Digital design method of three-dimensional prototype clothes

Abstract

The invention relates to the technical field of clothing data processing, in particular to a digital design method of three-dimensional prototype clothing. The method comprises the following steps: obtaining human body three-dimensional scanning data and carrying out feature point labeling, reconstructing a three-dimensional human body model as basic data of costume design, carrying out contour looseness calculation on the human body model, generating a looseness data set, carrying out sample plate plane analysis to obtain a plane sample plate data set, and after collecting costume fabric data, carrying out data processing on the plane sample plate data set. The method comprises the following steps: performing physical characteristic mapping on a human body model and a planar template, reconstructing a three-dimensional garment model conforming to fabric characteristics, performing spatial positioning on the template, performing virtual sewing simulation, generating a shape data set of the garment, performing dynamic motion analysis on the shape data of the garment according to the human body three-dimensional model, and evaluating the comfort level of the garment. The garment form is locally adjusted to reconstruct a planar template. According to the invention, a more comprehensive and more reliable digital design method of the three-dimensional prototype clothing is realized.

Description

Technical Field

[0001] The invention relates to the technical field of clothing data processing, and in particular to a digital design method for three-dimensional prototype clothing. Background Art

[0002] The traditional clothing design process still relies on manual drawing of samples and repeated debugging of actual fitting, which is not only time-consuming and inefficient, but also has the limitation of not being able to quickly and accurately achieve personalized customization. Especially when designing complex clothing styles, traditional methods are difficult to effectively deal with the diversity of human body sizes and differences in fabric properties, resulting in a large number of trial and error and rework in the design process, affecting the design efficiency and the comfort and adaptability of the final product. 3D human body scanning and virtual fitting technology have gradually become important research directions in the field of clothing design. However, the existing technology is not fully integrated between 3D modeling of the human body and 3D reconstruction of clothing. There is a lack of accurate calculation and simulation methods to truly achieve a high degree of matching between clothing and the human body, especially in the mapping between the physical properties of clothing fabrics and 3D models. There are still large technical bottlenecks. Current virtual design often ignores the complexity of human body dynamic movement, resulting in the lack of comfort and fit of the designed clothing in real wear, and the comfort evaluation and personalized adjustment of clothing in dynamic wearing state are still not refined enough. Summary of the invention

[0003] Based on this, it is necessary to provide a digital design method for three-dimensional prototype clothing to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a digital design method for three-dimensional prototype clothing includes the following steps:

[0005] Step S1: obtaining three-dimensional scanning data of a human body; annotating feature points of the three-dimensional scanning data of the human body to obtain annotated feature data; reconstructing a three-dimensional model of the human body based on the annotated feature data to generate a three-dimensional model of the human body;

[0006] Step S2: performing contour loose volume calculation on the human body three-dimensional model to obtain a loose volume data set; performing template plane analysis on the human body three-dimensional model based on the loose volume data set to generate a plane template data set;

[0007] Step S3: collecting clothing fabric data; mapping the physical properties of the plane sample data set based on the clothing fabric data to obtain a physical data set; reconstructing a clothing 3D model of the physical data set to generate a clothing 3D model;

[0008] Step S4: spatially positioning the plane sample data set to obtain a sample position data set; performing virtual sewing simulation on the garment three-dimensional model based on the sample position data set to obtain a garment shape data set;

[0009] Step S5: performing dynamic motion analysis on the clothing morphology data set according to the human body three-dimensional model to generate dynamic clothing change data; performing comfort evaluation on the dynamic clothing change data to obtain a clothing comfort score;

[0010] Step S6: Based on the clothing comfort score, the clothing shape data set is locally adjusted to obtain adjusted clothing data; the plane sample data set is reconstructed using the adjusted clothing data to generate an adjusted plane sample data set to execute the intelligent digital design method of the three-dimensional prototype clothing.

[0011] The present invention reconstructs a three-dimensional model of a human body by acquiring three-dimensional scanning data of a human body and marking feature points. The high-precision three-dimensional scanning technology can realize accurate capture of complex human body shapes, and the fineness and accuracy of the human body model are improved by marking feature points. The generated three-dimensional human body model has a real physical shape. The contour looseness of the human body three-dimensional model is calculated, and a plane sample data set is generated based on the looseness data set. By calculating the looseness of the human body contour, the morphological changes and wearing space of different parts of the human body can be accurately reflected, providing a scientific basis for the design of plane samples. Through the sample plane analysis, the structural design of the clothing is further optimized, so that it can better fit the human body curve, avoiding the phenomenon of looseness and inappropriateness in traditional sample design. The clothing fabric data is collected and the physical properties of the plane sample data set are mapped to the plane sample data set based on the fabric data to reconstruct the clothing three-dimensional model. The physical properties of the clothing fabric, such as elasticity, air permeability and softness, etc., can be collected and analyzed. The fabric properties can be accurately mapped to the plane sample, thereby generating a high-precision three-dimensional clothing model, ensuring that the designed clothing matches the actual fabric in physical properties. The plane sample data set is spatially positioned, and the clothing three-dimensional model is mapped based on the sample position data set. Virtual sewing simulation is performed to obtain a clothing morphology dataset. The arrangement and placement of the samples in three-dimensional space are optimized through the spatial positioning of the samples. Virtual sewing simulation technology can simulate clothing deformation and fabric stress in the actual sewing process. Dynamic motion analysis of the clothing morphology dataset is performed based on the three-dimensional model of the human body, and the comfort of the dynamic clothing change data is evaluated to generate a clothing comfort score. Combined with the dynamic motion analysis of the three-dimensional model of the human body, the posture changes of the human body under different actions can be simulated to evaluate the comfort of clothing in various motion states. Through the analysis of the dynamic changes of clothing, the adaptability and comfort of clothing can be grasped in real time during the design process. Based on the clothing comfort score, the clothing morphology dataset is locally adjusted, and the adjusted clothing data is used to reconstruct the flat sample dataset to generate an adjusted flat sample dataset. Through the local morphology adjustment technology, the fit and comfort of clothing can be accurately optimized to ensure that the clothing can adapt to the dynamic changes of the human body to the greatest extent during actual wearing. Through sample reconstruction, the adjusted data can effectively reflect the real needs of the human body in motion. The final generated adjusted flat sample dataset provides accurate design support for the intelligent digital design of three-dimensional prototype clothing.

[0012] Preferably, step S1 comprises the following steps:

[0013] Step S11: collecting three-dimensional scanning data of a human body; performing human feature point recognition on the three-dimensional scanning data of the human body to obtain feature point data;

[0014] Step S12: highlighting and marking the feature point data to obtain marked feature data; performing surface fitting processing on the marked feature data to generate a surface data set;

[0015] Step S13: constructing a skeleton point structure for the surface data set based on the annotated feature data to generate a human skeleton data set;

[0016] Step S14: reconstructing the three-dimensional model of the human skeleton data set to generate a three-dimensional model of the human body.

[0017] The present invention acquires high-precision human body shape information by collecting three-dimensional scanning data of the human body, provides a basis for feature point recognition, and ensures the accuracy of the model. Human body feature point recognition can accurately locate key parts, and the generated feature point data provides a geometric basis for subsequent processing, improves the accuracy of the design, and highlights and annotates the feature point data. The generated annotated feature data makes the key parts prominent, which is convenient for subsequent processing and improves the visualization effect. The surface fitting process converts discrete feature points into continuous surface data sets, provides a smooth representation for the human body shape, and ensures the realism of the model. The human skeleton data set formed by the bone point structure provides a structured basis for motion analysis and clothing design, and helps to understand the human body's motion characteristics. The complete human body model generated by the three-dimensional model reconstruction provides detailed size and proportion data for digital clothing design, improves the scientificity and practicality of the design, and the entire digital design method can shorten the product development cycle, improve design efficiency, and meet the market demand for personalized and customized clothing.

[0018] Preferably, step S2 comprises the following steps:

[0019] Step S21: Slice the human body three-dimensional model in cross section to obtain human body model slice data; calculate key girths of the human body model slice data to generate girth data;

[0020] Step S22: performing contour looseness calculation on the human body model slice data based on the circumference data to obtain a looseness data set; performing size calibration calculation on the looseness data set to generate template adjustment data;

[0021] Step S23: performing plane projection conversion on the human body three-dimensional model to obtain candidate model projection data; performing structure line layout processing on the candidate model projection data to obtain structure line layout data;

[0022] Step S24: Calculate the structural parameters of the structural line layout data to generate plane template structural data; calibrate the plane template structural data based on the template adjustment data to generate a plane template data set.

[0023] The present invention slices a human body three-dimensional model in cross section, and the generated model slice data provides a basis for subsequent circumference calculation, ensuring the accuracy and reliability of the circumference data. The calculation of the circumference data can provide key size information for clothing design, so that the design is more in line with the actual shape of the human body. The contour looseness calculation based on the circumference data can accurately reflect the tightness of clothing in different parts. The generated looseness data set provides a basis for size calibration, ensuring that the design can take into account both comfort and aesthetics. The step of plane projection conversion of the human body three-dimensional model can convert the three-dimensional shape into a plane pattern. The generated candidate model projection data lays the foundation for subsequent structural line layout processing. The structural line layout processing can optimize the overall structure of the design, making the plane template easier to operate and adjust in actual production. The structural line layout data generates plane template structure data through structural parameter calculation, providing a detailed design blueprint for template production. The plane template structure data is calibrated based on the template adjustment data to ensure that the finally generated plane template data set meets the design requirements, thereby improving the accuracy and efficiency of digital design, promoting the innovation and development of three-dimensional prototype clothing design, and meeting the needs of personalization and customization.

[0024] Preferably, step S22 includes the following steps:

[0025] Performing contour extraction on the slice data of the human body model to obtain a slice contour data set; performing feature region division on the slice contour data set to generate feature region data;

[0026] The curvature of the feature area data is calculated to obtain a regional curvature data set; local looseness distribution is performed on the regional curvature data set based on the circumference data to obtain a looseness data set;

[0027] Performing dimension measurement on the loose volume data set to obtain loose volume measurement data; performing correction amount calculation on the loose volume measurement data to generate dimension correction amount data;

[0028] The size correction amount data is mapped to the clothing pattern to generate pattern adjustment data.

[0029] The present invention provides a basis for subsequent feature area division by performing contour extraction on human body model slice data, so that key parts in the design process are clearly identified, the generation of feature area data ensures a detailed analysis of each important area, the curvature calculation can reflect the shape changes of different areas, the obtained regional curvature data set provides a basis for further looseness allocation, the operation of local looseness allocation on the regional curvature data set based on the circumference data ensures that the tightness of each feature area is reasonably allocated, and the comfort of the clothing is improved. The looseness measurement data generated by the looseness data set after the size measurement can provide an accurate numerical basis for subsequent design adjustments, and the size correction data generated by the implementation of the correction calculation provides a specific adjustment plan for the designer. Finally, the step of mapping the size correction data to the clothing sample ensures that the generation of the sample adjustment data is consistent with the actual design requirements, thereby improving the digital design accuracy and efficiency of the three-dimensional prototype clothing, promoting the realization of personalized customization, and optimizing the fit and overall aesthetics of the clothing.

[0030] Preferably, step S3 comprises the following steps:

[0031] Step S31: collecting clothing fabric data; performing a drape test on the clothing fabric data to obtain clothing drape data;

[0032] Step S32: performing clothing characteristic analysis on the clothing drape data to generate a clothing physical characteristic data set; performing physical characteristic mapping on the plane sample data set based on the clothing physical characteristic data set to obtain a physical data set;

[0033] Step S33: performing stress distribution calculation on the physical data set to obtain clothing physical stress data; performing deformation simulation processing on the clothing physical stress data to generate simulated deformation data;

[0034] Step S34: performing clothing shape prediction on the simulated deformation data to obtain predicted clothing shape data; performing three-dimensional model reconstruction on the predicted clothing shape data to generate a clothing three-dimensional model.

[0035] The invention collects clothing fabric data, and the obtained raw data provides a basis for subsequent drape test. The clothing drape data generated by the implementation of the drape test provides an intuitive quantitative index for the drape characteristics and fluidity of the fabric. The clothing physical property data set generated by analyzing the clothing drape data can show various physical properties of the fabric, such as stiffness, softness and breathability. The operation of mapping the physical properties of the plane sample data set based on these physical property data sets ensures that the actual performance of the fabric is fully considered in the design. The generated physical data set provides a detailed basis for the subsequent stress distribution calculation. The clothing physical stress data after the stress distribution calculation can reflect the stress conditions of the fabric under different wearing conditions. The simulated deformation data generated by further deformation simulation processing provides designers with the deformation conditions that will occur in the actual wearing of the fabric. The predicted clothing morphology data obtained by analyzing the simulated deformation data in the step of clothing morphology prediction provides an important reference for the subsequent three-dimensional model reconstruction. The finally generated clothing three-dimensional model can truly reflect the design intention and fabric characteristics, and provide a basis for further virtual fitting and market feedback, which improves the accuracy and practicality of digital design as a whole and promotes the development of the clothing industry in the direction of personalization and customization.

[0036] Preferably, step S4 comprises the following steps:

[0037] Step S41: calibrating the reference points of the plane sample data set to obtain sample reference data; performing spatial coordinate conversion on the sample reference data to generate sample coordinate data;

[0038] Step S42: Calculate the posture angle of the template coordinate data to obtain coordinate angle data; adjust the relative position of the template reference data based on the coordinate angle data to generate template position data;

[0039] Step S43: performing stitching line recognition on the template position data to obtain the template stitching line position; performing stitching path simulation on the garment three-dimensional model based on the template stitching line position to generate a simulated candidate stitching path;

[0040] Step S44: performing seam deformation calculation on the simulated candidate suture path to generate seam deformation data; performing suture path adjustment on the simulated candidate suture path according to the seam deformation data to obtain a simulated suture path;

[0041] Step S45: performing virtual sewing simulation on the three-dimensional clothing model based on the simulated sewing path to obtain a clothing morphology data set.

[0042] The present invention generates template benchmark data by benchmarking the planar template data set, which provides an accurate starting reference for the subsequent spatial coordinate conversion, making the performance of the template in three-dimensional space more accurate. The template coordinate data generated after the template benchmark data is converted into spatial coordinates can lay a foundation for the positioning and adjustment of the template. The coordinate angle data obtained by the implementation of posture angle calculation provides a quantitative basis for the direction and inclination of the template. The operation of relative position adjustment of the template benchmark data based on the coordinate angle data ensures that the layout of the template in three-dimensional space meets the design requirements. The template suture line position generated after the template position data is identified by the suture line provides necessary information for the subsequent suture path simulation. , making the simulated sewing path more operational. The simulated candidate sewing path generated by the sewing path simulation provides a preliminary reference for the actual sewing process. The seam deformation data generated by the implementation of the simulated candidate sewing path by the seam deformation calculation provides a practical basis for the adjustment of the sewing path. Finally, the simulated candidate sewing path is adjusted according to the seam deformation data. The obtained simulated sewing path provides a basis for the virtual sewing simulation of clothing. The clothing morphology data set generated by the virtual sewing simulation of the three-dimensional clothing model based on the simulated sewing path can truly reflect the appearance and structure of the clothing after actual sewing, which improves the efficiency and accuracy of digital design as a whole and promotes the innovation and development of clothing design.

[0043] Preferably, step S44 includes the following steps:

[0044] Calculate stress points on the simulated candidate suture path to obtain suture stress data; determine the force direction of the suture stress data to generate stress direction data;

[0045] Perform stress accumulation calculation on the stitching stress data based on the stress direction data to generate stress accumulation data; perform deformation calculation on the three-dimensional model of the clothing based on the stress accumulation data to obtain deformation data;

[0046] Perform surface topology analysis on the three-dimensional clothing model according to the deformation data to obtain surface topology data; perform deformation trend prediction on the surface topology data to obtain seam deformation data;

[0047] Repositioning nodes of the simulated candidate suture path based on the seam deformation data to obtain repositioning data; performing curve fitting processing on the repositioning data to generate repositioning fitting data;

[0048] The simulated candidate stitching path is modified according to the repositioned fitting data to generate a simulated stitching path.

[0049] The present invention provides a basis for subsequent force analysis by calculating the stress points of the simulated candidate suture path, making the suture path design more scientific and reasonable. The stress direction data generated after the suture stress data is judged by the force direction can indicate the force condition of the suture part in actual use. The stress accumulation data generated by the stress accumulation calculation of the suture stress data based on the stress direction data provides designers with a quantitative assessment of the potential risks of the suture path. The calculation of the deformation data based on the deformation amount calculation of the three-dimensional model of the clothing based on the stress accumulation data can predict the deformation characteristics of the clothing after being stressed. The surface topology data generated by the analysis of the deformation data can be The seam deformation data generated by the analysis of the surface topology data provides an important basis for the optimization of the stitching path. The node relocation based on the seam deformation data can ensure the adaptability of the stitching path in actual production. The relocation fitting data generated by the curve fitting processing of the relocation data can provide support for the smooth adjustment of the stitching path. Finally, the simulated stitching path generated by modifying the stitching path of the simulated candidate stitching path according to the relocation fitting data can improve the durability and comfort of the garment while ensuring the appearance, which improves the accuracy and operability of the digital design as a whole and promotes the progress of the scientificity and practicality of clothing design.

[0050] Preferably, step S5 comprises the following steps:

[0051] Step S51: calibrating joint points of a human body three-dimensional model to obtain joint data; calculating motion trajectories of the joint data to generate motion trajectory data;

[0052] Step S52: performing a motion range trajectory analysis on the movable trajectory data to obtain a movable fluctuation range; performing a clothing change analysis on the clothing form data set based on the movable fluctuation range to generate dynamic clothing change data;

[0053] Step S53: Calculate the contact area of ​​the dynamic clothing change data based on the three-dimensional human body model to obtain contact area data; calculate the local pressure distribution of the contact area data to generate a local stress data set;

[0054] Step S54: performing pressure uniformity evaluation on the local stress data set to obtain pressure uniformity data; performing activity restriction evaluation on the pressure uniformity data according to a preset pressure uniformity threshold to generate local clothing activity restriction data;

[0055] Step S55: Perform comfort mapping on the local clothing activity restriction data to obtain a clothing comfort score.

[0056] The invention provides a basis for subsequent motion trajectory calculation by calibrating the joint points of the human body three-dimensional model, making the motion analysis more accurate. The movable trajectory data generated by the result of the motion trajectory calculation can clearly show the dynamic changes of the human body during the motion process. The movable fluctuation range obtained by the implementation of the motion range trajectory analysis provides an important motion restriction parameter for clothing design. The dynamic clothing change data generated by the clothing change analysis of the clothing form data set based on the movable fluctuation range can fully consider the actual needs of the human body during activities. The implementation of the contact area calculation based on the human body three-dimensional model can clarify the area where the clothing contacts the human body, which provides a basis for the calculation of local pressure distribution. The local stress data set generated by the local pressure distribution calculation can reflect the pressure applied by the clothing to the human body during exercise. The execution of the pressure uniformity evaluation provides designers with an important quantitative index of clothing comfort. After the obtained pressure uniformity data is compared with the preset pressure uniformity threshold, the generated local clothing activity restriction data can effectively identify clothing design problems that affect the freedom of movement. The clothing comfort score generated by the comfort mapping based on the local clothing activity restriction data provides a specific improvement direction for the subsequent optimization design, which improves the consideration of digital design in comfort and functionality as a whole, and lays a foundation for personalized and humanized clothing design.

[0057] Preferably, step S52 includes the following steps:

[0058] Performing direction change identification on the movable trajectory data to obtain direction change data; performing speed distribution analysis on the direction change data to generate change speed data;

[0059] Performing trajectory feature integration on the direction change data and the change speed data to obtain trajectory feature data; performing extreme position marking on the trajectory feature data to obtain marked position data;

[0060] Determine the fluctuation range of the marker position data and generate a movable fluctuation range;

[0061] The clothing morphology data set is deformed mapped based on the movable fluctuation range to obtain clothing deformation mapping data; clothing wrinkles are predicted on the clothing deformation mapping data to generate dynamic clothing change data.

[0062] The present invention provides dynamic change details for motion analysis by identifying direction changes of movable trajectory data, so that the design is more in line with actual motion needs. The change speed data generated by the implementation of speed distribution analysis can quantify the speed change during motion. The trajectory feature data generated by integrating the direction change data with the change speed data provides a comprehensive perspective for subsequent motion range analysis. The step of extreme position marking clarifies the key positions in the motion trajectory. The generated marking position data provides a basis for determining the movable fluctuation range. The determination of the fluctuation range provides the necessary flexibility and adaptability for clothing design. The operation of deformation mapping the clothing morphology data set based on the movable fluctuation range ensures that the design can reflect the deformation during actual motion. The dynamic clothing change data generated by the implementation of clothing wrinkle prediction provides designers with a foresight of the appearance changes of clothing during motion, which overall improves the accuracy of digital design in motion adaptability and visual expression, and provides a scientific basis and practical tools for personalized clothing design.

[0063] Preferably, step S6 comprises the following steps:

[0064] Step S61: defining the adjustment area of ​​the clothing form data set based on the clothing comfort score to obtain adjustment area data; calculating the adjustment amount of the adjustment area based on the clothing comfort score to generate adjustment amount data;

[0065] Step S62: performing local shape adjustment on the adjustment area data according to the adjustment amount data to obtain adjusted clothing data;

[0066] Step S63: reconstructing the seam line of the plane sample data based on the adjusted clothing data to obtain reconstructed seam line data;

[0067] Step S64: reconstructing the plane sample data according to the reconstructed seam line data to generate an adjusted plane sample data set to execute the intelligent digital design method for the three-dimensional prototype garment.

[0068] The present invention defines the adjustment area data of the clothing morphological data set based on the clothing comfort score to generate adjustment area data, which provides a clear target for subsequent local adjustments and makes the design process more precise. The adjustment amount data generated by the implementation of adjusting the adjustment amount calculation of the adjustment area based on the clothing comfort score provides a quantitative basis for specific modifications, ensuring the effectiveness and pertinence of the adjustment. The step of performing local morphological adjustment on the adjustment area data according to the adjustment amount data can directly improve the fit and comfort of the clothing. The obtained adjusted clothing data provides a basis for subsequent seam line reconstruction. The reconstructed seam line data generated by performing seam line reconstruction on the plane sample data based on the adjusted clothing data can ensure the accuracy and manufacturability of the sample. The implementation of sample reconstruction generates an adjusted plane sample data set by performing sample reconstruction on the plane sample data based on the reconstructed seam line data, which can effectively reflect the design intention and actual wearing needs, and overall improves the scientificity and practicality of the intelligent digital design method of three-dimensional prototype clothing, and provides strong support for personalized customization and rapid response to market demand. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 A schematic diagram of the steps of a digital design method for three-dimensional prototype clothing;

[0070] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0071] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0072] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0073] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0074] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0075] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0076] To achieve this, please refer to Figures 1 to 3 , a digital design method for three-dimensional prototype clothing, comprising the following steps:

[0077] Step S1: obtaining three-dimensional scanning data of a human body; annotating feature points of the three-dimensional scanning data of the human body to obtain annotated feature data; reconstructing a three-dimensional model of the human body based on the annotated feature data to generate a three-dimensional model of the human body;

[0078] Step S2: performing contour loose volume calculation on the human body three-dimensional model to obtain a loose volume data set; performing template plane analysis on the human body three-dimensional model based on the loose volume data set to generate a plane template data set;

[0079] Step S3: collecting clothing fabric data; mapping the physical properties of the plane sample data set based on the clothing fabric data to obtain a physical data set; reconstructing a clothing 3D model of the physical data set to generate a clothing 3D model;

[0080] Step S4: spatially positioning the plane sample data set to obtain a sample position data set; performing virtual sewing simulation on the garment three-dimensional model based on the sample position data set to obtain a garment shape data set;

[0081] Step S5: performing dynamic motion analysis on the clothing morphology data set according to the human body three-dimensional model to generate dynamic clothing change data; performing comfort evaluation on the dynamic clothing change data to obtain a clothing comfort score;

[0082] Step S6: Based on the clothing comfort score, the clothing shape data set is locally adjusted to obtain adjusted clothing data; the plane sample data set is reconstructed using the adjusted clothing data to generate an adjusted plane sample data set to execute the intelligent digital design method of the three-dimensional prototype clothing.

[0083] The present invention reconstructs a three-dimensional model of a human body by acquiring three-dimensional scanning data of a human body and marking feature points. The high-precision three-dimensional scanning technology can realize accurate capture of complex human body shapes, and the fineness and accuracy of the human body model are improved by marking feature points. The generated three-dimensional human body model has a real physical shape. The contour looseness of the human body three-dimensional model is calculated, and a plane sample data set is generated based on the looseness data set. By calculating the looseness of the human body contour, the morphological changes and wearing space of different parts of the human body can be accurately reflected, providing a scientific basis for the design of plane samples. Through the sample plane analysis, the structural design of the clothing is further optimized, so that it can better fit the human body curve, avoiding the phenomenon of looseness and inappropriateness in traditional sample design. The clothing fabric data is collected and the physical properties of the plane sample data set are mapped to the plane sample data set based on the fabric data to reconstruct the clothing three-dimensional model. The physical properties of the clothing fabric, such as elasticity, air permeability and softness, etc., can be collected and analyzed. The fabric properties can be accurately mapped to the plane sample, thereby generating a high-precision three-dimensional clothing model, ensuring that the designed clothing matches the actual fabric in physical properties. The plane sample data set is spatially positioned, and the clothing three-dimensional model is mapped based on the sample position data set. Virtual sewing simulation is performed to obtain a clothing morphology dataset. The arrangement and placement of the samples in three-dimensional space are optimized through the spatial positioning of the samples. Virtual sewing simulation technology can simulate clothing deformation and fabric stress in the actual sewing process. Dynamic motion analysis of the clothing morphology dataset is performed based on the three-dimensional model of the human body, and the comfort of the dynamic clothing change data is evaluated to generate a clothing comfort score. Combined with the dynamic motion analysis of the three-dimensional model of the human body, the posture changes of the human body under different actions can be simulated to evaluate the comfort of clothing in various motion states. Through the analysis of the dynamic changes of clothing, the adaptability and comfort of clothing can be grasped in real time during the design process. Based on the clothing comfort score, the clothing morphology dataset is locally adjusted, and the adjusted clothing data is used to reconstruct the flat sample dataset to generate an adjusted flat sample dataset. Through the local morphology adjustment technology, the fit and comfort of clothing can be accurately optimized to ensure that the clothing can adapt to the dynamic changes of the human body to the greatest extent during actual wearing. Through sample reconstruction, the adjusted data can effectively reflect the real needs of the human body in motion. The final generated adjusted flat sample dataset provides accurate design support for the intelligent digital design of three-dimensional prototype clothing.

[0084] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a digital design method for a three-dimensional prototype garment of the present invention. In this example, the digital design method for a three-dimensional prototype garment comprises the following steps:

[0085] Step S1: obtaining three-dimensional scanning data of a human body; annotating feature points of the three-dimensional scanning data of the human body to obtain annotated feature data; reconstructing a three-dimensional model of the human body based on the annotated feature data to generate a three-dimensional model of the human body;

[0086] In this embodiment, a three-dimensional scanner (such as a structured light scanner or a laser scanner) is used to perform a full-body scan of the human body, collect its surface geometry data, and obtain a high-precision three-dimensional data set. The three-dimensional scanning data includes all geometric information on the surface of the human body, such as curved surfaces, depressions, protruding parts, etc., and the data format is usually a point cloud (point cloud) or a triangular mesh (mesh). Then, based on the scanned data, the key parts (such as shoulders, chest, waist, hips, knees, etc.) in the human body data are marked with feature points using a computer vision algorithm. The feature points are the key positioning points of the human body model and play a vital role in the subsequent analysis. After the feature point marking is completed, the obtained marked feature data set will contain all the marked key point coordinate information. Finally, the marked feature data is converted into a three-dimensional model using a voxel-based (voxel) or mesh reconstruction algorithm. The model automatically performs surface smoothing through the algorithm, repairs any irregular or missing parts, and thus generates the final human body three-dimensional model. The model can be output in a standard STL (stereolithography) format as the basis for subsequent clothing design.

[0087] Step S2: performing contour loose volume calculation on the human body three-dimensional model to obtain a loose volume data set; performing template plane analysis on the human body three-dimensional model based on the loose volume data set to generate a plane template data set;

[0088] In the present embodiment, the contour looseness calculation is performed on the generated human body three-dimensional model, and the contour looseness calculation is used to determine the spatial looseness between each part of the human body and the clothing. This looseness determines the comfort and range of activities of the clothing when wearing. A geometric distance calculation algorithm, such as the shortest distance algorithm, is used to measure the contact distance between the human body surface and the ideal clothing fabric. The looseness data set contains the looseness value of each part, and the data format is a point cloud or a curved surface, which represents the gap between the human body and the clothing design. Then, based on the looseness data set, the sample plane analysis is performed, and the three-dimensional human body model is converted into a two-dimensional plane sample data set using a cutting plane algorithm (such as principal component analysis PCA). During the analysis process, the key parts of the human body model are mapped to a plane using a spatial projection technique to generate a corresponding clothing sample. This process takes into account the curve changes of different parts of the human body, and ensures that the sample keeps the shape of the human body as much as possible after flattening. The generated plane sample data set will be used for subsequent clothing design and adjustment.

[0089] Step S3: collecting clothing fabric data; mapping the physical properties of the plane sample data set based on the clothing fabric data to obtain a physical data set; reconstructing a clothing 3D model of the physical data set to generate a clothing 3D model;

[0090] In this embodiment, the physical data of clothing fabrics are collected, and the clothing fabric data includes physical properties such as material type, fiber composition, density, elasticity, tensile strength, etc., and relevant data are obtained using material testing equipment (such as a universal material testing machine), and the physical data of the fabrics are organized into a database. Then, based on the clothing fabric data, the finite element analysis (FEA) technology is used to map the physical properties of the plane sample data set, simulate the physical performance of the fabric under different conditions such as stress, strain, deformation, etc., and generate a physical data set. The physical data set contains the deformation characteristics of each fabric area, which serves as the basis for generating a three-dimensional model of clothing. Next, the plane sample data is reconstructed into a three-dimensional model of clothing using the physical data set, and simulation is performed using physics-based simulation software (such as CLO 3D, TUKAcad, etc.). By simulating the deformation of the fabric in three-dimensional space, a three-dimensional model of clothing is generated, and the model will present the natural droop, wrinkle and tension characteristics of the fabric, ensuring that the final three-dimensional model truly reflects the physical properties of the clothing.

[0091] Step S4: spatially positioning the plane sample data set to obtain a sample position data set; performing virtual sewing simulation on the garment three-dimensional model based on the sample position data set to obtain a garment shape data set;

[0092] In this embodiment, the plane sample data set is spatially positioned, and the various parts of the plane sample are positioned to the appropriate positions of the three-dimensional human body model by using a spatial coordinate transformation algorithm (such as Euclidean transformation), taking into account the changes in human body shape and the natural fluidity of clothing, to obtain a sample position data set. The data set contains information such as the position, direction, and curvature of the sample in three-dimensional space. Then, based on the sample position data set, the three-dimensional clothing model is stitched by virtual sewing simulation technology to simulate how the clothing fabric is combined during the cutting and sewing process, and virtual sewing is performed by computer-aided design software (such as CLO 3D or Optitex) to obtain a clothing morphology data set. Virtual sewing simulation can accurately simulate the direction of the suture line, the curvature and tension of the fabric, so that the clothing presents a realistic form in three-dimensional space, ensuring that the clothing can fit the actual size of the human body.

[0093] Step S5: performing dynamic motion analysis on the clothing morphology data set according to the human body three-dimensional model to generate dynamic clothing change data; performing comfort evaluation on the dynamic clothing change data to obtain a clothing comfort score;

[0094] In the present embodiment, dynamic motion analysis is performed according to the human body three-dimensional model, and the dynamic changes of the human body in different activities are captured using human motion capture technology (such as Vicon Motion Capture), and combined with the clothing morphology data set, how the clothing responds to the action of the human body during dynamic motion is simulated. Physical simulation software (such as Simulink and Matlab combined with motion simulation module) is used to analyze the performance of clothing under human motion, and dynamic clothing change data is generated, including the change processes such as the stretching, contraction, and wrinkles of clothing fabrics. Then, based on the dynamic clothing change data, the comfort of clothing is evaluated, and the comfort score of clothing in motion is calculated using a comfort model (such as a model based on factors such as heat conduction and moisture emission), and the comfort score takes into account factors such as the fit of clothing, freedom of movement, and breathability of fabrics, and finally generates clothing comfort score.

[0095] Step S6: Based on the clothing comfort score, the clothing shape data set is locally adjusted to obtain adjusted clothing data; the plane sample data set is reconstructed using the adjusted clothing data to generate an adjusted plane sample data set to execute the intelligent digital design method of the three-dimensional prototype clothing.

[0096] In this embodiment, the clothing shape data set is locally adjusted according to the clothing comfort score, and the uncomfortable parts are optimized by analyzing the comfort differences of different parts. During the adjustment, the fabric tension, curvature, etc. of each part are finely controlled to obtain the adjusted clothing data. Then, the adjusted clothing data is used to reconstruct the flat sample data set. Based on the adjusted three-dimensional clothing shape, the corrected three-dimensional shape is mapped to the flat sample using reverse engineering technology. The adjusted flat sample data set is generated through the sample reconstruction algorithm (such as reverse planning technology). The data set will reflect the optimized shape of the clothing, and finally the flat sample file for production is output.

[0097] Preferably, step S1 comprises the following steps:

[0098] Step S11: collecting three-dimensional scanning data of a human body; performing human feature point recognition on the three-dimensional scanning data of the human body to obtain feature point data;

[0099] Step S12: highlighting and marking the feature point data to obtain marked feature data; performing surface fitting processing on the marked feature data to generate a surface data set;

[0100] Step S13: constructing a skeleton point structure for the surface data set based on the annotated feature data to generate a human skeleton data set;

[0101] Step S14: reconstructing the three-dimensional model of the human skeleton data set to generate a three-dimensional model of the human body.

[0102] In this embodiment, a full-body scan of a human body is performed by a three-dimensional scanner (such as a structured light scanner or a laser scanner) to collect high-precision three-dimensional data. The scanning result is usually presented in the form of point cloud data or a triangular mesh. The point cloud data contains all geometric information on the human body surface. Then, the collected three-dimensional data is processed using computer vision and image processing algorithms. The key feature points of the human body, including shoulders, waist, knees, ankles, etc., are automatically identified from the point cloud by a detection algorithm (such as a convolutional neural network CNN based on deep learning). The feature points are the basis for positioning the human body model. During the recognition process, the accuracy is improved by extracting information such as surface normals and point density. The feature point data set obtained contains the precise three-dimensional coordinates of the key parts of the human body. As the basis for subsequent reconstruction and analysis, the feature points in the three-dimensional data of the human body are highlighted and annotated using graphic processing technology. The marked feature points are highlighted by color mapping or brightness enhancement technology, so that these points are easier to identify and operate in the subsequent processing process. The annotation process is usually combined with three-dimensional rendering technology based on OpenGL for real-time visualization. Next, based on the highlighted annotated feature data, a surface fitting algorithm (such as B-spline fitting or NURBS fitting) is used to smooth and fit the human body surface. During the fitting process, the surface around the feature points is modeled through an optimization algorithm (such as the least squares method) to obtain a smoother and continuous surface. The generated surface dataset contains mathematical expressions of various parts of the human body surface, including detailed surface shapes of shoulders, waist, chest and other parts, providing accurate geometric data for subsequent three-dimensional model reconstruction. According to the annotated feature data, the key points of the human body are selected as bone points, and a skeleton structure is constructed based on these bone points. The skeleton structure adopts a segmented connection method and uses an interpolation algorithm (such as linear interpolation or spline interpolation) to connect different feature points to construct the joints and skeleton data of the human body. This can accurately describe the spatial relationship and angle between each part. The generated skeleton structure dataset will contain the spatial coordinates of each bone point and the skeleton line segments connecting the bone points. Next, these skeleton points are further optimized using 3D modeling tools (such as Blender or Maya) to ensure that the skeleton dataset conforms to the natural anatomical structure of the human body. The skeleton dataset is not only used to represent the human body's posture, but also provides an accurate framework for clothing design, as the basis for subsequent clothing morphology reconstruction and sample generation. Based on the generated human skeleton dataset, a skeleton-driven 3D model reconstruction method is adopted. First, the human skeleton data is mapped to the corresponding 3D surface, and the skeleton is controlled by using a skeleton-driven deformation algorithm (such as free shape deformation FFD or Laplace smoothing algorithm) to reconstruct the human body's outer contour and ensure that the model conforms to the natural anatomical structure of the human body.The reconstructed skeleton-driven 3D mesh is refined using modeling software (such as ZBrush or 3D Studio Max) to generate a complete 3D human model, which not only accurately reflects the various parts of the human body, such as the chest, abdomen, hips, legs, etc., but also reflects the structure of muscles and bones. The 3D model is optimized in detail, and existing seams and transition problems are repaired to ensure that the final model has high fidelity, and finally output as a file in STL or OBJ format as the basic data for subsequent clothing design and virtual fitting.

[0103] Preferably, step S2 comprises the following steps:

[0104] Step S21: Slice the human body three-dimensional model in cross section to obtain human body model slice data; calculate key girths of the human body model slice data to generate girth data;

[0105] Step S22: performing contour looseness calculation on the human body model slice data based on the circumference data to obtain a looseness data set; performing size calibration calculation on the looseness data set to generate template adjustment data;

[0106] Step S23: performing plane projection conversion on the human body three-dimensional model to obtain candidate model projection data; performing structure line layout processing on the candidate model projection data to obtain structure line layout data;

[0107] Step S24: Calculate the structural parameters of the structural line layout data to generate plane template structural data; calibrate the plane template structural data based on the template adjustment data to generate a plane template data set.

[0108] As an example of the present invention, see Figure 2 In this example, step S2 includes:

[0109] Step S21: Slice the human body three-dimensional model in cross section to obtain human body model slice data; calculate key girths of the human body model slice data to generate girth data;

[0110] In this embodiment, a three-dimensional modeling software (such as Blender and Maya) is used to perform cross-sectional slices on the three-dimensional human body model, and the cutting plane is set to cut from top to bottom at specific intervals (for example, every 5 cm) to obtain a series of slice data. During the slicing process, the three-dimensional shape of the model is converted into a two-dimensional plane using orthogonal projection, and the contour information of the human body is extracted through the point cloud data to generate a file containing slice data of various parts of the human body. The data of each slice includes the coordinate information of all points on the cutting line. Then, key circumference calculations are performed on the slice data. The circumference calculations are solved by measuring the maximum horizontal width of each slice and the circumferences of key parts such as chest circumference and waist circumference. The circumference data include multiple circumference values ​​such as chest circumference, waist circumference, hip circumference, etc., which are used to characterize the sizes of various parts of the human body and provide accurate references for subsequent sample design and clothing production.

[0111] Step S22: performing contour looseness calculation on the human body model slice data based on the circumference data to obtain a looseness data set; performing size calibration calculation on the looseness data set to generate template adjustment data;

[0112] In this embodiment, contour looseness calculation is performed on each cross-sectional slice data. The looseness calculation is performed by comparing the difference between the actual three-dimensional surface data of the human body and the wearing space required for the clothing, taking into account the curvature of the human body surface and the ductility of the clothing fabric, and calculating the looseness value of each slice. The looseness value reflects the degree of looseness of the clothing in certain parts, and a looseness data set is obtained. The looseness data set records the looseness information of various parts (such as chest, abdomen, buttocks, etc.). Then, based on the looseness data set, a size calibration calculation is performed. During the calibration process, a preset standard size template is used to compare with the current data, and the size parameters of each part are adjusted to generate sample adjustment data. The sample adjustment data provides the specific size that should be adjusted for each part to ensure the suitability of the clothing. The adjustment data is mainly used for subsequent plane sample generation to ensure that the designed clothing can adapt to the shape of the target human body.

[0113] Step S23: performing plane projection conversion on the human body three-dimensional model to obtain candidate model projection data; performing structure line layout processing on the candidate model projection data to obtain structure line layout data;

[0114] In this embodiment, the three-dimensional model of the human body is converted into a plane projection, and the three-dimensional shape of the human body is projected into a two-dimensional plane using a projection method (such as orthogonal projection or perspective projection), and a specific projection direction (such as front view, side view or upward view) is selected to obtain candidate model projection data. During the projection process, the three-dimensional surface data of the human body is projected according to the projection direction to obtain a two-dimensional contour map. Then, the candidate model projection data is processed for structural line layout. By analyzing the key morphological features in the projection data, an algorithm is used to automatically generate the structural lines of the clothing, such as shoulder line, chest line, waist line, hip line, etc. The structural line layout data records the specific position and shape of each structural line in the clothing design, and a CAD (computer-aided design) system or a special clothing design software (such as Optitex or TUKAcad) is used to optimize and adjust the distribution of these structural lines to ensure that they conform to the natural shape of the human body.

[0115] Step S24: Calculate the structural parameters of the structural line layout data to generate plane template structural data; calibrate the plane template structural data based on the template adjustment data to generate a plane template data set.

[0116] In this embodiment, structural parameter calculation is performed on the structural line layout data, and the curvature, angle, distance and other parameters of the structural line are accurately calculated through geometric calculation and analysis algorithms. The structural parameter calculation takes into account the range of motion, comfort and fit of the human body, and generates plane sample structure data. The sample structure data contains detailed information of each part, including the specific shape and size of the front piece, back piece, sleeves, etc. Then, based on the sample adjustment data, the size of the plane sample structure data is calibrated. During the calibration process, the size of each part is optimized and fine-tuned according to the sample adjustment data obtained in the previous step, ensuring that the various parameters of the plane sample data set are completely matched with the target human body model. The generated plane sample data set records the final design size of the clothing, providing basic data for subsequent actual clothing production. The sample data set can be exported to DXF or PDF format for subsequent cutting and production processes.

[0117] Preferably, step S22 includes the following steps:

[0118] Performing contour extraction on the slice data of the human body model to obtain a slice contour data set; performing feature region division on the slice contour data set to generate feature region data;

[0119] The curvature of the feature area data is calculated to obtain a regional curvature data set; local looseness distribution is performed on the regional curvature data set based on the circumference data to obtain a looseness data set;

[0120] Performing dimension measurement on the loose volume data set to obtain loose volume measurement data; performing correction amount calculation on the loose volume measurement data to generate dimension correction amount data;

[0121] The size correction amount data is mapped to the clothing pattern to generate pattern adjustment data.

[0122] In this embodiment, contour extraction is performed on the slice data of the human body model, and a contour detection algorithm (such as the Canny edge detection algorithm) is used to analyze the boundary of each slice of the human body to extract the contour information of the slice. The contour data is obtained by performing edge analysis on the two-dimensional data of the slice. The extracted contour data set includes the shape and size of each cross section of the human body. The tool used can be the OpenCV library based on the Python language or the image processing toolbox in MATLAB. The edge of the slice image is extracted by setting different thresholds to obtain clear contour information. The slice contour data set includes the vertex coordinates and connection information of each slice, and records the external boundary of the human body shape. The extracted slice contour data set is divided into feature regions. First, a region growing algorithm (Region The region division is based on the morphological characteristics of different parts of the human body, such as the chest, abdomen, buttocks, etc. During the division process, the contour is divided into different regions according to factors such as the smoothness, curvature and edge change of the contour. Each region contains a set of similar curve segments. By calculating the inner and outer boundaries and curve shapes of each region in the contour, a feature region data set is generated. The feature region data contains the specific geometric information of different parts and the boundary points of each region and the shape parameters within the region. After the feature region data is divided, the curvature calculation is performed. The curvature calculation algorithm (such as discrete curvature or Gaussian curvature calculation) is used to perform curvature analysis on the boundary of each region. The curvature calculation takes into account the curvature of the curve in the region. The curvature value is obtained by calculating the second-order derivative of the boundary point of each region. The regional curvature data set includes the curvature distribution of each feature region. The tool used is the Python-based SciPy library. The curvature calculation result is represented by the curvature value of each region and the coordinates of its corresponding position. The calculation process is performed by performing multiple operations on the curve of each region. The precise curvature value is obtained by fitting the formula. The looseness is allocated to the area with larger or smaller curvature according to the circumference information of the human body parts (such as chest circumference, waist circumference, hip circumference, etc.). The basis for the allocation of looseness is the flexibility and comfort requirements of various parts of the body. For areas with larger curvature (such as joints), larger looseness is allocated to ensure comfort during clothing design. For areas with smaller curvature (such as chest or abdomen), smaller looseness is allocated. By calculating the relationship between circumference data and curvature, a looseness data set is generated. The looseness data set contains the looseness value to be allocated to each area. The looseness allocation process uses a volume algorithm combined with least squares optimization to accurately calculate the looseness demand of each area, and the size of the looseness data set is measured. The looseness of each feature area is quantitatively evaluated using a geometric measurement algorithm. During the measurement process, the initial size of each area is first calculated, and the actual size of the area is adjusted according to the looseness data. The looseness measurement data is obtained by adjusting the circumference, length and width of each area. The looseness measurement data records the looseness increment of each area and its corresponding size change. The specific measurement method uses a linear regression algorithm.By calibrating the known size model, the influence of loose adjustment on the size of each area is obtained, and the loose measurement data is obtained. Based on the loose measurement data, the size correction amount is calculated. The correction amount calculation uses the least squares method or iterative optimization algorithm to fine-tune the size data according to the loose requirements of different parts. The nonlinear characteristics of the human body model and the physical properties of the fabric are taken into account during the correction process. The adjustment result is adjusted by correcting the specific size of each part to ensure that the clothing meets the comfort requirements of the human body. The input of the correction amount calculation is the loose measurement data, and the output is the size correction amount data. The size correction amount data records the specific values ​​​​needed to adjust for each area. The correction amount calculation method combines the clothing design standards and the human body model data for global optimization through the algorithm to ensure To ensure that the final size correction data conforms to the overall proportion of the human body, the size correction data is mapped to the clothing pattern. First, the size correction data is compared with the original plane pattern, and the correction is applied to each pattern part through parametric mapping. The pattern adjustment data generates a new plane pattern by applying the correction to the size of key parts such as the chest, waist, and hips. During the clothing pattern mapping process, the CAD system (such as Gerber, Lectra, etc.) is used to reconstruct the pattern. The mapped pattern adjustment data includes the size parameters adjusted according to the correction and the corresponding plane pattern structure data. The generated pattern adjustment data set provides the final optimized pattern size, providing accurate data support for actual production and cutting.

[0123] Preferably, step S3 comprises the following steps:

[0124] Step S31: collecting clothing fabric data; performing a drape test on the clothing fabric data to obtain clothing drape data;

[0125] Step S32: performing clothing characteristic analysis on the clothing drape data to generate a clothing physical characteristic data set; performing physical characteristic mapping on the plane sample data set based on the clothing physical characteristic data set to obtain a physical data set;

[0126] Step S33: performing stress distribution calculation on the physical data set to obtain clothing physical stress data; performing deformation simulation processing on the clothing physical stress data to generate simulated deformation data;

[0127] Step S34: performing clothing shape prediction on the simulated deformation data to obtain predicted clothing shape data; performing three-dimensional model reconstruction on the predicted clothing shape data to generate a clothing three-dimensional model.

[0128] As an example of the present invention, see Figure 3 In this example, step S3 includes:

[0129] Step S31: collecting clothing fabric data; performing a drape test on the clothing fabric data to obtain clothing drape data;

[0130] In this embodiment, the relevant physical data of the clothing fabric is collected by sensors, and the sensor network is used to collect information such as the density, thickness, elastic modulus, etc. of the fabric. The fabric data collection uses a tension sensor (such as Futek's force sensor) to monitor the physical properties of the fabric such as stretching, bending and rebound in real time. The obtained fabric data set contains various mechanical property parameters of the fabric. Next, a drape test is performed. The clothing fabric is vertically hung on a fixed point using a hanging device to measure the drooping shape of the fabric under the action of gravity. During the test, the stress condition of the fabric is detected by a strain gauge, and the data records the drooping angle, curvature and other characteristics of the fabric at different positions. The clothing drape data set is generated through these data. The drape characteristics of the fabric reflect the softness, thickness and elasticity of the fabric.

[0131] Step S32: performing clothing characteristic analysis on the clothing drape data to generate a clothing physical characteristic data set; performing physical characteristic mapping on the plane sample data set based on the clothing physical characteristic data set to obtain a physical data set;

[0132] In this embodiment, clothing characteristics analysis is performed on clothing drape data through data analysis, and the finite element analysis (FEA) method is used to perform numerical simulation on the clothing drape data, simulate the deformation and response of the fabric under different stress conditions, analyze the elasticity and stiffness of the fabric in the data set, and the mechanical response in the drooping state. The clothing physical characteristic data set includes parameters such as elastic modulus, Young's modulus, Poisson's ratio, and tensile strength of the clothing fabric. Then, physical characteristics mapping is performed on the plane sample data set based on the clothing physical characteristic data set, and the physical characteristics of the clothing fabric are mapped to different areas of the sample using a numerical optimization method. The mapping process generates a corresponding physical data set by simulating the contact mode and deformation state of the fabric and the sample. The physical data set contains the mechanical properties applied by the fabric in different areas, including the stress distribution and deformation coefficient of the fabric. These physical characteristics are combined with the geometric shape of the plane sample through a CAD system (such as Gerber or Lectra).

[0133] Step S33: performing stress distribution calculation on the physical data set to obtain clothing physical stress data; performing deformation simulation processing on the clothing physical stress data to generate simulated deformation data;

[0134] In this embodiment, stress distribution calculation is performed on the physical data set, and stress calculation is performed on the physical data set of the clothing using a finite element analysis tool (such as ANSYS or Abaqus). The input physical data set includes the elastic modulus and actual force distribution of the fabric. The stress state of each part of the clothing during wearing is calculated through stress analysis. The obtained physical stress data of the clothing records the stress value and its corresponding position of the clothing at each part. Next, a deformation simulation algorithm is used to perform deformation simulation processing on the physical stress data of the clothing. The nonlinear finite element analysis (NLFEA) method is used to input the stress distribution of the fabric into the clothing model to simulate the deformation of the clothing under different force conditions. The deformation simulation data includes the deformation amount of the clothing at each key part (such as shoulders, chest, waist, buttocks, etc.), and the generated simulated deformation data records the deformation amplitude and displacement of the clothing, as well as wrinkles, stretching, and other phenomena that may occur during the deformation process.

[0135] Step S34: performing clothing shape prediction on the simulated deformation data to obtain predicted clothing shape data; performing three-dimensional model reconstruction on the predicted clothing shape data to generate a clothing three-dimensional model.

[0136] In this embodiment, the morphology of the clothing is predicted based on the simulated deformation data, and the morphology change of the clothing in the actual wearing state is predicted using a physics-based morphology prediction algorithm (for example, a morphology analysis method based on fluid dynamics). The final morphology data of the clothing is deduced by combining the simulated deformation data and the physical properties of the fabric. The clothing morphology prediction includes the deformation effect of each part of the clothing during the wearing process and the position and degree of wrinkles of the clothing. Then, a three-dimensional model is reconstructed according to the predicted clothing morphology data, and the predicted clothing morphology is modeled using three-dimensional modeling software (for example, Blender or Rhinoceros) to construct a three-dimensional clothing model that conforms to the actual wearing state. During the model reconstruction process, the details of the three-dimensional model are adjusted using the predicted data to ensure that each part of the clothing matches the predicted data, and finally a three-dimensional model of the clothing is generated. The model not only has an accurate geometric shape, but also reflects the morphological characteristics of the clothing under force, thereby providing data support for the subsequent virtual wearing effect display.

[0137] Preferably, step S4 comprises the following steps:

[0138] Step S41: calibrating the reference points of the plane sample data set to obtain sample reference data; performing spatial coordinate conversion on the sample reference data to generate sample coordinate data;

[0139] Step S42: Calculate the posture angle of the template coordinate data to obtain coordinate angle data; adjust the relative position of the template reference data based on the coordinate angle data to generate template position data;

[0140] Step S43: performing stitching line recognition on the template position data to obtain the template stitching line position; performing stitching path simulation on the garment three-dimensional model based on the template stitching line position to generate a simulated candidate stitching path;

[0141] Step S44: performing seam deformation calculation on the simulated candidate suture path to generate seam deformation data; performing suture path adjustment on the simulated candidate suture path according to the seam deformation data to obtain a simulated suture path;

[0142] Step S45: performing virtual sewing simulation on the three-dimensional clothing model based on the simulated sewing path to obtain a clothing morphology data set.

[0143] In this embodiment, the plane sample data set is calibrated with reference points. Several reference points are selected from the design pattern of the sample. The key areas of the sample (such as shoulders, waist and hips) are usually selected as calibration points. The specific positions of these reference points are marked by a two-dimensional coordinate system. The calibration process can be performed by digitally scanning the sample with a high-precision digital scanner (such as a FARO scanner) and extracting coordinate information to obtain the sample reference data. Subsequently, the calibrated sample reference data is converted from the two-dimensional coordinate system to the three-dimensional coordinate system using a spatial coordinate conversion method. The common spatial coordinate conversion algorithm ( The 3D coordinate system of the computer is a very powerful concept used in almost all computer graphics applications. The computer graphics software is used to generate the 3D coordinate system of the computer graphics software. The 3D coordinate system of the computer graphics software is a very powerful concept used in almost all computer graphics applications. The 3D coordinate system of the computer graphics software is a very powerful concept used in almost all computer graphics applications. The relative position of the template reference data is adjusted. During the adjustment process, the coordinate translation and rotation methods are used to optimize the position of the template in the three-dimensional space to ensure that the position of the template meets the design requirements. The template position data contains the precise position and posture of the template after adjustment. Through this step, the precise placement and alignment of the template in the three-dimensional space are achieved. The template position data is used for seam line recognition. By analyzing the outline and design drawing of the template, the seam lines in the template are identified. Computer vision technology (such as image edge detection algorithm Canny or Hough transform) is used to analyze the image of the template to extract the marked seam line positions. The position data of the sample seam line are obtained. These data record the position, line type and direction of each part of the sample that needs to be sewn. Then, based on the position data of the sample seam line, the three-dimensional clothing model is simulated by seam path. First, the seam line of the sample is mapped to the surface of the three-dimensional clothing model. The path planning algorithm (such as A* algorithm) is used to simulate the seam path to generate candidate seam path data. The bending and stretching characteristics of the fabric need to be considered during the simulation process to ensure that the seam path fits the actual shape of the clothing during the simulation process. The seam deformation of the simulated candidate seam path is calculated. The finite element analysis method (Finite Element Analysis,FEA) performs deformation calculation of the seam area on the simulated candidate sewing path. The specific method is to apply the simulated path to the clothing model, calculate the local stress and deformation caused by sewing on both sides of the seam line, and generate seam deformation data by simulating the stress-strain relationship of the fabric. The seam deformation data includes information such as contraction, expansion and stretching of the fabric caused by sewing during the sewing process. Then, the simulated candidate sewing path is adjusted based on the seam deformation data. During the adjustment process, the original sewing path is optimized using the seam deformation data. The adjusted sewing path can maintain the morphological consistency of the sample and the three-dimensional model of the clothing during the actual sewing process, avoiding deformation distortion during the sewing process, and finally generating an optimized simulated sewing path. Based on the optimized simulated sewing path, the three-dimensional model of the clothing is virtually sewn. Computer-aided design (CAD) software (such as CLO 3D or Browzwear) performs virtual sewing on the three-dimensional model of clothing. By applying the optimized sewing path to the three-dimensional model in the simulation environment, the sewing process of the clothing is simulated. In the simulation, deformation calculation is performed according to the physical properties of different fabrics to generate the final shape of the clothing after sewing. During the simulation process, various data of the clothing need to be recorded, including the overall shape change, deformation of each part, and stress distribution at the seam. Finally, the clothing shape data set is obtained. This data set contains the appearance, size and detail data of the clothing after virtual sewing, providing data support for subsequent sample production and physical fitting. ,

[0144] Preferably, step S44 includes the following steps:

[0145] Calculate stress points on the simulated candidate suture path to obtain suture stress data; determine the force direction of the suture stress data to generate stress direction data;

[0146] Perform stress accumulation calculation on the stitching stress data based on the stress direction data to generate stress accumulation data; perform deformation calculation on the three-dimensional model of the clothing based on the stress accumulation data to obtain deformation data;

[0147] Perform surface topology analysis on the three-dimensional clothing model according to the deformation data to obtain surface topology data; perform deformation trend prediction on the surface topology data to obtain seam deformation data;

[0148] Repositioning nodes of the simulated candidate suture path based on the seam deformation data to obtain repositioning data; performing curve fitting processing on the repositioning data to generate repositioning fitting data;

[0149] The simulated candidate stitching path is modified according to the repositioned fitting data to generate a simulated stitching path.

[0150] In this embodiment, stress points of the simulated candidate stitching path are calculated, and the finite element analysis (FEA) technology is used to divide the three-dimensional clothing model into several small units. The stress value of each point on the stitching path is obtained by performing stress analysis and calculation on these units. The mechanical properties of the material, such as elastic modulus and Poisson's ratio, are considered in the calculation process to obtain the data of each stress point on the stitching path. Then, the force direction of the stitching stress data is judged. The vector analysis method is used to judge the force direction of each stress point according to the components of the stress data in different directions. The main stress direction calculation is usually used, that is, the maximum value of the stress data and its corresponding direction are analyzed to generate stress direction data. These data record the main force direction of each point on the stitching path. The stitching stress data is analyzed based on the stress direction data. Stress accumulation calculation is performed. Under the guidance of stress direction data, the stress of each stress point on the stitching path is accumulated. First, according to the geometric shape of the stitching path, the path is divided into multiple segments. The stress data of each segment is accumulated by direction. The stress superposition effect of the adjacent nodes of each segment is taken into account during the calculation process. The specific operation is to calculate the total stress of each segment along the stitching path direction to generate stress accumulation data. The accumulation result can reflect the stress distribution on the entire stitching path, especially in the area with large local pressure. The deformation variable of the three-dimensional clothing model is calculated using the stress accumulation data, and the entire three-dimensional clothing model is analyzed by the deformation theory of the mechanical model. The finite element method (FEA) is used for further calculation. The deformation of the model after being subjected to force, first convert the stress accumulation data into the form of force, apply it to each node of the three-dimensional clothing model, use computer simulation software (such as ANSYS or ABAQUS) to analyze the force model, calculate the deformation value of each node, the deformation data includes the displacement of each node, deformation morphology and other information, these data reflect the deformation of the clothing model under stress, based on the deformation data, the three-dimensional clothing model is subjected to surface topological analysis, by mapping the deformation data to the three-dimensional surface of the clothing, the topological structure is calculated and analyzed, and the topological changes of the clothing surface after deformation are analyzed using geometric features such as surface curvature and normal direction. First, the clothing is generated using a three-dimensional mesh generation algorithm. The surface of the model is divided into multiple grids, and the grid nodes are corrected in combination with the deformation data. The topological changes of each grid unit are calculated to generate surface topological data. The surface topological data includes the deformation trend, morphological change and local surface change information of each area on the clothing surface. The deformation trend of the surface topological data is predicted. The surface fitting and morphological transformation model is used to analyze the deformation trend of the clothing surface and calculate the deformation trend of each area of ​​the clothing in combination with the movement of the points on the surface. The deformation at the seam is predicted. First, the deformed clothing surface is smoothed using surface fitting technology (such as B-spline surface or NURBS surface), the deformation trend of the seam area is predicted, and the seam deformation data is obtained.These data include deformation information such as stretching, shrinkage, and distortion at the seams during the suturing process. The nodes of the simulated candidate suturing path are relocated based on the seam deformation data. The nodes on the suturing path are relocated by calculating the new position of each node after deformation. First, the seam deformation data is compared with the preliminary node position of the suturing path, and the displacement value of each node is calculated. Then, based on these displacement values, the position of the suturing path nodes is adjusted to obtain the relocated data. The relocated data includes the new accurate positions of all suturing path nodes after deformation. Curve fitting is performed on the relocated data. Curve smoothing is performed on the relocated suturing path nodes through a curve fitting algorithm (such as the least squares method and Bezier curve fitting). First, all node data of the suturing path are preprocessed to remove abnormal data, and then the curve fitting is performed. The algorithm generates a smooth stitching path and obtains the repositioning fitting data. The repositioning fitting data is a smooth stitching path after adjustment, which can ensure the rationality and accuracy of the stitching line in the three-dimensional model of the garment. The simulated candidate stitching path is modified according to the repositioning fitting data. First, the repositioning fitting data is compared with the original path of the simulated candidate stitching path, and the difference between the two is calculated. The position and shape of the original path are adjusted according to the fitting data. The adjusted path is optimized using a path optimization algorithm (such as Bézier curve optimization or Catmull-Rom spline) to ensure that the path is smoother and conforms to the garment shape. Finally, the optimized simulated stitching path is generated. The modified stitching path can fit the three-dimensional garment model more accurately in the actual stitching process, ensuring that the stitching effect is consistent with the design requirements. ,

[0151] Preferably, step S5 comprises the following steps:

[0152] Step S51: calibrating joint points of a human body three-dimensional model to obtain joint data; calculating motion trajectories of the joint data to generate motion trajectory data;

[0153] Step S52: performing a motion range trajectory analysis on the movable trajectory data to obtain a movable fluctuation range; performing a clothing change analysis on the clothing form data set based on the movable fluctuation range to generate dynamic clothing change data;

[0154] Step S53: Calculate the contact area of ​​the dynamic clothing change data based on the three-dimensional human body model to obtain contact area data; calculate the local pressure distribution of the contact area data to generate a local stress data set;

[0155] Step S54: performing pressure uniformity evaluation on the local stress data set to obtain pressure uniformity data; performing activity restriction evaluation on the pressure uniformity data according to a preset pressure uniformity threshold to generate local clothing activity restriction data;

[0156] Step S55: Perform comfort mapping on the local clothing activity restriction data to obtain a clothing comfort score.

[0157] In this embodiment, the joint points of the human body three-dimensional model are calibrated, and a motion capture system (such as OptiTrack or Vicon) is used to accurately collect three-dimensional data of the human body through multi-camera technology to obtain three-dimensional coordinate data of human joints. During calibration, the positions of key joints of the human body (such as knee joints, elbow joints, shoulder joints, etc.) are accurately identified to obtain joint data, which include the three-dimensional coordinates and joint angle information of the joints. Then, the motion trajectory of the joint data is calculated, and the trajectory of each joint in motion is calculated using a physical modeling algorithm (such as the Euler angle method or the quaternion method) to generate movable trajectory data, which records the motion path of each joint within a certain time range, taking into account the degree of freedom of the joint and the approximate Constraint conditions are set to obtain the trajectory information of human joints in various activities. Based on the movable trajectory data, the motion range of each joint is analyzed. Curve fitting and interpolation methods (such as B-spline or Lagrange interpolation) are used to accurately model the motion trajectory of each joint, calculate the fluctuation range of the joint within the maximum range of motion, and generate movable fluctuation range data. The maximum and minimum angle restrictions of the joints in different activity states are taken into account during the analysis process. Then, based on the movable fluctuation range, the clothing morphology data set is analyzed for clothing changes. By combining the motion trajectory of the human body with the clothing morphology, physical simulation algorithms (such as finite element analysis or rigid body dynamics) are used to simulate the morphological changes of clothing during joint movement, and dynamic clothing is generated. The contact area of ​​dynamic clothing change data is calculated based on the three-dimensional model of the human body. By calculating each point where the clothing contacts the human body, the clothing surface is divided into multiple small units using meshing technology (such as Delaunay triangulation), and then the area of ​​contact between each small unit and the human body surface is calculated to obtain contact area data. This data records the size of the contact area between the clothing and the human body under different motion states. Next, the local pressure distribution of the contact area data is calculated. By introducing a mechanical model and combining the biomechanical characteristics of the human body, the pressure on each contact point is simulated. The finite element analysis (FEA) method is used to apply mechanical stress to each contact point of the clothing to obtain a local stress data set. This data records the contact area of ​​each clothing. The distribution of forces at different contact points of the part is used to evaluate the pressure uniformity of the local stress data set. By calculating the pressure distribution of the clothing in different areas, statistical methods such as standard deviation and root mean square error (RMS) are used to evaluate the uniformity of the pressure. The specific operation is to compare the pressure value of each contact point with the pressure value of the adjacent point, calculate the pressure distribution balance of each area on the surface of the clothing, and obtain the pressure uniformity data. This data reflects the uniformity of the force-bearing area of ​​the clothing. Then, the pressure uniformity data is evaluated for activity restriction according to the preset pressure uniformity threshold. If the pressure uniformity of a certain area is lower than the set threshold, it indicates that the pressure distribution in the area is uneven, which will lead to activity restriction or discomfort, and generate local clothing activity restriction data.The data provides clothing activity restriction areas based on pressure analysis, and comfort mapping is performed based on local clothing activity restriction data. By combining activity restriction data with clothing comfort scoring models, the activity restriction data of different areas are converted into comfort scores using the weighted average method. First, the comfort score of each area is calculated based on the area and pressure distribution of the restricted area in the local clothing activity restriction data. Then, the comfort scores of all areas are combined according to a certain weight to obtain the overall clothing comfort score. During the scoring process, the areas with the most concentrated force, such as shoulders, waist, knees, etc., are given priority consideration to ensure that the comfort in these key areas can be reasonably evaluated. Finally, the clothing comfort score is generated, which can be used to guide the optimization and improvement of clothing design.

[0158] Preferably, step S52 includes the following steps:

[0159] Performing direction change identification on the movable trajectory data to obtain direction change data; performing speed distribution analysis on the direction change data to generate change speed data;

[0160] Performing trajectory feature integration on the direction change data and the change speed data to obtain trajectory feature data; performing extreme position marking on the trajectory feature data to obtain marked position data;

[0161] Determine the fluctuation range of the marker position data and generate a movable fluctuation range;

[0162] The clothing morphology data set is deformed mapped based on the movable fluctuation range to obtain clothing deformation mapping data; clothing wrinkles are predicted on the clothing deformation mapping data to generate dynamic clothing change data.

[0163] In this embodiment, the direction change of the movable trajectory data is identified, and the trajectory of the human joint at each moment in the movement process is refined and analyzed using a three-dimensional trajectory analysis algorithm (such as an acceleration vector method), the tangent direction of the motion path is calculated, and the point where the direction changes in the trajectory is identified to obtain the direction change data, which includes the time point when the direction change occurs and the magnitude of the change. Then, the direction change data is analyzed for speed distribution, and a numerical integration method (such as the Euler method or the fourth-order Runge-Kutta method) is used to calculate the movement speed near each direction change point. By analyzing the speed increment near the motion trajectory change point, the change speed data is generated, and the data reflects the speed change when the direction changes. , align the direction change data and the change speed data through time synchronization (such as interpolation method) to form comprehensive trajectory feature data. These feature data include the time when the direction change occurs, the amplitude of the change and the related speed information. The least squares-based curve fitting technology is used to smooth the data to reduce the influence of noise, and a characteristic diagram of the joint movement is drawn according to the calculated trajectory feature data. The movement mode of each trajectory segment is further annotated to generate comprehensive trajectory feature data. The peak detection-based algorithm is used to mark the extreme position of the trajectory feature data. The sliding window technology (such as Hamming window) is used to perform local extreme value analysis on the trajectory data to identify the extreme position in the motion trajectory, such as the extreme position of the motion trajectory. The maximum displacement point and the minimum displacement point, these extreme positions mark the boundaries of the movement. In specific implementation, the velocity data of each trajectory segment is smoothed, and the highest peak and lowest valley of each segment are identified. These extreme positions are marked to obtain the marked position data, which includes the movement extreme position of each joint and its corresponding timestamp. Based on the marked position data, the fluctuation range of the motion trajectory is determined. First, the data of each marked position is classified, and the adjacent extreme position points are connected to form a fluctuation range. The change amplitude of each fluctuation range is evaluated using statistical methods (such as standard deviation calculation) to ensure that the fluctuation range reflects the actual range of motion of the joint during the movement. Finally, combined with the physical characteristics of the joint, The range of motion is generated based on the sex and kinematics model. The data of the range of motion records in detail the fluctuation of human joints within the maximum range of motion. The range of motion is compared and analyzed with the clothing morphology data set. The finite element analysis (FEA) method is used to calculate the local deformation of the clothing surface to simulate the influence of the movement of human joints in different fluctuation ranges on the clothing. The clothing surface will deform with the movement of the joints. In the simulation process, the deformation of each part of the clothing such as stretching, squeezing or shrinking during the movement is calculated according to the actual force of the joints during the movement, and the clothing deformation mapping data is obtained to form the morphological change data of dynamic clothing in the active state. By analyzing the local area of ​​the clothing deformation mapping data,Use deformation and stress simulation (such as stretching theory and Bernoulli-Euler beam theory) to infer the areas where wrinkles appear in certain parts, and use algorithms (such as virtual molding methods or wrinkle generation algorithms) to simulate the wrinkles generated by clothing during specific activities, and generate dynamic clothing change data. This data records in detail the wrinkle morphology and generation process of clothing in motion. Ultimately, the generated dynamic clothing change data will provide an intuitive reference for clothing design, ensuring the comfort and aesthetics of clothing when actually worn.

[0164] Preferably, step S6 comprises the following steps:

[0165] Step S61: defining the adjustment area of ​​the clothing form data set based on the clothing comfort score to obtain adjustment area data; calculating the adjustment amount of the adjustment area based on the clothing comfort score to generate adjustment amount data;

[0166] Step S62: performing local shape adjustment on the adjustment area data according to the adjustment amount data to obtain adjusted clothing data;

[0167] Step S63: reconstructing the seam line of the plane sample data based on the adjusted clothing data to obtain reconstructed seam line data;

[0168] Step S64: reconstructing the plane sample data according to the reconstructed seam line data to generate an adjusted plane sample data set to execute the intelligent digital design method for the three-dimensional prototype garment.

[0169] In this embodiment, based on the clothing comfort score data, the adjustment area of ​​the clothing morphology data set is defined, and a multidimensional data analysis method based on the comfort score is adopted, combined with human kinematics and clothing stress distribution model, to determine the area with a high correlation with the comfort score in the clothing morphology data set, and by performing point-by-point analysis on various parts of the clothing, the parts that may cause discomfort, such as shoulders, chest, knees, etc., are identified to generate adjustment area data. Next, the adjustment amount of the adjustment area is calculated according to the clothing comfort score, and the finite element analysis method (FEA) is used to perform local stress analysis on the morphology of the adjustment area, and the deformation required for adjustment in the area is calculated to generate the adjustment area data. The adjustment amount data is generated, which describes in detail the specific adjustment value of each point in the adjustment area. The adjustment amount data is used to perform local morphological adjustment on the adjustment area data. The morphology of the adjustment area is accurately modeled using three-dimensional surface fitting technology. The adjustment amount data is applied to the model. The calculated adjustment amount is applied to each local area of ​​the clothing through node relocation and shape transformation. The clothing morphology is gradually optimized and adjusted using a finite element model based on mesh refinement. In the local adjustment process, a nonlinear deformation algorithm is used for constraint, so that the adjusted morphology can meet the requirements of the comfort score without affecting the stability of the overall clothing structure, and the adjusted clothing is obtained. The data is used to ensure that each local area of ​​the garment is optimized and adjusted. The adjusted garment data is converted into the geometric structure of the plane sample data. The garment data is projected using a three-dimensional conversion algorithm to obtain the basic form of the plane sample. Then, the known garment seam line model is used to reconstruct the seam line position of the sample by geometrically matching the adjusted garment data and the plane sample. The seam line optimization technology based on the gradient descent method is used to accurately calculate the path and angle of the seam line at each seam point to ensure that no error or deformation is caused during the reconstruction process. Finally, the reconstructed seam line data is obtained, which includes the position, curvature and intersection of each seam line of the plane sample. The reconstructed seam line data is used as a constraint condition, and the template reconstruction algorithm (such as polygon splitting and merging algorithm) is applied to adjust the morphology of each area of ​​the plane template. During the reconstruction process, the area around the seam line is first meshed, and the deformation of each mesh is calculated. The mesh is adjusted using the method of minimizing energy to ensure that the shape of the plane template meets the functional requirements and comfort standards of clothing design after the seam line is reconstructed. Finally, an adjusted plane template dataset is generated, which contains all the adjusted plane template data and is converted into a three-dimensional model through a conversion algorithm for executing the intelligent digital design method of three-dimensional prototype clothing.

Claims

1. A digital design method for three-dimensional prototype clothing, characterized in that: The following steps are involved: Step S1: obtaining three-dimensional scanning data of a human body; annotating feature points of the three-dimensional scanning data of the human body to obtain annotated feature data; Reconstructing the human body three-dimensional model based on the annotated feature data to generate a human body three-dimensional model; Step S2: performing contour loose volume calculation on the human body three-dimensional model to obtain a loose volume data set; performing template plane analysis on the human body three-dimensional model based on the loose volume data set to generate a plane template data set; Step S3: Collect clothing fabric data; Based on the clothing fabric data, the physical characteristics of the plane sample data set are mapped to obtain a physical data set; the clothing three-dimensional model is reconstructed on the physical data set to generate a clothing three-dimensional model; Step S4: spatially positioning the plane sample data set to obtain a sample position data set; performing virtual sewing simulation on the garment three-dimensional model based on the sample position data set to obtain a garment shape data set; Step S5: performing dynamic motion analysis on the clothing morphology data set according to the human body three-dimensional model to generate dynamic clothing change data; performing comfort evaluation on the dynamic clothing change data to obtain a clothing comfort score; Step S6: Based on the clothing comfort score, the clothing shape data set is locally adjusted to obtain adjusted clothing data; the plane sample data set is reconstructed using the adjusted clothing data to generate an adjusted plane sample data set to execute the intelligent digital design method of the three-dimensional prototype clothing.

2. The digital design method of three-dimensional prototype clothing according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: collecting three-dimensional scanning data of a human body; performing human feature point recognition on the three-dimensional scanning data of the human body to obtain feature point data; Step S12: highlighting and marking the feature point data to obtain marked feature data; performing surface fitting processing on the marked feature data to generate a surface data set; Step S13: constructing a skeleton point structure for the surface data set based on the annotated feature data to generate a human skeleton data set; Step S14: reconstructing the three-dimensional model of the human skeleton data set to generate a three-dimensional model of the human body.

3. The digital design method of three-dimensional prototype clothing according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: Slice the human body three-dimensional model in cross section to obtain human body model slice data; calculate key girths of the human body model slice data to generate girth data; Step S22: performing contour looseness calculation on the human body model slice data based on the circumference data to obtain a looseness data set; performing size calibration calculation on the looseness data set to generate template adjustment data; Step S23: performing plane projection conversion on the human body three-dimensional model to obtain candidate model projection data; performing structure line layout processing on the candidate model projection data to obtain structure line layout data; Step S24: Calculate the structural parameters of the structural line layout data to generate plane template structural data; calibrate the plane template structural data based on the template adjustment data to generate a plane template data set.

4. The digital design method of three-dimensional prototype clothing according to claim 3, characterized in that: Step S22 includes the following steps: Performing contour extraction on the slice data of the human body model to obtain a slice contour data set; performing feature region division on the slice contour data set to generate feature region data; The curvature of the feature area data is calculated to obtain a regional curvature data set; local looseness distribution is performed on the regional curvature data set based on the circumference data to obtain a looseness data set; Performing dimension measurement on the loose volume data set to obtain loose volume measurement data; performing correction amount calculation on the loose volume measurement data to generate dimension correction amount data; The size correction amount data is mapped to the clothing pattern to generate pattern adjustment data.

5. The digital design method of three-dimensional prototype clothing according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: collecting clothing fabric data; performing a drape test on the clothing fabric data to obtain clothing drape data; Step S32: performing clothing characteristic analysis on the clothing drape data to generate a clothing physical characteristic data set; performing physical characteristic mapping on the plane sample data set based on the clothing physical characteristic data set to obtain a physical data set; Step S33: performing stress distribution calculation on the physical data set to obtain clothing physical stress data; performing deformation simulation processing on the clothing physical stress data to generate simulated deformation data; Step S34: performing clothing shape prediction on the simulated deformation data to obtain predicted clothing shape data; performing three-dimensional model reconstruction on the predicted clothing shape data to generate a clothing three-dimensional model.

6. The digital design method of three-dimensional prototype clothing according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: calibrating the reference points of the plane sample data set to obtain sample reference data; performing spatial coordinate conversion on the sample reference data to generate sample coordinate data; Step S42: Calculate the posture angle of the template coordinate data to obtain coordinate angle data; adjust the relative position of the template reference data based on the coordinate angle data to generate template position data; Step S43: performing stitching line recognition on the template position data to obtain the template stitching line position; performing stitching path simulation on the garment three-dimensional model based on the template stitching line position to generate a simulated candidate stitching path; Step S44: performing seam deformation calculation on the simulated candidate suture path to generate seam deformation data; performing suture path adjustment on the simulated candidate suture path according to the seam deformation data to obtain a simulated suture path; Step S45: performing virtual sewing simulation on the three-dimensional clothing model based on the simulated sewing path to obtain a clothing morphology data set.

7. The digital design method of three-dimensional prototype clothing according to claim 6, characterized in that: Step S44 includes the following steps: Calculate stress points on the simulated candidate suture path to obtain suture stress data; determine the force direction of the suture stress data to generate stress direction data; Based on the stress direction data, stress accumulation calculation is performed on the stitching stress data to generate stress accumulation data; based on the stress accumulation data, deformation amount calculation is performed on the three-dimensional model of the clothing to obtain deformation amount data; Perform surface topology analysis on the three-dimensional clothing model according to the deformation data to obtain surface topology data; perform deformation trend prediction on the surface topology data to obtain seam deformation data; Reposition nodes of the simulated candidate suture path based on the seam deformation data to obtain reposition data; perform curve fitting processing on the reposition data to generate reposition fitting data; The simulated candidate stitching path is modified according to the repositioned fitting data to generate a simulated stitching path.

8. The digital design method of three-dimensional prototype clothing according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: calibrating joint points of a human body three-dimensional model to obtain joint data; calculating motion trajectories of the joint data to generate motion trajectory data; Step S52: performing a motion range trajectory analysis on the movable trajectory data to obtain a movable fluctuation range; performing a clothing change analysis on the clothing form data set based on the movable fluctuation range to generate dynamic clothing change data; Step S53: Calculate the contact area of ​​the dynamic clothing change data based on the three-dimensional human body model to obtain contact area data; calculate the local pressure distribution of the contact area data to generate a local stress data set; Step S54: performing pressure uniformity evaluation on the local stress data set to obtain pressure uniformity data; performing activity restriction evaluation on the pressure uniformity data according to a preset pressure uniformity threshold to generate local clothing activity restriction data; Step S55: Perform comfort mapping on the local clothing activity restriction data to obtain a clothing comfort score.

9. The digital design method of three-dimensional prototype clothing according to claim 8, characterized in that: Step S52 includes the following steps: Performing direction change identification on the movable trajectory data to obtain direction change data; performing speed distribution analysis on the direction change data to generate change speed data; Performing trajectory feature integration on the direction change data and the change speed data to obtain trajectory feature data; performing extreme position marking on the trajectory feature data to obtain marked position data; Determine the fluctuation range of the marker position data and generate a movable fluctuation range; The clothing morphology data set is deformed mapped based on the movable fluctuation range to obtain clothing deformation mapping data; clothing wrinkles are predicted on the clothing deformation mapping data to generate dynamic clothing change data.

10. The digital design method of three-dimensional prototype clothing according to claim 1, characterized in that: Step S6 includes the following steps: Step S61: defining the adjustment area of ​​the clothing form data set based on the clothing comfort score to obtain adjustment area data; calculating the adjustment amount of the adjustment area based on the clothing comfort score to generate adjustment amount data; Step S62: performing local shape adjustment on the adjustment area data according to the adjustment amount data to obtain adjusted clothing data; Step S63: reconstructing the seam line of the plane sample data based on the adjusted clothing data to obtain reconstructed seam line data; Step S64: reconstructing the plane sample data according to the reconstructed seam line data to generate an adjusted plane sample data set to execute the intelligent digital design method for the three-dimensional prototype garment.

Images