data into two parts, namely, the two parts with the Y-axis coordinate y≥0 and the Y-axis coordinate y<0, and write them into the corresponding contour line data text respectively.

[0018] In a feasible implementation manner, the specific steps of Step 3 include:

[0019] Step 31: The server loads the text of the sagittal plane cross-section point cloud data, extracts the data in the second and third columns of the point cloud coordinates, and defines them as the Z-axis coordinate value z and the Y-axis coordinate value y respectively.

[0020] Step 32: Statistically calculate the minimum value min_Z of the Z-axis coordinate value z. The specific formula can be:

[0021] min_Z = min(z);

[0022] Step 33: Subtract min_Z from each z to obtain the updated coordinate value z' for determining the three-dimensional origin position. The specific formula can be:

[0023] z' = z - min_Z;

[0024] Step 34: Based on the vertical axis of the three-dimensional origin, through conditional indexing, divide the sagittal plane cross-sectional point cloud data into two parts, front and back, and write them into the corresponding contour line data text respectively:

[0025] The conditional indexing for the front part includes z > 0 and y ≥ 0;

[0026] The conditional indexing for the back part includes z > 0 and y < 0;

[0027] In this way, the sagittal plane cross-sectional point cloud data can be divided into two parts, front and back, for subsequent mannequin manufacturing respectively. Of course, the encoding and direction of the coordinate axes can also be changed according to actual needs for subsequent processing.

[0028] Step 4: Based on the contour line data text, respectively fit and predict the optimal contour lines for the front and back parts through a BP neural network.

[0029] In a feasible implementation manner, the training process of the BP neural network includes:

[0030] Step 41: The server loads the contour line data text, performs normalization processing, and then randomly divides it into a training set, a validation set, and a test set;

[0031] Step 42: Create a BP neural network:

[0032] The number of hidden layers (feedforwardnet) is set to 10 layers;

[0033] The number of training epochs (trainParam.epochs) is set to 1000;

[0034] The training target error (trainParam.goal) is set to 1e-5;

[0035] Step 43: Train the BP neural network until the correlation coefficient R values of the training set, the validation set, the test set, and the entire set are all greater than or equal to 0.9, so that the BP neural network has a reliable fitting and prediction ability.

[0036] Step 5: Based on the optimal contour lines, update the three-dimensional surface model, and calculate the zero-crossing points through the first derivative to determine the feature points of the front and back parts.

[0037] In a feasible implementation, the specific steps for determining the feature points in step 5 include:

[0038] Step 51: Calculate the first derivative of the optimal contour line;

[0039] Step 52: Take the zero-crossing points of the first derivative as feature points to reflect the changes of the optimal contour line;

[0040] Step 53: Output the number and coordinates of the feature points, and mark the first serial number and coordinate values of the feature points on the optimal contour line for visualization.

[0041] Preferably, the first serial number can be Roman numerals.

[0042] Preferably, the zero-crossing points in step 52 do not include the human face area, which can reduce the workload of subsequent processing without affecting the clothing design.

[0043] Step 6: Mark the feature points in the three-dimensional surface model; perform parallel slicing on the three-dimensional surface model with the cross-sectional planes at the Z-axis coordinate values of each feature point to obtain a number of feature cross-sections for the front and back parts; calculate the combination of plates for filling based on the distance between adjacent feature cross-sections, the type of plate, and the thickness of the plate; fill the layers of plates between the adjacent feature cross-sections of the front and back parts based on the combination of plates, and combine with the corresponding optimal contour line to obtain a number of human body parts; output the corresponding processing data based on the human body parts; the processing data includes the combination of plates, the third serial number, and the cutting contour line; the third serial number is used to distinguish the plates and can include the second serial number and the corresponding plate number; the cutting contour line is the circumferential contour line of the plate.

[0044] In a feasible implementation, step 6 specifically includes:

[0045] Step 61: Mark the feature points in the three-dimensional surface model through the coordinate values;

[0046] Step 62: Perform parallel slicing on the three-dimensional surface model with the cross-sectional planes at the Z-axis coordinate values of each feature point (when the three-dimensional surface model is in a vertical state, the cross-sectional plane is a horizontal plane) to obtain a number of feature cross-sections for the front and back parts;

[0047] Step 63: Starting from the cross-sectional plane where the three-dimensional origin is located, connect each feature cross-section in sequence;

[0048] Step 64: Calculate the combination of plates for filling based on the distance between adjacent feature cross-sections, the type of plate, and the thickness of the plate;

[0049] Step 65: Based on the sheet combination, fill the sheet layer between the adjacent feature cross-sections of the front and rear parts, and combine with the corresponding optimal contour line to obtain several human body parts; based on the human body parts, output the corresponding processing data; the processing data includes the sheet combination, the third serial number, and the cutting contour line; set positioning marks at the two-dimensional origin of each human body part, and the positioning marks include positioning symbols, the second serial number, and thickness marks; the positioning symbol is used to position the sheet of the human body part during the subsequent assembly of the fitting mannequin; the second serial number is used to distinguish the human body parts and is the first serial number of the feature points to which the feature cross-section belongs; the thickness mark is the first digit after the decimal point of the thickness value of the human body part, and the unit of the thickness value of the human body part is cm.

[0050] In a feasible implementation manner, the types of sheets include foam boards and PVC foam boards. This not only saves costs, but also these two types of sheets are soft in texture, not easily deformed, and elastic, which is beneficial for placing pins in the three-dimensional cutting of clothing design and can be reused; among them, foam boards are suitable for large-thickness cutting processing, and PVC foam boards are suitable for use as small-thickness filling layers.

[0051] The thickness of the sheets is as follows:

[0052] The thickness of the foam board is 1 cm.

[0053] The thickness of the PVC foam board is 0.1 cm, 0.2 cm, and 0.5 cm.

[0054] The specific method for calculating the sheet combination is as follows:

[0055] When the distance value H between adjacent feature cross-sections is an integer multiple A of 1 cm, the sheet combination is A foam boards.

[0056] When the distance value H between adjacent feature cross-sections is greater than the integer multiple A of 1 cm, calculate the difference value T1 between the two; then calculate the difference value T2 between T1 and 0.5 cm:

[0057] If T2 is equal to 0, the sheet combination is A foam boards and 1 PVC foam board with a thickness of 0.5 cm.

[0058] If T2 is not equal to 0, calculate the difference value T3 between T2 and an integer multiple B of 0.2 cm, and the specific formula is T3 = T2 - 0.2 * B.

[0059] If T3 is equal to 0, the sheet combination is A foam boards, 1 PVC foam board with a thickness of 0.5 cm, and B PVC foam boards with a thickness of 0.2 cm.

[0060] If T3 is not equal to 0, then take T3 as an integer multiple C of 0.1 cm, and the sheet combination is A foam boards, 1 PVC foam board with a thickness of 0.5 cm, B PVC foam boards with a thickness of 0.2 cm, and C PVC foam boards with a thickness of 0.1 cm;

[0061] When the distance value H between adjacent feature cross-sections is less than 1 cm, directly calculate the difference T2' between H and 0.5 cm:

[0062] If T2' is equal to 0, then the sheet combination is 1 PVC foam board with a thickness of 0.5 cm;

[0063] If T2' is not equal to 0, then calculate the difference T3' between T2' and an integer multiple B of 0.2 cm. The specific formula is T3' = T2' - 0.2 * B:

[0064] If T3' is equal to 0, then the sheet combination is 1 PVC foam board with a thickness of 0.5 cm and B PVC foam boards with a thickness of 0.2 cm;

[0065] If T3' is not equal to 0, then take T3' as an integer multiple C of 0.1 cm, and the sheet combination is 1 PVC foam board with a thickness of 0.5 cm, B PVC foam boards with a thickness of 0.2 cm, and C PVC foam boards with a thickness of 0.1 cm;

[0066] Through the above method, an optimized common sheet combination can be obtained, which is convenient for manufacturing a layered mannequin with fewer sheets and less sheet cutting time in the subsequent process, thereby improving the mannequin manufacturing efficiency and reducing the mannequin manufacturing cost.

[0067] Preferably, the positioning symbol includes a semi-cross structure, which is convenient for subsequent positioning and fixing of human body parts according to the positioning symbol.

[0068] Preferably, the positioning symbol further includes concave-convex structures arranged on both sides of the semi-cross structure, which are used to combine the sheets of the front and rear parts of the human body parts into one body by inserting the concave-convex structures, thereby avoiding the use of curing means such as glue bonding during the subsequent assembly of the mannequin and further reducing the cost.

[0069] Preferably, the concave-convex structure is a T-shaped structure, that is, a T-shaped protrusion is arranged on the sheet of the front part of the human body part, and a corresponding T-shaped groove is arranged on the sheet of the rear part of the human body part; of course, the reverse setting can also be carried out.

[0070] Preferably, the T-shaped structure also includes achieving an anti-misoperation effect by adjusting the length dimension to avoid using the wrong sheets between different mannequins in the future.

[0071] Step 7: The server sends the processing data to the sheet cutting equipment for manufacturing; the sheet cutting equipment is used to cut and manufacture each sheet corresponding to the human body part according to the shape of the optimal contour line, and cut the positioning holes on the sheet according to the shape of the positioning symbol; mark the third serial number on the sheet.

[0072] Step 8: Based on the third serial number, through the positioning holes at the positioning symbols, layer by layer and sequentially assemble each sheet of the human body part on the positioning fixture to obtain a mannequin for clothing design; mark the corresponding human body sample information on the mannequin for reference during subsequent clothing design.

[0073] In a second aspect, based on the same inventive concept, the present application further provides a manufacturing system adopting the above-mentioned personalized mannequin manufacturing method, including a client and a server;

[0074] The client is used to collect the three-dimensional point cloud data of the human body sample and send it to the server together with the human body sample information;

[0075] The server includes a data receiving module, a data processing module and a result generating module;

[0076] The data receiving module is used to receive the three-dimensional point cloud data and the human body sample information;

[0077] The data processing module includes a sagittal plane cross-section point cloud data unit, a contour line data text unit, a fitting prediction unit and a segmentation unit;

[0078] The sagittal plane cross-section point cloud data unit generates a three-dimensional surface model from the three-dimensional point cloud data and extracts the human body sagittal plane cross-section point cloud data text;

[0079] The contour line data text unit, in the sagittal plane cross-section point cloud data text, takes the point cloud at the minimum Z-axis coordinate as the three-dimensional origin, and takes the vertical axis of this three-dimensional origin as the reference, divides the sagittal plane cross-section point cloud data into two parts, front and back, and writes them into the corresponding contour line data text respectively;

[0080] The fitting prediction unit stores a BP neural network; based on the contour line data text, through the BP neural network, respectively fit and predict the optimal contour lines of the two parts, front and back;

[0081] The splitting unit updates the three-dimensional surface model based on the optimal contour line, calculates the zero-crossing points through the first derivative, and determines the feature points of the front and rear parts; marks the feature points in the three-dimensional surface model; performs parallel slicing on the three-dimensional surface model with cross-sectional planes at the Z-axis coordinate values of each feature point to obtain a number of feature cross-sections of the front and rear parts; calculates the sheet combination for filling based on the distance between adjacent feature cross-sections, the type of sheet material, and the thickness of the sheet material; fills the sheet layers between adjacent feature cross-sections of the front and rear parts based on the sheet combination, and combines with the corresponding optimal contour line to obtain a number of human body parts; outputs the corresponding processing data based on the human body parts.

[0082] The result generation module is used to send out the processing data and the human body sample information.

[0083] In a third aspect, based on the same inventive concept, the present application further provides a manufacturing device for a personalized mannequin, including a processor, a memory, and a bus. The memory stores instructions and data that can be read by the processor. The processor is used to call the instructions and data in the memory to execute a method for manufacturing a personalized mannequin as described above. The bus connects between the various functional components to transmit information.

[0084] In a feasible implementation manner, the manufacturing device further includes a three-dimensional human body scanner for performing three-dimensional scanning on the human body sample.

[0085] In a feasible implementation manner, the manufacturing device further includes a sheet cutting device for cutting out each sheet corresponding to the human body part in imitation of the shape of the optimal contour line, and cutting the positioning holes on the sheet in imitation of the shape of the positioning symbol.

[0086] In a feasible implementation manner, the manufacturing device further includes a positioning tooling for fixing each sheet corresponding to the human body part; the positioning tooling includes a base, a rotating disk, and a bracket.

[0087] The center of the lower surface of the rotating disk is pivotally connected to the center of the base; a clamping groove is provided at the center of the upper surface of the rotating disk; the bracket is vertically fixed at the clamping groove; the bracket cooperates with the positioning holes on the sheet.

[0088] Preferably, the positioning hole is a semi-cross structure (the positioning holes of the front and rear parts of the human body part sheet can correspond to form a complete cross structure), and the bracket is a cross structure, which is convenient for horizontal orientation and fixation of the human body part.

[0089] Fourthly, based on the same inventive concept, the present application further provides a personalized mannequin using the above-mentioned personalized mannequin manufacturing method. The personalized mannequin is divided into front and back parts by the coronal plane; each part is composed of multiple layers of plates combined along the vertical axis; the same positioning holes are provided at the two-dimensional origin of each plate.

[0090] In a feasible implementation manner, the personalized mannequin and the positioning tooling are combined into one. The positioning tooling includes a base, a rotating disk, and a bracket;

[0091] The center of the lower surface of the rotating disk is pivotally connected to the center of the base; a clamping groove is provided at the center of the upper surface of the rotating disk; the bracket is vertically fixed at the clamping groove; the bracket cooperates with the positioning holes on the plate.

[0092] By adopting the above technical solutions, the present invention has the following beneficial effects:

[0093] A personalized mannequin and its manufacturing method, system, and device provided by the present invention obtain three-dimensional point cloud data of a human body sample through three-dimensional human body scanning and construct a three-dimensional curved surface model; perform front-back segmentation and up-down layering operations on the three-dimensional curved surface model to generate processing data containing information such as plate combination; through the processing data, cut standard plates and assemble them into a complete and personalized layered mannequin. Compared with the prior art, this solution can significantly reduce the manufacturing cost of the mannequin while retaining the personalized body shape information of the customer, and can quickly and accurately manufacture a professional layered mannequin that meets the requirements of clothing design. Description of the Drawings

[0094] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0095] Figure 1 It is a flowchart of a manufacturing method of a personalized mannequin provided by an embodiment of the present invention;

[0096] Figure 2 It is an explanatory diagram of the human anatomy coordinate system in the prior art;

[0097] Figure 3 It is a schematic diagram of the sagittal plane cross-sectional point cloud provided by an embodiment of the present invention;

[0098] Figure 4R value diagrams of each data set related to the BP neural network for predicting and fitting the posterior contour line of the human body provided by the embodiments of the present invention: Among them, Figure a represents the training set, Figure b represents the validation set, Figure c represents the test set, and Figure d represents the entire set;

[0099] Figure 5 R value diagrams of each data set related to the BP neural network for predicting and fitting the anterior contour line of the human body provided by the embodiments of the present invention: Among them, Figure a represents the training set, Figure b represents the validation set, Figure c represents the test set, and Figure d represents the entire set;

[0100] Figure 6 Provided by the embodiments of the present invention Figure 3 Top view example diagram of the human body part at feature point a in the front part;

[0101] Figure 7 Manufacturing system diagram of a personalized dress form provided by the embodiments of the present invention;

[0102] Figure 8 Cross-sectional view of the positioning tooling for the personalized dress form provided by the embodiments of the present invention;

[0103] Figure 9 Stereogram of the positioning tooling for the personalized dress form provided by the embodiments of the present invention.

[0104] Reference numerals:

[0105] 1 - Base; 2 - Rotating disk; 3 - Bracket. Detailed implementation manners

[0106] Next, the technical solutions of the present invention will be clearly and completely described in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0107] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, the terms "first", "second", "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0108] In the description of the present invention, it should be noted that unless otherwise clearly specified and defined, the terms "installation", "connection", and "coupling" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be a direct connection or an indirect connection through an intermediate medium, and it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0109] The following further explains the present invention in conjunction with specific embodiments.

[0110] It should also be noted that the following specific embodiments or specific implementation manners are a series of optimized setting manners listed by the present invention to further explain the specific invention content, and these setting manners can be combined with each other or used in association with each other.

[0111] Embodiment 1:

[0112] As Figure 1 shown, a manufacturing method of a personalized mannequin provided in this embodiment includes the following steps:

[0113] Step 1: The client collects the three-dimensional point cloud data of the human body sample through a three-dimensional human body scanner and sends it to the server together with the human body sample information; the three-dimensional point cloud data establishes a coordinate system with the axes in human anatomy. As Figure 2 shown: The Y-axis is the sagittal axis (referring to the axis from front to back of a standing human body and perpendicular to the vertical axis), the X-axis is the coronal axis (referring to the axis from left to right of a standing human body and perpendicular to both the sagittal axis and the vertical axis at the same time), and the Z-axis is the vertical axis (referring to the axis from head to tail of a standing human body and perpendicular to the ground plane); the human body sample information includes customer ID, name, age, weight, height, skin color, collection date, etc.

[0114] Further, the specific content of Step 1 includes:

[0115] Step 11: Prepare the human body sample according to the three-dimensional point cloud collection requirements; the three-dimensional point cloud collection requirements include: wearing a white tight-fitting garment, wearing a white swimming cap, and removing accessories; feet separated by 10 - 20 cm, head held high, chest out, standing parallel, looking straight ahead; forearms hanging naturally, upper arms abducted at 20° with the body, hands clenched; maintaining normal breathing, etc.

[0116] Step 12: Use a three-dimensional human body scanner to perform three-dimensional scanning on the human body sample to obtain three-dimensional point cloud data; the three-dimensional human body scanner can use existing equipment.

[0117] Step 13: After encrypting and compressing the three-dimensional point cloud data, send it from the client to the server.

[0118] Through the above steps, in physical stores, experience stores, etc., 3D point cloud data of the customer's body sample can be collected through a 3D body scanner and sent to the server through the client, which is conducive to building a data foundation for personalized mannequin manufacturing; and fully protecting the privacy of the customer's body shape information, etc.

[0119] Step 2: The server generates a 3D surface model from the 3D point cloud data and extracts the text of the sagittal plane cross-section point cloud data of the human body.

[0120] Furthermore, the specific steps of Step 2 include:

[0121] Step 21: The server decompresses and decrypts the 3D point cloud data to generate a 3D surface model of the human body sample;

[0122] Step 22: As Figure 3 shown, extract all the point cloud data with the X-axis coordinate of 0 in the 3D point cloud data, that is, the point cloud data on the reference plane where the center line of the left and right directions of the human body sample is located, as the text of the sagittal plane cross-section point cloud data, which can be named Standard_Section_0.txt.

[0123] Step 3: In the text of the sagittal plane cross-section point cloud data, use the point cloud at the minimum value of the Z-axis coordinate as the 3D origin, and based on the vertical axis of this 3D origin, divide the sagittal plane cross-section point cloud data into two parts, namely the two parts with the Y-axis coordinate y≥0 and the Y-axis coordinate y<0, and write them into the corresponding contour line data text respectively.

[0124] Furthermore, the specific steps of Step 3 include:

[0125] Step 31: The server loads the text of the sagittal plane cross-section point cloud data and extracts the data in the second and third columns of the point cloud coordinates, which are respectively defined as the coordinate values of the Z-axis and the Y-axis;

[0126] Step 32: Statistically find the minimum value min_Z of the Z-axis coordinate value z. The specific formula can be:

[0127] min_Z = min(z);

[0128] Step 33: Subtract min_Z from each z to obtain the updated coordinate value z' for determining the position of the 3D origin. The specific formula can be:

[0129] z' = z - min_Z;

[0130] Step 34: Based on the vertical axis of this 3D origin, through conditional indexing, divide the sagittal plane cross-section point cloud data into two parts and write them into the corresponding contour line data text respectively:

[0131] The conditional index of the front part includes z > 0 and y ≥ 0;

[0132] The conditional index of the rear part includes z > 0 and y < 0;

[0133] In this way, the sagittal plane cross-sectional point cloud data can be divided into two parts, the front and the rear, for subsequent mannequin manufacturing respectively; of course, the coding and direction of the coordinate axes can also be changed according to actual needs for subsequent processing.

[0134] Step 4: Based on the contour line data text, respectively fit and predict the optimal contour lines of the front and rear parts through a BP neural network.

[0135] Furthermore, the training process of the BP neural network includes:

[0136] Step 41: The server loads the contour line data text, performs normalization processing, and then randomly divides it into a training set, a validation set, and a test set, with the specific division ratio being 14:3:3;

[0137] Step 42: Create a BP neural network:

[0138] The number of hidden layers (feedforwardnet) is set to 10 layers;

[0139] The number of training epochs (trainParam.epochs) is set to 1000;

[0140] The training target error (trainParam.goal) is set to 1e-5;

[0141] Step 43: Train the BP neural network until the correlation coefficient R values of the training set, the validation set, the test set, and the entire set are all greater than or equal to 0.9, so that the BP neural network has a reliable fitting and prediction ability:

[0142] As Figure 4 shown, Figure 4 in Figure a, the R value of the training set of the rear part contour line data text in the BP neural network is 0.99967; Figure 4 in Figure b, the R value of the validation set of the rear part contour line data text in the BP neural network is 0.9995; Figure 4 in Figure c, the R value of the training set of the rear part contour line data text in the BP neural network is 0.99973; Figure 4 in Figure d, the R value of the training set of the rear part contour line data text in the BP neural network is 0.99965;

[0143] As Figure 5 shown, Figure 5 in Figure a, the R value of the training set of the front part contour line data text in the BP neural network is 0.99334;Figure 5 In Figure b, the verification set of the front part contour line data text has an R value of 0.99557 in the BP neural network; Figure 5 In Figure c, the training set of the front part contour line data text has an R value of 0.99899 in the BP neural network; Figure 5 In Figure d, the training set of the front part contour line data text has an R value of 0.99422 in the BP neural network;

[0144] In summary, the BP neural network meets the requirements.

[0145] Step 5: Based on the optimal contour line, update the three-dimensional surface model, and calculate the zero-crossing points through the first derivative to determine the feature points of the front and rear parts.

[0146] Further, the specific steps for determining the feature points in Step 5 include:

[0147] Step 51: Calculate the first derivative of the optimal contour line;

[0148] Step 52: Take the zero-crossing points of the first derivative as the feature points to reflect the change of the optimal contour line;

[0149] Step 53: Output the number and coordinates of the feature points, and mark the first serial number and coordinate values of the feature points on the optimal contour line for visualization.

[0150] Preferably, the first serial number can be Roman numerals.

[0151] Preferably, the zero-crossing points in Step 52 do not include the human face area, which can reduce the workload of subsequent processing without affecting clothing design.

[0152] Step 6: Mark the feature points in the three-dimensional surface model; perform parallel slicing on the three-dimensional surface model with cross-sectional planes at the Z-axis coordinate values of each feature point to obtain a number of feature cross-sections of the front and rear parts; calculate the sheet combination for filling based on the distance between adjacent feature cross-sections, the type of sheet, and the sheet thickness; fill the sheet layer between adjacent feature cross-sections of the front and rear parts based on the sheet combination, and combine with the corresponding optimal contour line to obtain a number of human body parts; output the corresponding processing data based on the human body parts; the processing data includes the sheet combination, the third serial number, and the cutting contour line; the third serial number is used to distinguish the sheets and can include the second serial number and the corresponding sheet number; the cutting contour line is the circumferential contour line of the sheet.

[0153] Further, Step 6 specifically includes:

[0154] Step 61: Mark the feature points in the three-dimensional surface model through the coordinate values;

[0155] Step 62: Perform parallel slicing on the three-dimensional surface model with the cross-sectional planes at the Z-axis coordinate values of each feature point (when the three-dimensional surface model is in a vertical state, the cross-sectional planes are horizontal planes), to obtain a number of feature cross-sections for the front and rear parts;

[0156] Step 63: Starting from the cross-sectional plane where the three-dimensional origin is located, connect each feature cross-section in sequence;

[0157] Step 64: Calculate the combination of plates for filling based on the distance between adjacent feature cross-sections, the type of plate, and the thickness of the plate;

[0158] Step 65: Based on the combination of plates, fill the plate layers between adjacent feature cross-sections of the front and rear parts, and combine with the corresponding optimal contour lines to obtain a number of human body parts; based on the human body parts, output the corresponding processing data; the processing data includes the combination of plates, the third serial number, and the cutting contour line; set positioning marks at the two-dimensional origin of each human body part, and the positioning marks include positioning symbols, the second serial number, and thickness marks; the positioning symbols are used to position the plates of the human body parts during subsequent assembly of the fitting stand; the second serial number is used to distinguish the human body parts and is the first serial number of the feature point to which the feature cross-section belongs; the thickness mark is the first digit after the decimal point of the thickness value of the human body part, and the unit of the thickness value of the human body part is cm;

[0159] The types of plates include foam boards and PVC foam boards. This not only saves costs, but also these two types of plates have a soft texture, are not easily deformed, and have elasticity, which is beneficial for placing pins during three-dimensional tailoring of clothing design, and can be reused; among them, foam boards are suitable for large-thickness cutting and processing, and PVC foam boards are suitable as small-thickness filling layers;

[0160] The thickness of the plate is:

[0161] The thickness of the foam board is 1 cm;

[0162] The thicknesses of the PVC foam boards are 0.1 cm, 0.2 cm, and 0.5 cm;

[0163] The method for calculating the combination of plates specifically includes:

[0164] When the distance value H between adjacent feature cross-sections is equal to an integer multiple A of 1 cm, the combination of plates is A foam boards;

[0165] When the distance value H between adjacent feature cross-sections is greater than an integer multiple A of 1 cm, calculate the difference value T1 between the two; then calculate the difference value T2 between T1 and 0.5 cm:

[0166] If T2 is equal to 0, the combination of plates is A foam boards and 1 PVC foam board with a thickness of 0.5 cm;

[0167] If T2 is not equal to 0, then calculate the difference T3 between T2 and the integer multiple B of 0.2 cm. The specific formula is T3 = T2 - 0.2 * B:

[0168] If T3 is equal to 0, the sheet combination is A foam sheets, 1 PVC foam board with a thickness of 0.5 cm, and B PVC foam boards with a thickness of 0.2 cm;

[0169] If T3 is not equal to 0, then take T3 as the integer multiple C of 0.1 cm. The sheet combination is A foam sheets, 1 PVC foam board with a thickness of 0.5 cm, B PVC foam boards with a thickness of 0.2 cm, and C PVC foam boards with a thickness of 0.1 cm;

[0170] When the distance value H between adjacent characteristic cross-sections is less than 1 cm, directly calculate the difference T2' between H and 0.5 cm:

[0171] If T2' is equal to 0, the sheet combination is 1 PVC foam board with a thickness of 0.5 cm;

[0172] If T2' is not equal to 0, then calculate the difference T3' between T2' and the integer multiple B of 0.2 cm. The specific formula is T3' = T2' - 0.2 * B:

[0173] If T3' is equal to 0, the sheet combination is 1 PVC foam board with a thickness of 0.5 cm and B PVC foam boards with a thickness of 0.2 cm;

[0174] If T3' is not equal to 0, then take T3' as the integer multiple C of 0.1 cm. The sheet combination is 1 PVC foam board with a thickness of 0.5 cm, B PVC foam boards with a thickness of 0.2 cm, and C PVC foam boards with a thickness of 0.1 cm;

[0175] Through the above method, an optimized sheet combination can be obtained, which facilitates the subsequent manufacture of a mannequin with fewer sheets and less sheet cutting time, thereby improving the mannequin manufacturing efficiency and reducing the mannequin manufacturing cost.

[0176] Step 7: The server sends the processing data to the sheet cutting equipment for manufacturing; the sheet cutting equipment is used to cut and manufacture each sheet corresponding to the human body parts according to the shape of the optimal contour line, and cut the positioning holes on the sheet according to the shape of the positioning symbol; mark the third serial number on the sheet.

[0177] Step 8: Based on the third serial number, through the positioning holes at the positioning symbols, layer and assemble each sheet of the human body parts on the positioning fixture in sequence to obtain a mannequin for clothing design; mark the corresponding human body sample information on the mannequin for comparison during subsequent clothing design.

[0178] Embodiment 2:

[0179] As Figure 7 shown, this embodiment provides a manufacturing system adopting the above-mentioned personalized mannequin manufacturing method, including a client and a server;

[0180] The client is used to collect the three-dimensional point cloud data of the human body sample and send it to the server together with the human body sample information;

[0181] The server includes a data receiving module, a data processing module and a result generating module;

[0182] The data receiving module is used to receive the three-dimensional point cloud data and the human body sample information;

[0183] The data processing module includes a sagittal plane cross-section point cloud data unit, a contour line data text unit, a fitting prediction unit and a segmentation unit;

[0184] The sagittal plane cross-section point cloud data unit generates a three-dimensional surface model from the three-dimensional point cloud data and extracts the human body sagittal plane cross-section point cloud data text;

[0185] The contour line data text unit uses the point cloud at the minimum Z-axis coordinate value in the sagittal plane cross-section point cloud data text as the three-dimensional origin, and takes the vertical axis of the three-dimensional origin as the reference to divide the sagittal plane cross-section point cloud data into two parts, the front and the back, and writes them into the corresponding contour line data texts respectively;

[0186] The fitting prediction unit stores a BP neural network; based on the contour line data text, the optimal contour lines of the front and back parts are respectively obtained through the BP neural network;

[0187] The segmentation unit updates the three-dimensional surface model based on the optimal contour line, calculates the zero-crossing points through the first derivative, and determines the feature points of the front and back parts; marks the feature points on the three-dimensional surface model; performs parallel slicing on the three-dimensional surface model with the cross-section at the Z-axis coordinate value of each feature point to obtain several feature cross-sections of the front and back parts; calculates the sheet combination for filling based on the distance between adjacent feature cross-sections, the type of sheet and the thickness of the sheet; fills the sheet layer between the adjacent feature cross-sections of the front and back parts based on the sheet combination, combines the corresponding optimal contour line, and obtains several human body components; outputs the corresponding processing data based on the human body components;

[0188] The result generating module is used to send out the processing data and the human body sample information.

[0189] Embodiment Three:

[0190] This embodiment provides a manufacturing device for a personalized mannequin, which includes a processor, a memory, and a bus. The memory stores instructions and data that can be read by the processor. The processor is used to call the instructions and data in the memory to execute a manufacturing method for a personalized mannequin as described above. The bus connects various functional components to transmit information.

[0191] Further, the manufacturing device further includes a three-dimensional human body scanner for three-dimensionally scanning a human body sample.

[0192] Further, the manufacturing device further includes a plate cutting device, which can use existing numerical control equipment to cut and manufacture each plate corresponding to the human body components according to the shape of the optimal contour line, and cut positioning holes on the plate according to the shape of the positioning symbols.

[0193] Further, the manufacturing device further includes a positioning tooling for fixing each plate corresponding to the human body components, as Figures 8 - 9 shown; the positioning tooling includes a base 1, a rotating disk 2, and a bracket 3;

[0194] The center of the lower surface of the rotating disk 2 is pivotally connected to the center of the base 1; a card slot is provided at the center of the upper surface of the rotating disk 2; the bracket 3 is vertically fixed at the card slot; the bracket 3 cooperates with the positioning holes on the plate.

[0195] The positioning holes are of a semi-cross structure (the positioning holes of the front and rear two parts of the human body component plates can correspond to form a complete cross structure), and the bracket 3 is of a cross structure, which is convenient for horizontally orienting and fixing the human body components;

[0196] Based on Figure 3 the feature points a, b, c, d, e, f, g, h, i, j, k and the origin o vertex s, the corresponding human body components are defined. For the specific plate combination, refer to the calculation method in Embodiment 1, and the results are as follows:

[0197] Human body component a (about 9.6 cm) includes: 9 foam boards, 1 PVC foam board with a thickness of 0.5 cm, and 1 PVC foam board with a thickness of 0.1 cm;

[0198] Human body component b (about 7.2 cm) includes: 7 foam boards, 1 PVC foam board with a thickness of 0.2 cm;

[0199] Human body component c (about 7.5 cm) includes: 7 foam boards, 1 PVC foam board with a thickness of 0.5 cm;

[0200] Human body component d (about 5.3 cm) includes: 5 foam boards, 1 PVC foam board with a thickness of 0.2 cm, and 1 PVC foam board with a thickness of 0.1 cm;

[0201] The human body part e (about 8.1 cm) includes: 8 foam boards and 1 PVC foam board with a thickness of 0.1 cm;

[0202] The human body part f (about 31.3 cm) includes: 31 foam boards, 1 PVC foam board with a thickness of 0.2 cm and 1 PVC foam board with a thickness of 0.1 cm;

[0203] The human body part s (about 30 cm) includes: 30 foam boards (the topmost foam board has no positioning holes and is used for capping);

[0204] The human body part g (about 13.3 cm) includes: 13 foam boards, 1 PVC foam board with a thickness of 0.2 cm and 1 PVC foam board with a thickness of 0.1 cm;

[0205] The human body part h (about 18.6 cm) includes: 18 foam boards, 1 PVC foam board with a thickness of 0.5 cm and 1 PVC foam board with a thickness of 0.1 cm;

[0206] The human body part i (about 23.5 cm) includes: 23 foam boards and 1 PVC foam board with a thickness of 0.5 cm;

[0207] The human body part j (about 23.5 cm) includes: 23 foam boards and 1 PVC foam board with a thickness of 0.5 cm;

[0208] The human body part k (about 10.6 cm) includes: 10 foam boards, 1 PVC foam board with a thickness of 0.5 cm and 1 PVC foam board with a thickness of 0.1 cm;

[0209] The human body part - s (about 9.5 cm) includes: 9 foam boards and 1 PVC foam board with a thickness of 0.5 cm (without positioning holes and used for capping).

[0210] In another implementation mode of this solution, it can be realized by means of an integrated device, and the device can include corresponding modules for executing each or several steps in the above - mentioned various implementation modes. The module can be one or more hardware modules specifically configured to execute the corresponding steps, or be realized by a processor configured to execute the corresponding steps, or be stored in a computer - readable medium for being realized by the processor, or be realized through a certain combination.

[0211] The processor executes the various methods and processes described above. For example, the method embodiments in this solution can be implemented as a software program that is tangibly included in a machine-readable medium, such as a memory. In some embodiments, part or all of the software program can be loaded and / or installed via the memory and / or communication interface. When the software program is loaded into the memory and executed by the processor, one or more steps of the methods described above can be executed. Alternatively, in other embodiments, the processor can be configured to execute one of the above methods by any other suitable means (e.g., by means of firmware).

[0212] The device can be implemented using a bus architecture. The bus architecture can include any number of interconnected buses and bridges, depending on the specific application of the hardware and overall design constraints. The bus connects various circuits including one or more processors, memories, and / or hardware modules together. The bus can also connect various other circuits such as peripheral devices, voltage regulators, power management circuits, external antennas, etc.

[0213] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0214] Embodiment 4:

[0215] This embodiment provides a personalized mannequin using the aforementioned personalized mannequin manufacturing method. The personalized mannequin is divided into front and back parts in the coronal plane; each part is composed of multiple layers of plates combined along the vertical axis; the same positioning holes are provided at the two-dimensional origin of each plate.

[0216] Furthermore, the personalized mannequin and the positioning tooling are combined into one body. The positioning tooling includes a base, a rotating disk, and a bracket;

[0217] The center of the lower surface of the rotating disk is pivotally connected to the center of the base; a card slot is provided at the center of the upper surface of the rotating disk; the bracket is vertically fixed at the card slot; the bracket cooperates with the positioning holes on the plate.

[0218] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A manufacturing method of a personalized mannequin, characterized in that, Including: Step 1: The client collects the three-dimensional point cloud data of the human body sample through a three-dimensional human body scanner and sends it to the server together with the human body sample information; The three-dimensional point cloud data establishes a coordinate system with the axes in human anatomy: the Y-axis is the sagittal axis, the X-axis is the coronal axis, and the Z-axis is the vertical axis; Step 2: The server generates a three-dimensional surface model from the three-dimensional point cloud data and extracts the text of the sagittal plane cross-sectional point cloud data of the human body; Step 3: In the text of the sagittal plane cross-sectional point cloud data, the point cloud at the minimum Z-axis coordinate value is used as the three-dimensional origin. Based on the vertical axis of this three-dimensional origin, the sagittal plane cross-sectional point cloud data is divided into two parts, the front and the back, and written into the corresponding contour line data text respectively; Step 4: Based on the contour line data text, through a BP neural network, the optimal contour lines of the front and back parts are respectively fitted and predicted; Step 5: Based on the optimal contour lines, the three-dimensional surface model is updated, and the zero-crossing points are calculated through the first derivative to determine the characteristic points of the front and back parts; Step 6: Mark the characteristic points on the three-dimensional surface model; perform parallel slicing on the three-dimensional surface model with the cross-sections at the Z-axis coordinate values of each characteristic point to obtain a number of characteristic cross-sections of the front and back parts; Calculate the combination of plates for filling based on the distance between adjacent characteristic cross-sections, the type of plate, and the thickness of the plate; based on the combination of plates, fill the plate layers between adjacent characteristic cross-sections of the front and back parts, and combine the corresponding optimal contour lines to obtain a number of human body parts; based on the human body parts, output the corresponding processing data; the processing data includes the combination of plates, the third serial number, and the cutting contour line; Step 7: The server sends the processing data to the plate cutting equipment for manufacturing; the plate cutting equipment is used to cut and manufacture each plate corresponding to the human body part in the shape of the optimal contour line, and cut the positioning holes on the plate in the shape of the positioning symbol; mark the third serial number on the plate; Step 8: Based on the third serial number, through the positioning holes at the positioning symbols, layer by layer assemble each plate of the human body part on the positioning fixture in sequence to obtain a mannequin for clothing design; mark the corresponding human body sample information on the mannequin.

2. The method according to claim 1, wherein The specific content of Step 1 includes: Step 11: Prepare the human body sample according to the three-dimensional point cloud acquisition requirements; the three-dimensional point cloud acquisition requirements include: wearing a white tight-fitting clothing, a white swimming cap on the head, and removing accessories; feet apart, head held high, standing parallel, looking straight ahead; forearms hanging naturally, upper arms abducted, hands clenched; maintaining normal breathing; Step 12: Through a three-dimensional human body scanner, perform three-dimensional scanning on the human body sample to obtain three-dimensional point cloud data; Step 13: After encrypting and compressing the three-dimensional point cloud data, the client sends it to the server.

3. The method according to claim 2, characterized in that, The specific content of Step 2 includes: Step 21: The server decompresses and decrypts the three-dimensional point cloud data to generate a three-dimensional surface model of the human body sample; Step 22: Extract all the point cloud data with an X-axis coordinate of 0 from the three-dimensional point cloud data as the text of the sagittal plane cross-sectional point cloud data.

4. The method according to claim 1, characterized in that The specific content of Step 3 includes: Step 31: The server loads the sagittal plane cross-sectional point cloud data text, extracts the data in the second and third columns of the point cloud coordinates, and defines them as the Z-axis coordinate value z and the Y-axis coordinate value y respectively; Step 32: Statistically calculate the minimum value min_Z of the Z-axis coordinate value z. The specific formula is: min_Z = min(z); Step 33: Subtract min_Z from each z to obtain the updated coordinate value z', which is used to determine the three-dimensional origin position. The specific formula is: z' = z - min_Z; Step 34: Based on the vertical axis of this three-dimensional origin, through conditional indexing, divide the sagittal plane cross-sectional point cloud data into two parts, front and back, and write them into the corresponding contour line data texts respectively: The conditional indexing for the front part includes z > 0 and y ≥ 0; The conditional indexing for the back part includes z > 0 and y < 0.

5. The method according to claim 1, wherein The training process of the said BP neural network includes: Step 41: The server loads the contour line data text, performs normalization processing, and then randomly divides it into a training set, a validation set, and a test set; Step 42: Create a BP neural network: The number of hidden layers is set to 10 layers; The number of training cycles is set to 1000; The training target error is set to 1e-5; Step 43: Train the BP neural network until the correlation coefficient R values of the training set, validation set, test set, and all sets are all greater than or equal to 0.

9.

6. The method according to claim 1, wherein The specific steps for determining the feature points in the said Step 5 include: Step 51: Calculate the first derivative of the optimal contour line; Step 52: Take the zero-crossing points of the first derivative as feature points to reflect the change of the optimal contour line; Step 53: Output the number and coordinates of the feature points, and mark the first serial number and coordinate values of the feature points on the optimal contour line.

7. The method according to claim 1, characterized in that, The said Step 6 specifically includes: Step 61: Mark the said feature points in the three-dimensional surface model through the coordinate values; Step 62: Perform parallel slicing on the three-dimensional surface model with the cross-sections at the Z-axis coordinate values of each feature point to obtain several feature cross-sections for the front and back parts; Step 63: Starting from the cross-section of the three-dimensional origin, connect each feature cross-section in sequence; Step 64: Calculate the board combination for filling based on the distance between adjacent feature cross-sections, the board type, and the board thickness; Step 65: Based on the said board combination, fill the board layers between adjacent feature cross-sections of the front and back parts, and combine with the corresponding optimal contour line to obtain several human body parts; based on the human body parts, output the corresponding processing data; the processing data includes the board combination, the third serial number, and the cutting contour line; set positioning marks at the two-dimensional origins of each human body part, and the positioning marks include positioning symbols, the second serial number, and thickness marks; the positioning symbol is used to position the boards of the human body parts during the subsequent assembly of the mannequin; the second serial number is used to distinguish the human body parts and is the first serial number of the feature points to which the feature cross-section belongs; the thickness mark is the first digit after the decimal point of the thickness value of the human body part, and the unit of the thickness value of the human body part is cm.

8. The method according to claim 7, wherein The said board types include foam boards and PVC foam boards; The said board thickness is: The thickness of the foam board is 1 cm; The thicknesses of the PVC foam boards are 0.1 cm, 0.2 cm, and 0.5 cm; The method for calculating the combined plates specifically includes: When the distance value H between adjacent characteristic cross-sections is equal to an integer multiple A of 1 cm, the combined plates are A foam boards; When the distance value H between adjacent characteristic cross-sections is greater than an integer multiple A of 1 cm, calculate the difference value T1 between them; then calculate the difference value T2 between T1 and 0.5 cm: If T2 is equal to 0, the combined plates are A foam boards and 1 PVC foam board with a thickness of 0.5 cm; If T2 is not equal to 0, calculate the difference value T3 between T2 and an integer multiple B of 0.2 cm, and the specific formula is T3 = T2 - 0.2 * B: If T3 is equal to 0, the combined plates are A foam boards, 1 PVC foam board with a thickness of 0.5 cm, and B PVC foam boards with a thickness of 0.2 cm; If T3 is not equal to 0, then take T3 as an integer multiple C of 0.1 cm, and the combined plates are A foam boards, 1 PVC foam board with a thickness of 0.5 cm, B PVC foam boards with a thickness of 0.2 cm, and C PVC foam boards with a thickness of 0.1 cm; When the distance value H between adjacent characteristic cross-sections is less than 1 cm, directly calculate the difference value T2' between H and 0.5 cm: If T2' is equal to 0, the combined plates are 1 PVC foam board with a thickness of 0.5 cm; If T2' is not equal to 0, calculate the difference value T3' between T2' and an integer multiple B of 0.2 cm, and the specific formula is T3' = T2' - 0.2 * B: If T3' is equal to 0, the combined plates are 1 PVC foam board with a thickness of 0.5 cm and B PVC foam boards with a thickness of 0.2 cm; If T3' is not equal to 0, then take T3' as an integer multiple C of 0.1 cm, and the combined plates are 1 PVC foam board with a thickness of 0.5 cm, B PVC foam boards with a thickness of 0.2 cm, and C PVC foam boards with a thickness of 0.1 cm.

9. A manufacturing system for a personalized mannequin using the method according to any one of claims 1-8, characterized in that, It includes a client and a server; The client is used to collect the three-dimensional point cloud data of the human body sample and send it to the server together with the human body sample information; The server includes a data receiving module, a data processing module, and a result generating module; The data receiving module is used to receive the three-dimensional point cloud data and the human body sample information; The data processing module includes a sagittal plane cross-section point cloud data unit, a contour line data text unit, a fitting and prediction unit, and a segmentation unit; The sagittal plane cross-section point cloud data unit generates a three-dimensional surface model from the three-dimensional point cloud data and extracts the human body sagittal plane cross-section point cloud data text; The contour line data text unit, in the sagittal plane cross-section point cloud data text, takes the point cloud at the minimum value of the Z-axis coordinate as the three-dimensional origin, and based on the vertical axis of this three-dimensional origin, divides the sagittal plane cross-section point cloud data into two parts, the front and the back, and writes them into the corresponding contour line data text respectively; The fitting and prediction unit stores a BP neural network; based on the contour line data text, through the BP neural network, the optimal contour lines of the front and back parts are respectively fitted and predicted; The segmentation unit updates the three-dimensional surface model based on the optimal contour line, calculates the zero-crossing points through the first derivative, and determines the feature points of the front and rear parts; marks the feature points in the three-dimensional surface model; performs parallel slicing on the three-dimensional surface model with cross-sectional planes at the Z-axis coordinate values of each feature point to obtain a number of feature cross-sections of the front and rear parts. Based on the distance between adjacent feature cross-sections, the type of sheet material, and the thickness of the sheet material, calculate the sheet material combination for filling; based on the sheet material combination, fill the sheet material layer between adjacent feature cross-sections of the front and rear parts, and combine with the corresponding optimal contour line to obtain a number of human body parts; output corresponding processing data based on the human body parts. The result generation module is used to send the processing data and human body sample information externally.

10. A manufacturing device for a personalized mannequin, characterized in that, It includes a processor, a memory, and a bus. The memory stores instructions and data read by the processor. The processor is used to call the instructions and data in the memory to execute the method described in any one of claims 1-8. The bus is connected between each functional component for transmitting information.

Images