A method for automatically comparing and verifying construction progress of a building project based on three-dimensional point clouds

Abstract

The application discloses a kind of based on three-dimensional point cloud's construction engineering construction progress automatic comparison verification method, comprising: importing engineering BIM design model;After engineering BIM design model is triangulated faceted and grid, generate reference three-dimensional point cloud after downsampling;Acquisition construction site's measured three-dimensional point cloud, and registration is carried out;After registration, measured three-dimensional point cloud is component semantic segmentation;Calculate component completion degree, and combine preset determination threshold, determine the construction completion state of each component;All component completion degrees are summarized, and progress completion rate is calculated according to subpart project level weighting, and progress deviation coefficient is calculated based on planned progress timing parameter;According to progress deviation coefficient, trigger multi-level early warning, and automatically generate progress verification report.The application realizes complex construction site component level automation progress comparison, dynamic reference update, multi-level deviation early warning closed-loop control, greatly reduces manual intervention, improves verification precision and applicable scene range.

Description

Technical Field

[0001] This invention relates to the field of construction management and control technology, specifically to an automatic comparison and verification method for construction progress based on three-dimensional point clouds. Background Technology

[0002] With the popularization of industrialized construction and digital twin technology, relying on automation to replace manual inspections for construction progress verification has become an industry necessity. Prior art document CN119130354A discloses a construction progress verification system based on BIM and video fusion technology. This system uses drones and unmanned vehicles to capture two-dimensional video images, fuses single-frame images with BIM model calibration, extracts image edge features, and matches them with a preset feature library to determine construction progress. However, this existing solution has several technical shortcomings, limiting its application in complex construction site scenarios:

[0003] (1) Relying on two-dimensional images, lacking depth geometric information, the recognition of occluded scenes fails. Scaffolding, formwork, building materials, and mechanical equipment at the construction site can easily obscure building components. Two-dimensional images may miss components and have distorted feature matching, leading to serious deviations in progress judgment. Moreover, two-dimensional images cannot quantify the construction volume of components, but can only qualitatively determine their presence or absence, and cannot accurately calculate the percentage of completion.

[0004] (2) The feature library is static and fixed, and cannot adapt to design changes. The existing feature library is established once in the early stage of the project and only stores the image features of the standard construction stage. During the construction of the project, there are common design changes, on-site approvals, and component adjustments. The benchmark features cannot be updated automatically, and the benchmark for comparison of changed areas becomes invalid. It is necessary to manually re-annotate key areas and rebuild the feature library, which is extremely costly.

[0005] (3) High dependence on manual annotation and low degree of automation. Existing solutions require users to manually annotate all key areas in the BIM model in advance. Large buildings have many sub-items, and the workload of manual annotation is huge. Camera calibration relies on the simulation of image matching from a full affine sample library. The process is cumbersome, and there is no on-site measurement of three-dimensional geometry calibration, resulting in large calibration errors.

[0006] (4) Lack of fine-grained component-level quantitative comparison results in low computational efficiency. Existing solutions rely solely on coarse matching of global image features, which cannot distinguish between independent components such as beams, columns, walls, and pipelines, and therefore cannot output component-level progress data. Furthermore, the lack of a hierarchical spatial retrieval structure leads to a large computational load for full feature matching of the entire image, making it difficult to achieve real-time on-site verification.

[0007] (5) Lack of multi-source 3D acquisition and collaboration mechanism, resulting in incomplete high-altitude / indoor data. The existing solution relies solely on camera equipment to capture 2D images, with drones serving only as mobile carriers and not collecting 3D geometric data; effective information cannot be fully obtained for indoor foundation pits, steel structure nodes, building facades, and other areas, resulting in incomplete full-area monitoring coverage.

[0008] The above shortcomings urgently need to be improved. Summary of the Invention

[0009] To overcome the problems of occlusion misjudgment, lack of 3D quantization, poor change adaptation, excessive manual intervention, incomplete coverage, and insufficient real-time performance in existing construction progress verification technologies, this invention provides an automatic comparison and verification method for construction progress of building engineering based on 3D point clouds. This method enables automated progress comparison at the component level in complex building construction sites, dynamic benchmark updates, and multi-level deviation early warning closed-loop management, significantly reducing manual intervention and improving verification accuracy and the scope of applicable scenarios.

[0010] The technical solution of this invention is as follows:

[0011] In a first aspect, the present invention provides an automatic comparison and verification method for construction progress of building projects based on three-dimensional point clouds, comprising the following steps:

[0012] Import the engineering BIM design model with semantic attributes of sub-items;

[0013] After triangulating the engineering BIM design model into a mesh, downsampling is performed to generate a baseline 3D point cloud. Then, a unique semantic label and a planned schedule time parameter are bound to each component according to the building component level to build a BIM baseline semantic point cloud library.

[0014] The actual 3D point cloud of the construction site was collected using point cloud acquisition equipment and preprocessed.

[0015] The preprocessed measured 3D point cloud is registered with the reference 3D point cloud.

[0016] The registered measured 3D point cloud is subjected to component semantic segmentation, and the measured component point cloud set with component semantic labels, 3D bounding boxes and spatial coordinates is output; the measured component point cloud set includes the BIM reference component point cloud and the measured component point cloud with all components matched.

[0017] The completion status of each component is determined by comparing the measured 3D point cloud of each component with the baseline 3D point cloud, and by combining the results with a preset judgment threshold.

[0018] Summarize the completion status of all components, calculate the progress completion rate by weighting the sub-item project level, and calculate the progress deviation coefficient based on the planned progress time parameters;

[0019] Multi-level early warnings are triggered based on the schedule deviation coefficient, and a schedule verification report is automatically generated.

[0020] As a preferred embodiment of the present invention, the step of downsampling the engineering BIM design model after triangular meshing to generate a reference 3D point cloud, and binding a unique semantic label and planned schedule timing parameters to each component according to the building component level, includes:

[0021] All components in the engineering BIM design model are processed into triangular meshes;

[0022] The Poisson sampling algorithm is used to downsample the triangular facets at a preset sampling interval to generate the reference 3D point cloud of each component;

[0023] Each component is assigned a unique semantic tag according to its building component level, and the planned schedule timing parameters are embedded in the tag.

[0024] Establish a three-dimensional association index of component semantics, spatial geometry, and project schedule to form a BIM benchmark semantic point cloud library.

[0025] As a preferred embodiment of the present invention, the unique semantic tags include foundation, column, beam, slab, wall, and electromechanical pipeline.

[0026] As a preferred embodiment of the present invention, the point cloud acquisition device includes an inspection drone equipped with a lidar and a positioning module, and a ground-based 3D laser scanner; the inspection drone and the ground-based 3D laser scanner are synchronized to acquire a unified acquisition clock through a hardware synchronization trigger module.

[0027] The inspection drone generates an autonomous inspection route based on the facade outline of the engineering BIM design model, and flies at a constant speed around the building to collect 3D point clouds of oblique photography of the facade and roof, and collects oblique photography point clouds of the facade and roof area with full coverage.

[0028] The ground-based 3D laser scanner is deployed in the foundation pit, the interior of the standard floor, and the steel structure nodes of the stairwell to collect fine point clouds of the interior through fixed-point scanning.

[0029] As a preferred embodiment of the present invention, the step of acquiring measured three-dimensional point clouds of the construction site using point cloud acquisition equipment includes:

[0030] The inspection drone and the ground-based 3D laser scanner are used to collect measured 3D point clouds of the construction site, and simultaneously record equipment spatial pose parameters, on-site light intensity, and dust concentration.

[0031] Spatiotemporal alignment, statistical filtering for noise reduction, and voxel downsampling preprocessing are performed on the measured 3D point cloud to output a standardized measured point cloud dataset.

[0032] As a preferred embodiment of the present invention, the registration of the preprocessed measured 3D point cloud with the reference 3D point cloud includes:

[0033] Extract the FPFH geometric features of the preprocessed measured 3D point cloud and the reference 3D point cloud, match the planar and angular features, generate the initial coordinate transformation matrix, and complete the coarse registration.

[0034] Based on the ICP iterative algorithm, the point cloud distance of the initial coordinate transformation matrix is ​​corrected by combining the equipment spatial pose parameters, on-site light intensity, and dust concentration to complete the fine registration;

[0035] The precisely registered measured 3D point cloud is uniformly mapped to the BIM reference coordinate system.

[0036] As a preferred embodiment of the present invention, the step of performing component semantic segmentation on the registered measured 3D point cloud includes:

[0037] Edge computing terminals are deployed at the construction site, and each edge computing terminal has a built-in lightweight hierarchical semantic segmentation network.

[0038] Component semantic segmentation is performed on the registered measured point cloud using a lightweight hierarchical semantic segmentation network.

[0039] As a preferred embodiment of the present invention, the determination of the construction completion status of each component based on the measured three-dimensional point cloud and the reference three-dimensional point cloud of each component, combined with a preset judgment threshold, includes:

[0040] For each matched component, a multi-level octree spatial comparison structure is constructed. The spatial voxels of the measured 3D point cloud and the reference 3D point cloud are traversed layer by layer. The ratio of the measured overlapping volume of the component to the total volume of the component BIM is calculated and used as the component completion degree.

[0041] Set a primary judgment threshold and a secondary judgment threshold. When the completion degree of a component is less than the primary judgment threshold, the component is judged to be in an unconstructed state; when the completion degree of a component is greater than the primary judgment threshold but less than the secondary judgment threshold, the component is judged to be in a partially constructed state; when the completion degree of a component is greater than the secondary judgment threshold, the component is judged to be in a completed state.

[0042] The system identifies newly added structures in the measured 3D point cloud that do not have corresponding components in the BIM reference point cloud, or BIM reference point cloud that contains missing, unconstructed, or canceled components, and marks them as change areas.

[0043] Extract the geometric and semantic information of the changed area, automatically update the BIM benchmark semantic point cloud library, and synchronously update the subsequent comparison and judgment threshold.

[0044] In a second aspect, the present invention provides an electronic device, comprising:

[0045] At least one processor; and,

[0046] A memory communicatively connected to the at least one processor; wherein,

[0047] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the above-described automatic comparison and verification method for construction progress of building engineering based on three-dimensional point clouds.

[0048] Thirdly, the present invention provides a computer-readable storage medium, including a data storage area and a program storage area, wherein the data storage area stores created data and the program storage area stores a computer program; wherein, when the computer program is executed by a processor, it implements the above-described method for automatic comparison and verification of construction progress of building engineering based on three-dimensional point clouds.

[0049] According to the above-described solution, the beneficial effects of this invention are as follows:

[0050] This invention utilizes a drone equipped with a lidar system and a ground-based laser scanner to collaboratively collect measured 3D point clouds, fully preserving the 3D spatial contours and volumetric geometric information of components. Scaffolding and building materials do not obstruct the extraction of spatial features from underlying components, enabling accurate identification of the construction status of obscured components. Simultaneously, the percentage of completed components is quantified by the overlap volume ratio of the point clouds, achieving quantitative verification and effectively improving accuracy and quantification capabilities. Furthermore, octree spatial comparison automatically identifies on-site modified components, extracts the semantic information of the modified component's 3D point cloud, automatically updates the BIM benchmark semantic point cloud library, and synchronously refreshes the comparison threshold. The entire process requires no manual intervention, adapting to design changes and on-site approval scenarios throughout the entire construction process, significantly improving automation. Attached Figure Description

[0051] Figure 1 This is a flowchart illustrating an automatic comparison and verification method for construction progress based on three-dimensional point clouds in one embodiment of the present invention.

[0052] Figure 2 for Figure 1 A detailed flowchart of step S6 is shown below;

[0053] Figure 3 This is a schematic diagram of the structure of an automatic comparison and verification device for construction progress based on three-dimensional point clouds in one embodiment of the present invention;

[0054] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0055] To make the technical problems to be solved, the technical solutions, and the beneficial effects of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not intended to limit the present invention.

[0056] It should be noted that the terms "comprising" and "having," and any variations thereof, in the specification and claims of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0057] like Figure 1 As shown, one embodiment of the present invention provides an automatic comparison and verification method for construction progress of building engineering based on three-dimensional point clouds, including the following steps:

[0058] S1. Import BIM Model: Import the engineering BIM design model with semantic attributes for each component. Each component in the engineering BIM design model is pre-labeled with its component type, floor, sub-item, quantity, planned start date, and planned completion date. Components include construction components such as foundations, columns, beams, slabs, walls, and MEP pipelines.

[0059] S2. BIM Model Preprocessing: After triangular meshing of the engineering BIM design model, downsampling is performed to generate a baseline 3D point cloud. A unique semantic label and planned schedule time parameters are bound to each component according to the building component level to build a BIM baseline semantic point cloud library.

[0060] Specifically, the process involves: first, processing all components of the engineering BIM design model into triangular meshes, transforming the component entities into continuous triangular meshes; second, using the Poisson sampling algorithm to downsample the triangular meshes at a preset sampling interval (e.g., 0.01m) to generate a baseline 3D point cloud for each component; third, binding a unique semantic tag to each component according to its building component level, including Foundation, Column, Beam, Slab, Wall, and MEP (Mechanical, Electrical, and Plumbing) tags, and embedding planned schedule time parameters (including planned start and completion time parameters); and fourth, establishing a 3D association index of component semantics, spatial geometry, and planned schedule, with the index key being the globally unique identifier (GUID) of the component, and the index value storing a subset of the component point cloud, the center coordinates of the 3D bounding box, the planned start and end times, and the component's quantity. All component point clouds and indexes are integrated and stored to form a BIM baseline semantic point cloud library.

[0061] S3. Point Cloud Acquisition and Preprocessing: The actual 3D point cloud of the construction site is acquired through point cloud acquisition equipment and preprocessed.

[0062] Specifically, the point cloud acquisition equipment includes an inspection drone equipped with LiDAR and a positioning module, and a ground-based 3D laser scanner. The inspection drone and the ground-based 3D laser scanner use a hardware synchronization trigger module to unify the acquisition clock and eliminate timing deviations. The inspection drone generates an autonomous inspection flight path based on the facade outline of the engineering BIM design model, and flies at a constant speed around the building to collect 3D point clouds of the facade and roof using oblique photography, achieving full coverage acquisition of oblique photography point clouds of the facade and roof area from the air. The ground-based 3D laser scanner is deployed in the first-floor foundation pit, the interior of the standard floor, and the steel structure nodes of the stairwell, and performs fixed-point scanning to collect detailed point clouds of the interior.

[0063] During the data acquisition process, the spatial pose parameters of the equipment, the ambient light intensity, and the dust concentration are recorded simultaneously. After the data acquisition is completed, the measured 3D point cloud is preprocessed: the point clouds of the two types of equipment are spatiotemporally aligned based on a unified timestamp, statistical filtering is used to remove distant outliers, the point cloud density is unified by 0.01m voxel downsampling, and a standardized measured point cloud dataset is output.

[0064] S4. Point cloud registration: Register the preprocessed measured 3D point cloud with the reference 3D point cloud.

[0065] Specifically, the FPFH geometric features of the preprocessed measured 3D point cloud and the reference 3D point cloud are extracted, and stable features such as building planes and beam and column corners are matched to generate an initial coordinate transformation matrix to complete coarse registration, with the coarse registration error controlled within 5cm. Based on the ICP iterative algorithm, the distance measurement error compensation factor is set in combination with equipment spatial pose parameters, on-site light intensity, and dust concentration. The point cloud distance of the initial coordinate transformation matrix is ​​iteratively corrected to complete fine registration, so that the final global registration accuracy is controlled within ±2mm, which greatly reduces the progress judgment error caused by environmental interference. The finely registered measured 3D point cloud is uniformly mapped to the BIM reference coordinate system to complete the spatial alignment of the measured point cloud and the BIM model.

[0066] S5. Component semantic segmentation: Perform component semantic segmentation on the registered measured 3D point cloud, and output the measured component point cloud set with component semantic labels, 3D bounding boxes, and spatial coordinates.

[0067] Specifically, edge computing terminals are deployed at the construction site. These terminals have a built-in lightweight hierarchical semantic segmentation network (such as PointNet++). The registered measured point cloud is input into the lightweight hierarchical semantic segmentation network, which extracts local geometric features of the point cloud layer by layer. It automatically distinguishes components such as foundations, columns, beams, slabs, walls, and electromechanical pipelines, and outputs a subset of the point cloud for each component. The corresponding semantic tags, 3D bounding boxes, and spatial coordinates of the component are bound simultaneously to form a set of measured component point clouds. The set of measured component point clouds includes the BIM benchmark component point clouds and the measured component point clouds of all components that have been matched.

[0068] S6. Completion Calculation and Status Determination: Based on the measured 3D point cloud and the baseline 3D point cloud of each component, the completion degree of the component is calculated, and combined with a preset judgment threshold, the construction completion status of each component is determined. For example... Figure 2 As shown, the specific steps include:

[0069] S601. For each matched component, construct a multi-level octree spatial comparison structure. The maximum depth of the octree is set to 6 levels, and the minimum voxel size is 5cm×5cm×5cm. Traverse the spatial voxels of the measured 3D point cloud and the reference 3D point cloud layer by layer, calculate the ratio of the measured overlap volume of the component to the total volume of the component's BIM, and use this ratio as the component's completion degree. The calculation formula is as follows:

[0070] ;

[0071] in, Let i be the component completion degree. Let i be the measured overlap volume of component i. Let i be the total BIM volume of component i.

[0072] S602. Set a first-level judgment threshold (e.g., 10%) and a second-level judgment threshold (90%). When the completion degree of a component is less than the first-level judgment threshold, the component is judged to be in an unconstructed state. When the completion degree of a component is greater than the first-level judgment threshold and less than the second-level judgment threshold, the component is judged to be in a partially constructed state. When the completion degree of a component is greater than the second-level judgment threshold, the component is judged to be in a completed state.

[0073] S603. Traverse and identify newly added structures in the measured 3D point cloud that do not have corresponding components in the BIM reference point cloud, or BIM reference point cloud that has missing, unconstructed, or canceled components in the measured data, and mark them uniformly as change areas.

[0074] S604 Extracts the geometric and semantic information (including 3D point cloud, semantic ID, and engineering quantity parameters) of the changed area, automatically updates the BIM benchmark semantic point cloud library, and synchronously updates the subsequent comparison and judgment threshold without requiring manual modification of the BIM benchmark semantic point cloud library.

[0075] S7. Schedule Deviation Calculation: Summarize the completion status of all components, calculate the progress completion rate by weighting the sub-item project level, and calculate the schedule deviation coefficient based on the planned schedule time parameters.

[0076] Specifically, after summarizing the completion status of all components, the progress completion rate of sub-items, sub-sections, floors, and units is calculated by weighting the component quantity as the weight and working upwards layer by layer.

[0077] The formula for calculating the progress completion rate of a sub-project is as follows:

[0078] ;

[0079] in, The progress completion rate of each sub-project. This represents the weight of the component's engineering quantity.

[0080] The formula for calculating the progress completion rate of a sub-project is:

[0081] ;

[0082] in, The progress completion rate of the sub-project. The weight of each item in the project.

[0083] The formula for calculating the progress completion rate of a floor / unit project is as follows:

[0084] ;

[0085] in, The progress completion rate of the floor / unit project. Weights for floors / units of the project.

[0086] The formula for calculating the schedule deviation factor is:

[0087] ;

[0088] in, This is the schedule deviation coefficient. To achieve the planned completion rate, , , This is the current time of this point cloud data collection and verification. Let i be the planned start time. Let i be the planned completion time of component i.

[0089] S8. Multi-level early warning and verification report generation: Trigger multi-level early warnings based on the progress deviation coefficient and automatically generate progress verification reports.

[0090] Specifically, the early warning classification standards are as follows:

[0091] 1) If the absolute value of the schedule deviation coefficient is ≤5%, it is considered a minor deviation of level one. The schedule is normal, and the system platform will display a pop-up message.

[0092] 2) If the absolute value of the schedule deviation coefficient is less than 5% and less than or equal to 15%, it is considered a Level 2 moderate deviation, or a minor schedule deviation. The project engineer will be notified via SMS.

[0093] 3) If the absolute value of the schedule deviation coefficient is greater than 15%, it is considered a Level 3 serious deviation. In case of serious schedule deviation, a schedule verification report will be sent to the project manager.

[0094] The progress verification report includes:

[0095] 1) Project progress completion rate and deviation analysis;

[0096] 2) Detailed schedule of progress for each sub-item of the project;

[0097] 3) List of delayed components (including component number, location coordinates, number of days of delay, and suggested corrective measures);

[0098] 4) An embedded 3D fusion model is used, with red highlighting of the lagging component point cloud difference areas, green marking of completed areas, and yellow marking of some construction areas.

[0099] This embodiment of the automatic comparison and verification method for construction progress of building engineering based on 3D point clouds utilizes a drone equipped with LiDAR and a ground-based laser scanner to collaboratively collect measured 3D point clouds, completely preserving the 3D spatial contours and volumetric geometric information of components. Scaffolding and building materials obstructing the view do not affect the extraction of spatial features of underlying components, allowing for accurate identification of the construction status of obscured components. Simultaneously, the percentage of completed components is quantified by the overlap volume ratio of the point clouds, achieving quantitative verification and effectively improving accuracy and quantification capabilities. Octree spatial comparison automatically identifies on-site changed components, extracts the 3D point cloud semantic information of the changed components, automatically updates the BIM benchmark semantic point cloud library, and synchronously refreshes the comparison threshold. The entire process requires no manual intervention, adapting to design changes and on-site approval scenarios throughout the entire construction process, significantly improving the degree of automation. Furthermore, the method utilizes unmanned aerial vehicles (UAVs) to automatically identify on-site changed components, extracts the 3D point cloud semantic information of the changed components, automatically updates the BIM benchmark semantic point cloud library, and synchronously refreshes the comparison threshold. The system is equipped with a lidar to collect point clouds of the building facade from high altitude, while a ground-based laser scanner collects detailed point clouds of the interior. The hardware is synchronized in time and space, providing complete coverage of the entire building area and solving the problem of limited range for 2D image acquisition. It relies on a multi-level octree to traverse spatial voxels, skipping blank areas and reducing invalid calculations, enabling millisecond-level progress comparison on-site to meet real-time management requirements. Through a lightweight hierarchical semantic segmentation network, it automatically performs semantic classification of point cloud components and binds BIM component labels, eliminating the need for manual annotation of key areas, significantly reducing upfront manual input, and adapting to ultra-large and complex engineering projects. It calculates the completion degree of each component, accurately locates lagging beams, columns, walls, and pipelines, and pushes early warnings according to the deviation coefficient. The 3D report highlights the difference point clouds, providing accurate data support for refined progress correction of the project.

[0100] like Figure 3 As shown, one embodiment of the present invention provides an automatic comparison and verification device for construction progress of building engineering based on three-dimensional point clouds, comprising:

[0101] BIM Model Import Module 1 is used to import engineering BIM design models with semantic attributes of sub-items;

[0102] BIM model preprocessing module 2 is used to generate a baseline 3D point cloud by downsampling the triangular facet mesh of the engineering BIM design model, and bind a unique semantic label and planned schedule time parameters to each component according to the building component level to build a BIM baseline semantic point cloud library.

[0103] The point cloud acquisition and preprocessing module 3 is used to acquire the measured three-dimensional point cloud of the construction site through the point cloud acquisition device and perform preprocessing.

[0104] Point cloud registration module 4 is used to register the preprocessed measured 3D point cloud with the reference 3D point cloud.

[0105] The component semantic segmentation module 5 is used to perform component semantic segmentation on the registered measured 3D point cloud and output the measured component point cloud set with component semantic labels, 3D bounding boxes and spatial coordinates;

[0106] The calculation and status determination module 6 is used to calculate the completion degree of each component based on the measured three-dimensional point cloud and the benchmark three-dimensional point cloud, and combined with the preset determination threshold, to determine the construction completion status of each component.

[0107] The schedule deviation calculation module 7 is used to summarize the completion status of all components, calculate the progress completion rate by weighted average according to the sub-item project level, and calculate the schedule deviation coefficient based on the planned schedule time parameters.

[0108] The early warning and report generation module 8 is used to trigger multi-level early warnings based on the progress deviation coefficient and automatically generate progress verification reports.

[0109] The automatic comparison and verification device for construction progress of building engineering based on three-dimensional point cloud provided in this application embodiment can execute the above method embodiment. Its implementation principle and technical effect are similar, and will not be repeated here.

[0110] Figure 4 This is a schematic diagram of the electronic device used in this invention to realize an automatic comparison and verification method for construction progress of building engineering based on three-dimensional point clouds.

[0111] The electronic device may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as an automatic comparison and verification program for construction progress of building engineering based on three-dimensional point clouds.

[0112] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing an automatic comparison and verification program for construction progress based on 3D point clouds), and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0113] The memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as the code of an automatic comparison and verification program for construction progress based on 3D point clouds, but also to temporarily store data that has been output or will be output.

[0114] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0115] Communication interface 13 is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), and optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0116] Figure 4 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 4 The structure shown does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0117] For example, a power supply, although not shown, may also include a power source (such as a battery) to power various components. Preferably, the power supply can be logically connected to at least one processor 10 via a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power sources, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be elaborated further here.

[0118] It should be understood that the embodiments are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0119] The automatic comparison and verification program for construction progress based on 3D point clouds, stored in the memory 11 of the electronic device, is a combination of multiple computer programs. For the specific implementation method of the aforementioned computer programs by the processor 10, please refer to [reference needed]. Figure 1 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0120] Furthermore, if the modules / units integrated into an electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, a computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, and read-only memory (ROM).

[0121] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following functions: Figure 1 The flowchart illustrates the automatic comparison and verification method for construction progress of building projects based on 3D point clouds.

[0122] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0123] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0124] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0125] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0126] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0127] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0128] Furthermore, although the operations of the method of the present invention are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0129] It should be understood that those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

[0130] The present invention has been described above with reference to the accompanying drawings. Obviously, the implementation of the present invention is not limited to the above-described manner. Any improvements made using the inventive concept and technical solution of the present invention, or the direct application of the inventive concept and technical solution of the present invention to other situations without modification, are all within the protection scope of the present invention.

Claims

1. A method for automatically comparing and verifying the construction progress of building projects based on 3D point clouds, characterized in that, Includes the following steps: Import the engineering BIM design model with semantic attributes of sub-items; After triangular meshing of the engineering BIM design model, downsampling is performed to generate a baseline 3D point cloud. Then, a unique semantic label and planned schedule time parameters are bound to each component according to the building component level to build a BIM baseline semantic point cloud library. The actual 3D point cloud of the construction site was collected using point cloud acquisition equipment and preprocessed. The preprocessed measured 3D point cloud is registered with the reference 3D point cloud. The registered measured 3D point cloud is subjected to component semantic segmentation, and the measured component point cloud set with component semantic labels, 3D bounding boxes and spatial coordinates is output; the measured component point cloud set includes the BIM reference component point cloud with all components matched and the measured component point cloud. The completion status of each component is determined by comparing the measured 3D point cloud of each component with the baseline 3D point cloud, and by combining the results with a preset judgment threshold. Summarize the completion status of all components, calculate the progress completion rate by weighting the sub-item project level, and calculate the progress deviation coefficient based on the planned progress time parameters; Multi-level early warnings are triggered based on the schedule deviation coefficient, and a schedule verification report is automatically generated.

2. The automatic comparison and verification method for construction progress of building engineering based on three-dimensional point clouds according to claim 1, characterized in that, The process of downsampling the engineering BIM design model after triangulation to generate a baseline 3D point cloud, and binding a unique semantic label and planned schedule timing parameters to each component according to the building component level, includes: All components in the engineering BIM design model are processed into triangular meshes; The Poisson sampling algorithm is used to downsample the triangular facets at a preset sampling interval to generate the reference 3D point cloud of each component; Each component is assigned a unique semantic tag according to its building component level, and the planned schedule timing parameters are embedded in the tag. Establish a three-dimensional association index of component semantics, spatial geometry, and project schedule to form a BIM benchmark semantic point cloud library.

3. The automatic comparison and verification method for construction progress of building engineering based on three-dimensional point clouds according to claim 1, characterized in that, The unique semantic tags include foundation, column, beam, slab, wall, and electromechanical pipeline.

4. The automatic comparison and verification method for construction progress of building engineering based on three-dimensional point clouds according to claim 1, characterized in that, The point cloud acquisition device includes an inspection drone equipped with a lidar and a positioning module, and a ground-based 3D laser scanner; the inspection drone and the ground-based 3D laser scanner are synchronized to a unified acquisition clock via a hardware synchronization trigger module; The inspection drone generates an autonomous inspection route based on the facade outline of the engineering BIM design model, and flies at a constant speed around the building to collect 3D point clouds of oblique photography of the facade and roof, and collects oblique photography point clouds of the facade and roof area with full coverage. The ground-based 3D laser scanner is deployed in the foundation pit, the interior of the standard floor, and the steel structure nodes of the stairwell to collect fine point clouds of the interior through fixed-point scanning.

5. The automatic comparison and verification method for construction progress of building engineering based on three-dimensional point clouds according to claim 4, characterized in that, The acquisition of measured 3D point clouds of the construction site using point cloud acquisition equipment includes: The inspection drone and the ground-based 3D laser scanner are used to collect measured 3D point clouds of the construction site, and simultaneously record equipment spatial pose parameters, on-site light intensity, and dust concentration. Spatiotemporal alignment, statistical filtering for noise reduction, and voxel downsampling preprocessing are performed on the measured 3D point cloud to output a standardized measured point cloud dataset.

6. The automatic comparison and verification method for construction progress of building engineering based on three-dimensional point clouds according to claim 5, characterized in that, The registration of the preprocessed measured 3D point cloud with the reference 3D point cloud includes: Extract the FPFH geometric features of the preprocessed measured 3D point cloud and the reference 3D point cloud, match the planar and angular features, generate the initial coordinate transformation matrix, and complete the coarse registration. Based on the ICP iterative algorithm, the point cloud distance of the initial coordinate transformation matrix is ​​corrected by combining the equipment spatial pose parameters, on-site light intensity, and dust concentration to complete the fine registration; The precisely registered measured 3D point cloud is uniformly mapped to the BIM reference coordinate system.

7. The automatic comparison and verification method for construction progress of building engineering based on three-dimensional point clouds according to claim 1, characterized in that, The step of performing component semantic segmentation on the registered measured 3D point cloud includes: Edge computing terminals are deployed at the construction site, and each edge computing terminal has a built-in lightweight hierarchical semantic segmentation network. Component semantic segmentation is performed on the registered measured point cloud using a lightweight hierarchical semantic segmentation network.

8. The automatic comparison and verification method for construction progress of building engineering based on three-dimensional point clouds according to claim 1, characterized in that, The completion status of each component is determined by comparing the measured 3D point cloud of each component with the baseline 3D point cloud, and combining this with a preset judgment threshold. This includes: For each matched component, a multi-level octree spatial comparison structure is constructed. The spatial voxels of the measured 3D point cloud and the reference 3D point cloud are traversed layer by layer. The ratio of the measured overlapping volume of the component to the total volume of the component BIM is calculated and used as the component completion degree. Set a primary judgment threshold and a secondary judgment threshold. When the completion degree of a component is less than the primary judgment threshold, the component is judged to be in an unconstructed state; when the completion degree of a component is greater than the primary judgment threshold but less than the secondary judgment threshold, the component is judged to be in a partially constructed state; when the completion degree of a component is greater than the secondary judgment threshold, the component is judged to be in a completed state. The system identifies newly added structures in the measured 3D point cloud that do not have corresponding components in the BIM reference point cloud, or BIM reference point cloud that contains missing, unconstructed, or canceled components, and marks them as change areas. Extract the geometric and semantic information of the changed area, automatically update the BIM benchmark semantic point cloud library, and synchronously update the subsequent comparison and judgment threshold.

9. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the automatic comparison and verification method for construction progress of building engineering based on three-dimensional point clouds as described in any one of claims 1 to 8.

10. A computer-readable storage medium storing computer-executable instructions, characterized in that, It includes a data storage area and a program storage area. The data storage area stores the created data, and the program storage area stores the computer program. When the computer program is executed by the processor, it implements the automatic comparison and verification method for construction progress of building engineering based on three-dimensional point cloud as described in any one of claims 1 to 8.

Images