Modeling Method and System for Luggage and Its Accessories Based on 3D Point Cloud

Abstract

The present invention relates to the field of data processing, and particularly to a method and system for modeling a luggage and its accessories based on three-dimensional point clouds. The method includes: acquiring and preprocessing the point cloud data of the currently collected luggage and its accessories; calculating the texture complexity coefficient of each point cloud data; performing density division on the point cloud data according to the texture complexity coefficient, dividing the point cloud data into multiple density categories, and calculating the optimal density value corresponding to each density category; sampling the point cloud data according to the optimal density value corresponding to each density category to obtain a model of the luggage and its accessories. By sampling according to the optimal density value of each density category, the present invention can ensure reducing redundant data while maintaining the detailed features of the model, making the finally obtained model of the luggage and its accessories more accurate.

Description

Technical Field

[0001] The present invention relates to the field of data processing. More specifically, the present invention relates to a method and system for modeling luggage and its accessories based on three-dimensional point clouds. Background Art

[0002] In the design and production process of luggage and its accessories, there are extremely high requirements for the accuracy of three-dimensional models. Among them, the modeling method based on three-dimensional point clouds can provide three-dimensional models with higher accuracy, more accurately grasp information such as the size, shape, and texture of products, thereby improving the design quality and production efficiency of products.

[0003] The prior art, such as the patent application document with the publication number CN117057206A, discloses an intelligent modeling method and system for three-dimensional molds. The intelligent modeling method includes: obtaining a calibrated mold image set through a preset camera, and extracting partition feature point clouds from the calibrated mold image set to obtain mold point cloud data; performing three-dimensional point cloud densification on the mold point cloud data to obtain three-dimensional point cloud data; constructing a mold three-dimensional model based on the three-dimensional point cloud data, and performing parameter adjustment and iterative optimization on the mold three-dimensional model to obtain an optimal fitting three-dimensional model; performing parametric description on the optimal fitting three-dimensional model to obtain a parametric model; obtaining mold requirement data, and performing first mold model optimization on the parametric model according to the mold requirement data to obtain an optimized mold model; performing mechanical simulation performance simulation on the optimized mold model to obtain mold working simulation data; performing second mold model optimization on the optimized mold model according to the mold working simulation data to obtain an optimal mold model, and converting the optimal mold model into manufacturing parameter data to obtain mold manufacturing parameter data.

[0004] However, in the above intelligent modeling method, for complex molds, their characteristics are irregular, etc., resulting in a large amount of redundant information in the densified point cloud data, increasing the difficulty and computational amount of subsequent processing, thereby reducing the construction accuracy and efficiency of three-dimensional models. Summary of the Invention

[0005] To solve the technical problem that the densified point cloud data contains redundant information, resulting in a reduction in the construction accuracy and efficiency of three-dimensional modeling, the present invention provides solutions in the following aspects.

[0006] In a first aspect, a method for modeling luggage and its accessories based on three-dimensional point clouds includes:

[0007] Obtaining and preprocessing the point cloud data of the currently collected luggage and its accessories;

[0008] Calculating the texture complexity coefficient of each point cloud data;

[0009] Divide the point cloud data into multiple density categories according to the texture complexity coefficient, and calculate the optimal density value corresponding to each density category;

[0010] Sample the point cloud data according to the optimal density value corresponding to each density category to obtain the model of the luggage and its accessories.

[0011] The present invention first calculates the texture complexity coefficient of the point cloud data, which can reasonably determine the boundary and range of the density category, and then specifically samples different densities for regions with different complexities, avoiding unnecessary waste of computing resources. Further sampling according to the optimal density value of each density category can ensure that while maintaining the detailed features of the model, redundant data is reduced, making the finally obtained model of the luggage and its accessories more accurate.

[0012] Preferably, the process of obtaining the texture complexity coefficient of the point cloud data includes:

[0013] Take any point cloud data as the target point cloud, obtain the neighborhood point cloud of the target point cloud, and obtain the normal vectors of the target point cloud and the neighborhood point cloud; calculate the mean value of the variances of the normal vectors of the neighborhood point cloud in three dimensions, and obtain the normal vector consistency of the target point cloud by taking the negative correlation mapping of the mean value of the variances of the normal vectors of the neighborhood point cloud in three dimensions; cluster all the point cloud data, count the total number of point cloud data in the category where the target point cloud is located, and calculate the in-category point cloud ratio of the target point cloud; wherein, each category in the clustering result corresponds to a normal plane;

[0014] Take the product of the normal vector consistency of the target point cloud and the in-category point cloud ratio as the texture complexity coefficient.

[0015] By calculating the mean value of the variances of the normal vectors of the neighborhood point cloud in three dimensions and performing negative correlation mapping, the normal vector consistency of the target point cloud can be obtained. This index reflects the smoothness of the local surface of the point cloud and the consistency of geometric features. The higher the normal vector consistency, the smoother the local surface of the point cloud and the more consistent the geometric features, which helps to more accurately evaluate the complexity of the texture;

[0016] By clustering all the point cloud data and counting the total number of point cloud data in the category where the target point cloud is located, the in-category point cloud ratio of the target point cloud can be calculated. This ratio reflects the similarity and aggregation degree of the target point cloud and its surrounding point clouds. The higher the in-category point cloud ratio, the more similar the texture features of the target point cloud and its surrounding point clouds, which helps to further refine the evaluation of the texture complexity;

[0017] By combining the normal vector consistency and the in-class point cloud ratio, a rapid assessment of the texture complexity of point cloud data can be achieved. This process avoids the complex calculations and feature extraction steps in traditional texture analysis methods, thereby improving the processing efficiency.

[0018] Preferably, the density division of the point cloud data according to the texture complexity coefficient and the division of the point cloud data into multiple density categories include:

[0019] Dividing the point cloud data with a texture complexity coefficient less than a preset first threshold into a low-density category; dividing the point cloud data with a texture complexity coefficient greater than or equal to the preset first threshold and less than the preset second threshold into a medium-density category; dividing the point cloud data with a texture complexity coefficient greater than or equal to the preset second threshold into a high-density category.

[0020] Density division of the point cloud data according to the texture complexity coefficient and division of the point cloud data into low-density, medium-density, and high-density categories have the effects of optimizing the data processing strategy, improving the quality of model construction, and supporting multi-scale analysis and visualization.

[0021] Preferably, the calculation of the optimal density value corresponding to each density category includes:

[0022] For each density category, set multiple sampling intervals, and evenly sample the point cloud data at each interval; calculate the average value of the errors between the surfaces fitted by the point clouds corresponding to all interval samplings and the surface fitted by the original point cloud.

[0023] Perform a negative correlation mapping on the average value of the errors between the surfaces fitted by the point clouds corresponding to all interval samplings and the surface fitted by the original point cloud, and obtain the interval corresponding to the minimum value after the negative correlation mapping. This interval is used as the optimal density value for the corresponding density category.

[0024] By setting multiple sampling intervals for each density category and performing even sampling, the characteristics of the point cloud data at different sampling densities can be analyzed more carefully. Then, by calculating the average value of the errors between the surfaces fitted by the point clouds corresponding to all interval samplings and the surface fitted by the original point cloud, the influence of the sampling density on the fitting accuracy of the point cloud data can be objectively evaluated. And by performing a negative correlation mapping and obtaining the interval corresponding to the minimum value, the optimal density value can be directly found, avoiding an exhaustive search at all possible sampling densities.

[0025] Preferably, the interval corresponding to the minimum value after the negative correlation mapping is expressed by the relational expression:

[0026] ; where is the optimal density value of the th density category, For the average error between the surface fitted by the sampling points corresponding to the interval z and the surface fitted by the original point cloud data within the nth density category, it is an exponential function with the natural constant e as the base; represents a function, that is, it inputs the minimum weighted error and outputs the corresponding optimal density value; z represents the sampling interval.

[0027] Preferably, the sampling the point cloud data according to the optimal density value corresponding to each density category to obtain the model of the luggage and its accessories includes:

[0028] Select voxel grid sampling and set the voxel size of the density category to the resolution corresponding to the optimal density value of the density category, and downsample the currently acquired point cloud data of the luggage and its accessories;

[0029] Denoise and filter the sampled point cloud data, and use 3D modeling software to model the processed point cloud data.

[0030] By selecting the voxel grid sampling method and setting the corresponding voxel size (i.e., resolution) according to the optimal density value of the density category, accurate sampling of the point cloud data can be achieved. This sampling strategy can effectively reduce the data volume and improve the processing speed while maintaining the characteristics of the point cloud data. At the same time, since the sampling process is based on the optimal density value, the detailed information of the point cloud data can be retained to the greatest extent, thereby improving the accuracy and realism of the model.

[0031] Preferably, the process of obtaining the texture complexity coefficient of the point cloud data includes:

[0032] Select any point cloud data as the target point cloud, construct the neighborhood of the target point cloud according to the preset number of neighborhood points, and calculate the average value of the angles between the normal vectors of all neighborhood points and the normal vector of the target point cloud;

[0033] Calculate the standard deviation of the curvatures of all point cloud data within the neighborhood of the target point cloud;

[0034] Normalize the product of the average angle and the standard deviation of the curvatures of all point cloud data within the neighborhood of the target point cloud to obtain the texture complexity coefficient of the target point cloud.

[0035] This operation not only considers the average value of the angles between the normal vectors of the target point cloud and its neighborhood point clouds, but also introduces the standard deviation of the curvatures of the point cloud data within the neighborhood. The average angle reflects the geometric feature consistency of the local surface of the target point cloud, while the curvature standard deviation reflects the degree of geometric shape change of the point cloud data within the neighborhood. After normalizing their product, the texture complexity of the point cloud can be evaluated more comprehensively.

[0036] In the second aspect, a luggage and accessories modeling system based on three-dimensional point clouds includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned luggage and accessories modeling method based on three-dimensional point clouds is implemented.

[0037] The beneficial effects of the present invention are:

[0038] The present invention can more accurately capture the detailed features of luggage and its accessories by performing texture complexity analysis on point cloud data, divide the density according to the texture complexity coefficient, divide the point cloud data into different density categories, perform targeted sampling, optimize resource allocation, and improve modeling efficiency and accuracy; select the optimal sampling density by minimizing the error to ensure that the sampled point cloud data reaches the best balance between fitting accuracy and computational efficiency, perform sampling and modeling according to the optimal density value, generate high-quality point cloud data, thereby quickly constructing a three-dimensional model, while retaining the details of complex areas and improving the overall modeling quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0040] Figure 1 It is a method flow chart of steps S1 to S4 in the method for modeling bags and their accessories based on three-dimensional point clouds in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0042] The embodiment of the present invention discloses a modeling method for bags and their accessories based on three-dimensional point clouds, referring to Figure 1 , including steps S1 to S4, which are specifically as follows:

[0043] S1: Acquire and preprocess the point cloud data of the currently collected luggage and its accessories.

[0044] Point cloud data can accurately reflect the three-dimensional shape and surface features of luggage and its accessories. By collecting point cloud data, operators can quickly obtain a three-dimensional model of the product for further design optimization and improvement.

[0045] Specifically, a point cloud acquisition device (such as a binocular camera, a point cloud scanner, etc.) is used to collect data of the luggage and its accessories.

[0046] The point cloud data collected by the acquisition device is a set of several three-dimensional points, and each point contains its coordinates (x, y, z) in space, which is used to describe the surface shape of the luggage and its accessories.

[0047] After the point cloud data is collected, it needs to be preprocessed, including denoising and outlier filtering, so as to reduce errors and interference in the data and make the point cloud data more accurately reflect the true surface features of the luggage and its accessories.

[0048] S2: Calculate the texture complexity coefficient of each point cloud data.

[0049] After collecting the three-dimensional point cloud data of the luggage and its accessories, in order to obtain a high-precision model, high-density point cloud data is usually required. However, high-density point cloud data has low efficiency in modeling. Therefore, it is necessary to sample the dense point cloud to reduce the point cloud density, thereby improving the modeling efficiency.

[0050] In addition, there are both flat areas and complex concave-convex patterns on the surface of the luggage. If overly dense point clouds are used, it will lead to data redundancy; if overly dense point clouds are not used, it will lead to a reduction in the complexity of the concave-convex patterns. Therefore, by calculating the texture complexity coefficient, the point cloud density can be dynamically adjusted to optimize the model.

[0051] Specifically, first, calculate the normal vector of each point cloud data (that is, the vector perpendicular to the plane where the point cloud data is located) to initially understand the local surface features of each point cloud data.

[0052] Then, find the point cloud data within the corresponding neighborhood of each point cloud data, calculate the variances of the normal vectors of these neighborhood point cloud data in three dimensions (x, y, z), and take the mean of the variances of these three dimensions, that is, obtain the mean variance of the normal vectors of the neighborhoods of each point cloud data. The smaller this mean variance is, the more concentrated the distribution of the corresponding point cloud data in each dimension is, that is, the higher the consistency. On the contrary, the larger the mean variance is, the lower the consistency. Therefore, the mean variance of the normal vectors of the neighborhoods of each point cloud data is negatively correlated and mapped to obtain the normal vector consistency of the corresponding point cloud data.

[0053] Exemplarily, taking any one point cloud data as an example and using it as the target point cloud, obtain the neighborhood data in three dimensions of the target point cloud (a total of 26 neighborhood data), calculate the variances of all normal vectors in each dimension, and take the negative correlation mapping of the mean of the variances of the normal vectors in the three dimensions to obtain the normal vector consistency of the target point cloud, that is, the relational expression is satisfied as:

[0054]

[0055] In the formula, is the normal vector consistency of the th point cloud data, is the mean variance of the normal vectors of all neighborhood data corresponding to the th point cloud data.

[0056] Secondly, use a clustering method (such as mean shift or DBSCAN) to classify each point cloud data and its normal vector, and classify the point cloud data with similar normal vectors into the same class. These point cloud data can be approximately considered to be on the same plane.

[0057] Further determine which class the above th point cloud data belongs to (each class represents a normal plane), count the total number of point cloud data in the class where the th point cloud data is located, calculate the ratio of the total number of point cloud data in the class where the th point cloud data is located to all point cloud data, and use this ratio as the in-class point cloud ratio of the th point cloud data, that is, the relational expression is satisfied as:

[0058]

[0059] In the formula, is the in-class point cloud ratio of the th point cloud data, is the total number of point cloud data in the class where the th point cloud data is located, is the total number of point cloud data collected in S1 above.

[0060] Among them, The larger it is, the more point cloud data is in the same normal plane as the th point cloud data, which means that the point cloud density on this plane is relatively high, so the required sampling density can be reduced; on the contrary, The smaller it is, the fewer point cloud data is in the same normal plane as the th point cloud data, which means that the point cloud density on this plane is relatively low, so a higher sampling density may be required to ensure the integrity and accuracy of the data.

[0061] Finally, take the product of the normal vector consistency of the th point cloud data and the in-class point cloud ratio as the texture complexity coefficient of the th point cloud data, that is, the relational expression is satisfied as:

[0062]

[0063] In the formula, is the The texture complexity coefficient of the point cloud data is the normal vector consistency of the th point cloud data is the in-class point cloud ratio of the th point cloud data

[0064] The larger the texture complexity coefficient of the th point cloud data, the more complex the surface features of the area where the th point cloud data is located, and the higher the required point cloud density

[0065] Furthermore, repeat the above steps for all point cloud data to obtain the value of each point cloud data

[0066] In another embodiment, another method for calculating the texture complexity coefficient of point cloud data is provided, and the specific steps are as follows

[0067] Select any point cloud data as the target point cloud, construct the neighborhood of the target point cloud according to the preset number of neighborhood points (specifically set according to the actual situation, for example, set a smaller number of neighborhood points in areas with higher density; while in areas with lower density or more noise, set a larger number of neighborhood points to include sufficient neighborhood points), and calculate the average value of the angles between the normal vectors of all neighborhood points and the normal vector of the target point cloud

[0068] Calculate the standard deviation of the curvatures of all point cloud data within the neighborhood of the target point cloud

[0069] Normalize the product of the average value of the angles and the standard deviation of the curvatures of all point cloud data within the neighborhood of the target point cloud to obtain the texture complexity coefficient of the target point cloud

[0070] S3: Divide the point cloud data into multiple density categories according to the texture complexity coefficient, and calculate the optimal density value corresponding to each density category

[0071] The texture complexity coefficient of the point cloud data calculated according to S2 above can reflect the difference in the overall texture complexity of the point cloud data, such as the trend of being dense or sparse, but cannot be accurate to the specific density value

[0072] First, according to the texture complexity coefficient of each point cloud data, the point cloud data is preliminarily divided into multiple density categories (such as dense, medium, sparse, etc.). Exemplarily, the point cloud data with a texture complexity coefficient less than a preset first threshold is divided into a low-density category; the point cloud data with a texture complexity coefficient greater than or equal to the preset first threshold and less than the preset second threshold is divided into a medium-density category; the point cloud data with a texture complexity coefficient greater than or equal to the preset second threshold is divided into a high-density category. Wherein the first threshold is taken as 0.3 and the second threshold is taken as 0.7.

[0073] Further, for each density category, surface fitting is performed, and the surface fitting error at different sampling intervals is calculated. The specific steps are as follows:

[0074] Set the sampling density of the point cloud data of each category in space. For example, take a point every z units. Exemplarily, for the th density category, try multiple different z values, such as z = 1, 2, 3,..., 10. Further, using uniform sampling (i.e., equidistant sampling), calculate the average value of the error between the surface fitted by the sampling points corresponding to the interval z and the surface fitted by the original point cloud data, and mark it as . The calculated error is used to judge the effect of the current sampling interval. It should be noted that the calculation of the fitting error is a prior art and will not be elaborated here.

[0075] The above under the sampling at interval z, the larger it is, the greater the error after sampling, that is, the worse the uniform sampling effect at the current interval z.

[0076] In order to achieve a sparse and high-precision luggage model, a sampling interval z needs to be found such that under this interval, is relatively small.

[0077] Specifically, perform a negative correlation mapping on (that is, multiply by ). That is, when is larger, due to the attenuation effect of , the value of will decrease; and when z is larger (i.e., the sampling interval is larger), will also decrease, which helps to find a balance between sparse sampling and precision.

[0078] Further, by obtaining the z value corresponding to the minimum value of , it is used as the optimal density value of this category. Exemplarily, the z value corresponding to the minimum value of obtaining satisfies the relational expression:

[0079]

[0080] In the formula, is the optimal density value of the th density category, is the average value of the errors between the surface fitted by the sampling points corresponding to the interval z within the th density category and the surface fitted by the original point cloud data, is the exponential function with the natural constant e as the base, represents a function that accepts an input (i.e., the minimum weighted error) and outputs a result (i.e., the optimal density value ).

[0081] S4: Sample the point cloud data according to the optimal density value corresponding to each density category to obtain the models of the luggage and its accessories.

[0082] According to the characteristics of the point cloud data and the modeling requirements, through the operations of the above steps S1 - step S3, the optimal density value of each density category is determined.

[0083] The embodiment of the present invention also discloses a modeling system for luggage and its accessories based on three - dimensional point cloud, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the modeling method for luggage and its accessories based on three - dimensional point cloud according to the present invention is implemented.

[0084] The system also includes other components well - known to those skilled in the art such as a communication bus and a communication interface, and their settings and functions are known in the art, so they will not be elaborated here.

[0085] In the present invention, the aforementioned memory can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device, or device. For example, the computer - readable storage medium can be any suitable magnetic storage medium or magneto - optical storage medium, such as resistive random - access memory RRAM (Resistive Random Access Memory), dynamic random - access memory DRAM (Dynamic Random Access Memory), static random - access memory SRAM (Static Random - Access Memory), enhanced dynamic random - access memory EDRAM (Enhanced Dynamic Random Access Memory), high - bandwidth memory HBM (High - Bandwidth Memory), hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application program, module, or both. Any such computer storage medium can be part of the device or accessible or connectable to the device.

[0086] In the description of this specification, the meanings of "a plurality of" and "several" are at least two, such as two, three or more, etc., unless otherwise specifically defined.

[0087] Although this specification has shown and described multiple embodiments of the present invention, it is obvious to those skilled in the art that such embodiments are provided only by way of example. Those skilled in the art will think of many changes, alterations and alternative ways without departing from the spirit and concept of the present invention. It should be understood that various alternative solutions to the embodiments of the present invention described herein can be adopted in the practice of the present invention.

Claims

1. A method for modeling a luggage and its accessories based on 3D point clouds, characterized in that Including: Obtain and preprocess the point cloud data of the currently collected luggage and its accessories; Calculate the texture complexity coefficient of each point cloud data; Take any point cloud data as the target point cloud, obtain the neighborhood point cloud of the target point cloud, and obtain the normal vectors of the target point cloud and the neighborhood point cloud; calculate the mean value of the variances of the normal vectors of the neighborhood point cloud in three dimensions, and take the negative correlation mapping of the mean value of the variances of the normal vectors of the neighborhood point cloud in three dimensions to obtain the normal vector consistency of the target point cloud; cluster all the point cloud data, count the total number of point cloud data in the category where the target point cloud is located, and calculate the in-category point cloud ratio of the target point cloud; among them, each category in the clustering result corresponds to a normal plane; Take the product of the normal vector consistency of the target point cloud and the in-category point cloud ratio as the texture complexity coefficient; Perform density division on the point cloud data according to the texture complexity coefficient, divide the point cloud data into multiple density categories, and calculate the optimal density value corresponding to each density category; for each density category, set multiple sampling intervals, and evenly sample the point cloud data at each interval; calculate the average value of the errors between the surfaces fitted by the point cloud data after sampling at all intervals and the surface fitted by the original point cloud; perform negative correlation mapping on the average value of the errors between the surfaces fitted by the point cloud data after sampling at all intervals and the surface fitted by the original point cloud, and obtain the interval corresponding to the minimum value after the negative correlation mapping, and this interval is used as the optimal density value of the corresponding density category; Sample the point cloud data according to the optimal density value corresponding to each density category to obtain the luggage and its accessories model.

2. The method for modeling a luggage and its accessories based on 3D point cloud according to claim 1, characterized in that, The performing density division on the point cloud data according to the texture complexity coefficient and dividing the point cloud data into multiple density categories includes: Dividing the point cloud data with a texture complexity coefficient less than a preset first threshold into a low-density category; dividing the point cloud data with a texture complexity coefficient greater than or equal to the preset first threshold and less than the preset second threshold into a medium-density category; dividing the point cloud data with a texture complexity coefficient greater than or equal to the preset second threshold into a high-density category.

3. The method for modeling a luggage and its accessories based on 3D point cloud according to claim 1, characterized in that, The interval corresponding to the minimum value after the negative correlation mapping is expressed by the relational expression: ; where, is the optimal density value of the -th density category, is the average value of the error between the surface fitted by the sampling points corresponding to the interval z and the surface fitted by the original point cloud data within the -th density category, is the exponential function with the natural constant e as the base; represents a function, that is, input the minimum weighted error and output the corresponding optimal density value; z represents the sampling interval.

4. The method for modeling a luggage and its accessories based on 3D point cloud according to claim 1, wherein The sampling the point cloud data according to the optimal density value corresponding to each density category to obtain the luggage and its accessories model includes: Select voxel grid sampling and set the voxel size of the density category to the resolution corresponding to the optimal density value of the density category, and downsample the point cloud data of the currently collected luggage and its accessories; Denoise and filter the sampled point cloud data, and use 3D modeling software to model the processed point cloud data.

5. The method for modeling a luggage and its accessories based on a three-dimensional point cloud according to claim 1, characterized in that, The process of obtaining the texture complexity coefficient of the point cloud data includes: Select any point cloud data as the target point cloud, construct the neighborhood of the target point cloud according to the preset number of neighborhood points, and calculate the mean value of the angles between the normal vectors of all neighborhood points and the normal vector of the target point cloud; Calculate the standard deviation of the curvatures of all point cloud data in the neighborhood of the target point cloud; Normalize the product of the mean value of the angles and the standard deviation of the curvatures of all point cloud data in the neighborhood of the target point cloud to obtain the texture complexity coefficient of the target point cloud.

6. A modeling system for luggage and its accessories based on 3D point clouds, characterized in that, Including: A processor and a memory, the memory storing computer program instructions which, when executed by the processor, implement the method for modeling a luggage and its accessories based on a three-dimensional point cloud according to any one of claims 1-5.

Images