Method, device and equipment for detecting construction progress of surface type component

Abstract

The invention provides a construction progress detection method, device and equipment for a surface type component, and the method comprises the steps: firstly, carrying out the photographing of a construction site wall, obtaining image data, carrying out the distortion correction and compression of an image, and extracting the pixel matrix information; a voxelization technology is utilized to segment the wall body model into a plurality of voxels, each voxel corresponds to one pixel, and the wall body construction progress is analyzed and modeled based on pixel information; the color gamuts of different construction stages are established, the colors of the voxels are compared with the color gamuts, the construction stage to which the voxels belong is judged, and then the overall construction progress of the wall is analyzed. The accuracy and robustness of construction progress calculation are improved, the application range is wide, operation is easy and convenient, the automation degree is high, real-time interaction with the BIM model can be achieved, and new technical support is provided for an intelligent construction site and intelligent construction.

Description

Technical Field

[0001] The present invention relates to the technical field of construction progress detection, and in particular to a construction progress detection method, device and equipment for a surface component. Background Art

[0002] With the rapid development of information technology, Building Information Modeling (BIM) technology has become an indispensable tool in project management and construction. Specifically, the application of BIM technology not only improves the efficiency of design and construction, but also provides strong data support for project management. However, despite the significant progress made by BIM technology in the field of construction, real-time monitoring and management of construction progress remains a challenge; for example: traditional BIM technology is prone to errors when dealing with wall openings, has a narrow scope of application, high training costs, low degree of automation, and is not intuitive enough in software expression. Especially in the construction process of surface components such as walls, how to accurately analyze the construction progress and update the model in real time has become an urgent problem to be solved in the industry.

[0003] Currently, there are two main technical solutions: one is the image processing principle, which remaps the distorted image pixels to the correct position by establishing a distortion model, so that the image can be restored to its normal shape; the other is the image segmentation technology, which divides the entire wall into constructed and unconstructed areas. Based on the feature differences of pixels, the algorithm classifies pixels with similar features into the same area to achieve the division of the wall area. These technologies express the completion progress of the construction by calculating the ratio of the constructed area to the unconstructed area.

[0004] Although these technical solutions can realize the calculation of the real-time progress of the construction wall, there are still major deficiencies in the development needs of digital twins and intelligent construction. First of all, from a technical point of view, if there are openings in the construction wall, such as window openings and door openings, it will cause errors in the final calculation of the scheme. This is because the situation with openings is not taken into account, or the technology using image segmentation is not applicable to the situation with openings, and the openings will be confused with the unconstructed areas. Secondly, from the implementation point of view, it is currently only applicable to the progress analysis of indoor tiling, with low applicability, and before use, a large number of training of its large model is required, which has high time and computing power costs. The most important thing is that the whole process is not automated enough. Finally, from the expression point of view, it is not intuitive to calculate a completion rate by connecting to external software, and then connect the completion rate from the external software as only a parameter to the BIM model.

[0005] In general, the existing technology has defects in both technical implementation and expression effect due to its failure to properly handle wall openings, narrow scope of application, high training costs and insufficient automation, as well as software defects.

[0006] In view of this, this application is filed. Summary of the invention

[0007] The present invention provides a method, device and equipment for detecting the construction progress of a surface component, which can at least partially improve the above-mentioned problem.

[0008] To achieve the above object, the present invention adopts the following technical solutions:

[0009] A construction progress detection method for a surface component, comprising:

[0010] Establishing a BIM model according to preset construction drawings and design requirements, or obtaining an already established BIM model, wherein a model camera having a location and orientation consistent with that of the construction site is placed in the BIM model;

[0011] Acquire a model image captured by a model camera, perform model wall preprocessing on the surface component in the model image based on a Dynamo script, and obtain four vertices of the surface of the surface component after distortion correction;

[0012] Acquire a real image captured by a camera arranged at the construction site, perform distortion correction and compression processing on the real image according to the four vertices of the surface of the surface component after the distortion correction, and extract a pixel matrix of the real image from the compressed image based on the Dynamo script;

[0013] Performing voxel segmentation processing on the pixel matrix of the real image and the actual size of the component, and coloring the segmented voxel units to obtain a voxelized model;

[0014] According to the building materials actually used in the construction, a color gamut of the construction stage is established, the color gamut of the construction stage is compared with the voxel unit of the voxelized model to obtain a color gamut detection result, and the construction completion degree is calculated according to the color gamut detection result;

[0015] The current construction stage of the surface component is determined according to the color gamut detection result, the expression mode of the voxelized model is modified according to the current construction stage, and the construction completion degree and the current construction stage are imported into the BIM model and the voxelized model as parameters, so that the model can reflect the construction progress and status in real time.

[0016] The present invention also provides a construction progress detection device for a surface-shaped component, which comprises:

[0017] A preprocessing unit, used to establish a BIM model according to preset construction drawings and design requirements, or to obtain a BIM model that has been established, wherein a model camera having a position and orientation consistent with that of the construction site is placed in the BIM model;

[0018] A model image processing unit is used to obtain a model image collected by a model camera, and perform model wall preprocessing on the surface component in the model image based on a Dynamo script to obtain four vertices of the surface of the surface component after distortion correction;

[0019] A real image processing unit, used for acquiring a real image collected by a camera arranged at the construction site, performing distortion correction processing and compression processing on the real image according to the four vertices of the surface of the surface component after the distortion correction, and extracting a pixel matrix of the real image from the compressed image based on the Dynamo script;

[0020] A model voxelization unit, used for performing voxel segmentation processing on the pixel matrix of the real image and the actual size of the component, and coloring the segmented voxel units to obtain a voxelized model;

[0021] A color gamut detection unit is used to establish a color gamut in a construction stage according to the building materials actually used in the construction, compare the color gamut in the construction stage with the voxel unit of the voxelized model, obtain a color gamut detection result, and calculate the degree of construction completion according to the color gamut detection result;

[0022] The model expression unit is used to determine the current construction stage of the surface component according to the color gamut detection result, modify the expression mode of the voxelized model according to the current construction stage, and import the construction completion degree and the current construction stage as parameters into the BIM model and the voxelized model, so that the model can reflect the construction progress and status in real time.

[0023] The present invention also provides a construction progress detection device for a surface-shaped component, which includes a memory and a processor, wherein the memory stores a computer program, and the computer program can be executed by the processor to implement the construction progress detection method for a surface-shaped component as described in any one of the above.

[0024] In summary, the construction progress detection method of the surface component is used to perform real-time modeling and construction progress detection on the surface component during the construction process. It realizes accurate analysis and modeling of the wall at the construction site through the reverse modeling principle and voxelization processing; it also captures the wall image through the camera, performs distortion correction and pixel matrix extraction, and then compares it with the color gamut to determine the construction stage and calculate the progress. This method not only improves the accuracy of monitoring, but also has wide applicability and can adapt to different construction environments and conditions.

[0025] In addition, the construction progress detection method of the surface component reduces manual intervention and saves time and cost through an automated processing flow; after being integrated with the BIM model, it realizes real-time updating and visualization of the construction progress, greatly improving the efficiency and quality of construction management. Moreover, this method enables the BIM model to change from static to dynamic, reflecting the construction progress and actual situation on site in real time, providing new technical support for smart construction sites and intelligent construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a schematic flow chart of the construction progress detection method of the surface-shaped component provided by the first aspect of the present invention;

[0027] Figure 2 It is a schematic flow chart of a construction progress detection method for a surface-shaped component provided by the second aspect of the present invention;

[0028] Figure 3 It is a schematic diagram of the model processing of Figure 1 provided in the first embodiment of the present invention;

[0029] Figure 4 2 is a schematic diagram of distortion correction provided by the first embodiment of the present invention;

[0030] Figure 5 is a schematic diagram of a wall in the wall-building stage provided by the first embodiment of the present invention;

[0031] Figure 6 is a schematic diagram of a wall in a completion stage provided by the first embodiment of the present invention;

[0032] Figure 7 It is a module schematic diagram of a construction progress detection device for a surface component provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0034] refer to Figure 1 , Figure 2 As shown, the first embodiment of the present invention discloses a construction progress detection method for a surface-shaped component, which can be executed by a construction progress detection device for a surface-shaped component (hereinafter referred to as a detection device), and in particular, executed by one or more processors in the detection device to implement the following method:

[0035] S1, establishing a BIM model according to preset construction drawings and design requirements, or obtaining an already established BIM model, wherein a model camera having a position and direction consistent with the construction site is placed in the BIM model;

[0036] In this embodiment, we first start by building or acquiring a BIM model that matches the actual construction site; this BIM model is carefully built based on the preset construction drawings and design requirements, ensuring that every architectural detail is consistent with the actual construction blueprint. In this process, special attention needs to be paid to the placement of the model camera, which is precisely arranged in the BIM model to ensure that its position and orientation are completely consistent with the actual situation on the construction site. Such an arrangement allows the model camera to capture the construction progress from the best perspective, providing an accurate visual benchmark for subsequent construction progress analysis.

[0037] In addition, the camera is loaded into the visual programming tool using the SELECT ELEMENT node, and the camera view is adjusted to match the camera view on site. This precise model camera arrangement ensures that the captured image truly reflects the conditions on the construction site, which is critical for subsequent image processing and analysis. The precise placement of the model camera also means that image distortion can be reduced, improving the accuracy of subsequent construction progress analysis. This is particularly important in construction management because it directly affects the monitoring and prediction of construction progress.

[0038] S2, obtaining a model image captured by a model camera, performing model wall preprocessing on the surface component in the model image based on a Dynamo script, and obtaining four vertices of the surface of the surface component after distortion correction;

[0039] Specifically, step S2 includes: acquiring a model image captured by the model camera;

[0040] Based on the Dynamo script, the surface components in the model image are screened, and the surface components are pre-processed to obtain four vertices of a surface that is closest to the model camera and has the largest volume;

[0041] The model image is cropped according to the Dynamo script and the four vertices, and the positions of the four vertices after distortion correction are generated based on the pixel matrix of the cropped model image.

[0042] Preferably, the surface components in the model image are screened based on the Dynamo script, and the surface components are pre-processed to obtain the four vertices of a surface that is closest to the model camera and has the largest volume, specifically:

[0043] Obtaining faces of multiple face-shaped components according to the Element.Faces node in the dynamo script;

[0044] According to the Surface.Area node in the Dynamo script, the surface area of ​​each surface component is obtained, and the surfaces of the two surface components with the largest area and the second largest area are screened out;

[0045] Based on the Geometry.DistanceTo node in the Dynamo script, respectively obtain the distance from the surface of the surface component with the largest area to the model camera, and the distance from the surface of the surface component with the second largest area to the model camera;

[0046] From the faces of the above two surface components, the face of the surface component that is close to the model camera is selected, and the positions of the four vertices of the face are obtained according to the Topology.Vertices node and Vertex.PointGeometry node in the Dynamo script;

[0047] Based on the Sphere.ByCenterPointRadius node in the Dynamo script, four small balls with a radius of 100 mm are generated with these four vertices as the center;

[0048] Through the Element.OverrideColorInView node in the dynamo script or by setting the material, the color of the ball is set to red, and the RGB value of the ball is recorded.

[0049] Preferably, the model image is cropped according to the Dynamo script and the four vertices, and based on the pixel matrix of the cropped model image, the positions of the four vertices after distortion correction are generated, specifically:

[0050] According to the View, ElementAsImage node and four vertices in the Dynamo script, the model image is cropped to the positions of the four vertices;

[0051] Get the pixel matrix A of the cropped model image ij , and the pixel matrix A ij The elements in are divided into 0 or 1 according to the preset rules, and the positions of the four vertices after distortion correction are obtained.

[0052] See also Figure 3In this embodiment, a model camera is used to capture model images of the construction site. These images are key data for subsequent construction progress analysis and modeling. Through the Dynamo script, the surface component is pre-processed to extract the four vertices of the surface closest to the model camera and with the largest volume. These vertices are crucial for subsequent distortion correction.

[0053] Specifically, the Element.Faces node in the dynamo script is used to identify the faces of multiple face-shaped components in the model image; then, the Surface.Area node is used to calculate the area of ​​each face, and the two faces with the largest area and the second largest area are selected. The distances of the two faces to the model camera are measured through the Geometry.DistanceTo node to determine which face is closer to the camera. This step ensures that the construction progress detection method of the face-shaped component can accurately identify the most relevant face-shaped components, providing accurate geometric information for subsequent construction progress analysis. After selecting the face closest to the camera, the Topology.Vertices node and the Vertex.PointGeometry node are used to obtain the four vertex positions of the face. This step is the key to achieving accurate modeling because it provides the precise vertex data required to build the voxel model. In order to clearly mark these vertices in the model image, the Sphere.ByCenterPointRadius node can be used to generate small balls with a radius of 100mm at each vertex position, and the color of these small balls is set to red for easy identification in the image. By using the Element.OverrideColorInView node or setting the material, the RGB values ​​of these balls are recorded, providing an important reference for subsequent image processing.

[0054] Next, the model image is cropped according to the Dynamo script and the four vertices, retaining only the part containing the four vertices. This cropping process is implemented through the View,ElementAsImage node, which allows this method to focus on the most relevant image area, thereby improving the efficiency of subsequent processing. The cropped image is converted into a pixel matrix A ij , according to the preset rules, the elements in the pixel matrix are divided into 0 or 1 to generate the positions of the four vertices after distortion correction. This step is the key to achieve image distortion correction, ensuring that information corresponding to the actual construction status can be accurately extracted from the image.

[0055] In this embodiment, the pixel matrix A can be ij middle element a mn Divided into 0 and 1 according to the following logic:

[0056] Y is the RGB value of the ball

[0057]

[0058]

[0059]

[0060] S3, obtaining a real image collected by a camera arranged at the construction site, performing distortion correction processing and compression processing on the real image according to the four vertices of the surface of the surface component after the distortion correction, and extracting a pixel matrix of the real image from the compressed image based on the Dynamo script;

[0061] Specifically, step S3 includes: obtaining real images collected by multiple cameras arranged at the construction site, wherein the field of view of the cameras can completely cover the surface components to be analyzed, and there are no fixed objects blocking the camera's shooting line of sight;

[0062] According to the four vertices of the surface of the surface component after the distortion correction, the real image is processed using a distortion correction algorithm to remap the pixel points in the real image to the correct position;

[0063] According to a compression ratio based on actual needs, compressing the distortion-corrected real image, wherein the construction progress related information in the real image is retained during the compression process;

[0064] Based on the dynamo script, the pixel matrix of the real image is extracted from the compressed real image.

[0065] See also Figure 4 In this embodiment, real-time wall images are obtained from cameras deployed on site according to the set image acquisition frequency. The image acquisition frequency can be set according to the construction progress monitoring requirements, for example: collecting images every certain time (such as 3 minutes), or collecting images at key construction nodes (such as wall completion, plastering, etc.). To ensure the stability and continuity of image acquisition and avoid image loss or damage. These cameras are carefully arranged to ensure that their field of view can completely cover the surface components to be analyzed, while avoiding any fixed objects blocking the shooting line of sight, thereby ensuring the integrity and accuracy of the image. This step is fundamental because it provides us with direct visual data of the construction site, which will be used for subsequent construction progress analysis and modeling.

[0066] The collected real image is processed using a distortion correction algorithm, where the resolution of the real image is assumed to be m*n, and the distortion correction algorithm is (i*m,j*n)for i,j in Location1. According to the four vertices of the surface of the surface component after the distortion correction obtained previously, the pixel points in the real image are remapped to the correct position; in addition, for images containing multiple walls, the areas corresponding to each wall are respectively subjected to distortion correction to improve the accuracy of the analysis and to correct the image. Simply put, this step can eliminate the image distortion caused by the characteristics of the camera lens and ensure the accuracy of subsequent analysis. Distortion correction not only improves the image quality, but also provides a reliable basis for the accurate analysis of the construction progress.

[0067] After distortion correction, in order to reduce the amount of calculation, the image is compressed according to the compression ratio required in practice; the lower the pixel after compression, the lower the calculation accuracy and model accuracy, but the program running speed increases. In this embodiment, a suitable image compression algorithm (such as JPEG, PNG, etc.) is used, and the compression ratio is selected according to actual needs, such as compressing the image to a size of 50*50 pixels. This step is intended to reduce the amount of calculation for subsequent processing while retaining all key information related to the construction progress, such as wall color, texture, etc. Appropriate compression can improve processing speed while ensuring analysis accuracy, which is particularly important for real-time monitoring of construction progress.

[0068] Finally, the pixel matrix is ​​extracted from the compressed real image using the Dynamo script. The compressed image is loaded into the visual programming script written in the above steps. The pixel matrix is ​​extracted from the script to obtain the length, width and RGB color matrix of the pixel. These pixel data will serve as the basis for subsequent construction progress analysis and voxel modeling. The RGB value of each pixel will be used to compare with the color gamut to determine the construction stage it belongs to. This step involves converting the image into a digital format that can be used for further analysis, in which the color information of each pixel will be recorded. The extraction of the pixel matrix is ​​the key to automating the construction progress analysis because it provides the necessary data for subsequent voxelization and color gamut analysis.

[0069] S4, performing voxel segmentation processing on the pixel matrix of the real image and the actual size of the component, and coloring the segmented voxel units to obtain a voxelized model;

[0070] Specifically, step S4 includes: performing voxel segmentation on the pixel matrix of the real image and the actual size of the component, dividing the BIM model into a plurality of voxel units, wherein each voxel unit corresponds one-to-one to a pixel at the same position, the size of the voxel is V=A / Na*B / Nb*C / N, the number of voxels is M=m / N, A is the original length of the BIM model, B is the original width of the BIM model, C is the original thickness of the BIM model, a is the image pixel length, b is the image pixel width, N is a preset natural number, and m is the number of pixels;

[0071] The color of each voxel unit is set to the color of the pixel corresponding thereto, and a voxelized model is obtained to display the construction status of different areas of the surface component;

[0072] In the process of voxel modeling, the BIM model is hidden and only the voxel model is displayed.

[0073] In this embodiment, the pixel matrix of the real image and the actual size of the component are subjected to detailed voxel segmentation processing, and the component model is divided into a number of voxel units based on the voxel size; the voxel segmentation should ensure the accurate correspondence with the pixel so that the state of the voxel can be determined later based on the pixel information. Furthermore, based on the voxel segmentation, a coloring process is performed to set the color of each voxel unit to the color of its corresponding pixel. This step enables the voxel model to reflect the actual appearance of the wall in color, and then enables the obtained voxelized model to intuitively display the construction status of different areas of the surface component, such as distinguishing between constructed and unconstructed areas, or the color difference of areas at different construction stages. This intuitive color contrast not only makes it easier to monitor the construction progress, but also provides clear construction guidance for construction personnel.

[0074] In the process of voxel modeling, the construction progress detection method of the surface component chooses to hide the BIM model and only display the voxel model. The advantage of this is that the voxel-based construction progress and model status can be observed and analyzed more clearly, making the monitoring and management of the construction progress more intuitive and accurate. In addition, this voxel model display method is also convenient for communicating the construction progress with the construction team, because it provides a simple and intuitive way to display complex construction data.

[0075] S5, establishing a color gamut in the construction stage according to the building materials actually used in the construction, comparing the color gamut in the construction stage with the voxel unit of the voxelized model to obtain a color gamut detection result, and calculating the construction completion degree according to the color gamut detection result;

[0076] Specifically, step S5 includes: collecting and analyzing color samples of materials in different construction stages that are actually used in construction, establishing a color gamut for the construction stage, and determining the color gamut range of each construction stage in the RGB color space;

[0077] The RGB color of the voxel unit is compared with the color gamut of the construction stage one by one to determine the construction stage to which each voxel unit belongs;

[0078] The number v of voxels that do not belong to the color gamut of the current construction stage in all voxel units is counted, and the construction completion degree is calculated. The calculation formula is: W = v / M.

[0079] In this embodiment, the focus is first on establishing the color gamut of the construction stage, which involves collecting and analyzing color samples of materials in different construction stages actually used on the construction site. Through this process, the color gamut range of each construction stage can be determined in the RGB color space, thereby providing an accurate color benchmark for subsequent voxel unit comparison and construction progress analysis. Specifically, color samples of materials such as red bricks and cement mortar are first collected, and their RGB values ​​are measured using professional equipment. These data are used to define the color gamut range of each construction stage in the RGB color space. For example, by measuring the RGB values ​​of a large number of red brick samples, the color gamut range of the wall-laying stage is determined; similarly, the cement mortar samples are analyzed to determine the color gamut range of the plastering stage. The implementation of this step not only improves the accuracy of the construction progress analysis, but also provides a scientific basis for the quality control of construction materials.

[0080] The RGB color of each voxel unit in the voxelized model is compared with the established construction stage color gamut one by one to determine the construction stage to which each voxel belongs; this process is implemented through an automated algorithm, which can efficiently determine the construction stage to which each voxel unit belongs. Since the construction stages are sequential and exclusive (for example, a wall can only be in one of the stages of bricklaying, plastering, and completion), and these stages have a chronological or parallel relationship, based on these relationships and the comparison of voxel colors and stage color gamuts, voxel units in different construction stages can be distinguished, the construction progress can be accurately identified, and then the construction stage of the entire wall can be determined. For example: if most voxel colors are within the wall-laying stage color gamut, it can be determined that the wall is in the wall-laying stage.

[0081] After the comparison is completed, the number of voxels v that do not belong to the color gamut of the current construction stage is counted and the degree of construction completion is calculated. This calculation result provides users with a quantitative indicator of construction progress, allowing construction managers to monitor the construction progress in real time and make corresponding management decisions accordingly.

[0082] S6, judging the current construction stage of the surface component according to the color gamut detection result, modifying the expression of the voxelized model according to the current construction stage, and taking the construction completion degree and the current construction stage as parameters, importing them into the BIM model and the voxelized model, so that the model can reflect the construction progress and status in real time.

[0083] Specifically, step S6 includes: the current construction stage of the surface component includes the wall-building stage, the plastering stage and the completion stage;

[0084] When it is determined that the current construction stage is the wall-laying stage, the voxel units corresponding to the color domain that is not in the wall-laying stage are deleted, and only the voxel units in the wall-laying stage are retained and displayed with their corresponding pixel colors;

[0085] When it is determined that the current construction stage is the plastering stage, a wall model is generated on the side close to the camera for the voxel unit corresponding to the color domain in the plastering stage to simulate the thickness of the plastering layer;

[0086] When it is determined that the current construction stage is the completion stage, all voxel units are deleted and the BIM model is displayed.

[0087] See also Figure 5 , Figure 6 In this embodiment, the current construction stage of the surface component is determined by the color gamut detection result, and the expression of the voxelized model is updated accordingly to achieve real-time reflection of the construction progress and status. It ensures that the BIM model and the voxelized model can accurately display the actual situation of the construction site. Identify the construction stage of the surface component, which includes the wall-building stage, the plastering stage and the completion stage. For each stage, a different processing method is adopted to update the voxelized model. Taking the plastering stage as an example, for the voxels in the color gamut of the plastering stage, a wall model of appropriate thickness (such as 5mm) is generated on the plane where the plastering is located, that is, on the side close to the camera, so that the thickness of the plastering layer can be simulated. And represented by the corresponding pixel color, the model can reflect the construction situation more realistically.

[0088] Finally, throughout the entire process, the degree of construction completion and the current construction stage are used as parameters and imported into the BIM model and voxelized model. This operation enables the model to reflect the construction progress and status in real time, providing strong data support for construction management. Through this real-time update, the construction team can adjust the construction plan in a timely manner, optimize resource allocation, and improve construction efficiency.

[0089] In summary, the construction progress detection method of the surface component accurately tracks the progress of the construction process by combining voxelization technology and color gamut analysis. This method is particularly good at handling complex structures such as wall openings, ensuring that the openings will not be mistaken for unconstructed areas in the construction progress analysis, thereby greatly improving the accuracy and reliability of the analysis results. Specifically, this method is not limited to a single construction stage, and can flexibly adapt to various stages from walling, plastering, tiling to completion, and only needs to provide the corresponding color gamut value. It not only simplifies the complexity of using different algorithms for different stages in the past, but also reduces the difficulty of technical implementation. By using visual programming tools, the operation process becomes simple and intuitive, eliminating the need to train large models, saving a lot of time and computing resources, and improving work efficiency.

[0090] In short, the construction progress detection method of the surface component optimizes the monitoring and management of the construction progress through automation and intelligent means, reduces manual operations, reduces costs, and improves construction efficiency and quality. The application of this technology not only promotes the digital transformation of the construction industry, but also brings revolutionary changes to construction project management, providing more accurate progress control and quality assurance for construction projects.

[0091] See also Figure 7 The second embodiment of the present invention provides a construction progress detection device for a surface-shaped component, which comprises:

[0092] A preprocessing unit 201 is used to establish a BIM model according to preset construction drawings and design requirements, or to obtain a BIM model that has been established, wherein a model camera having a position and direction consistent with the construction site is placed in the BIM model;

[0093] The model image processing unit 202 is used to obtain the model image collected by the model camera, and perform model wall preprocessing on the surface component in the model image based on the Dynamo script to obtain four vertices of the surface of the surface component after distortion correction;

[0094] A real image processing unit 203 is used to obtain a real image collected by a camera arranged at the construction site, perform distortion correction processing and compression processing on the real image according to the four vertices of the surface of the surface component after the distortion correction, and extract a pixel matrix of the real image from the compressed image based on the Dynamo script;

[0095] The model voxelization unit 204 is used to perform voxel segmentation processing on the pixel matrix of the real image and the actual size of the component, and color the segmented voxel units to obtain a voxelized model;

[0096] The color gamut detection unit 205 is used to establish the color gamut of the construction stage according to the building materials actually used in the construction, compare the color gamut of the construction stage with the voxel unit of the voxelized model, obtain the color gamut detection result, and calculate the construction completion degree according to the color gamut detection result;

[0097] The model expression unit 206 is used to determine the current construction stage of the surface component according to the color gamut detection result, modify the expression method of the voxelized model according to the current construction stage, and import the construction completion degree and the current construction stage as parameters into the BIM model and the voxelized model, so that the model can reflect the construction progress and status in real time.

[0098] The third embodiment of the present invention provides a construction progress detection device for a surface-shaped component, which includes a memory and a processor, wherein the memory stores a computer program, and the computer program can be executed by the processor to implement the construction progress detection method for a surface-shaped component as described in any one of the above.

[0099] Exemplarily, the above-mentioned devices and process steps can be implemented by a computer program. The computer program can be divided into one or more units. The one or more units are stored in the memory and executed by the processor to complete the present invention.

[0100] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0101] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the present invention by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0102] Wherein, if the electronic device or printer integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0103] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0104] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A construction progress detection method for a surface component, characterized in that: include: Establishing a BIM model according to preset construction drawings and design requirements, or obtaining an already established BIM model, wherein a model camera having a location and orientation consistent with that of the construction site is placed in the BIM model; Acquire a model image captured by a model camera, perform model wall preprocessing on the surface component in the model image based on a Dynamo script, and obtain four vertices of the surface of the surface component after distortion correction; Acquire a real image captured by a camera arranged at the construction site, perform distortion correction and compression processing on the real image according to the four vertices of the surface of the surface component after the distortion correction, and extract a pixel matrix of the real image from the compressed image based on the Dynamo script; Performing voxel segmentation processing on the pixel matrix of the real image and the actual size of the component, and coloring the segmented voxel units to obtain a voxelized model; According to the building materials actually used in the construction, a color gamut of the construction stage is established, the color gamut of the construction stage is compared with the voxel unit of the voxelized model to obtain a color gamut detection result, and the construction completion degree is calculated according to the color gamut detection result; The current construction stage of the surface component is determined according to the color gamut detection result, the expression mode of the voxelized model is modified according to the current construction stage, and the construction completion degree and the current construction stage are imported into the BIM model and the voxelized model as parameters, so that the model can reflect the construction progress and status in real time.

2. The construction progress detection method of surface-shaped components according to claim 1, characterized in that: The model image captured by the model camera is obtained, and the surface component in the model image is preprocessed as a model wall based on the Dynamo script to obtain the four vertices of the surface of the surface component after distortion correction, specifically: Acquire a model image captured by the model camera; Based on the Dynamo script, the surface components in the model image are screened, and the surface components are pre-processed to obtain four vertices of a surface that is closest to the model camera and has the largest volume; The model image is cropped according to the Dynamo script and the four vertices, and the positions of the four vertices after distortion correction are generated based on the pixel matrix of the cropped model image.

3. The construction progress detection method of the surface component according to claim 2 is characterized in that: Based on the Dynamo script, the surface components in the model image are screened and pre-processed to obtain the surface components, and the four vertices of the surface closest to the model camera and with the largest volume are obtained, specifically: Obtaining faces of multiple face-shaped components according to the Element.Faces node in the dynamo script; According to the Surface.Area node in the Dynamo script, the surface area of ​​each surface component is obtained, and the surfaces of the two surface components with the largest area and the second largest area are screened out; Based on the Geometry.DistanceTo node in the Dynamo script, respectively obtain the distance from the surface of the surface component with the largest area to the model camera, and the distance from the surface of the surface component with the second largest area to the model camera; From the faces of the above two surface components, the face of the surface component that is close to the model camera is selected, and the positions of the four vertices of the face are obtained according to the Topology.Vertices node and Vertex.PointGeometry node in the Dynamo script; Based on the Sphere.ByCenterPointRadius node in the Dynamo script, four small balls with a radius of 100 mm are generated with these four vertices as the center; Through the Element.OverrideColorInView node in the dynamo script or by setting the material, the color of the ball is set to red, and the RGB value of the ball is recorded.

4. The construction progress detection method of surface-shaped components according to claim 2, characterized in that: The model image is cropped according to the Dynamo script and the four vertices, and based on the pixel matrix of the cropped model image, the positions of the four vertices after distortion correction are generated, specifically: According to the View, ElementAsImage node and four vertices in the Dynamo script, the model image is cropped to the positions of the four vertices; Get the pixel matrix A of the cropped model image ij , and the pixel matrix A ij The elements in are divided into 0 or 1 according to the preset rules, and the positions of the four vertices after distortion correction are obtained.

5. The construction progress detection method of surface-shaped components according to claim 1, characterized in that: The real image collected by the camera arranged at the construction site is obtained, and the real image is subjected to distortion correction and compression processing according to the four vertices of the surface of the surface component after the distortion correction, and the pixel matrix of the real image is extracted from the compressed image based on the Dynamo script, specifically: Acquire real images collected by multiple cameras deployed at the construction site, wherein the field of view of the cameras can completely cover the surface components to be analyzed, and there are no fixed objects blocking the camera's shooting line of sight; According to the four vertices of the surface of the surface component after the distortion correction, the real image is processed using a distortion correction algorithm to remap the pixel points in the real image to the correct position; According to a compression ratio based on actual needs, compressing the distortion-corrected real image, wherein the construction progress related information in the real image is retained during the compression process; Based on the dynamo script, the pixel matrix of the real image is extracted from the compressed real image.

6. The construction progress detection method of surface-shaped components according to claim 1, characterized in that: The pixel matrix of the real image and the actual size of the component are subjected to voxel segmentation processing, and the segmented voxel units are colored to obtain a voxelized model, specifically: Perform voxel segmentation on the pixel matrix of the real image and the actual size of the component, and divide the BIM model into multiple voxel units, wherein each voxel unit corresponds to a pixel at the same position one by one, the size of the voxel is V=A / Na*B / Nb*C / N, the number of voxels is M=m / N, A is the original length of the BIM model, B is the original width of the BIM model, C is the original thickness of the BIM model, a is the image pixel length, b is the image pixel width, N is a preset natural number, and m is the number of pixels; The color of each voxel unit is set to the color of the pixel corresponding thereto, and a voxelized model is obtained to display the construction status of different areas of the surface component; In the process of voxel modeling, the BIM model is hidden and only the voxel model is displayed.

7. The construction progress detection method of surface-shaped components according to claim 1, characterized in that: According to the building materials actually used in the construction, the color gamut of the construction stage is established, the color gamut of the construction stage is compared with the voxel unit of the voxelized model to obtain the color gamut detection result, and the construction completion degree is calculated according to the color gamut detection result, specifically: Collect and analyze color samples of materials actually used in different construction stages, establish the color gamut of the construction stage, and determine the color gamut range of each construction stage in the RGB color space; The RGB color of the voxel unit is compared with the color gamut of the construction stage one by one to determine the construction stage to which each voxel unit belongs; The number v of voxels that do not belong to the color gamut of the current construction stage in all voxel units is counted, and the construction completion degree is calculated. The calculation formula is: W = v / M.

8. The construction progress detection method of surface-shaped components according to claim 1, characterized in that: Modify the representation of the voxelized model according to the current construction stage, specifically: The current construction stages of the surface components include the wall-building stage, the plastering stage and the completion stage; When it is determined that the current construction stage is the wall-laying stage, the voxel units corresponding to the color domain that is not in the wall-laying stage are deleted, and only the voxel units in the wall-laying stage are retained and displayed with their corresponding pixel colors; When it is determined that the current construction stage is the plastering stage, a wall model is generated on the side close to the camera for the voxel unit corresponding to the color domain in the plastering stage to simulate the thickness of the plastering layer; When it is determined that the current construction stage is the completion stage, all voxel units are deleted and the BIM model is displayed.

9. A construction progress detection device for a surface component, characterized in that: include: A preprocessing unit, used to establish a BIM model according to preset construction drawings and design requirements, or to obtain a BIM model that has been established, wherein a model camera having a position and orientation consistent with that of the construction site is placed in the BIM model; A model image processing unit is used to obtain a model image collected by a model camera, and perform model wall preprocessing on the surface component in the model image based on a Dynamo script to obtain four vertices of the surface of the surface component after distortion correction; A real image processing unit, used for acquiring a real image collected by a camera arranged at the construction site, performing distortion correction processing and compression processing on the real image according to the four vertices of the surface of the surface component after the distortion correction, and extracting a pixel matrix of the real image from the compressed image based on the Dynamo script; A model voxelization unit, used for performing voxel segmentation processing on the pixel matrix of the real image and the actual size of the component, and coloring the segmented voxel units to obtain a voxelized model; A color gamut detection unit is used to establish a color gamut in a construction stage according to the building materials actually used in the construction, compare the color gamut in the construction stage with the voxel unit of the voxelized model, obtain a color gamut detection result, and calculate the degree of construction completion according to the color gamut detection result; The model expression unit is used to determine the current construction stage of the surface component according to the color gamut detection result, modify the expression mode of the voxelized model according to the current construction stage, and import the construction completion degree and the current construction stage as parameters into the BIM model and the voxelized model, so that the model can reflect the construction progress and status in real time.

10. A construction progress detection device for a surface component, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the computer program can be executed by the processor to implement the construction progress detection method of the surface component as described in any one of claims 1 to 8.

Images