3D Printing Modeling Method and System for Vehicle Parts

Abstract

The present invention discloses a 3D printing modeling method and system for vehicle parts, relating to the technical field of data processing. The method includes the following steps: S1, collecting a plurality of two-dimensional images of the parts, and performing denoising processing and rotation processing on each two-dimensional image to obtain a plurality of standard two-dimensional images; S2, generating the part contour of the standard two-dimensional image according to the outlier degree of the pixel points in the standard two-dimensional image; S3, based on the part contour of each standard two-dimensional image, cropping each standard two-dimensional image, and splicing the cropped plurality of standard two-dimensional images to generate a continuous image for the part; S4, constructing a three-dimensional model of the part based on the continuous image of the part, and completing 3D printing by using the three-dimensional model of the part. The present invention is applicable to parts of various shapes and complexities, can quickly generate a three-dimensional model and perform 3D printing manufacturing, and greatly shortens the product development cycle.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a 3D printing modeling method and system for vehicle parts. Background Art

[0002] In the field of vehicle part manufacturing, traditional modeling and manufacturing methods usually rely on physical molds and complex machining processes, which not only take a long time and are costly, but also are particularly limited when facing complex shapes or customized requirements. In recent years, with the rapid development of 3D printing technology, with its characteristics of high efficiency, flexibility and low cost, it has gradually become a new trend in vehicle part manufacturing.

[0003] However, most existing 3D printing modeling methods rely on CAD (Computer Aided Design) software and require professionals to manually draw 3D models. This process is not only time-consuming and laborious, but may also lead to a decrease in model accuracy due to human factors. In addition, for some parts with complex shapes or special textures, traditional CAD modeling methods may be difficult to accurately capture their detailed features.

[0004] To overcome the above deficiencies, the industry has begun to explore image-based 3D modeling methods, especially the technology of reconstructing 3D models from 2D images. This technology acquires multiple 2D images of parts, extracts feature information in the images using image processing algorithms, and then reconstructs the 3D models of the parts. However, there are still some challenges in existing image-based 3D modeling methods. For example, due to factors such as shooting conditions, lighting changes and image noise, the acquired 2D images may have quality problems, which will affect the subsequent 3D reconstruction effect. In addition, how to accurately and efficiently extract the part contours in the images is also an urgent problem in the current technology. Summary of the Invention

[0005] In order to solve the above problems, the present invention proposes a 3D printing modeling method and system for vehicle parts.

[0006] The technical solution of the present invention is: A 3D printing modeling method for vehicle parts includes the following steps:

[0007] S1. Acquire a number of 2D images of the part, and perform denoising processing and rotation processing on each 2D image to obtain a number of standard 2D images;

[0008] S2. Generate the part contour of the standard 2D image according to the outlier degree of pixel points in the standard 2D image;

[0009] S3. Based on the part contour of each standard 2D image, crop each standard 2D image, and splice the cropped standard 2D images to generate a continuous image for the part;

[0010] S4. Based on the continuous images of the parts, construct a 3D model of the parts and complete 3D printing using the 3D model of the parts.

[0011] Further, S2 includes the following sub-steps:

[0012] S21. Construct a pixel fluctuation range for each pixel point in the standard two-dimensional image;

[0013] S22. Calculate the outlier degree of each pixel point according to the pixel point and its corresponding pixel fluctuation range;

[0014] S23. Generate the part contour of the standard two-dimensional image according to the outlier degree and color value of each pixel point.

[0015] The beneficial effect of the above further solution is: In the present invention, by considering the edges of the standard two-dimensional image and all the neighborhoods of the pixel points to construct the pixel fluctuation range, the global (edge) and local (neighborhood) information of the image are combined, making the constructed fluctuation range more comprehensive and accurate; the edge information usually represents the main features and contours of the image, while the neighborhood information reflects the local environment of the pixel point; the upper and lower limits of the pixel fluctuation range are dynamically determined by comparing the edge average color value and the neighborhood average color value. In addition, the present invention also introduces random numbers to increase the flexibility of outlier degree calculation, making the result random to a certain extent, which helps to better extract the part contour in subsequent processing.

[0016] Further, in S21, construct a pixel fluctuation range according to the edges of the standard two-dimensional image and all the neighborhoods of the pixel points;

[0017] The upper limit of the pixel fluctuation range The calculation formula is:

[0018] ;

[0019] In the formula, represents the average color value of all pixel points in the edge of the standard two-dimensional image, represents the average color value of all neighborhoods of the pixel point, represents taking the maximum value, represents rounding up;

[0020] The lower limit of the pixel fluctuation range The calculation formula is:

[0021] ;

[0022] In the formula, represents taking the minimum value, represents rounding down.

[0023] Further, in S22, the outlier degree of the pixel point is calculated by the formula:

[0024] ;

[0025] In the formula, represents the lower limit of the pixel fluctuation range, represents the upper limit of the pixel fluctuation range, represents the color value of the pixel point, represents generating a random number between 0 and 1.

[0026] Further, S23 includes the following sub-steps:

[0027] S231. Construct a feature evaluation function according to the outlier degree and color value of each pixel point;

[0028] S232. Calculate the relative feature value between each pixel point and the feature evaluation function;

[0029] S233. Take the sum of all relative feature values as the evaluation threshold;

[0030] S234. Take the pixel points with outlier degree greater than the evaluation threshold as the part contour of the standard two-dimensional image.

[0031] The beneficial effect of the above further solution is: In the present invention, the construction of the feature evaluation function is based on the maximum / minimum outlier degree and the color value of the pixel point, which not only considers the difference degree (outlier degree) between the pixel point and the surrounding pixels, but also considers its color characteristics, helping to improve the accuracy of contour extraction. By calculating the relative feature value, the evaluation threshold is set to automatically determine which pixel points belong to the part contour.

[0032] Further, in S231, the feature evaluation function is expressed as:

[0033] ;

[0034] In the formula, represents the maximum outlier degree, represents the minimum outlier degree, represents the color value of the th pixel point in the standard two-dimensional image, represents the color value of the pixel point corresponding to the maximum outlier degree in the standard two-dimensional image, represents the color value of the pixel point corresponding to the minimum outlier degree in the standard two-dimensional image, represents the total number of pixel points in the standard two-dimensional image.

[0035] Further, in S232, the relative eigenvalue between the pixel and the feature evaluation function is calculated by the formula:

[0036] ;

[0037] In the formula, represents the color value of the pixel, represents the feature evaluation function, represents the exponential function.

[0038] Further, in S4, the continuous images of the component are subjected to format conversion, and the format-converted continuous images are modeled using a 3D modeling tool to generate a 3D model of the component, and 3D printing is completed using the 3D model of the component.

[0039] The 3D modeling tool can adopt tools such as Kaedim3D tool and DAZ Studio.

[0040] The beneficial effects of the present invention are as follows: By performing denoising processing and rotation processing on the two-dimensional image, the present invention can eliminate the noise and interference in the image; when generating the contour of the component, the contour is extracted according to the outlier degree of the pixel points in the standard two-dimensional image, which can more accurately capture the shape and features of the component, thereby improving the accuracy of the 3D model; in addition, the present invention also generates continuous images through steps such as cropping and splicing, making the present invention applicable to components of various shapes and complexities, quickly generating a 3D model and performing 3D printing manufacturing, greatly shortening the product development cycle.

[0041] Based on the above method, the present invention also proposes a 3D printing modeling system for vehicle components, including a two-dimensional image acquisition unit, a component contour acquisition unit, a continuous image acquisition unit, and a 3D printing unit;

[0042] The two-dimensional image acquisition unit is used to collect several two-dimensional images of the component, and perform denoising processing and rotation processing on each two-dimensional image to obtain several standard two-dimensional images;

[0043] The component contour acquisition unit is used to generate the component contour of the standard two-dimensional image according to the outlier degree of the pixel points in the standard two-dimensional image;

[0044] The continuous image acquisition unit is used to crop each standard two-dimensional image based on the component contour of each standard two-dimensional image, and splice the cropped several standard two-dimensional images to generate a continuous image for the component;

[0045] The 3D printing unit is used to construct a 3D model of the component based on the continuous image of the component, and complete 3D printing using the 3D model of the component.

[0046] The beneficial effects of the present invention are as follows: The 3D printing modeling system for vehicle parts is applicable to parts of different materials and sizes, and has strong versatility and adaptability. Description of the Drawings

[0047] Figure 1 is a flowchart of a 3D printing modeling method for vehicle parts;

[0048] Figure 2 is a schematic structural diagram of a 3D printing modeling system for vehicle parts. Detailed Embodiments

[0049] The embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0050] As Figure 1 shown, the present invention provides a 3D printing modeling method for vehicle parts, including the following steps:

[0051] S1. Collect a number of two-dimensional images of the part, and perform denoising processing and rotation processing on each two-dimensional image to obtain a number of standard two-dimensional images;

[0052] S2. Generate the part contour of the standard two-dimensional image according to the outlier degree of the pixel points in the standard two-dimensional image;

[0053] S3. Based on the part contour of each standard two-dimensional image, crop each standard two-dimensional image, and splice the cropped standard two-dimensional images to generate a continuous image for the part;

[0054] S4. Based on the continuous image of the part, construct a three-dimensional model of the part, and complete 3D printing using the three-dimensional model of the part.

[0055] In the embodiment of the present invention, S2 includes the following sub-steps:

[0056] S21. Construct a pixel fluctuation range for each pixel point in the standard two-dimensional image;

[0057] S22. Calculate the outlier degree of each pixel point according to the pixel point and its corresponding pixel fluctuation range;

[0058] S23. Generate the part contour of the standard two-dimensional image according to the outlier degree and color value of each pixel point.

[0059] In the present invention, by considering the edges of the standard two-dimensional image and all the neighborhoods of the pixel points to construct the pixel fluctuation range, the global (edge) and local (neighborhood) information of the image are combined, making the constructed fluctuation range more comprehensive and accurate; the edge information usually represents the main features and contours of the image, while the neighborhood information reflects the local environment of the pixel point; the upper and lower limits of the pixel fluctuation range are dynamically determined by comparing the edge average color value and the neighborhood average color value. In addition, the present invention also introduces a random number to increase the flexibility of the outlier degree calculation, making the result random to a certain extent, which helps to better extract the part contours in the subsequent processing.

[0060] In the embodiment of the present invention, in S21, the pixel fluctuation range is constructed according to the edges of the standard two-dimensional image and all the neighborhoods of the pixel points;

[0061] The upper limit of the pixel fluctuation range The calculation formula is:

[0062] ;

[0063] In the formula, represents the average color value of all the pixel points in the edge of the standard two-dimensional image, represents the average color value of all the neighborhoods of the pixel point, represents taking the maximum value, represents rounding up;

[0064] The lower limit of the pixel fluctuation range The calculation formula is:

[0065] ;

[0066] In the formula, represents taking the minimum value, represents rounding down.

[0067] In the embodiment of the present invention, in S22, the outlier degree of the pixel point The calculation formula is:

[0068] ;

[0069] In the formula, represents the lower limit of the pixel fluctuation range, represents the upper limit of the pixel fluctuation range, represents the color value of the pixel point, represents generating a random number between 0 and 1.

[0070] In the embodiment of the present invention, S23 includes the following sub-steps:

[0071] S231. Construct a feature evaluation function based on the outlier degree and color value of each pixel point;

[0072] S232. Calculate the relative feature value between each pixel point and the feature evaluation function;

[0073] S233. Take the sum of all relative feature values as the evaluation threshold;

[0074] S234. Take the pixel points with an outlier degree greater than the evaluation threshold as the part contours of the standard two-dimensional image.

[0075] In the present invention, the construction of the feature evaluation function is based on the maximum / minimum outlier degree and the color value of the pixel points. It not only considers the degree of difference between the pixel points and the surrounding pixels (outlier degree), but also considers their color characteristics, which helps to improve the accuracy of contour extraction. By calculating the relative feature values, the evaluation threshold is set to automatically determine which pixel points belong to the part contours.

[0076] In the embodiment of the present invention, in S231, the feature evaluation function has the following expression:

[0077] ;

[0078] In the formula, represents the maximum outlier degree, represents the minimum outlier degree, represents the color value of the th pixel point in the standard two-dimensional image, represents the color value of the pixel point corresponding to the maximum outlier degree in the standard two-dimensional image, represents the color value of the pixel point corresponding to the minimum outlier degree in the standard two-dimensional image, represents the total number of pixel points in the standard two-dimensional image.

[0079] In the embodiment of the present invention, in S232, the relative feature value between the pixel point and the feature evaluation function has the following calculation formula:

[0080] ;

[0081] In the formula, represents the color value of the pixel point, represents the feature evaluation function, represents the exponential function.

[0082] In the embodiment of the present invention, in S4, perform format conversion on the continuous images of the parts, and use a 3D modeling tool to perform modeling processing on the format-converted continuous images to generate a 3D model of the parts, and complete 3D printing using the 3D model of the parts.

[0083] 3D modeling tools can include Kaedim3D tool, DAZ Studio, etc.

[0084] Based on the above method, the present invention also proposes a 3D printing modeling system for vehicle parts, as Figure 2 shown, which includes a two-dimensional image acquisition unit, a parts contour acquisition unit, a continuous image acquisition unit, and a 3D printing unit;

[0085] The two-dimensional image acquisition unit is used to collect several two-dimensional images of the parts, and perform denoising processing and rotation processing on each two-dimensional image to obtain several standard two-dimensional images;

[0086] The parts contour acquisition unit is used to generate the parts contour of the standard two-dimensional image according to the outlier degree of the pixel points in the standard two-dimensional image;

[0087] The continuous image acquisition unit is used to crop each standard two-dimensional image based on the parts contour of each standard two-dimensional image, and splice the cropped several standard two-dimensional images to generate a continuous image for the parts;

[0088] The 3D printing unit is used to construct a three-dimensional model of the parts based on the continuous image of the parts, and complete 3D printing using the three-dimensional model of the parts.

[0089] Those of ordinary skill in the art will realize that the embodiments described herein are to assist the reader in understanding the principles of the present invention, and it should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific deformations and combinations without departing from the essence of the present invention according to the technical revelations disclosed in the present invention, and these deformations and combinations are still within the protection scope of the present invention.

Claims

1. A 3D printing modeling method for automotive parts, characterized in that: The following steps are involved: S1, collecting several two-dimensional images of parts, and performing denoising and rotation processing on each two-dimensional image to obtain several standard two-dimensional images; S2, generating a component outline of a standard two-dimensional image according to the outlier degree of the pixel points in the standard two-dimensional image; S3, based on the component outline of each standard two-dimensional image, cropping each standard two-dimensional image, and splicing the cropped standard two-dimensional images to generate a continuous image for the component; S4, constructing a three-dimensional model of the parts based on the continuous images of the parts, and completing 3D printing using the three-dimensional model of the parts; The S2 comprises the following sub-steps: S21, constructing a pixel fluctuation range for each pixel point in the standard two-dimensional image; S22, calculating the outlier degree of each pixel point according to the pixel point and its corresponding pixel fluctuation range; S23, generating a component outline of a standard two-dimensional image according to the outlier degree and color value of each pixel point; In S22, the outlier degree of the pixel point The calculation formula is: ； In the formula, Indicates the lower limit of the pixel fluctuation range, Indicates the upper limit of the pixel fluctuation range. Represents the color value of a pixel. Indicates generating a random number between 0 and 1; The S23 comprises the following sub-steps: S231, constructing a feature evaluation function according to the outlier degree and color value of each pixel; S232, calculating the relative characteristic value between each pixel point and the characteristic evaluation function; S233, taking the sum of all relative characteristic values ​​as the evaluation threshold; S234, taking the pixel points whose outlier degree is greater than the evaluation threshold as the component contour of the standard two-dimensional image; In S21, a pixel fluctuation range is constructed according to the edge of the standard two-dimensional image and all neighborhoods of the pixel point; The upper limit of the pixel fluctuation range The calculation formula is: ； In the formula, Represents the mean color value of all pixels on the edge of a standard two-dimensional image. Represents the mean color value of all neighborhoods of a pixel, Indicates taking the maximum value, Indicates rounding up; The lower limit of the pixel fluctuation range The calculation formula is: ； In the formula, Indicates taking the minimum value, Indicates rounding down; In S231, the feature evaluation function The expression is: ； In the formula, represents the maximum outlier degree, represents the minimum outlier degree, Represents the first The color value of each pixel, Indicates the color value of the pixel corresponding to the maximum outlier in the standard two-dimensional image. Indicates the color value of the pixel corresponding to the minimum outlier in the standard two-dimensional image. Represents the total number of pixels of a standard two-dimensional image; In S232, the relative characteristic value between the pixel point and the characteristic evaluation function The calculation formula is: ； In the formula, Represents the color value of a pixel. represents the feature evaluation function, Represents an exponential function.

2. The 3D printing modeling method for automotive parts according to claim 1, characterized in that: In S4, the continuous images of the parts are converted into a format, and the continuous images after the format conversion are modeled using a three-dimensional modeling tool to generate a three-dimensional model of the parts, and the three-dimensional model of the parts is used to complete 3D printing.

3. A 3D printing modeling system for automotive parts, characterized in that: The 3D printing modeling system for vehicle parts is used to execute the 3D printing modeling method for vehicle parts according to claim 1, and the system includes a two-dimensional image acquisition unit, a component contour acquisition unit, a continuous image acquisition unit and a 3D printing unit; The two-dimensional image acquisition unit is used to collect a plurality of two-dimensional images of the parts, and perform denoising and rotation processing on each two-dimensional image to obtain a plurality of standard two-dimensional images; The component contour acquisition unit is used to generate the component contour of the standard two-dimensional image according to the outlier degree of the pixel points in the standard two-dimensional image; The continuous image acquisition unit is used to crop each standard two-dimensional image based on the component outline of each standard two-dimensional image, and to splice a plurality of cropped standard two-dimensional images to generate a continuous image for the component; The 3D printing unit is used to construct a three-dimensional model of the component based on the continuous images of the component, and complete 3D printing using the three-dimensional model of the component.

Images