Engineering amount estimation method and device of power grid infrastructure project and storage medium

Abstract

The invention discloses a project amount estimation method and device for a power grid infrastructure project and a storage medium, and the method comprises the steps: determining three-dimensional point cloud data of a foundation pit at a target position in response to a project amount estimation signal of the power grid infrastructure project at the target position, geological attribute information and environment attribute information of the position where the foundation pit is located and excavation mode information and supporting information of the foundation pit in the excavation process are determined; constructing a foundation pit three-dimensional model of the foundation pit based on the three-dimensional point cloud data, and determining the volume of an excavation area based on the foundation pit three-dimensional model; based on the excavation area volume, the geological attribute information, the environment attribute information, the excavation mode information and the support information, earth volume information of the foundation pit in the excavation process is determined; on the basis of the supporting information, supporting engineering quantity information of the foundation pit in the supporting process is determined; and based on the earth volume information and the support engineering quantity information, the engineering quantity of the foundation pit in the excavation process in the power grid infrastructure project is determined.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid construction, and in particular, to a method, device, and storage medium for estimating the engineering quantity of power grid infrastructure projects. Background Art

[0002] The foundation pit excavation process is an important process in power grid infrastructure projects. After the completion of the foundation pit, in order to facilitate subsequent project audits and project maintenance, it is necessary to calculate the engineering quantity during the excavation process of the foundation pit.

[0003] Currently, the engineering quantity is usually estimated by manual work at the construction site. However, this manual method of estimating the engineering quantity requires staff to follow the entire construction process, wasting costs and time. At the same time, due to the negligence of the staff or uneven technical levels, the accuracy of the estimated engineering quantity will be relatively low. Summary of the Invention

[0004] The present invention provides a method, device, and storage medium for estimating the engineering quantity of power grid infrastructure projects, mainly capable of improving the estimation efficiency and accuracy of the engineering quantity and saving the estimation cost of the engineering quantity.

[0005] According to a first aspect of the present invention, there is provided a method for estimating the engineering quantity of a power grid infrastructure project, including:

[0006] In response to a signal for estimating the engineering quantity of a power grid infrastructure project at a target location, determining three-dimensional point cloud data of a foundation pit at the target location, and determining geological attribute information and environmental attribute information of the location where the foundation pit is located, excavation method information and support information during the excavation process of the foundation pit;

[0007] Based on the three-dimensional point cloud data, constructing a three-dimensional model of the foundation pit, and based on the three-dimensional model of the foundation pit, determining the volume of the excavation area;

[0008] Based on the volume of the excavation area, the geological attribute information, the environmental attribute information, the excavation method information, and the support information, determining the earthwork quantity information during the excavation process of the foundation pit;

[0009] Based on the support information, determining the support engineering quantity information during the support process of the foundation pit;

[0010] Based on the earthwork quantity information and the support engineering quantity information, determining the engineering quantity during the excavation process of the foundation pit in the power grid infrastructure project.

[0011] Optionally, the constructing a three-dimensional model of the foundation pit based on the three-dimensional point cloud data includes:

[0012] Determining a two-dimensional image of the foundation pit;

[0013] Determine the sparsity of the three-dimensional point cloud data, and determine whether the sparsity is greater than a preset threshold;

[0014] If the sparsity is greater than the preset threshold, based on the three-dimensional point cloud data, determine a three-dimensional voxel grid, and based on the three-dimensional voxel grid, construct an initial three-dimensional model of the foundation pit;

[0015] If the sparsity is less than or equal to the preset threshold, based on the three-dimensional point cloud data, determine a triangular grid, and based on the triangular grid, construct an initial three-dimensional model of the foundation pit;

[0016] Map the texture of the two-dimensional image to the initial three-dimensional model of the foundation pit to obtain the three-dimensional model of the foundation pit.

[0017] Optionally, before constructing the initial three-dimensional model of the foundation pit based on the three-dimensional voxel grid, the method further includes:

[0018] Determine any vertex in the three-dimensional voxel grid as a target voxel vertex respectively, determine the neighboring vertices corresponding to the target voxel vertex, and determine the target position information corresponding to the target voxel vertex and the neighboring position information corresponding to the neighboring vertices;

[0019] Based on the target position information and the neighboring position information, determine the position weighted average value between the target voxel vertex and the neighboring vertices;

[0020] Based on the position weighted average value, adjust the target position information of the target voxel vertex to obtain the target voxel vertex after adjusting the position;

[0021] Based on the target voxel vertex after adjusting the position, obtain the adjusted three-dimensional voxel grid;

[0022] The constructing the initial three-dimensional model of the foundation pit based on the three-dimensional voxel grid includes:

[0023] Based on the adjusted three-dimensional voxel grid, construct the initial three-dimensional model of the foundation pit;

[0024] Before constructing the initial three-dimensional model of the foundation pit based on the triangular grid, the method further includes:

[0025] Determine any vertex in the triangular grid as a target triangular vertex respectively, and determine the adjacent triangular grid corresponding to the target triangular vertex;

[0026] Based on the vertex coordinates of each of the adjacent triangular meshes, determine the normal vectors of each of the adjacent triangular meshes, and determine the angles between the normal vectors;

[0027] Based on the normal vectors of each of the adjacent triangular meshes, the angles between the normal vectors, and the position information of the target triangular vertex, determine the curvature parameter of the target triangular vertex, and determine whether the curvature parameter is greater than a preset parameter threshold;

[0028] If the curvature parameter is greater than the preset parameter threshold, move the target triangular vertex towards the domain vertex corresponding to the target triangular vertex to obtain the adjusted target triangular vertex, and based on the adjusted target triangular vertex, obtain the adjusted triangular mesh;

[0029] The constructing the initial three-dimensional foundation pit model of the foundation pit based on the triangular mesh includes:

[0030] Based on the adjusted triangular mesh, construct the initial three-dimensional foundation pit model of the foundation pit.

[0031] Optionally, the determining the earthwork volume information during the excavation of the foundation pit based on the excavation area volume, the geological attribute information, the environmental attribute information, the excavation method information, and the support information includes:

[0032] Determine the volume feature vector corresponding to the excavation area volume, the address feature vector corresponding to the geological attribute information, the environmental feature vector corresponding to the environmental attribute information, the excavation feature vector corresponding to the excavation method information, and the support feature vector corresponding to the support information;

[0033] Perform cross-processing on the volume feature vector, the address feature vector, the environmental feature vector, the excavation feature vector, and the support feature vector to obtain a cross feature vector;

[0034] Input the cross feature vector into a preset earthwork volume prediction model for prediction to obtain the earthwork volume information during the excavation of the foundation pit.

[0035] Optionally, after the determining the engineering quantity during the excavation of the foundation pit in the power grid infrastructure project based on the earthwork volume information and the support engineering quantity information, the method further includes:

[0036] Generate an engineering quantity report form based on the engineering quantity, and send the engineering quantity report form to at least one audit terminal for auditing;

[0037] After receiving the audit passing results of each audit terminal, dynamically generate a two-dimensional code for the engineering quantity report form based on the audited engineering quantity report form.

[0038] Optionally, determining the three-dimensional point cloud data of the foundation pit at the target location includes:

[0039] Obtaining multi-view images captured of the foundation pit from multiple perspectives, and determining the image acquisition parameters of the imaging device corresponding to the multi-view images;

[0040] Extracting feature points with significant geometric structures in each of the images, performing cross-image matching on the feature points in each of the images to obtain feature point pairs;

[0041] Based on the feature point pairs and the image acquisition parameters, performing three-dimensional reconstruction on the foundation pit points in the foundation pit represented by the feature point pairs to obtain the three-dimensional point cloud data of the foundation pit.

[0042] Optionally, before constructing the three-dimensional model of the foundation pit based on the three-dimensional point cloud data, the method further includes:

[0043] Determining the data density within a preset neighborhood corresponding to each point in the three-dimensional point cloud data, and based on the data density, determining core points and non-core points among each of the points;

[0044] Taking any one of the core points as a target core point, and clustering the remaining core points with the target core point as the clustering center to obtain core points under different clustering categories;

[0045] Taking any one of the non-core points as a target non-core point, determining the reference core point closest to the non-core point among the core points under each of the clustering categories, and determining whether the distance between the non-core point and the reference core point is less than a preset distance threshold;

[0046] If the distance between the non-core point and the reference core point is less than the preset distance threshold, then classifying the non-core point into the clustering category to which the reference core point belongs, otherwise, determining the non-core point as an outlier;

[0047] Removing the outliers from the three-dimensional point cloud data to obtain the cleaned three-dimensional point cloud data.

[0048] According to the second aspect of the present invention, there is provided a device for estimating the engineering quantity of a power grid infrastructure project, including:

[0049] A first determination unit, configured to respond to a signal for estimating the engineering quantity of a power grid infrastructure project at a target location, determine the three-dimensional point cloud data of the foundation pit at the target location, and determine the geological attribute information and environmental attribute information of the location where the foundation pit is located, the excavation method information and support information during the excavation of the foundation pit;

[0050] A construction unit, configured to construct a three-dimensional model of the foundation pit based on the three-dimensional point cloud data, and determine the excavation area volume based on the three-dimensional model of the foundation pit;

[0051] A second determination unit, configured to determine the earthwork volume information during the excavation of the foundation pit based on the excavation area volume, the geological attribute information, the environmental attribute information, the excavation method information, and the support information;

[0052] A third determination unit, configured to determine the support project quantity information during the support of the foundation pit based on the support information;

[0053] A fourth determination unit, configured to determine the project quantity during the excavation of the foundation pit in the power grid infrastructure project based on the earthwork volume information and the support project quantity information.

[0054] According to the third aspect of the present invention, there is provided a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned method for estimating the project quantity of the power grid infrastructure project is implemented.

[0055] According to the fourth aspect of the present invention, there is provided a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the above-mentioned method for estimating the project quantity of the power grid infrastructure project is implemented.

[0056] According to a method, device, and storage medium for estimating the project quantity of a power grid infrastructure project provided by the present invention, compared with the current method of estimating the project quantity by manually going to the construction site, the present invention constructs a three-dimensional model of the foundation pit by collecting three-dimensional point cloud data of the foundation pit at the target location, and uses the three-dimensional model to determine the excavation area volume, which can avoid the time wasted by manual measurement of the excavation volume and the risk of measurement errors. Therefore, the present invention can improve the determination efficiency and accuracy of the excavation area volume. After that, the present invention comprehensively analyzes the excavation area volume, geological attribute information, environmental attribute information, excavation method information, and support information to determine the earthwork volume information during the excavation of the foundation pit, which can avoid the time wasted by manually measuring only the volume of the foundation pit to determine the earthwork volume and the situation of determination errors. Therefore, the present invention can improve the determination efficiency and accuracy of the earthwork volume information. At the same time, the present invention determines the support project quantity information according to the support information, which can improve the determination accuracy and efficiency of the support project quantity. Finally, according to the accurately determined earthwork volume information and support project quantity information, the project quantity during the excavation of the foundation pit is determined, thereby improving the determination efficiency and accuracy of the project quantity. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings described herein are used to provide a further understanding of the present invention and form a part of this application. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0058] Figure 1 A flowchart of a method for estimating the quantity of work in a power grid infrastructure project provided by an embodiment of the present invention is shown;

[0059] Figure 2 A flowchart of another method for estimating the quantity of work in a power grid infrastructure project provided by an embodiment of the present invention is shown;

[0060] Figure 3 A schematic structural diagram of a device for estimating the quantity of work in a power grid infrastructure project provided by an embodiment of the present invention is shown;

[0061] Figure 4 A schematic structural diagram of another device for estimating the quantity of work in a power grid infrastructure project provided by an embodiment of the present invention is shown;

[0062] Figure 5 A schematic physical structure diagram of a computer device provided by an embodiment of the present invention is shown. Detailed implementation manners

[0063] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments. It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other.

[0064] Currently, the method of estimating the quantity of work by manually going to the construction site requires staff to follow the entire construction process, resulting in a low efficiency in determining the quantity of work. At the same time, due to the negligence of the staff or the uneven technical levels, the accuracy of estimating the quantity of work will be low.

[0065] To solve the above problems, an embodiment of the present invention provides a method for estimating the quantity of work in a power grid infrastructure project, as Figure 1 shown, the method includes:

[0066] 101. In response to a signal for estimating the quantity of work in a power grid infrastructure project at a target location, determine the three-dimensional point cloud data of the foundation pit at the target location, and determine the geological attribute information and environmental attribute information of the location where the foundation pit is located, the excavation method information and support information during the excavation of the foundation pit.

[0067] Among them, the address attribute information includes the soil layer distribution of the location where the foundation pit is located (such as the name, thickness, physical and mechanical properties of each soil layer), groundwater level information (such as the height of the groundwater level), topographic and geomorphic information (such as the terrain undulation, slope change around the foundation pit, and whether there are water bodies such as rivers and lakes), geological structure information (such as faults, folds, joints, etc.), soil physical and mechanical properties (such as physical and mechanical properties such as soil density, compressibility, shear strength, etc.); the environmental attribute information includes: rainfall, wind direction and speed, temperature, surrounding facilities, etc. during the excavation of the foundation pit; the excavation method information includes: progressive excavation method, drill and blast method, sinking excavation method, slope excavation method, etc.; the support information includes: the type of support structure during the excavation of the foundation pit (such as row pile support, diaphragm wall support, anchor support, etc.), support structure parameters (such as the size of the support structure, the material of the support structure, the layout of the support structure, etc.).

[0068] For the embodiments of the present invention, three-dimensional laser scanning technology can be used to determine the three-dimensional point cloud data of the foundation pit. Specifically, according to the shape, size and surrounding environment of the foundation pit, the positions and quantities of the scanning stations can be reasonably set to ensure full coverage of the foundation pit area, and high-resolution photos of the foundation pit are collected in the form of point clouds (emitting hundreds of thousands or even millions of points per unit time), so as to basically restore the three-dimensional structure of the foundation pit and form a pseudo-3D graph of the deep foundation pit. This method has a fast operation speed, high restoration accuracy, low labor intensity, and is not affected by the complex terrain on site, effectively overcoming the defects of the total station measurement method, such as time-consuming, laborious, and low engineering quantity calculation accuracy caused by the lack of three-dimensional visual expression, and providing fast and accurate data support for the calculation of the foundation pit engineering quantity. At the same time, obtain the geological attribute information and environmental attribute information of the location where the foundation pit is located, the excavation method information and support information during the excavation of the foundation pit in the power grid infrastructure project database.

[0069] 102. Based on the three-dimensional point cloud data, construct a three-dimensional model of the foundation pit, and based on the three-dimensional model of the foundation pit, determine the volume of the excavation area.

[0070] For the embodiments of the present invention, remove the abnormal points, outliers and noise points in the point cloud data to improve the data quality, and splice the point cloud data obtained from multiple stations to form complete point cloud data of the foundation pit. On the basis of splicing, further merge the point cloud data, and remove the point cloud irrelevant to the foundation pit to reduce the data volume and improve the processing efficiency, so as to obtain three-dimensional point cloud data that can accurately reflect the three-dimensional information of the foundation pit. Further, convert the processed three-dimensional point cloud data into a continuous surface model, smooth the reconstructed surface model, fill the holes, and improve the accuracy and integrity of the model. Then, according to the characteristics and requirements of the foundation pit, perform detail processing on the smoothed model, such as adding textures, adjusting lighting, etc., to enhance the realism and visualization effect of the model, so as to obtain a three-dimensional model of the foundation pit.

[0071] Furthermore, if the foundation pit has a complex shape or contains multiple parts with different shapes, the 3D model of the foundation pit can be first divided into several simple geometric regions, such as rectangles, trapezoids, triangles, etc. For each divided region, determine its key dimensions such as length, width, height, etc. Then, based on the key dimensions such as length, width, height, etc., determine the volume of each region. After that, add up the volumes of all regions to obtain the volume of the excavation area of the foundation pit. By reconstructing the 3D model of the foundation pit to determine the volume of the excavation area of the foundation pit, it is possible to avoid the time wasted and measurement errors caused by manual on-site measurement using measuring tools. Therefore, the embodiments of the present invention can improve the determination efficiency and determination accuracy of the volume of the excavation area of the foundation pit.

[0072] 103. Determine the earthwork volume information during the excavation of the foundation pit based on the excavation area volume, geological attribute information, environmental attribute information, excavation method information, and support information.

[0073] Among them, the earthwork volume information refers to the volume of earthwork that needs to be cleared and processed during the excavation of the foundation pit.

[0074] For the embodiments of the present invention, a preset earthwork volume prediction model can be used to predict the earthwork volume information during the excavation of the foundation pit. In order to improve the prediction accuracy of the preset earthwork volume prediction model, first, it is necessary to construct the preset earthwork volume prediction model. Based on this, the method includes: constructing an initial model and obtaining a sample data set, where the sample data set includes sample input data (the sample excavation area volume of the sample foundation pit, sample geological attribute information, sample environmental attribute information, sample excavation method information, sample support information) and its corresponding annotation information, and the annotation information is the actual earthwork volume information of the sample foundation pit; dividing the sample data set into training data and test data, and using the training data to train the initial model; using the test data to test the trained initial model, and determining the trained initial model that meets the test conditions as the preset earthwork volume prediction model.

[0075] Furthermore, after constructing the preset earthwork volume prediction model, input the excavation area volume, geological attribute information, environmental attribute information, excavation method information, and support information into the preset earthwork volume prediction model together, and output the earthwork volume information during the excavation of the foundation pit through the preset earthwork volume prediction model. Thus, the embodiments of the present invention can improve the prediction efficiency and prediction accuracy of the earthwork volume information by predicting the earthwork volume information during the excavation of the foundation pit through the preset earthwork volume prediction model. At the same time, when predicting the earthwork volume information, the embodiments of the present invention comprehensively analyze the excavation area volume, geological attribute information, environmental attribute information, excavation method information, support information, etc., to avoid the situation where the staff determines the earthwork volume only based on the volume of the foundation pit, resulting in incorrect determination of the earthwork volume. Therefore, the embodiments of the present invention can further improve the prediction accuracy of the earthwork volume information.

[0076] 104. Determine the support project quantity information during the foundation pit support process based on the support information.

[0077] Among them, the support project quantity information refers to the project quantity required for the support measures taken to prevent the foundation pit from collapsing.

[0078] For the embodiments of the present invention, based on information such as the support structure type and support structure parameters during the excavation process of the foundation pit, determine the support project quantity information during the foundation pit support process. For example, the support project quantity of the soil nail wall can be calculated according to the length and quantity of the soil nails; the support pile project quantity can be calculated according to parameters such as the quantity, length, diameter, and depth of the support piles.

[0079] 105. Determine the project quantity during the excavation process of the foundation pit in the power grid infrastructure project based on the earthwork quantity information and the support project quantity information.

[0080] For the embodiments of the present invention, after obtaining the earthwork quantity information and the support project quantity information, the two can be added to obtain the project quantity during the excavation process of the foundation pit. In another embodiment of the present invention, if there is a certain overlap or intersection between the earthwork quantity and the support project quantity (such as the support structure may be embedded in the earthwork), these parts need to be appropriately processed during the calculation of the project quantity to avoid double counting, that is, after calculating the earthwork quantity information, the volume of the support structure embedded in the earthwork is excluded from the earthwork quantity. The embodiments of the present invention determine the earthwork quantity information during the excavation process of the foundation pit by comprehensively analyzing the excavation area volume, geological attribute information, environmental attribute information, excavation method information, and support information, which can improve the determination efficiency and determination accuracy of the earthwork quantity information. At the same time, the present invention determines the support project quantity information based on the support information, which can improve the determination accuracy and determination efficiency of the support project quantity. Finally, based on the accurately determined earthwork quantity information and support project quantity information, determine the project quantity during the excavation process of the foundation pit, thereby improving the determination efficiency and determination accuracy of the project quantity.

[0081] According to a method for estimating the project quantity of a power grid infrastructure project provided by the present invention, compared with the current method of manually estimating the project quantity at the construction site, the present invention constructs a three-dimensional model of the foundation pit by collecting the three-dimensional point cloud data of the foundation pit at the target location, and uses the three-dimensional model to determine the volume of the excavation area, which can avoid the time wasted by manual measurement of the excavation volume and the risk of measurement errors. Therefore, the present invention can improve the determination efficiency and determination accuracy of the excavation area volume. After that, the present invention determines the earthwork quantity information during the excavation of the foundation pit by comprehensively analyzing the excavation area volume, geological attribute information, environmental attribute information, excavation method information, and support information, which can avoid the time wasted by manually measuring only the volume of the foundation pit to determine the earthwork quantity and the situation of determination errors. Therefore, the present invention can improve the determination efficiency and determination accuracy of the earthwork quantity information. At the same time, the present invention determines the support project quantity information according to the support information, which can improve the determination accuracy and determination efficiency of the support project quantity. Finally, according to the accurately determined earthwork quantity information and support project quantity information, the project quantity during the excavation of the foundation pit is determined, thereby improving the determination efficiency and determination accuracy of the project quantity.

[0082] Further, in order to better illustrate the above process of estimating the project quantity of the power grid infrastructure project, as a refinement and expansion of the above embodiment, the embodiment of the present invention provides another method for estimating the project quantity of the power grid infrastructure project, as Figure 2 shown, the method includes:

[0083] 201. In response to the signal for estimating the project quantity of the power grid infrastructure project at the target location, determine the three-dimensional point cloud data of the foundation pit at the target location, and determine the geological attribute information and environmental attribute information of the location where the foundation pit is located, the excavation method information and support information during the excavation of the foundation pit.

[0084] For the embodiment of the present invention, when receiving the project quantity estimation signal, first obtain the geological attribute information and environmental attribute information of the location where the foundation pit is located, the excavation method information and support information during the excavation of the foundation pit in the database, and then use the determined three-dimensional point cloud data of the foundation pit. Based on this, the specific method for determining the three-dimensional point cloud data of the foundation pit includes: obtaining multi-view images obtained by photographing the foundation pit from multiple perspectives, and determining the image acquisition parameters of the imaging device corresponding to the multi-view images; extracting the feature points with significant geometric structures in each of the images, performing cross-image matching on the feature points in each of the images to obtain feature point pairs; based on the feature point pairs and the image acquisition parameters, performing three-dimensional reconstruction on the foundation pit points in the foundation pit represented by the feature point pairs to obtain the three-dimensional point cloud data of the foundation pit.

[0085] Among them, the imaging device is a device such as a camera; the image acquisition parameters are the resolution, frame rate, exposure time, aperture, focal length, sensor size, gain, contrast, saturation, focal length, principal point coordinates, distortion coefficient, etc. of the image acquisition device, as well as parameters such as the position and attitude of the image acquisition device when acquiring each image; the feature points of the significant geometric structure can be the corner points, edge points, etc. of the foundation pit.

[0086] Specifically, use devices such as drones to carry the image acquisition device to take pictures of the foundation pit from various angles to obtain images from various angles, that is, multi-view images. At the same time, the image acquisition parameters such as the resolution and resolution of the image acquisition device can be obtained by calibrating the image acquisition device. Use algorithms such as scale-invariant feature transform algorithm and oriented fast detection algorithm to extract feature points such as corner points and edge points in each image, and calculate the similarity between each feature point across images. For example, based on the feature point a in image A, calculate the similarity between the feature point a and each feature point in other images, and in each of the other images, determine the feature point with the largest similarity as the similar feature point of the feature point a, and form a feature point pair from the feature point a and its corresponding similar feature point. Then, using the matched feature point pairs and image acquisition parameters, the fundamental matrix between each image can be estimated. Among them, the fundamental matrix describes the geometric relationship between corresponding points in different images. Then, based on the fundamental matrix and the matched feature point pairs, the method of triangulation can be used to restore the positions of the regional points of the foundation pit in three-dimensional space. Among them, triangulation is to find corresponding points in two different images, calculate their positions in three-dimensional space, and perform global optimization on the points in three-dimensional space through methods such as bundle adjustment to improve the accuracy and consistency of three-dimensional reconstruction. Through the above method, the coordinates of a series of three-dimensional points in the foundation pit can be obtained, and these three-dimensional points with coordinates constitute the three-dimensional point cloud data of the foundation pit. In the embodiment of the present invention, the three-dimensional point cloud data is constructed through feature point pairs, which can ensure that when constructing the three-dimensional point cloud data, the images from different perspectives can be accurately corresponded, which helps to reduce the error in constructing the three-dimensional point cloud data caused by factors such as perspective differences and shooting errors. Therefore, the determination accuracy of the three-dimensional point cloud data is improved, and further the estimation accuracy of the engineering quantity is improved.

[0087] Further, after determining the three-dimensional point cloud data, in order to improve the construction accuracy of the foundation pit three-dimensional model, it is necessary to clean the three-dimensional point cloud data. Based on this, the method includes: determining the data density within the preset neighborhood corresponding to each point in the three-dimensional point cloud data, and based on the data density, determining core points and non-core points among each point; taking any core point among the core points as a target core point respectively, and clustering the remaining core points with the target core point as the clustering center to obtain core points under different clustering categories; taking any non-core point among the non-core points as a target non-core point respectively, determining the reference core point closest to the non-core point among the core points under each clustering category, and judging whether the distance between the non-core point and the reference core point is less than the preset distance threshold; if the distance between the non-core point and the reference core point is less than the preset distance threshold, then classifying the non-core point into the clustering category to which the reference core point belongs, otherwise, determining the non-core point as an abnormal point; removing the abnormal points from the three-dimensional point cloud data to obtain the cleaned three-dimensional point cloud data.

[0088] Among them, the preset neighborhood is set according to actual needs, and the preset distance threshold is set according to actual needs. The data density can specifically be the data volume. Specifically, if the data density within the preset neighborhood corresponding to a certain point in the three-dimensional point cloud data is greater than the preset density threshold, then this point is determined as a core point. On the contrary, if the data density within the preset neighborhood corresponding to a certain point is less than or equal to the preset density threshold, then this point is determined as a non-core point. Then, each core point is used as a clustering center respectively to cluster the remaining core points to obtain different clustering categories. Then, it is determined whether each non-core point can be clustered into the above-mentioned clustering categories. Finally, the non-core points that cannot be clustered into all the above-mentioned clustering categories are determined as abnormal points. Further, the abnormal points in the three-dimensional point cloud data are deleted to obtain the cleaned three-dimensional point cloud data. By cleaning the three-dimensional point cloud data in the embodiments of the present invention, the data quality can be improved, the computing resources wasted by useless data parameter operations can be avoided, and the situation where inaccurate foundation pit three-dimensional models are constructed due to abnormal data participating in operations can also be avoided. That is, by pre-cleaning the three-dimensional point cloud data in the embodiments of the present invention, the data quality of the three-dimensional point cloud data can be improved, the model performance can be enhanced, and the computing cost can be reduced.

[0089] 202. Determine the two-dimensional image of the foundation pit, determine the sparsity of the three-dimensional point cloud data, and judge whether the sparsity is greater than the preset threshold.

[0090] 203. If the sparsity is greater than the preset threshold, then based on the three-dimensional point cloud data, determine the three-dimensional voxel grid, and based on the three-dimensional voxel grid, construct the initial foundation pit three-dimensional model of the foundation pit.

[0091] Among them, the preset threshold is set according to actual requirements. For the embodiments of the present invention, a two-dimensional image of the foundation pit can be captured by a camera device, and then the sparsity of the three-dimensional point cloud is determined. According to the sparsity of the point cloud, the generation method of the initial three-dimensional model of the foundation pit is determined. For example, if the sparsity is greater than the preset threshold, that is, if the three-dimensional point cloud data is relatively dense, the three-dimensional point cloud data is connected into a triangular mesh (the vertices in the triangular mesh are the points in the three-dimensional point cloud) to form a continuous surface, and through this continuous surface, an initial three-dimensional model of the foundation pit can be formed. If the sparsity is less than or equal to the preset threshold, that is, if the three-dimensional point cloud data is relatively sparse, the point cloud data is converted into a three-dimensional voxel grid (each voxel represents a small cubic space), and finally, the initial three-dimensional model of the foundation pit is constituted by each three-dimensional voxel grid. Then, each point in the two-dimensional image is matched with each point in the initial three-dimensional model of the foundation pit, and based on the matching result and the texture coordinates of each point in the two-dimensional image, the texture of the two-dimensional image is mapped to the initial three-dimensional model of the foundation pit to obtain the three-dimensional model of the foundation pit.

[0092] Further, in order to improve the construction accuracy of the three-dimensional model of the foundation pit, after determining the three-dimensional voxel grid, it is also necessary to perform smooth adjustment on the three-dimensional voxel grid. Based on this, the method includes: determining any vertex in the three-dimensional voxel grid as a target voxel vertex respectively, determining the adjacent vertices corresponding to the target voxel vertex, and determining the target position information corresponding to the target voxel vertex and the adjacent position information corresponding to the adjacent vertices; determining the position weighted average value between the target voxel vertex and the adjacent vertices based on the target position information and the adjacent position information; adjusting the target position information of the target voxel vertex based on the position weighted average value to obtain the target voxel vertex after adjusting the position; and obtaining the adjusted three-dimensional voxel grid based on the target voxel vertex after adjusting the position.

[0093] Specifically, each voxel in the three-dimensional voxel grid is converted into one or more vertex coordinates to obtain each vertex of the three-dimensional voxel grid. Taking one vertex as an example, the new position of this vertex is specifically determined by the following formula:

[0094]

[0095] Among them, L is the new position information of the vertex in the three-dimensional voxel grid, D is the target position information (original position information) of the vertex, λ is a smoothing factor constant, ω i is the weight of the i-th adjacent vertex, n is the number of adjacent vertices, N iis the position information (neighborhood position information) of the i-th domain vertex. Thus, according to the above formula, the new position information of each vertex in the three-dimensional voxel grid can be calculated. After that, the positions of each vertex are adjusted using the new position information. Finally, based on the adjusted vertices, the adjusted three-dimensional voxel grid is determined, and based on the adjusted three-dimensional voxel grid, the initial three-dimensional model of the foundation pit is constructed. By adjusting the vertices of the three-dimensional voxel grid in the embodiments of the present invention, geometric errors caused by inaccurate grid division or initial vertex positions can be reduced, thereby improving the construction accuracy of the three-dimensional model of the foundation pit.

[0096] 204. If the sparsity is less than or equal to the preset threshold, based on the three-dimensional point cloud data, a triangular mesh is determined, and based on the triangular mesh, the initial three-dimensional model of the foundation pit is constructed.

[0097] 205. Map the texture of the two-dimensional image to the initial three-dimensional model of the foundation pit to obtain the three-dimensional model of the foundation pit.

[0098] For the embodiments of the present invention, when the sparsity of the three-dimensional point cloud data is less than or equal to the preset threshold, a three-dimensional surface of the foundation pit is generated using a surface reconstruction algorithm such as the polygon fitting method. After that, the three-dimensional surface is divided into a series of small triangular meshes. According to the shape and size of the triangular meshes, a three-dimensional model framework is initialized. According to actual needs, more detailed elements such as texture, material, and lighting are added to the three-dimensional model framework to obtain the initial three-dimensional model of the foundation pit. Then, the texture of the two-dimensional image is mapped to the initial three-dimensional model of the foundation pit to obtain the three-dimensional model of the foundation pit.

[0099] Further, in order to improve the construction accuracy of the three-dimensional model of the foundation pit, after determining the triangular mesh, the triangular mesh needs to be smoothed and adjusted. Based on this, the method includes: respectively determining any vertex in the triangular mesh as a target triangular vertex, and determining the adjacent triangular meshes corresponding to the target triangular vertex; based on the vertex coordinates of each adjacent triangular mesh, determining the normal vectors of each adjacent triangular mesh, and determining the angles between the normal vectors; based on the normal vectors of each adjacent triangular mesh, the angles between the normal vectors, and the position information of the target triangular vertex, determining the curvature parameter of the target triangular vertex, and determining whether the curvature parameter is greater than the preset parameter threshold; if the curvature parameter is greater than the preset parameter threshold, moving the target triangular vertex towards the neighborhood vertex corresponding to the target triangular vertex to obtain the adjusted target triangular vertex, and based on the adjusted target triangular vertex, obtaining the adjusted triangular mesh.

[0100] Among them, the preset parameter threshold is set according to actual requirements. Specifically, for each vertex in the triangular mesh, all common edges containing the vertex and the two adjacent triangles (adjacent triangular meshes) connected by these common edges are determined. For each common edge, its unit vector (i.e., direction vector) is calculated, and its length is saved. The included angle between the normal vectors of two adjacent triangles is calculated and symbolized. Based on the unit vector of the common edge, the included angle of the normal vector, the symbol, and the length of the common edge and the vertex position information, a curvature formula is constructed. The constructed curvature formula is matrix decomposed to solve the eigenvalues and eigenvectors. The smallest eigenvalue is the minimum curvature, and the largest eigenvalue is the maximum curvature. Then, the average value of the minimum curvature and the maximum curvature is determined to obtain the curvature parameter of the vertex. Further, if the curvature parameter is greater than the preset parameter threshold, the vertex belongs to the high-curvature region. At this time, the vertex needs to be moved to other vertices in its neighborhood to reduce the curvature value, so as to realize the adjustment of the initial foundation pit three-dimensional model. If the curvature parameter is less than or equal to the preset parameter threshold, the vertex belongs to the low-curvature region. At this time, there is no need to adjust the position of the vertex. By adjusting the three-dimensional model through the vertex curvature in the embodiments of the present invention, important geometric features of the three-dimensional model, such as edges, corners, and significant changes on the surface, can be identified and retained, which helps to prevent excessive blurring of the details and features of the model during the smoothing process and improve the construction accuracy of the foundation pit three-dimensional model.

[0101] 206. Based on the three-dimensional model of the foundation pit, determine the volume of the excavation area.

[0102] Specifically, based on the three-dimensional model of the foundation pit, the three-dimensional geometric dimensions of the foundation pit can be determined. Finally, based on the three-dimensional geometric dimensions, the volume of the excavation area is determined.

[0103] 207. Based on the volume of the excavation area, geological attribute information, environmental attribute information, excavation method information, and support information, determine the earthwork volume information during the excavation of the foundation pit.

[0104] For the embodiments of the present invention, in order to determine the engineering quantity during the excavation of the foundation pit, first, the earthwork volume information during the excavation of the foundation pit needs to be determined. Based on this, step 207 specifically includes: determining the volume feature vector corresponding to the volume of the excavation area, the address feature vector corresponding to the geological attribute information, the environmental feature vector corresponding to the environmental attribute information, the excavation feature vector corresponding to the excavation method information, and the support feature vector corresponding to the support information; performing cross-processing on the volume feature vector, the address feature vector, the environmental feature vector, the excavation feature vector, and the support feature vector to obtain a cross feature vector; inputting the cross feature vector into a preset earthwork volume prediction model for prediction to obtain the earthwork volume information during the excavation of the foundation pit.

[0105] Specifically, the volume feature vector corresponding to the volume of the excavation area, the address feature vector corresponding to the address attribute information, the environmental feature vector corresponding to the environmental attribute information, the excavation feature vector corresponding to the excavation method information, and the support feature vector corresponding to the support information are respectively determined by means of word embedding and the like. After that, in order to make full use of the relationships between the data, extract more implicit features, and take into account both high-order and low-order processing to make the data utilization more sufficient and the subsequent prediction results more accurate to meet the requirements of the actual application scenario, it is necessary to perform cross-processing on the volume feature vector, address feature vector, environmental feature vector, excavation feature vector, and support feature vector. The specific cross-processing methods include: performing feature-level cross-processing on the volume feature vector, address feature vector, environmental feature vector, excavation feature vector, and support feature vector to obtain a feature cross vector; performing element-level cross-processing on the volume feature vector, address feature vector, environmental feature vector, excavation feature vector, and support feature vector to obtain an element cross vector; performing low-order cross-processing on the volume feature vector, address feature vector, environmental feature vector, excavation feature vector, and support feature vector to obtain a low-order cross vector; and performing transformation processing on the feature cross vector, element cross vector, and low-order cross vector to obtain a cross feature vector.

[0106] For example, if the volume feature vector is (a1, a2), the address feature vector is (b1, b2), the environmental feature vector is (c1, c2), the excavation feature vector is (d1, d2), and the support feature vector is (e1, e2), the specific cross - processing methods include: performing cross - processing at the feature level between different feature vectors, that is, after performing the Hadamard product on all elements between the vectors, performing a convolution transformation under a certain weight to obtain the feature cross - vector as f(w*(a1*b1*c1*d1*e1, a2*b2*c2*d2*e2, a3*b3*c3*d3*e3)); at the same time, performing cross - processing at the element level on all feature vector data, that is, performing the Hadamard product on each element between the vectors, assigning different weight values to each product result, and then performing a linear transformation to obtain the element cross - vector as f(w1*a1*b1*c1*d1*e1, w2*a2*b2*c2*d2*e2, w3*a3*b3*c3*d3*e3); in addition, performing low - order cross - processing on all feature vectors, then assigning a weight coefficient to the result of the cross - processing, and then performing a linear transformation to obtain the low - order cross - vector as f(w2(a1, a2, b1, b2, c1, c2, d1, d2, e1, e2)); finally, using a preset transformation function (the preset transformation function can be set according to the actual situation, and this embodiment does not limit it) to perform transformation processing on the above - mentioned feature cross - vector, element cross - vector, and low - order cross - vector, such as horizontal splicing, to obtain the cross - feature vector. It should be noted that the above examples are only illustrative and do not limit the embodiments of the present application. Thus, by performing cross - processing on the volume feature vector, address feature vector, environmental feature vector, excavation feature vector, and support feature vector, different features can be automatically or explicitly combined to generate new feature combinations. These combined features may contain complex non - linear relationships between the original features, enabling the model to capture more refined and rich information in the data, that is, being able to make full use of the relationships between various data, extract more implicit features, taking into account both high - order and low - order processing, making the data utilization more sufficient, and making the subsequent obtained earthwork volume information result more accurate, meeting the requirements of the actual application scenario.

[0107] Further, input the cross - feature vector into a preset earthwork volume prediction model for prediction, and the earthwork volume information during the excavation of the foundation pit can be output through the preset earthwork volume prediction model.

[0108] In another embodiment of the present invention, the working principle of the unmanned aerial vehicle (UAV) photogrammetry technology and its application method in earthwork measurement can also be adopted to measure the earthwork volume. By taking advantage of the significant advantages of the UAV aerial survey, such as its flexibility, strong data currency, high image resolution, reduction of labor intensity, and improvement of production efficiency, the problems existing in the traditional method, such as large fieldwork volume, low efficiency, and high cost, are solved. The earthwork volume is obtained through field data collection and indoor data processing, avoiding a large amount of manual work and reducing the investment in personnel safety guarantee.

[0109] Specifically, a UAV equipped with an earthwork measurement device includes a UAV main body and a measurement mechanism. Suction grooves are symmetrically formed on the lower surface of the UAV main body, and a slot is formed in the middle of the UAV main body. Two groups of elastic clamping strips are symmetrically installed on the inner wall of the slot, and the elastic clamping strips are electrically connected to the power supply of the UAV main body. It further includes a mounting plate, and the lower surface of the mounting plate is movably connected to the measurement mechanism; a connecting mechanism for facilitating the connection of the mounting plate and the UAV main body into one body. The connecting mechanism includes a connecting column installed on the upper surface of the mounting plate, and the connecting column is electrically connected to the measurement mechanism and the elastic clamping strips. A disc is sleeved on the surface of the connecting column, and the disc is elastically connected to the mounting plate through a return spring. Two groups of slopes are symmetrically formed on the surface of the disc, and two symmetrically arranged trapezoidal blocks are slidably engaged with the surfaces of the slopes. Two symmetrically arranged electromagnets are fixedly installed on the upper surface of the mounting plate, and the electromagnets are attracted to the suction grooves. The connecting column is inserted into the slot, and two groups of notches are equidistantly formed around the surface of the connecting column, and the notches are clamped and matched with the elastic clamping strips. Two groups of chutes are formed around the surface of the connecting column. Two groups of sliders are symmetrically installed on the inner wall of the disc, and the sliders are slidably engaged with the chutes. The trapezoidal blocks are arranged inside the mounting grooves formed on the inner wall of the slot, and the trapezoidal blocks are elastically connected to the inner wall of the mounting groove through connecting springs. By setting the connecting mechanism and the coordinated use with other components, when the UAV needs to replace the earthwork measurement device during use, after the UAV is powered off, the measuring device can be quickly replaced, not only realizing quick installation and replacement, but also ensuring good contact of the circuit during use, and at the same time making the device simple in structure and strong in practicability.

[0110] 208. Based on the support information, determine the support project quantity information during the foundation pit support process.

[0111] Specifically, according to information such as the support type and support structure design parameters, calculate the quantities of various projects respectively, such as the volume of the retaining wall, the number and length of the support piles, etc. Summarize the quantities of various projects to obtain the support project quantity information during the foundation pit support process.

[0112] 209. Based on the earthwork volume information and the support project quantity information, determine the project quantity during the excavation of the foundation pit in the power grid infrastructure project.

[0113] Specifically, by adding the earthwork volume information and the support project quantity information, the project quantity during the excavation of the foundation pit in the power grid infrastructure project can be obtained.

[0114] Furthermore, for the convenience of information transmission and data management, it is necessary to generate a QR code for the project quantity report form. Based on this, the method includes: generating a project quantity report form based on the project quantity and sending the project quantity report form to at least one review terminal for review; after receiving the review passed results of each review terminal, dynamically generating a QR code for the project quantity report form based on the reviewed project quantity report form.

[0115] Specifically, a project quantity report form is generated, which includes information related to the project name, project number, etc., and also includes the project quantity of this project. Then, the project quantity report form is sent to each review terminal for review. After the review is passed, the inspection-free platform will generate a corresponding QR code for the project quantity report form to query the authenticity of the information and realize the "ID card" management of the detailed information of the project quantity confirmation. At the same time, before scanning the QR code to view the information, corresponding verification information needs to be added. When scanning the QR code on the mobile device, it will prompt to select the SMS recipient. After clicking to send the SMS and entering the verification code and submitting, the details can be viewed, realizing the real-time dynamic query management of the project quantity confirmation information. This project quantity report form can be embedded in the whole-process management nodes of the digital platform for the whole process of infrastructure inspection-free control. At key nodes such as engineering construction bidding, start of work on site, sectional settlement, and final settlement, real-time step-by-step confirmation is carried out for six major modules, including the five-party visa project list, five-party visa QR code confirmation form, tender project quantity confirmation, construction drawing project quantity confirmation, sectional settlement project quantity confirmation, and final settlement project quantity confirmation, to ensure the consistency, effectiveness, and reliability of the project quantity throughout the construction process.

[0116] For the embodiments of the present invention, during the excavation of the foundation pit, due to the wide range, long distance, lack of power supply and poor network coverage in the cable tunnel project, the communication is basically interrupted during the construction process due to the lack of network coverage. The on-site dynamics and emergencies cannot be conveyed to the outside world in a timely manner, and remote monitoring cannot be achieved, objectively causing complex problems in the supervision environment. The situation at the operation site is transmitted to the supervision video monitoring center through a wireless Internet of Things base station, realizing data collection and video monitoring in the complex scenarios of the cable tunnel project. In addition, through equipment technologies such as the photovoltaic DC power generation system, intelligent storage box, and wireless Internet of Things intelligent base station carried by the portable intelligent monitoring pole, the functions of intelligent remote monitoring power supply and wireless deployment are realized, and the use effect is presented for the first time at the construction site of the cable tunnel of the 110 kV Qidu substation and transmission project. Multiple (such as 3) intelligent dome cameras are used to conduct a 360-degree panoramic scan at each construction point, not only solving the problems of network coverage and data transmission, but also greatly improving the supervision work efficiency and the ability to perform safety and quality duties. The "intelligent" expert system for geotechnical engineering foundation treatment realizes the collection of construction data and automatic reports, intelligent engineering quality monitoring, and full-life cycle quality traceability through the real-time "monitoring-detection-analysis-feedback" closed-loop management covering multiple pile types, multiple processes, and the entire process of foundation treatment construction. At the same time, by setting conditions in combination with soil layer conditions, site conditions, etc., the monitoring data of multiple regions and multiple projects are sorted and analyzed to guide the design and construction under various complex conditions such as various sites and strata. According to the continuous and intelligent monitoring of the unit construction workload, the real-time and stage conditions of the unit construction period and specific equipment are mastered, and an operation effectiveness report is formed, providing a direct reference basis for the adjustment of the construction period and the assessment of the progress.

[0117] According to another method for estimating the engineering quantity of the power grid infrastructure project provided by the present invention, compared with the current method of estimating the engineering quantity by manually going to the construction site, the present invention constructs a three-dimensional model of the foundation pit through the three-dimensional point cloud data of the foundation pit at the target position collected, and uses the three-dimensional model to determine the volume of the excavation area, which can avoid the time wasted by manual measurement of the excavation volume and the risk of measurement errors. Therefore, the present invention can improve the determination efficiency and determination accuracy of the excavation area volume. After that, the present invention comprehensively analyzes the excavation area volume, geological attribute information, environmental attribute information, excavation method information, and support information to determine the earthwork quantity information during the excavation of the foundation pit, which can avoid the time wasted by manually only measuring the volume of the foundation pit to determine the earthwork quantity and the situation of determination errors. Therefore, the present invention can improve the determination efficiency and determination accuracy of the earthwork quantity information. At the same time, the present invention determines the support engineering quantity information according to the support information, which can improve the determination accuracy and determination efficiency of the support engineering quantity. Finally, according to the accurately determined earthwork quantity information and support engineering quantity information, the engineering quantity during the excavation of the foundation pit is determined, and thus the determination efficiency and determination accuracy of the engineering quantity can be improved.

[0118] Further, asFigure 1 For the specific implementation, an embodiment of the present invention provides a device for estimating the engineering quantity of a power grid infrastructure project. As Figure 3 shown, the device includes: a first determination unit 31, a construction unit 32, a second determination unit 33, a third determination unit 34, and a fourth determination unit 35.

[0119] The first determination unit 31 can be used to respond to a signal for estimating the engineering quantity of a power grid infrastructure project at a target location, determine the three-dimensional point cloud data of the foundation pit at the target location, and determine the geological attribute information and environmental attribute information of the location where the foundation pit is located, the excavation method information and support information during the excavation process of the foundation pit.

[0120] The construction unit 32 can be used to construct a three-dimensional model of the foundation pit based on the three-dimensional point cloud data, and determine the excavation area volume based on the three-dimensional model of the foundation pit.

[0121] The second determination unit 33 can be used to determine the earthwork quantity information during the excavation process of the foundation pit based on the excavation area volume, the geological attribute information, the environmental attribute information, the excavation method information, and the support information.

[0122] The third determination unit 34 can be used to determine the support engineering quantity information during the support process of the foundation pit based on the support information.

[0123] The fourth determination unit 35 can be used to determine the engineering quantity during the excavation process of the foundation pit in the power grid infrastructure project based on the earthwork quantity information and the support engineering quantity information.

[0124] In a specific application scenario, in order to construct a three-dimensional model of the foundation pit, as Figure 4 shown, the construction unit 32 includes a first determination module 321, a judgment module 322, a construction module 323, and a mapping module 324.

[0125] The first determination module 321 can be used to determine a two-dimensional image of the foundation pit.

[0126] The judgment module 322 can be used to determine the sparsity of the three-dimensional point cloud data and judge whether the sparsity is greater than a preset threshold.

[0127] The construction module 323 can be used to, if the sparsity is greater than the preset threshold, determine a three-dimensional voxel grid based on the three-dimensional point cloud data, and construct an initial three-dimensional model of the foundation pit based on the three-dimensional voxel grid.

[0128] The building module 323 can also be used to determine a triangular mesh based on the three-dimensional point cloud data if the sparsity is less than or equal to the preset threshold, and construct an initial three-dimensional model of the foundation pit based on the triangular mesh.

[0129] The mapping module 324 can be used to map the texture of the two-dimensional image to the initial three-dimensional model of the foundation pit to obtain the three-dimensional model of the foundation pit.

[0130] In a specific application scenario, in order to adjust the three-dimensional voxel grid and the triangular mesh, the building unit 32 further includes an adjustment module 325.

[0131] The adjustment module 325 can be used to respectively determine any vertex in the three-dimensional voxel grid as a target voxel vertex, determine the neighboring vertices corresponding to the target voxel vertex, and determine the target position information corresponding to the target voxel vertex and the neighboring position information corresponding to the neighboring vertices; based on the target position information and the neighboring position information, determine the position weighted average value between the target voxel vertex and the neighboring vertices; based on the position weighted average value, adjust the target position information of the target voxel vertex to obtain the target voxel vertex after the position is adjusted; based on the target voxel vertex after the position is adjusted, obtain the adjusted three-dimensional voxel grid.

[0132] The building module 323 can also be used to construct an initial three-dimensional model of the foundation pit based on the adjusted three-dimensional voxel grid.

[0133] The adjustment module 325 can also be used to respectively determine any vertex in the triangular mesh as a target triangular vertex, and determine the adjacent triangular meshes corresponding to the target triangular vertex; based on the vertex coordinates of each adjacent triangular mesh, determine the normal vectors of each adjacent triangular mesh and determine the included angles between the normal vectors; based on the normal vectors of each adjacent triangular mesh, the included angles between the normal vectors, and the position information of the target triangular vertex, determine the curvature parameter of the target triangular vertex, and determine whether the curvature parameter is greater than the preset parameter threshold; if the curvature parameter is greater than the preset parameter threshold, move the target triangular vertex towards the neighboring vertices corresponding to the target triangular vertex to obtain the adjusted target triangular vertex, and based on the adjusted target triangular vertex, obtain the adjusted triangular mesh.

[0134] The building module 323 can also be used to construct an initial three-dimensional model of the foundation pit based on the adjusted triangular mesh.

[0135] In a specific application scenario, in order to determine the earthwork volume information during the excavation of the foundation pit, the second determination unit 33 includes a second determination module 331, a cross module 332, and a prediction module 333.

[0136] The second determination module 331 can be used to determine the volume feature vector corresponding to the excavation area volume, the address feature vector corresponding to the geological attribute information, the environmental feature vector corresponding to the environmental attribute information, the excavation feature vector corresponding to the excavation method information, and the support feature vector corresponding to the support information.

[0137] The cross module 332 can be used to perform cross processing on the volume feature vector, the address feature vector, the environmental feature vector, the excavation feature vector, and the support feature vector to obtain a cross feature vector.

[0138] The prediction module 333 can be used to input the cross feature vector into a preset earthwork volume prediction model for prediction to obtain the earthwork volume information during the excavation of the foundation pit.

[0139] In a specific application scenario, in order to dynamically generate a QR code for the project quantity report, the device further includes a generation unit 36.

[0140] The generation unit 36 can be used to generate a project quantity report based on the project quantity and send the project quantity report to at least one review terminal for review; after receiving the review pass results of each review terminal, dynamically generate a QR code for the project quantity report based on the reviewed project quantity report.

[0141] In a specific application scenario, in order to determine the three-dimensional point cloud data, the first determination unit 31 includes an acquisition module 311, an extraction module 312, and a three-dimensional reconstruction module 313.

[0142] The acquisition module 311 can be used to acquire multi-view images obtained by photographing the foundation pit from multiple perspectives and determine the image acquisition parameters of the camera device corresponding to the multi-view images.

[0143] The extraction module 312 can be used to extract feature points with significant geometric structures in each image, perform cross-image matching on the feature points in each image to obtain feature point pairs.

[0144] The three-dimensional reconstruction module 313 can be used to perform three-dimensional reconstruction on the foundation pit points in the foundation pit represented by the feature point pairs based on the feature point pairs and the image acquisition parameters to obtain the three-dimensional point cloud data of the foundation pit.

[0145] In a specific application scenario, in order to detect abnormal points in 3D point cloud data, the device further includes: a data cleaning unit 37.

[0146] The data cleaning unit 37 can be used to determine the data density within a preset neighborhood corresponding to each point in the 3D point cloud data, and based on the data density, determine core points and non-core points among the points; take any one of the core points as a target core point, and use the target core point as a clustering center to cluster the remaining core points to obtain core points under different clustering categories; take any one of the non-core points as a target non-core point, determine the reference core point closest to the non-core point among the core points under each clustering category, and determine whether the distance between the non-core point and the reference core point is less than a preset distance threshold; if the distance between the non-core point and the reference core point is less than the preset distance threshold, then classify the non-core point into the clustering category to which the reference core point belongs, otherwise, determine the non-core point as an abnormal point; remove the abnormal points from the 3D point cloud data to obtain the cleaned 3D point cloud data.

[0147] It should be noted that for other corresponding descriptions of each functional module involved in the engineering quantity estimation device for a power grid infrastructure project provided in the embodiments of the present invention, reference can be made to Figure 1 the corresponding description of the method shown, which will not be elaborated here.

[0148] Based on the above as Figure 1 shown method, correspondingly, the embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the following steps are implemented: in response to a signal for estimating the engineering quantity of a power grid infrastructure project at a target location, determine the 3D point cloud data of the foundation pit at the target location, and determine the geological attribute information and environmental attribute information of the location where the foundation pit is located, the excavation method information and support information during the excavation of the foundation pit; based on the 3D point cloud data, construct a 3D model of the foundation pit, and based on the 3D model of the foundation pit, determine the excavation area volume; based on the excavation area volume, the geological attribute information, the environmental attribute information, the excavation method information, and the support information, determine the earthwork volume information during the excavation of the foundation pit; based on the support information, determine the support engineering quantity information during the support of the foundation pit; based on the earthwork volume information and the support engineering quantity information, determine the engineering quantity of the foundation pit during the excavation in the power grid infrastructure project.

[0149] Based on the above as Figure 1 shown method and the embodiments of the device as Figure 3 shown, the embodiments of the present invention also provide an entity structure diagram of a computer device, as Figure 5As shown in the figure, the computer device includes: a processor 41, a memory 42, and a computer program stored on the memory 42 and executable on the processor. Both the memory 42 and the processor 41 are arranged on a bus 43. When the processor 41 executes the program, the following steps are implemented: in response to an engineering quantity estimation signal for grid infrastructure construction at a target location, determine the three-dimensional point cloud data of the foundation pit at the target location, and determine the geological attribute information and environmental attribute information of the location where the foundation pit is located, the excavation method information and support information during the excavation of the foundation pit; based on the three-dimensional point cloud data, construct a three-dimensional model of the foundation pit, and based on the three-dimensional model of the foundation pit, determine the excavation area volume; based on the excavation area volume, the geological attribute information, the environmental attribute information, the excavation method information, and the support information, determine the earthwork quantity information during the excavation of the foundation pit; based on the support information, determine the support engineering quantity information during the support of the foundation pit; based on the earthwork quantity information and the support engineering quantity information, determine the engineering quantity of the foundation pit during the excavation in the grid infrastructure construction.

[0150] Through the technical solution of the present invention, the present invention constructs a three-dimensional model of the foundation pit by collecting the three-dimensional point cloud data of the foundation pit at the target location, and uses the three-dimensional model to determine the excavation area volume, which can avoid the time wasted by manual measurement of the excavation volume and the risk of measurement errors. Therefore, the present invention can improve the determination efficiency and determination accuracy of the excavation area volume. After that, the present invention comprehensively analyzes the excavation area volume, geological attribute information, environmental attribute information, excavation method information, and support information to determine the earthwork quantity information during the excavation of the foundation pit, which can avoid the time wasted by manually measuring only the volume of the foundation pit to determine the earthwork quantity and the situation of incorrect determination. Therefore, the present invention can improve the determination efficiency and determination accuracy of the earthwork quantity information. At the same time, the present invention determines the support engineering quantity information according to the support information, which can improve the determination accuracy and determination efficiency of the support engineering quantity. Finally, based on the accurately determined earthwork quantity information and support engineering quantity information, the engineering quantity of the foundation pit during the excavation is determined, thereby improving the determination efficiency and determination accuracy of the engineering quantity.

[0151] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a sequence different from that here, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. In this way, the present invention is not limited to any specific combination of hardware and software.

[0152] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for estimating the quantity of work in a power grid infrastructure project, characterized in that Including: In response to an engineering quantity estimation signal for power grid infrastructure construction at a target location, determining the three-dimensional point cloud data of the foundation pit at the target location, and determining the geological attribute information and environmental attribute information of the location where the foundation pit is located, the excavation method information and support information during the excavation of the foundation pit; Based on the three-dimensional point cloud data, constructing a three-dimensional model of the foundation pit, and based on the three-dimensional model of the foundation pit, determining the excavation area volume; Based on the excavation area volume, the geological attribute information, the environmental attribute information, the excavation method information, and the support information, determining the earthwork quantity information during the excavation of the foundation pit; Based on the support information, determining the support engineering quantity information during the support of the foundation pit; Based on the earthwork quantity information and the support engineering quantity information, determining the engineering quantity during the excavation of the foundation pit in the power grid infrastructure construction.

2. The method according to claim 1, wherein The constructing the three-dimensional model of the foundation pit based on the three-dimensional point cloud data includes: Determining the two-dimensional image of the foundation pit; Determining the sparsity of the three-dimensional point cloud data and determining whether the sparsity is greater than a preset threshold; If the sparsity is greater than the preset threshold, based on the three-dimensional point cloud data, determining a three-dimensional voxel grid, and based on the three-dimensional voxel grid, constructing an initial three-dimensional model of the foundation pit; If the sparsity is less than or equal to the preset threshold, based on the three-dimensional point cloud data, determining a triangular mesh, and based on the triangular mesh, constructing an initial three-dimensional model of the foundation pit; Mapping the texture of the two-dimensional image to the initial three-dimensional model of the foundation pit to obtain the three-dimensional model of the foundation pit.

3. The method according to claim 2, wherein Before constructing the initial three-dimensional model of the foundation pit based on the three-dimensional voxel grid, the method further includes: Respectively determining any vertex in the three-dimensional voxel grid as a target voxel vertex, determining the adjacent vertices corresponding to the target voxel vertex, and determining the target position information corresponding to the target voxel vertex and the adjacent position information corresponding to the adjacent vertices; Based on the target position information and the adjacent position information, determining the position weighted average value between the target voxel vertex and the adjacent vertices; Based on the position weighted average value, adjusting the target position information of the target voxel vertex to obtain the target voxel vertex after adjusting the position; Based on the target voxel vertex after adjusting the position, obtaining the adjusted three-dimensional voxel grid; The constructing the initial three-dimensional model of the foundation pit based on the three-dimensional voxel grid includes: Based on the adjusted three-dimensional voxel grid, constructing the initial three-dimensional model of the foundation pit; Before constructing the initial three-dimensional model of the foundation pit based on the triangular mesh, the method further includes: Respectively determining any vertex in the triangular mesh as a target triangular vertex, and determining the adjacent triangular meshes corresponding to the target triangular vertex; Based on the vertex coordinates of each adjacent triangular mesh, determining the normal vectors of each adjacent triangular mesh and determining the included angles between the normal vectors; Based on the normal vectors of each of the adjacent triangular meshes, the angles between the normal vectors, and the position information of the target triangular vertex, determine the curvature parameter of the target triangular vertex, and determine whether the curvature parameter is greater than a preset parameter threshold; If the curvature parameter is greater than the preset parameter threshold, move the target triangular vertex towards the domain vertex corresponding to the target triangular vertex to obtain the adjusted target triangular vertex, and based on the adjusted target triangular vertex, obtain the adjusted triangular mesh; The constructing the initial three-dimensional foundation pit model of the foundation pit based on the triangular mesh includes: Construct the initial three-dimensional foundation pit model of the foundation pit based on the adjusted triangular mesh.

4. The method according to claim 1, wherein The determining the earthwork volume information of the foundation pit during the excavation process based on the excavation area volume, the geological attribute information, the environmental attribute information, the excavation method information, and the support information includes: Determine the volume feature vector corresponding to the excavation area volume, the address feature vector corresponding to the geological attribute information, the environmental feature vector corresponding to the environmental attribute information, the excavation feature vector corresponding to the excavation method information, and the support feature vector corresponding to the support information; Perform cross-processing on the volume feature vector, the address feature vector, the environmental feature vector, the excavation feature vector, and the support feature vector to obtain a cross feature vector; Input the cross feature vector into a preset earthwork volume prediction model for prediction to obtain the earthwork volume information of the foundation pit during the excavation process.

5. The method according to claim 1, characterized in that After determining the engineering quantity of the foundation pit during the excavation process in the power grid infrastructure project based on the earthwork volume information and the support engineering quantity information, the method further includes: Generate an engineering quantity report form based on the engineering quantity, and send the engineering quantity report form to at least one audit terminal for auditing; After receiving the audit passing results of each audit terminal, dynamically generate a two-dimensional code for the engineering quantity report form based on the audited engineering quantity report form.

6. The method according to claim 1, characterized in that, The determining the three-dimensional point cloud data of the foundation pit at the target position includes: Obtain multi-view images captured of the foundation pit from multiple perspectives, and determine the image acquisition parameters of the imaging device corresponding to the multi-view images; Extract the feature points with significant geometric structures in each of the images, perform cross-image matching on the feature points in each of the images to obtain feature point pairs; Based on the feature point pairs and the image acquisition parameters, perform three-dimensional reconstruction on the foundation pit points in the foundation pit represented by the feature point pairs to obtain the three-dimensional point cloud data of the foundation pit.

7. The method according to claim 1, wherein Before constructing the three-dimensional foundation pit model of the foundation pit based on the three-dimensional point cloud data, the method further includes: Determine the data density within a preset neighborhood corresponding to each point in the three-dimensional point cloud data, and based on the data density, determine the core points and non-core points among the points; Respectively use any one of the core points as a target core point, and perform clustering on the remaining core points with the target core point as the clustering center to obtain the core points under different clustering categories; Take any non-core point among the non-core points as a target non-core point respectively, determine the reference core point closest to the non-core point among the core points in each clustering category, and judge whether the distance between the non-core point and the reference core point is less than a preset distance threshold; If the distance between the non-core point and the reference core point is less than the preset distance threshold, classify the non-core point into the clustering category to which the reference core point belongs; otherwise, determine the non-core point as an outlier; Remove the outliers from the three-dimensional point cloud data to obtain the cleaned three-dimensional point cloud data.

8. An engineering quantity estimation device for power grid infrastructure projects, characterized in that, Comprising: A first determination unit, configured to, in response to an engineering quantity estimation signal for a power grid infrastructure project at a target location, determine the three-dimensional point cloud data of the foundation pit at the target location, and determine the geological attribute information and environmental attribute information of the location where the foundation pit is located, the excavation method information and support information during the excavation of the foundation pit; A construction unit, configured to construct a three-dimensional model of the foundation pit based on the three-dimensional point cloud data, and determine the excavation area volume based on the three-dimensional model of the foundation pit; A second determination unit, configured to determine the earthwork quantity information during the excavation of the foundation pit based on the excavation area volume, the geological attribute information, the environmental attribute information, the excavation method information, and the support information; A third determination unit, configured to determine the support engineering quantity information during the support of the foundation pit based on the support information; A fourth determination unit, configured to determine the engineering quantity during the excavation of the foundation pit in the power grid infrastructure project based on the earthwork quantity information and the support engineering quantity information.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images