A detection method for the assembly construction process of prefabricated buildings

Abstract

The present invention relates to the technical field of image processing, and particularly to a method for detecting the assembly construction process of prefabricated buildings. The method includes: determining the probability that the point cloud data at a position belongs to the same prefabricated building component as other point cloud data according to the coordinate information and color information of the point cloud data; determining that the point cloud data at a position belongs to the same prefabricated building component as other point cloud data; in the case where the number of point cloud data divided into the same prefabricated building component is less than a second threshold, marking it as noise information and removing it; determining the voxels corresponding to the point cloud data under the same prefabricated building component; and using the point cloud data within the voxels to detect the installation process of each prefabricated building component in the prefabricated building. The present invention optimizes the effect of denoising and reducing redundancy of point cloud data, retains the characteristics of the original point cloud data, and improves the quality of the point cloud data.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly relates to a method for detecting the assembly construction process of prefabricated buildings. Background Art

[0002] Prefabricated building is a modern building method. By prefabricating each component or module of the building in the factory and then transporting these prefabricated parts to the construction site for assembly. With the rapid development of modern building technology, prefabricated buildings, with the characteristics of high efficiency, environmental protection and energy conservation, have gradually become an important development direction in the construction industry. During the assembly construction process of prefabricated buildings, point cloud data can be used to detect the construction progress and details. Point cloud data is an advanced technical means that can provide high-precision three-dimensional information. Through steps such as data preprocessing, three-dimensional modeling, and observation and analysis, it can help comprehensively understand the actual situation and progress of the construction site, providing strong support for construction management and decision-making.

[0003] Generally, there will be noise and redundant data in point cloud data, so it is necessary to denoise and reduce redundancy of point cloud data. In the traditional process of denoising and reducing redundancy of point cloud data, a uniform voxel filtering method is often used to process point cloud data. However, since prefabricated buildings are completed by splicing different building components, and different building components have different characteristic manifestations, using a uniform voxel filtering method to denoise and reduce redundancy of the point cloud data of prefabricated buildings has a poor effect, easily leading to the loss of the characteristics of the original point cloud data, reducing the quality of the point cloud data, and further resulting in a poor effect of subsequent analysis and processing based on the point cloud data. Summary of the Invention

[0004] In order to solve the technical problem that the effect of denoising and reducing redundancy of point cloud data is poor, resulting in the loss of the characteristics of the original point cloud data and reducing the quality of the point cloud data, the purpose of the present invention is to provide a method for detecting the assembly construction process of prefabricated buildings.

[0005] The specific technical solutions adopted to solve the above technical problems are as follows:

[0006] An embodiment of the present invention provides a method for detecting the assembly construction process of a prefabricated building, including: obtaining point cloud data at different positions during the assembly construction process of the prefabricated building; determining the probability that the point cloud data at a position and other point cloud data belong to the same prefabricated building component according to the coordinate information and color information of the other point cloud data in the target space around the position and the point cloud data at the position; when the probability is greater than a first threshold, determining that the point cloud data at the position and the other point cloud data belong to the same prefabricated building component; when the number of point cloud data classified into the same prefabricated building component is less than a second threshold, marking it as noise information and removing it; when the number of point cloud data classified into the same prefabricated building component is not less than the second threshold, determining the voxel corresponding to the point cloud data under the same prefabricated building component according to the point cloud data in the same prefabricated building component, the average probability of the probability that adjacent point cloud data in the same prefabricated building component is classified into the same prefabricated building component, and the volume of the standard voxel; using the point cloud data in the voxel to detect the installation process of each prefabricated building component in the prefabricated building.

[0007] Optionally, determining the probability that the point cloud data at a position and other point cloud data belong to the same prefabricated building component according to the coordinate information and color information of the other point cloud data in the target space around the position and the point cloud data at the position includes: determining a first distance between the point cloud data at the position and the other point cloud data according to the coordinate information of the other point cloud data in the target space around the position and the point cloud data at the position; determining a color difference between the point cloud data at the position and the other point cloud data according to the color information of the other point cloud data in the target space around the position and the point cloud data at the position; using the first distance and the color difference to determine the probability that the point cloud data at the position and the other point cloud data belong to the same prefabricated building component.

[0008] Optionally, using the first distance and the color difference to determine the probability that the point cloud data at a position and other point cloud data belong to the same prefabricated building component includes: calculating a first product between the first distance and the color difference; performing a normalization process on the first product to obtain the probability that the point cloud data at the position and the other point cloud data belong to the same prefabricated building component.

[0009] Optionally, determining the voxel corresponding to the point cloud data under the same prefabricated building component based on the first quantity of the point cloud data in the same prefabricated building component, the average probability of the probability that adjacent point cloud data in the same prefabricated building component is divided into the same prefabricated building component, the maximum distance between the point cloud data in the same prefabricated building component, the first volume of the largest cuboid wrapped by the first quantity of point cloud data, and the second volume of the largest cuboid wrapped by all the point cloud data in the prefabricated building includes: determining the density parameter of the point cloud data under the same prefabricated building component; determining the voxel corresponding to the point cloud data under the same prefabricated building component according to the density parameter of the point cloud data under the same prefabricated building component and the volume of the standard voxel.

[0010] Optionally, determining the density parameter of the point cloud data under the same prefabricated building component based on the first quantity of the point cloud data in the same prefabricated building component, the average probability of the probability that adjacent point cloud data in the same prefabricated building component is divided into the same prefabricated building component, the maximum distance between the point cloud data in the same prefabricated building component, the first volume of the largest cuboid wrapped by the first quantity of point cloud data, and the second volume of the largest cuboid wrapped by all the point cloud data in the prefabricated building includes: calculating a first ratio between the average probability and the maximum distance, and a second ratio between the second volume and the first volume; determining that the second product of the first quantity, the first ratio, and the second ratio is the density parameter of the point cloud data under the same prefabricated building component.

[0011] Optionally, determining the voxel corresponding to the point cloud data under the same prefabricated building component according to the density parameter of the point cloud data under the same prefabricated building component and the volume of the standard voxel includes: determining the volume of the standard voxel according to the state of the point cloud data being uniform; performing normalization processing on the density parameter to obtain a normalized density parameter; determining that the third product of the normalized density parameter and the volume is the voxel corresponding to the point cloud data under the same prefabricated building component.

[0012] Optionally, using the point cloud data in the voxel to detect the installation process of each prefabricated building component in the prefabricated building includes: determining the average value of the point cloud data in the voxel as the target point cloud data corresponding to the voxel; using the target point cloud data to detect the installation process of each prefabricated building component corresponding to the target point cloud data in the prefabricated building.

[0013] Optionally, using the target point cloud data to detect the installation process of each prefabricated building component corresponding to the target point cloud data in the prefabricated building includes: determining the target prefabricated building component whose position information of the target point cloud data changes at adjacent times according to the target point cloud data of the prefabricated building component at adjacent times; determining the vector direction of each target point cloud data in the space in the target prefabricated building component according to the spatial coordinates of the target point cloud data of the target prefabricated building component at adjacent times; and using the vector direction of each target point cloud data in the space in the target prefabricated building component to detect the installation process of the target prefabricated building component.

[0014] Optionally, determining the vector direction of each target point cloud data in the space in the target prefabricated building component according to the spatial coordinates of the target point cloud data of the target prefabricated building component at adjacent times includes: calculating the difference between the spatial coordinates of the target point cloud data at adjacent times as the spatial vector of the target point cloud data in the space; and determining the vector direction of the spatial vector as the vector direction of the target point cloud data in the space.

[0015] Optionally, using the vector direction of each target point cloud data in the space in the target prefabricated building component to detect the installation process of the target prefabricated building component includes: if the vector directions of each target point cloud data in the space are inconsistent, determining that the installation process of the target prefabricated building component is abnormal; if the vector directions of each target point cloud data in the space are consistent, then along the vector direction, approaching the distribution direction of the corresponding target point cloud data. If the distribution direction is consistent with the vector direction of the corresponding target point cloud data, determining that the installation process of the target prefabricated building component is good; if the distribution direction is inconsistent with the vector direction of the corresponding target point cloud data, determining that the installation process of the target prefabricated building component is abnormal.

[0016] The present invention has the following beneficial effects: First, obtain the point cloud data at different positions during the assembly construction process of the prefabricated building; then, according to the coordinate information and color information of the point cloud data at the position and other point cloud data in the target space around the position, determine the probability that the point cloud data at the position and the other point cloud data belong to the same prefabricated building component; in the case where the probability is greater than the first threshold, determine that the point cloud data at the position and the other point cloud data belong to the same prefabricated building component; in the case where the number of point cloud data divided into the same prefabricated building component is less than the second threshold, mark it as noise information and remove it; in the case where the number of point cloud data divided into the same prefabricated building component is not less than the second threshold, determine the voxel corresponding to the point cloud data under the same prefabricated building component according to the point cloud data in the same prefabricated building component, the average probability of the probability that adjacent point cloud data in the same prefabricated building component are divided into the same prefabricated building component, and the volume of the standard voxel; use the point cloud data in the voxel to detect the installation process of each prefabricated building component in the prefabricated building.

[0017] In this way, the embodiment of the present invention can first determine and remove the noise information according to the number of point cloud data divided into the same prefabricated building component. Then, according to the point cloud data in each prefabricated building component, the volume of the standard voxel, and the average probability of each point cloud data, determine the voxel size suitable for each prefabricated building component. The voxel adapted to the prefabricated building component can accurately process the data redundancy of the prefabricated building component. In this way, the effects of denoising and reducing redundancy of the point cloud data are optimized, the characteristics of the original point cloud data are retained, the quality of the point cloud data is improved, and the subsequent analysis and processing effects based on the point cloud data are further improved. Further, using the denoised and redundancy-reduced point cloud data to detect the installation process of each prefabricated building component in the prefabricated building improves the detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0019] Figure 1 It is a flowchart of a method for detecting the assembly construction process of a prefabricated building provided by an embodiment of the present invention;

[0020] Figure 2 It is a structural schematic diagram of a prefabricated building component provided by an embodiment of the present invention;

[0021] Figure 3 Schematic diagram of the vector directions of the point cloud data at each point in a building component R provided by an embodiment of the present invention;

[0022] Figure 4 Schematic diagram of the vector directions and distribution directions of the point cloud data at each point in a building component R provided by an embodiment of the present invention;

[0023] Figure 5 Schematic diagram of the vector directions and distribution directions of the point cloud data at each point in a building component R provided by another embodiment of the present invention;

[0024] Figure 6 Schematic diagram of the structure of a detection system for the assembly construction process of a prefabricated building provided by an embodiment of the present invention. Detailed implementation manners

[0025] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of a detection method for the assembly construction process of a prefabricated building proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0027] The following specifically describes the specific solution of a detection method for the assembly construction process of a prefabricated building provided by the present invention with reference to the accompanying drawings.

[0028] Embodiment 1:

[0029] Please refer to Figure 1 , which shows the flowchart of a detection method for the assembly construction process of a prefabricated building provided by an embodiment of the present invention, including:

[0030] Step S101, obtaining point cloud data at different positions during the assembly construction process of the prefabricated building.

[0031] Specifically, in the embodiment of the present invention, a drone equipped with a high-precision lidar scanner can be used to scan the construction site during the assembly construction process of the prefabricated building to obtain the original data information during the assembly construction process of the prefabricated building. The original data information includes, but is not limited to, GPS and INS data. Then, the original data information is subjected to a solution process, and the return time of the laser pulse is accurately converted into point coordinates in a three-dimensional space using the GPS and INS data Data to generate initial point cloud data.

[0032] More specifically, the point cloud data collected in the above embodiments of the present invention often contains a large amount of noise and redundant data, and it is necessary to perform denoising, filtering, etc. on it to make the generated point cloud data more reliable. However, for prefabricated buildings, which are assembled from multiple prefabricated building components, simple holistic voxel filtering has poor effects. Therefore, in the embodiments of the present invention, by analyzing the characteristic manifestations of each prefabricated building component, voxels of different sizes are analyzed for different prefabricated building components, and then denoising and redundancy reduction are performed. The effect of such processing also retains the characteristics of the initial point cloud data. Then, according to the changes in the point cloud data before and after in time, the installation angle of the building component being installed is analyzed to complete the synchronous detection of the assembly construction process.

[0033] Step S102: Determine the probability that the point cloud data at the position and the other point cloud data belong to the same prefabricated building component according to the coordinate information and color information of the other point cloud data in the target space around the position and the point cloud data at the position.

[0034] Specifically, since prefabricated building components are usually relatively large, the three-dimensional point cloud data belonging to prefabricated building components has aggregation in space, which is mainly determined by the characteristics of the components themselves. According to this characteristic, the embodiments of the present invention perform noise processing on the initially generated three-dimensional point cloud data. Among them, since the sizes and shapes of prefabricated building components are different, and there are many situations of prefabricated building components with various sizes, in order to retain the original characteristics of prefabricated building components in the three-dimensional point cloud data, the embodiments of the present invention first distinguish the point cloud data belonging to the same prefabricated building component, and then use uneven voxels to perform voxel division on the three-dimensional point cloud data corresponding to the prefabricated building component. Exemplarily, as Figure 2 shown Figure 2 is a schematic structural diagram of a prefabricated building component provided by an embodiment of the present invention. Figure 2 It includes building component 1, building component 2, and building component 3, and the sizes and shapes of the three building components are all different.

[0035] More specifically, when determining the probability that the point cloud data at a certain position and other point cloud data belong to the same prefabricated building component, as an optional embodiment of the present invention, first, according to the coordinate information of other point cloud data and the point cloud data at the position within the target space around the position, determine the first distance between the point cloud data at the position and other point cloud data; then, according to the color information of other point cloud data and the point cloud data at the position within the target space around the position, determine the color difference between the point cloud data at the position and other point cloud data; finally, use the first distance and the color difference to determine the probability that the point cloud data at the position and other point cloud data belong to the same prefabricated building component.

[0036] Specifically, in the embodiment of the present invention, the target space can be the space around the point cloud data. Of course, the size of the target space can also be determined according to the actual situation, and the embodiment of the present invention does not limit this here. The embodiment of the present invention records the coordinate information of the th point cloud data as Based on the th point cloud data, judge the distance magnitude between the th point cloud data among other point cloud data within the space around it. In the embodiment of the present invention, the following formula is specifically used to calculate the first distance between the th point cloud data and the th point cloud data within the target space: In the above formula,

[0037]

[0038] represents the first distance between the th point cloud data and the th point cloud data within the target space. represents the spatial coordinate of the th point cloud data within the target space where the th point cloud data is located. represents the spatial coordinate of the th point cloud data. represents the th point cloud data.

[0039] More specifically, for the same prefabricated building component, its color performance is unified. And the point cloud data contains color values. The embodiment of the present invention records the color information of the th point cloud data as Based on the th point cloud data, judge the color difference between the th point cloud data within the space around it. Among them, represents the th point cloud data, and The color values of the RGB channels of the point cloud data. Further, in the embodiments of the present invention, the following formula is specifically used to calculate the th point cloud data and the th point cloud data in the target space

[0040]

[0041] In the above formula, represents the color difference between the th point cloud data and the th point cloud data in the target space. represents the color information of the th point cloud data in the space and the th point cloud data. represents the color information of the th point cloud data.

[0042] More specifically, when calculating the probability that the point cloud data at a certain position and other point cloud data belong to the same prefabricated building component, as an optional embodiment of the present invention, first calculate the first product between the first distance and the color difference; then perform normalization processing on the first product to obtain the probability that the point cloud data at the position and other point cloud data belong to the same prefabricated building component.

[0043] Specifically, the embodiments of the present invention specifically use the following formula to calculate the above probability:

[0044]

[0045] In the above formula, represents the probability that the th point cloud data and the th point cloud data in the target space belong to the same prefabricated building component. represents the first distance between the th point cloud data and the th point cloud data in the target space. represents the color difference between the th point cloud data and the th point cloud data in the target space. represents an inverse proportional normalization function, which is used to perform normalization processing on . Among them, for point cloud data, when the differences in position and color performance between two adjacent point cloud data are both small, the possibility that they belong to the same prefabricated building component is greater.

[0046] Step S103: When the probability is greater than the first threshold, determine that the point cloud data at the position and other point cloud data belong to the same prefabricated building component.

[0047] Specifically, the first threshold can be determined according to the actual situation, and the value in the embodiment of the present invention is 0.7. Taking the above embodiment of the present invention as an example, when it is calculated that , it means that this th point cloud data and the th point cloud data in the target space belong to the same prefabricated building component. Traverse all the point cloud data to complete the division of all the point cloud data into prefabricated building components.

[0048] Step S104: When the number of point cloud data divided into the same prefabricated building component is less than the second threshold, mark it as noise information and remove it; when the number of point cloud data divided into the same prefabricated building component is not less than the second threshold, determine the voxel corresponding to the point cloud data under the same prefabricated building component according to the point cloud data in the same prefabricated building component, the average probability of the probability of dividing adjacent point cloud data in the same prefabricated building component, and the volume of the standard voxel.

[0049] Specifically, for prefabricated building components, their volumes are generally large. Therefore, when very few point cloud data are divided into the same prefabricated building component, or only a single point cloud data is divided together, it is marked as noise information and removed. Among them, the second threshold can be determined according to the actual situation, and the embodiment of the present invention does not limit it here.

[0050] More specifically, when the number of point cloud data divided into the same prefabricated building component is not less than the second threshold, it is necessary to perform redundancy reduction processing on the point cloud data in the same prefabricated building component. In order to ensure the feature representation of the original point cloud data, the embodiment of the present invention uses different voxels to divide the point cloud data belonging to different prefabricated building components. Among them, the division of non-uniform voxels needs to be based on the specific performance of the point cloud data belonging to different prefabricated building components. When the point cloud data belonging to a certain prefabricated building component is relatively sparse, a larger voxel unit is used to divide it; when the point cloud data is relatively dense, a smaller voxel unit is used to divide it.

[0051] More specifically, when determining the voxels corresponding to the point cloud data under the same prefabricated building component, as an optional embodiment of the present invention, first, according to the first quantity of the point cloud data in the same prefabricated building component, the average probability of the probability that adjacent point cloud data in the same prefabricated building component are divided into the same prefabricated building component, the maximum distance between the point cloud data in the same prefabricated building component, the first volume of the largest cuboid wrapped by the first quantity of point cloud data, and the second volume of the largest cuboid wrapped by all the point cloud data in the prefabricated building, determine the density parameter of the point cloud data under the same prefabricated building component; then, according to the density parameter of the point cloud data under the same prefabricated building component and the volume of the standard voxel, determine the voxels corresponding to the point cloud data under the same prefabricated building component.

[0052] Among them, the point cloud data is three-dimensional data. In the coordinate system, the smallest rectangle that all the point cloud data can form, and all the point cloud data is included in this smallest rectangle. When determining the density parameter, first calculate the first ratio between the average probability and the maximum distance, and the second ratio between the second volume and the first volume; then determine the second product of the first quantity, the first ratio, and the second ratio as the density parameter of the point cloud data under the same prefabricated building component.

[0053] More specifically, taking the kth prefabricated building component as an example, the present invention embodiment specifically calculates the density parameter of the point cloud data in the kth prefabricated building component by the following formula:

[0054]

[0055] In the above formula, represents the density parameter of the point cloud data in the th prefabricated building component. represents the first quantity of the point cloud data subordinate to the th prefabricated building component. refers to the size of the first volume of the largest cuboid completely wrapped by the point cloud data under the th prefabricated building component. refers to the size of the second volume of the rectangle that can completely wrap all the point cloud data in the prefabricated building. represents the average probability of the probability that adjacent point cloud data under this th prefabricated building component are grouped together. represents the maximum distance between the point cloud data under this th prefabricated building component.

[0056] Among them, for the point cloud data under prefabricated building components, the smaller the overall spatial proportion of its distribution and the more point cloud data, the greater the complexity and the greater the distribution density of this prefabricated building component, and fine division is required, that is, smaller voxel units are used. In addition, the greater the possibility that these point cloud data belong together and the smaller the maximum distance between the point cloud data, the more concentrated these point cloud data are and the greater the distribution density.

[0057] More specifically, when determining the voxels corresponding to the point cloud data under the same prefabricated building component, as an optional embodiment of the present invention, first determine the volume of the standard voxel according to the state of the point cloud data under uniformity; then perform normalization processing on the density parameter to obtain the normalized density parameter; finally, determine that the third product between the normalized density parameter and the volume is the voxel corresponding to the point cloud data under the same prefabricated building component.

[0058] Specifically, the embodiment of the present invention first determines the voxel size under the uniform state of the entire prefabricated building. Specifically, by statistically calculating the maximum and minimum values of the X, Y, and Z coordinate values of the point cloud data of the entire prefabricated building and determining the row number, column number, and layer number according to the divided grid size L, it is evenly divided into multiple grids, and each point cloud data is assigned to the corresponding grid, and the volume of the grid is the volume of the standard voxel. It should be noted that the voxels in the embodiment of the present invention are small cubes. To prevent out-of-bounds situations, it is usually necessary to appropriately expand the maximum and minimum values of the X, Y, and Z coordinate values of the point cloud data outward to ensure that all point cloud data can be correctly divided into voxels.

[0059] Among them, the embodiment of the present invention takes the kth prefabricated building component as an example, and specifically uses the following formula to calculate the voxel corresponding to the point cloud data under the kth prefabricated building component:

[0060]

[0061] In the above formula, represents the voxel corresponding to the point cloud data under the kth prefabricated building component. represents the volume of the standard voxel. represents the density parameter of the point cloud data in the kth prefabricated building component. is an inverse proportional normalization function, which is used to perform normalization processing on . Among them, for data-intensive regions, the embodiment of the present invention uses smaller voxel units for division. Since the point cloud data subordinate to different prefabricated building components are divided into voxels here, and a single prefabricated building component is smaller than the overall prefabricated building, the volume of the voxels divided for a single prefabricated building component is smaller than the volume of the standard voxels divided for the overall prefabricated building.

[0062] Furthermore, the point cloud data within each voxel can be represented by its average value, thereby reducing data redundancy. Thus, the embodiment of the present invention has completed the denoising and redundancy reduction of the point cloud data.

[0063] Step S105: Use the point cloud data within the voxels to detect the installation process of each prefabricated building component in the prefabricated building.

[0064] Specifically, in the above embodiment of the present invention, the denoising and redundancy reduction of the acquired point cloud data are completed. For the assembly construction process of the prefabricated building, since these prefabricated building components are generally finished products assembled from large construction materials, during assembly, to ensure the quality of the building, they should be kept stable in the vertical or horizontal direction during installation without skewing or other phenomena. When skewing occurs, it may cause jamming of the prefabricated building components, resulting in poor assembly construction effect of this prefabricated building and requiring adjustment.

[0065] More specifically, when detecting the installation process of each prefabricated building component in the prefabricated building, as an optional embodiment of the present invention, first determine the average value of the point cloud data within the voxel as the target point cloud data corresponding to the voxel; then use the target point cloud data to detect the installation process of each prefabricated building component corresponding to the target point cloud data in the prefabricated building.

[0066] Among them, analyzing the synchronous detection during the assembly construction process of the prefabricated building needs to be analyzed under time conditions. Since the positions of the prefabricated building components that have been installed are fixed, the corresponding point cloud data of the prefabricated building components being installed will change in space over time. Therefore, the embodiment of the present invention detects the installation process of the prefabricated building components according to the target point cloud data at adjacent moments. Among them, as an optional embodiment of the present invention, first determine the target prefabricated building components whose position information of the target point cloud data at adjacent moments has changed according to the target point cloud data of the prefabricated building components at adjacent moments; then determine the vector direction of each target point cloud data in the space within the target prefabricated building component according to the spatial coordinates of the target point cloud data at adjacent moments within the target prefabricated building component; finally, use the vector direction of each target point cloud data in the space within the target prefabricated building component to detect the installation process of the target prefabricated building component.

[0067] Specifically, observe the distribution performance of the denoised and redundancy-reduced target point cloud data of the prefabricated building component at moment and moment in space. Specifically as follows: First obtain the denoised and redundancy-reduced point cloud data at moment, and at the same time obtain The point cloud data after denoising and redundancy reduction at a certain moment. Match two sets of point cloud data: Since the position of the pre-installed prefabricated building components remains unchanged, the position information of the corresponding point cloud data also does not change. Compare the two sets of point cloud data at adjacent moments, and combine the prefabricated building components to which the data in the two sets of point cloud data belong to obtain the target prefabricated building components corresponding to the point cloud data with changed position information . Further, the area size of the target prefabricated building component will not change, that is, the number of corresponding point cloud data remains the same before and after. Based on the distribution of the point cloud data on the target prefabricated building component , match the point cloud data corresponding to the target prefabricated building component at the moment and .

[0068] More specifically, when determining the vector direction of each target point cloud data in the space of the target prefabricated building component, as an optional embodiment of the present invention, first calculate the difference between the spatial coordinates of the target point cloud data at adjacent moments as the spatial vector of the target point cloud data in the space; then determine the vector direction of the spatial vector as the vector direction of the target point cloud data in the space

[0069] Specifically, the embodiment of the present invention specifically uses the following formula to calculate the spatial vector of the target point cloud data in the space

[0070]

[0071] In the above formula, represents the spatial vector of the i-th target point cloud data in the target prefabricated building component at the moment . represents the spatial coordinates of the j-th point cloud data corresponding to the target prefabricated building component at the moment . represents the spatial coordinates of the j-th point cloud data corresponding to the target prefabricated building component at the moment . Among them, the direction of is the vector direction of the target point cloud data in the space .

[0072] ​More specifically, in the embodiments of the present invention, the vector direction of each point cloud data in space is obtained through the above method. When detecting the installation process of the target prefabricated building component, if the vector directions of each target point cloud data in space are inconsistent, it is determined that the installation process of the target prefabricated building component is abnormal; if the vector directions of each target point cloud data in space are consistent, then along the vector direction, the distribution direction of the corresponding target point cloud data is approximated. If the distribution direction is consistent with the vector direction of the corresponding target point cloud data, it is determined that the installation process of the target prefabricated building component is good; if the distribution direction is inconsistent with the vector direction of the corresponding target point cloud data, it is determined that the installation process of the target prefabricated building component is abnormal.

[0073] Specifically, as Figure 3 shown, Figure 3 is a schematic diagram of the vector directions of the point cloud data in a building component R provided by an embodiment of the present invention. Figure 3 In, there are a total of three target point cloud data, and the overall vector directions of the three target point cloud data in space are inconsistent. Therefore, it is determined that the installation process of the target prefabricated building component is abnormal. Further, as Figure 4 and Figure 5 shown, Figure 4 is a schematic diagram of the vector direction and distribution direction of the point cloud data in a building component R provided by an embodiment of the present invention, Figure 5 is a schematic diagram of the vector direction and distribution direction of the point cloud data in a building component R provided by another embodiment of the present invention. Figure 4 In, the vector direction of each target point cloud data in space, the distribution direction of the target point cloud data, and are all consistent, indicating that the installation angle of the prefabricated building component is good. Figure 5 In, the vector directions of each target point cloud data in space are all consistent, but the distribution directions of the target point cloud data are inconsistent, indicating that there is a problem with the installation angle of the prefabricated building component.

[0074] It should be noted that when the above embodiments analyze that there is a problem with the installation process of the prefabricated building component being installed, an alarm is timely feedback to the relevant staff, so as to adjust the installation of the prefabricated building component, ensure the project quality during the assembly construction process of the prefabricated building, and at the same time complete the synchronous detection during the construction process.

[0075] In the embodiments of the present invention, first, noise information can be determined and removed according to the number of point cloud data divided into the same prefabricated building component. Then, according to the point cloud data in each prefabricated building component, the volume of the standard voxel, and the average probability of each point cloud data, the voxel size suitable for each prefabricated building component is determined. The voxel adapted to the prefabricated building component can accurately process the data redundancy of the prefabricated building component. In this way, the effects of denoising and redundancy reduction processing of the point cloud data are optimized, the characteristics of the original point cloud data are retained, the quality of the point cloud data is improved, and the subsequent analysis and processing effects based on the point cloud data are further improved. Further, the installation process of each prefabricated building component in the prefabricated building is detected by using the denoised and redundancy-reduced point cloud data, and the detection accuracy is improved.

[0076] Embodiment 2:

[0077] Corresponding to the prefabricated building assembly construction process detection method provided in the above embodiment, based on the same technical concept, the embodiments of the present invention also provide a prefabricated building assembly construction process detection system. The prefabricated building assembly construction process detection system is used to execute the above prefabricated building assembly construction process detection method. Figure 6 A structural schematic diagram of a prefabricated building assembly construction process detection system for implementing various embodiments of the present invention is shown in Figure 6 As shown at the hardware level, the prefabricated building assembly construction process detection system includes a processor. Optionally, it includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory, such as at least one disk memory, etc. Of course, the prefabricated building assembly construction process detection system may also include other hardware required for other services.

[0078] The processor, network interface, and memory can be interconnected through an internal bus. The internal bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, only a bidirectional arrow is used in this figure, but it does not mean that there is only one bus or one type of bus.

[0079] A memory for storing programs. Specifically, the program may include program code, and the program code includes computer operation commands. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0080] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a device for locating a specified user at the logical level. The processor executes the program stored in the memory and is specifically used to execute: Figure 1 The method disclosed in the illustrated embodiment and realizes the functions and beneficial effects of each method in the foregoing method embodiments, which will not be elaborated herein.

[0081] It should be noted that the prefabricated building assembly construction process detection system provided in the embodiments of the present invention and the prefabricated building assembly construction process detection method provided in the embodiments of the present invention are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the foregoing prefabricated building assembly construction process detection method, and has the same or similar beneficial effects, and the repeated parts will not be elaborated.

[0082] It should be noted that the above-mentioned sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0083] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. The key point of each embodiment is to illustrate the differences from other embodiments.

Claims

1. A method for detecting the assembly construction process of an assembled building, characterized in that: The method for detecting the assembly construction process of the prefabricated building comprises: Obtain point cloud data of different positions of prefabricated buildings during the assembly and construction process; Determine the probability that the point cloud data at the location and the other point cloud data belong to the same prefabricated building component based on the coordinate information and color information of other point cloud data in the target space around the location and the point cloud data at the location; When the probability is greater than a first threshold, determining that the point cloud data at the position and the other point cloud data belong to the same prefabricated building component; When the number of point cloud data classified into the same prefabricated building component is less than a second threshold, marking it as noise information and removing it; When the number of point cloud data classified into the same prefabricated building component is not less than a second threshold, determining the voxel corresponding to the point cloud data under the same prefabricated building component according to the point cloud data in the same prefabricated building component, the average probability of the probability that adjacent point cloud data in the same prefabricated building component are classified into the same prefabricated building component, and the volume of the standard voxel; The point cloud data in the voxel is used to detect the installation process of each prefabricated building component in the prefabricated building.

2. The method for detecting the assembly construction process of prefabricated buildings according to claim 1, characterized in that: Determining the probability that the point cloud data at the location and the other point cloud data belong to the same prefabricated building component based on the coordinate information and color information of the other point cloud data in the target space around the location and the point cloud data at the location includes: Determine a first distance between the point cloud data at the position and the other point cloud data according to coordinate information of other point cloud data and the point cloud data at the position in a target space around the position; Determine the color difference between the point cloud data at the position and the other point cloud data according to color information of other point cloud data and the point cloud data at the position in the target space around the position; The probability that the point cloud data at the position and the other point cloud data belong to the same prefabricated building component is determined by using the first distance and the color difference.

3. The method for detecting the assembly construction process of prefabricated buildings according to claim 2, characterized in that: The probability that the point cloud data at the position determined by using the first distance and the color difference and the other point cloud data belong to the same prefabricated building component includes: calculating a first product between the first distance and the color difference; The first product is normalized to obtain a probability that the point cloud data at the position and the other point cloud data belong to the same prefabricated building component.

4. The method for detecting the assembly construction process of prefabricated buildings according to claim 1, characterized in that: The step of determining the voxel corresponding to the point cloud data under the same prefabricated building component according to the point cloud data in the same prefabricated building component, the average probability of the probability of adjacent point cloud data in the same prefabricated building component being divided into the same prefabricated building component, and the volume of the standard voxel comprises: Determine a density parameter of the point cloud data under the same prefabricated building component according to a first number of point cloud data in the same prefabricated building component, an average probability of adjacent point cloud data in the same prefabricated building component being divided into the same prefabricated building component, a maximum distance between point cloud data in the same prefabricated building component, a first volume of a maximum cuboid wrapped by the first number of point cloud data, and a second volume of a maximum cuboid wrapped by all point cloud data in the prefabricated building; The voxel corresponding to the point cloud data under the same prefabricated building component is determined according to the density parameter of the point cloud data under the same prefabricated building component and the volume of the standard voxel.

5. The method for detecting the assembly construction process of prefabricated buildings according to claim 4, characterized in that: The method of determining the density parameter of the point cloud data under the same prefabricated building component according to the first number of point cloud data in the same prefabricated building component, the average probability of adjacent point cloud data in the same prefabricated building component being divided into the same prefabricated building component, the maximum distance between point cloud data in the same prefabricated building component, the first volume of the largest cuboid wrapped by the first number of point cloud data, and the second volume of the largest cuboid wrapped by all point cloud data in the prefabricated building comprises: calculating a first ratio between the average probability and the maximum distance, and a second ratio between the second volume and the first volume; A second product of the first number, the first ratio, and the second ratio is determined as a density parameter of the point cloud data of the same prefabricated building component.

6. The method for detecting the assembly construction process of prefabricated buildings according to claim 4, characterized in that: The step of determining the voxel corresponding to the point cloud data of the same prefabricated building component according to the density parameter of the point cloud data of the same prefabricated building component and the volume of the standard voxel comprises: Determine the volume of the standard voxel according to the point cloud data being in a uniform state; Normalizing the density parameter to obtain a normalized density parameter; A third product of the normalized density parameter and the volume is determined as a voxel corresponding to the point cloud data of the same prefabricated building component.

7. The method for detecting the assembly construction process of prefabricated buildings according to claim 1, characterized in that: The detecting the installation process of each prefabricated building component in the prefabricated building by using the point cloud data in the voxel includes: Determine the average value of the point cloud data in the voxel as the target point cloud data corresponding to the voxel; The target point cloud data is used to detect the installation process of each prefabricated building component corresponding to the target point cloud data in the prefabricated building.

8. The method for detecting the assembly construction process of prefabricated buildings according to claim 7, characterized in that: The detecting the installation process of each prefabricated building component corresponding to the target point cloud data in the prefabricated building by using the target point cloud data includes: Determine, based on the target point cloud data of the prefabricated building component at adjacent moments, a target prefabricated building component whose position information of the target point cloud data at adjacent moments changes; Determine the vector direction of each target point cloud data in the target prefabricated building component in space according to the spatial coordinates of the target point cloud data at adjacent moments in the target prefabricated building component; The installation process of the target prefabricated building component is detected by using the vector direction of each target point cloud data in the target prefabricated building component in space.

9. The method for detecting the assembly construction process of prefabricated buildings according to claim 8, characterized in that: The step of determining the vector direction of each target point cloud data in the target prefabricated building component in space according to the spatial coordinates of the target point cloud data at adjacent moments in the target prefabricated building component comprises: Calculate the difference between the spatial coordinates of the target point cloud data at adjacent moments as the spatial vector of the target point cloud data in space; The vector direction of the space vector is determined to be the vector direction of the target point cloud data in space.

10. The method for detecting the assembly construction process of prefabricated buildings according to claim 8, characterized in that: The detecting the installation process of the target prefabricated building component by using the vector direction of each target point cloud data in the space of the target prefabricated building component comprises: If the vector directions of each of the target point cloud data in space are inconsistent, it is determined that the installation process of the target prefabricated building component is abnormal; If the vector direction of each target point cloud data in space is consistent, the distribution direction of the corresponding target point cloud data is constructed along the vector direction; if the distribution direction is consistent with the vector direction of the corresponding target point cloud data, it is determined that the installation process of the target prefabricated building component is good; if the distribution direction is inconsistent with the vector direction of the corresponding target point cloud data, it is determined that the installation process of the target prefabricated building component is abnormal.

Images