Method and apparatus for detecting shrinkage of cement-based additive manufacturing products based on SFM three-dimensional reconstruction

Abstract

This invention discloses a method and apparatus for detecting the shrinkage of cement-based additive manufacturing products based on SFM three-dimensional reconstruction, comprising the following steps: S1: acquiring feature images of cement-based additive manufacturing shrinkage products based on epipolar geometric constraints; S2: batch processing the feature images, retaining only the feature factors of the feature images; S3: reconstructing the three-dimensional structure of the cement-based additive manufacturing shrinkage product by matching the feature factors through SFM, obtaining a three-dimensional reconstruction model; S4: correcting the three-dimensional reconstruction model according to the actual parameters of the cement-based additive manufacturing shrinkage product, and exporting the corrected three-dimensional reconstruction model as a point cloud model in point cloud file format; S5: preprocessing the point cloud model; S6: comparing the preprocessed point cloud model with the point cloud model of the original cement-based additive manufacturing product using the M3C2 algorithm, calculating all point distance differences between the two sets of models, and then determining the shrinkage of the cement-based additive manufacturing shrinkage product based on the point distance differences.

Description

Technical Field

[0001] This invention relates to the field of shrinkage testing of cement-based additive manufacturing products, and specifically to a method and apparatus for shrinkage testing of cement-based additive manufacturing products based on SFM three-dimensional reconstruction. Background Technology

[0002] Cement-based additive manufacturing, also known as concrete 3D printing, is a representative achievement of the digital transformation and intelligent construction of the construction industry, and a prominent application of this transformation. Breaking through the limitations of traditional cast-in-place cement-based materials, cement-based additive manufacturing can quickly form complex structures, offering advantages such as simple curing, high degree of freedom, and environmental friendliness. Due to its unique forming method, additive manufacturing of cement-based materials can reduce construction efficiency from months to days, and from days to hours, enabling customized designs without increasing construction costs. Therefore, the forming effect is a key evaluation indicator for cement-based additive manufacturing products; however, the inherent properties of cement-based materials mean that shrinkage significantly affects the forming effect during additive manufacturing.

[0003] However, current methods for measuring the shrinkage of cement-based additive manufacturing have not achieved accurate numerical evaluation. Existing methods, which measure shrinkage using a ruler and determine the shrinkage value of cement-based additive manufacturing through scale values, have large errors and lack scientific rigor and universality. The assessment of shrinkage for complex cement-based additive manufacturing products or specially customized shapes remains a challenge that needs to be addressed.

[0004] Therefore, given the current problem that search-based measurements of cement-based additive manufacturing products cannot achieve accurate numerical evaluation, developing a method and device for detecting the shrinkage of cement-based additive manufacturing products that can provide effective numerical feedback is an urgent technical problem to be solved. Summary of the Invention

[0005] The purpose of this invention is to provide a method for detecting the shrinkage of cement-based additive manufacturing products based on SFM three-dimensional reconstruction, so as to solve the problem that existing search-based measurements of cement-based additive manufacturing products cannot achieve accurate numerical evaluation.

[0006] To address the aforementioned technical problems, in a first aspect, the present invention provides a method for detecting the shrinkage of cement-based additive manufacturing products based on SFM three-dimensional reconstruction, comprising the following steps:

[0007] S1: Acquiring feature images of shrinkage products in cement-based additive manufacturing based on epipolar geometric constraints;

[0008] S2: Batch processing of feature images, retaining only the feature factors of the feature images;

[0009] S3: By matching feature factors using SFM, the three-dimensional structure of the shrinkage product in cement-based additive manufacturing is reconstructed to obtain a three-dimensional reconstruction model;

[0010] S4: According to the actual parameters of the shrinkage product manufactured by cement-based additive manufacturing, the three-dimensional reconstruction model is corrected, and the corrected three-dimensional reconstruction model is exported as a point cloud model in point cloud file format.

[0011] S5: Preprocess the point cloud model;

[0012] S6: The M3C2 algorithm is used to compare the preprocessed point cloud model with the original point cloud model of the cement-based additive manufacturing product. All point distance differences between the two models are calculated. Then, the Gaussian distribution model is used to fit the statistical values ​​of all point distance differences. Based on the statistical results, the shrinkage of the cement-based additive manufacturing shrinkage product is determined.

[0013] Furthermore, step S1 specifically includes:

[0014] CMOS sampling points are deployed based on the cement-based additive manufacturing shrinkage product. Then, under the condition of satisfying the epipolar geometry constraint, the cement-based additive manufacturing shrinkage product is sampled continuously multiple times until the sampling points globally cover the cement-based additive manufacturing shrinkage product.

[0015] The epipolar geometric constraints include: the angle between the epipolar lines of adjacent feature images is 150°, and the poles are located on the surface of the product perpendicular to the sampling point.

[0016] Furthermore, batch processing of feature images specifically includes: batch deleting the location information from all feature images.

[0017] Furthermore, step S3 specifically includes:

[0018] Global SFM is used to optimize the matching of feature factors in the feature image. During the matching, the geometric information of the two views is calculated. View calibration is performed on the geometric verification image and a search tree is built. Then, the feature factors in the search tree are reconstructed in three dimensions to restore the coordinate information of the feature factors in the current space and obtain the three-dimensional reconstruction model.

[0019] Furthermore, the specific steps in step S4 for correcting the 3D reconstructed model include:

[0020] S41: Perform horizontal correction on the 3D reconstructed model;

[0021] S42: Perform geometric correction on the 3D reconstructed model.

[0022] Furthermore, step S41 specifically includes:

[0023] Take the corner points of a quadrilateral on the horizontal plane where the cement-based additive manufacturing shrinkage product is placed, take the first point as the rotation center, take the vector formed between the second and third points as the new plane dimension, and take the fourth point to determine the plane, and perform horizontal calibration on the cement-based additive manufacturing shrinkage product.

[0024] Furthermore, step S42 specifically includes:

[0025] The scaling ratio is calculated based on the mapping value between the feature image marker size and the actual size of the cement-based additive manufacturing shrinkage product, maintaining the same scaling scale for the XYZ three dimensions; the three-dimensional points of the cement-based additive manufacturing shrinkage product are clipped and eliminated, and the cement-based additive manufacturing shrinkage product is geometrically calibrated.

[0026] Furthermore, step S5 specifically includes:

[0027] S51: Build an octree for the point cloud model, divide the spatial entity into several regions, and define the cell size and the number of octree voxels at the smallest subdivision level.

[0028] S52: Using an octree to divide the spatial region, perform coloring operations on the point cloud model, arrange the color levels with the Z-axis as the height ramp, apply the color band linearly and progressively to the point cloud model, obtain the point cloud coordinates containing the color progression information in the Z-axis direction, export the point cloud coordinates to the scalar domain, and display them in a "red-yellow-green-blue" color progression.

[0029] S53: Offset the position of the point cloud model by globally offsetting the spatial regions divided by the octree and moving the center of the bounding box to the current coordinate origin.

[0030] Secondly, the present invention provides a shrinkage testing device for cement-based additive manufacturing products based on SFM three-dimensional reconstruction, comprising: a processor and a memory; wherein the memory is used to store computer execution instructions, and when the device is running, the processor executes the computer execution instructions stored in the memory to cause the device to perform the testing method provided in the first aspect above.

[0031] The beneficial effects of this invention are as follows:

[0032] 1. By using epipolar constraints to acquire feature images, the perspective change between adjacent feature images is small, the mapping correspondence between feature images is maintained, the number of points to be matched is reduced, and the matching efficiency is improved.

[0033] 2. By using the SFM algorithm to match image feature factors, robustness and accuracy can be improved while maintaining scalability and efficiency. Cement-based additive manufacturing products are small in size, have a large number of feature image sampling times and a large number of points to be matched. SFM is more suitable for the 3D reconstruction of products with this feature, ensuring that the number of noise points in the 3D reconstruction model is small and the restoration is more accurate.

[0034] 3. By reconstructing cement-based additive manufacturing products in 3D, volume measurement can be performed globally, enabling non-destructive testing of product volume parameters. Point cloud comparison is used to obtain point distance differences, and a Gaussian distribution model is used to statistically analyze these differences, resulting in high measurement accuracy and quantification of product shrinkage. This provides data reference for evaluating the molding performance of cement-based additive manufacturing products, forming effective numerical feedback. Attached Figure Description

[0035] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, use the same reference numerals to denote the same or similar parts. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0036] Figure 1 This is a flowchart of one embodiment of the present invention.

[0037] Figure 2 A schematic diagram of image sampling for a spiral-shaped cement-based additive manufacturing shrinkage product.

[0038] Figure 3 This is a schematic diagram of image feature factor matching using SFM.

[0039] Figure 4 This is the numerical result of the point distance difference.

[0040] Figure 5 This is a statistical analysis of the shrinkage test values. Detailed Implementation

[0041] In a first aspect, this invention discloses a method for detecting the shrinkage of cement-based additive manufacturing products based on SFM three-dimensional reconstruction, such as... Figure 1 As shown, the steps include:

[0042] S1: Acquiring feature images of shrinkage products in cement-based additive manufacturing based on epipolar geometric constraints;

[0043] S2: Batch processing of feature images, retaining only the feature factors of the feature images;

[0044] S3: By matching feature factors using SFM, the three-dimensional structure of the shrinkage product in cement-based additive manufacturing is reconstructed to obtain a three-dimensional reconstruction model;

[0045] S4: According to the actual parameters of the shrinkage product manufactured by cement-based additive manufacturing, the three-dimensional reconstruction model is corrected, and the corrected three-dimensional reconstruction model is exported as a point cloud model in point cloud file format.

[0046] S5: Preprocess the point cloud model;

[0047] S6: The M3C2 algorithm is used to compare the preprocessed point cloud model with the original point cloud model of the cement-based additive manufacturing product. All point distance differences between the two models are calculated. Then, the Gaussian distribution model is used to fit the statistical values ​​of all point distance differences. Based on the statistical results, the shrinkage of the cement-based additive manufacturing shrinkage product is determined.

[0048] According to one embodiment of this application, step S1 specifically includes:

[0049] CMOS sampling points are deployed using the cement-based additive manufacturing shrinkage product as the base point. Then, under the condition of satisfying epipolar geometry constraints, the angle between the epipolar lines of adjacent feature images is 150°, and the poles are located on the surface of the product perpendicular to the sampling points. The cement-based additive manufacturing shrinkage product is sampled repeatedly until the sampling points globally cover the entire product. Figure 2 As shown in the figure. This embodiment uses epipolar constraints to acquire feature images, which minimizes the change in viewpoint between adjacent feature images, maintains the mapping correspondence between feature images, reduces the number of points to be matched, and improves matching efficiency.

[0050] According to one embodiment of this application, batch processing of feature images specifically includes: batch deleting the location information in all feature images, the geographic information including longitude, latitude, and altitude information; since the CMOS sampling points are equipped with a geographic information recording module, this embodiment removes the geographic information attached to the CMOS sampling points, retains only the feature image parameters, removes the interference information in the image, and reduces the amount of data to be transmitted to the next stage.

[0051] According to one embodiment of this application, step S3 specifically includes:

[0052] A global SFM is used to optimize the matching of feature factors in the feature image. During the matching process, the geometric information of the two views is calculated. View calibration is performed on the geometric verification image, and a search tree is built. Then, 3D reconstruction is performed on the feature factors in the search tree to restore the coordinate information of the feature factors in the current space. Figure 3 As shown, a 3D reconstruction model is obtained. This embodiment uses the SFM algorithm to match image feature factors, which can improve robustness and accuracy while maintaining scalability and efficiency. Cement-based additive manufacturing products are small in size, have a large number of feature image sampling times and a large number of points to be matched. SFM is more suitable for the 3D reconstruction of products with this feature, ensuring that the 3D reconstruction model has fewer noise points and higher restoration accuracy.

[0053] According to one embodiment of this application, the correction of the three-dimensional reconstruction model in step S4 specifically includes:

[0054] S41: Perform horizontal correction on the 3D reconstructed model;

[0055] S42: Perform geometric correction on the 3D reconstructed model.

[0056] This implementation corrects the scale and horizontal position of the 3D reconstruction model by performing horizontal and geometric corrections, thereby eliminating interference factors in the 3D reconstruction model and ensuring that subsequent calculations are performed without interfering 3D points.

[0057] According to one embodiment of this application, step S41 specifically includes:

[0058] Take the corner points of a quadrilateral on the horizontal plane where the cement-based additive manufacturing shrinkage product is placed, take the first point as the rotation center, take the vector formed between the second and third points as the new plane dimension, and take the fourth point to determine the plane, and perform horizontal calibration on the cement-based additive manufacturing shrinkage product.

[0059] According to one embodiment of this application, step S42 specifically includes:

[0060] The scaling ratio is calculated based on the mapping value between the feature image marker size and the actual size of the cement-based additive manufacturing shrinkage product, maintaining the same scaling scale for the XYZ three dimensions; the three-dimensional points of the cement-based additive manufacturing shrinkage product are clipped and eliminated, and the cement-based additive manufacturing shrinkage product is geometrically calibrated.

[0061] According to one embodiment of this application, step S5 specifically includes:

[0062] S51: Build an octree for the point cloud model, dividing the spatial entities into several regions. Define the cell size (which can be defined as 21) and the number of octree voxels (which can be defined as 2) at the smallest subdivision level. 21 );

[0063] S52: Using an octree to divide the spatial region, perform coloring operations on the point cloud model, arrange the color levels with the Z-axis as the height ramp, apply the color band linearly and progressively to the point cloud model, obtain the point cloud coordinates containing the color progression information in the Z-axis direction, export the point cloud coordinates to the scalar domain, and display them in a "red-yellow-green-blue" color progression.

[0064] S53: Perform position offset on the point cloud model, use the spatial region divided by the octree for global offset, move the center of the bounding box to the current coordinate origin, and use normalized matrix transformation instead of point cloud registration to improve point cloud alignment efficiency.

[0065] According to one embodiment of this application, in step S6, the shrinkage of cement-based additive manufacturing products is specifically manifested as the volume shrinkage generated during the setting and hardening process of cement-based materials. There is a volume difference between the original cement-based additive manufacturing product (product A) and the cement-based additive manufacturing shrinkage product (product B) after curing. Therefore, detecting the shrinkage of cement-based additive manufacturing products means using numerical evaluation to assess the above-mentioned volume difference.

[0066] The M3C2 algorithm was used to compare the preprocessed point cloud model with the original point cloud model of the cement-based additive manufacturing product. The calculation of all point distance differences between the two models specifically included: selecting the point cloud of product A as the core point cloud, fitting the normal vector using the point cloud of product A as a reference, controlling the projection depth to be 1 / 2 of the normal vector of the point cloud of product A, and measuring the distance between the fitted planes of the neighborhood point clouds; the normal calculation used the scalar domain values ​​of the point cloud of product A, and the measurement accuracy was defined by the scalar domain values, i.e., the measurement accuracy was measured with a Z-axis normal vector scaling factor of 1.0; the output carrier was selected as the point cloud of product B, and the standard deviation information was exported; such as Figure 4 As shown.

[0067] The standard deviation information is statistically analyzed using a Gaussian distribution model. The mean of the statistical results represents the overall value of the point distance difference, i.e., the shrinkage value of cement-based additive manufacturing products after curing. The chi-square distance of the statistical results represents the difference between the two point cloud models, i.e., the shrinkage rate of cement-based additive manufacturing products after curing. Shrinkage is reflected by the shrinkage value and shrinkage rate, such as... Figure 5 As shown.

[0068] Secondly, the present invention provides a shrinkage testing device for cement-based additive manufacturing products based on SFM three-dimensional reconstruction, comprising: a processor and a memory; wherein the memory is used to store computer execution instructions, and when the device is running, the processor executes the computer execution instructions stored in the memory to cause the device to perform the testing method provided in the first aspect above.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for detecting the shrinkage of cement-based additive manufacturing products based on SFM three-dimensional reconstruction, characterized in that, Including the following steps: S1: Acquiring feature images of shrinkage products in cement-based additive manufacturing based on epipolar geometric constraints; S2: Batch process the feature images, retaining only the feature factors of the feature images; S3: By matching feature factors using SFM, the three-dimensional structure of the shrinkage product in cement-based additive manufacturing is reconstructed to obtain a three-dimensional reconstruction model; S4: According to the actual parameters of the shrinkage product manufactured by cement-based additive manufacturing, the three-dimensional reconstruction model is corrected, and the corrected three-dimensional reconstruction model is exported as a point cloud model in point cloud file format. S5: Perform preprocessing on the point cloud model; S6: The M3C2 algorithm is used to compare the preprocessed point cloud model with the point cloud model of the original cement-based additive manufacturing product. All point distance differences between the two models are calculated. Then, the Gaussian distribution model is used to fit the statistical values ​​of all point distance differences. Based on the statistical results, the shrinkage of the cement-based additive manufacturing shrinkage product is determined. Step S1 specifically includes: CMOS sampling points are deployed based on the cement-based additive manufacturing shrinkage product. Then, under the condition of satisfying the epipolar geometry constraint, the cement-based additive manufacturing shrinkage product is sampled continuously multiple times until the sampling points globally cover the cement-based additive manufacturing shrinkage product. The epipolar geometric constraints include: the angle between the epipolar lines of adjacent feature images is 150°, and the pole is located on the surface of the product perpendicular to the sampling point.

2. The method for detecting shrinkage of cement-based additive manufacturing products based on SFM three-dimensional reconstruction according to claim 1, characterized in that, The batch processing of the feature images specifically includes: batch deleting the positioning information from all feature images.

3. The method for detecting shrinkage of cement-based additive manufacturing products based on SFM three-dimensional reconstruction according to claim 2, characterized in that, Step S3 specifically includes: Global SFM is used to optimize the matching of the feature factors in the feature image. During the matching, the geometric information of the two views is calculated. View calibration is performed on the geometric verification image and a search tree is built. Then, the feature factors in the search tree are reconstructed in three dimensions to restore the coordinate information of the feature factors in the current space and obtain the three-dimensional reconstruction model.

4. The method for detecting shrinkage of cement-based additive manufacturing products based on SFM three-dimensional reconstruction according to claim 3, characterized in that, In step S4, the correction of the three-dimensional reconstruction model specifically includes: S41: Perform horizontal correction on the 3D reconstructed model; S42: Perform geometric correction on the 3D reconstructed model.

5. The method for detecting shrinkage of cement-based additive manufacturing products based on SFM three-dimensional reconstruction according to claim 4, characterized in that, Step S41 specifically includes: Take the corner points of a quadrilateral on the horizontal plane where the cement-based additive manufacturing shrinkage product is placed, take the first point as the rotation center, take the vector formed between the second and third points as the new plane dimension, and take the fourth point to determine the plane, and perform horizontal calibration on the cement-based additive manufacturing shrinkage product.

6. The method for detecting shrinkage of cement-based additive manufacturing products based on SFM three-dimensional reconstruction according to claim 5, characterized in that, The specific steps in S42 include: The scaling ratio is calculated based on the mapping value between the feature image marker size and the actual size of the cement-based additive manufacturing shrinkage product, maintaining the same scaling scale for the XYZ three dimensions; the three-dimensional points of the cement-based additive manufacturing shrinkage product are clipped and eliminated, and the cement-based additive manufacturing shrinkage product is geometrically calibrated.

7. The method for detecting shrinkage of cement-based additive manufacturing products based on SFM three-dimensional reconstruction according to claim 6, characterized in that, Step S5 specifically includes: S51: Establish an octree for the point cloud model, divide the spatial entity into several regions, and define the cell size and the number of octree voxels at the smallest subdivision level. S52: Using an octree to divide the spatial region as the goal, perform a coloring operation on the point cloud model, arrange the color levels with the Z-axis direction as the height ramp, and apply the color band linearly and progressively to the point cloud model to obtain point cloud coordinates containing color progressive information in the Z-axis direction. Export the point cloud coordinates to the scalar domain and display them in a "red-yellow-green-blue" color progressive manner. S53: Offset the position of the point cloud model by globally offsetting the spatial regions divided by the octree and moving the center of the bounding box to the current coordinate origin.

8. A shrinkage testing device for cement-based additive manufacturing products based on SFM three-dimensional reconstruction, characterized in that, include: A processor and a memory; wherein the memory is used to store computer execution instructions, and when the device is running, the processor executes the computer execution instructions stored in the memory to cause the device to perform the detection method according to any one of claims 1-7.

Images