Building component defect positioning method, device and equipment

Abstract

The application discloses a building component defect positioning method, device and equipment. The method comprises the following steps: acquiring a two-dimensional pixel coordinate of a defect area image of a building engineering component; determining a component code ID matched with the two-dimensional pixel coordinate of the defect area image based on the two-dimensional pixel coordinate of the defect area image, a preset visual calibration parameter library and a preset BIM component level space index library; acquiring a target three-dimensional space coordinate corresponding to the two-dimensional pixel coordinate of the defect area image based on the component code ID; and positioning a defect point corresponding to the defect area image in a BIM model according to the component code ID and the target three-dimensional space coordinate. The application improves positioning accuracy and efficiency.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more specifically, to a method, apparatus, and equipment for locating defects in building components. Background Technology

[0002] Quality defect control during the construction phase of a building project is a core aspect of ensuring structural safety and project acceptance.

[0003] Currently, for the location of defects in building components, algorithms such as YOLOv8 can be used to output the pixel coordinates of the defect image and the detection results.

[0004] However, the above method suffers from low positioning accuracy. Summary of the Invention

[0005] The main purpose of this application is to provide a method, device, and equipment for locating defects in building components, thereby improving the accuracy and efficiency of the location.

[0006] To achieve the above objectives, firstly, this application provides a method for locating defects in building components, comprising: Obtain the two-dimensional pixel coordinates of the defect area image of a building component; Based on the two-dimensional pixel coordinates of the defect area image, a preset visual calibration parameter library, and a preset BIM component-level spatial index library, a component code ID that matches the two-dimensional pixel coordinates of the defect area image is determined. Based on the component code ID, obtain the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image; Based on the component code ID and the target 3D spatial coordinates, locate the defect points corresponding to the defect area image in the BIM model.

[0007] In one embodiment, based on the two-dimensional pixel coordinates of the defect area image, a preset visual calibration parameter library, and a preset BIM component-level spatial index library, a component code ID matching the two-dimensional pixel coordinates of the defect area image is determined, including: Obtain the component type identifier carried in the defect area image; According to the component type identifier, the corresponding calibration parameters are retrieved from the preset visual calibration parameter library, and the two-dimensional pixel coordinates are converted into initial three-dimensional spatial coordinates based on the calibration parameters. The initial three-dimensional spatial coordinates are compared with the component spatial boundary coordinates of the corresponding area in the preset BIM component-level spatial index library to obtain the component code ID to which the initial three-dimensional spatial coordinates belong. The component code ID to which the initial three-dimensional spatial coordinates belong is used as the component code ID that matches the two-dimensional pixel coordinates of the defect area image.

[0008] In one embodiment, obtaining the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image based on the component code ID includes: Based on the component code ID, retrieve the center coordinates and component size parameters of the component corresponding to the component code ID from the preset BIM component-level spatial index library; The initial three-dimensional spatial coordinates are corrected based on the center coordinates and size parameters of the component to obtain the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image.

[0009] In one embodiment, the initial three-dimensional spatial coordinates are corrected based on the center coordinates and size parameters of the component to obtain the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image, including: Based on the component size parameters, the proportional relationship between the actual size of the component in each direction in three-dimensional space and the corresponding component size in the BIM model is obtained, and the correction coefficients in each direction in three-dimensional space are obtained. Calculate the difference between the initial 3D spatial coordinates and the center coordinates in each direction of 3D space, and multiply the difference in each direction of 3D space by the corresponding correction coefficient to obtain the corrected offset; The center coordinates are superimposed with the corrected offset to obtain the target's three-dimensional spatial coordinates.

[0010] In one embodiment, locating the defect point corresponding to the defect area image in the BIM model based on the component code ID and the target three-dimensional spatial coordinates includes: Based on the component code ID, determine the corresponding target component in the BIM model; Based on the target's three-dimensional spatial coordinates, determine the defect points on the target component that correspond to the defect area image.

[0011] In one embodiment, the method further includes: Visual annotations are generated at the defect locations, where the visual annotations include the component code ID and the coordinate information of the target three-dimensional space.

[0012] In one embodiment, the method further includes: A linked database is constructed, which records the association between the unique defect code, component code ID, and rectification and acceptance status. The linked database is connected to the BIM model and the rectification and acceptance system through technical interfaces. All data fed back by the rectification and acceptance system carries the unique defect code.

[0013] In one embodiment, the method further includes: When the rectification and acceptance system sends a signal that the defect has been accepted, the linked database matches the unique defect code to the corresponding component code ID and sends a label status update instruction to the BIM model so that the BIM model can adjust the color of the visual label at the defect point and add a rectification and acceptance mark. When the rectification and acceptance system reports that the defect has failed the acceptance, the labeling status of the visual annotation at the defect location remains unchanged, and a rectification failure mark is added.

[0014] Secondly, embodiments of this application provide a defect location device for building components, comprising: The pixel coordinate acquisition module is used to acquire the two-dimensional pixel coordinates of the defect area image of the building engineering component; The component coding determination module is used to determine the component code ID that matches the two-dimensional pixel coordinates of the defect area image based on the two-dimensional pixel coordinates of the defect area image, a preset visual calibration parameter library, and a preset BIM component-level spatial index library. The 3D spatial mapping module is used to obtain the target 3D spatial coordinates corresponding to the 2D pixel coordinates of the defect area image based on the component code ID. The defect location module is used to locate the defect points corresponding to the defect area image in the BIM model based on the component code ID and the target three-dimensional spatial coordinates.

[0015] Thirdly, embodiments of this application provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of any of the methods described above.

[0017] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the methods described above.

[0018] This application provides a method, apparatus, and device for locating defects in building components, including: acquiring the two-dimensional pixel coordinates of an image of a defect area of ​​a building component; determining a component code ID that matches the two-dimensional pixel coordinates of the defect area image based on the two-dimensional pixel coordinates of the defect area image, a preset visual calibration parameter library, and a preset BIM component-level spatial index library; acquiring the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image based on the component code ID; and locating the defect point corresponding to the defect area image in the BIM model according to the component code ID and the target three-dimensional spatial coordinates. This application, based on the collaborative correction of spatial index driven by component code ID and visual calibration parameters, can control the positioning error to the centimeter level, achieving precise positioning of defects on components. This significantly improves the targeting and efficiency of defect investigation and rectification on construction sites. It eliminates the need for manual intervention to associate defect data with the BIM model, avoiding the inefficiency and error-prone problems caused by manual input and static annotation in traditional methods, thus improving positioning accuracy and efficiency. Attached Figure Description

[0019] The accompanying drawings, which form part of this application, are used to provide a further understanding of the application and to make other features, objects, and advantages of the application more apparent. The illustrative embodiments and descriptions of this application are used to explain the application and do not constitute an undue limitation of the application. In the drawings: Figure 1 This is a flowchart illustrating a method for locating defects in building components provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a defect location device for building components provided in an embodiment of this application; Figure 3 This is a schematic diagram of the computer device provided in the embodiments of this application. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0021] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein.

[0022] In the embodiments of this application, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0023] It should be understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0024] It should be understood that in this application, "comprising" and "having" and any variations thereof 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 necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product or device.

[0025] It should be understood that in this application, "multiple" refers to two or more. "And / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, "and / or B" can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "Contains A, B, and C", "Contains A, B, and C" means that all three A, B, and C are contained; "Contains A, B, or C" means that one of A, B, and C is contained; "Contains A, B, and / or C" means that any one, two, or three of A, B, and C are contained.

[0026] It should be understood that in this application, "B corresponding to A", "B corresponding to A", "A corresponds to B", or "B corresponds to A" means that B is associated with A, and B can be determined based on A. Determining B based on A does not mean determining B solely based on A; B can also be determined based on A and / or other information. Matching A and B is defined as a similarity between A and B that is greater than or equal to a preset threshold.

[0027] Depending on the context, "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection."

[0028] The data involved in this application may be data authorized by the tester or fully authorized by all parties. The collection, dissemination, and use of the data shall comply with the relevant laws, regulations and standards of the relevant countries and regions. The implementation methods / executives of this application may be combined with each other.

[0029] It is understood that in the specific embodiments of this application, data such as user information are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0030] The technical solutions of this application will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0031] Quality defect control during the construction phase of building engineering is a core aspect of ensuring structural safety and project acceptance. With the rapid development of computer vision and Building Information Modeling (BIM) technologies, AI visual recognition can automatically detect defects such as cracks and honeycomb-like pitting on component surfaces, while BIM models provide a three-dimensional digital representation of components. However, current technologies largely limit the fusion of AI recognition results with spatial data from BIM models to the regional level (e.g., floor or construction section), lacking a method to accurately map the pixel coordinates of defect images to component-level BIM three-dimensional spatial coordinates. This results in large positioning errors and an inability to determine specific beams, columns, or slabs. Furthermore, defect annotations in BIM models are typically done manually and statically, and the annotation status cannot be automatically updated with on-site rectification and acceptance results, leading to a disconnect where "defects have been rectified, but the BIM still issues warnings." Therefore, a technical solution capable of achieving accurate component-level mapping and automatic status linkage is urgently needed.

[0032] The prior art most similar to this invention includes two categories: one is a building surface defect detection system based on deep learning, which uses algorithms such as YOLOv8 to output the pixel coordinates of defect images and detection results, but does not have the ability to spatially map with the BIM model and cannot convert pixel coordinates into component-level three-dimensional coordinates; the other is a BIM-based engineering quality control system, which requires manual input of defect data and manual annotation to the BIM model, and changes in the defect annotation status also rely on manual modification, lacking an automated end-to-end mapping and dynamic linkage mechanism.

[0033] Because the existing technologies lack a precise mapping method between the pixel coordinates of defects at the building component level and the spatial coordinates of BIM, the defects identified by AI can only be presented as image pixels or approximate areas. The matching error is usually greater than or equal to 10cm, making it impossible to pinpoint the precise location of specific beam, column, or slab components. This makes it difficult for on-site rectification personnel to quickly find the BIM component corresponding to the defect. At the same time, the defect annotation in the existing BIM model is static and manual. There is no automatic technical linkage between the annotation status and the actual rectification and acceptance results. Once the defect has been rectified but the BIM annotation has not been updated in time, there will be a problem of the warning status being out of sync with the actual situation. Moreover, the entire data association process requires manual intervention, which is inefficient and prone to errors.

[0034] To address the aforementioned problems, this application provides a method for locating defects in building components.

[0035] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for locating defects in building components, provided as an embodiment of this application. Figure 1 As shown, it includes the following steps: Step S101: Obtain the two-dimensional pixel coordinates of the defect area image of the building component.

[0036] Specifically, the system receives images of building components containing quality defects, captured by on-site data acquisition equipment (such as drones or fixed cameras). An AI visual recognition module (e.g., a defect detection model based on YOLOv8) processes the image and outputs the pixel coordinates (Px, Py) of the defect within the image. For example, taking a crack on a concrete beam surface, the pixel coordinates output by the AI ​​model might be the coordinates of the boundary points at the top left and bottom right corners of the crack area, or the coordinates of the crack's center point. This step outputs a structured defect data package, which includes at least: the two-dimensional pixel coordinates (Px, Py) of the defect area image, the region code bound during image acquisition (e.g., "Area A - Tower 2 - 3rd Floor"), and the component type identifier (e.g., "beam").

[0037] Step S102: Based on the two-dimensional pixel coordinates of the defect area image, the preset visual calibration parameter library, and the preset BIM component-level spatial index library, determine the component code ID that matches the two-dimensional pixel coordinates of the defect area image.

[0038] In one embodiment, determining a component code ID that matches the two-dimensional pixel coordinates of the defect area image based on the two-dimensional pixel coordinates of the defect area image, a preset visual calibration parameter library, and a preset BIM component-level spatial index library includes: obtaining the component type identifier carried by the defect area image; retrieving the corresponding calibration parameters from the preset visual calibration parameter library according to the component type identifier, and converting the two-dimensional pixel coordinates into initial three-dimensional spatial coordinates based on the calibration parameters; comparing the initial three-dimensional spatial coordinates with the component spatial boundary coordinates of the corresponding area in the preset BIM component-level spatial index library to obtain the component code ID to which the initial three-dimensional spatial coordinates belong; and using the component code ID to which the initial three-dimensional spatial coordinates belong as the component code ID that matches the two-dimensional pixel coordinates of the defect area image.

[0039] Specifically, the component type identifier (e.g., "beam") and area code (e.g., "Area A - Tower 2 - 3rd Floor") are extracted from the defect data package output by the above steps. This information is used for subsequent rapid retrieval from the corresponding calibration parameter library and spatial index library.

[0040] This application pre-constructs a visual calibration parameter library. For each component type (beam, column, slab, etc.) in each construction area, the library stores the calibration parameters of the corresponding acquisition device at fixed shooting positions and angles, including: camera intrinsic parameters (focal length, pixel size), extrinsic parameters (shooting position coordinates Xcam, Ycam, Zcam, shooting angle pitch / yaw / roll angle), and imaging scale. Taking a concrete beam as an example, the calibration parameters correspond one-to-one with "area code - component type," for example, ("Area A - Tower 2 - 3rd floor" - "beam") corresponds to a set of calibration parameters.

[0041] Based on the obtained component type identifier "beam" and area code, the corresponding calibration parameters are retrieved from the visual calibration parameter library. Then, using a camera imaging model (such as a pinhole model), the two-dimensional pixel coordinates (Px, Py) are converted into initial three-dimensional spatial coordinates (Xc, Yc, Zc) in the actual on-site space. This conversion process includes distortion correction and coordinate inversion, and the accuracy of the obtained initial coordinates is approximately decimeter-level (with an error of approximately 10 cm).

[0042] This application also pre-constructs a BIM component-level spatial index library. This library decomposes and encodes the BIM model at the component level during the construction phase, assigning a unique component code ID to each independent component (such as beam L-101, column C-202, etc.), and extracting the three-dimensional spatial boundary coordinates (Xmin, Ymin, Zmin ~ Xmax, Ymax, Zmax) and the component center coordinates (X0, Y0, Z0) for each component. Simultaneously, each component is bound to a construction area code, forming an index structure of "area code - component code ID - spatial coordinates". This index library is linked to the BIM model in real time; when the component coordinates in the BIM model change, the index library is automatically updated.

[0043] Using the obtained initial 3D spatial coordinates (Xc, Yc, Zc) and area code as query criteria, a search is performed in the BIM component-level spatial index library. Specifically, all components within the area are first filtered out based on the area code, and then it is determined which component's spatial boundary coordinate range (Xc, Yc, Zc) falls within. For example, if Xc is between Xmin and Xmax, Yc is between Ymin and Ymax, and Zc is between Zmin and Zmax, then the initial coordinates are determined to belong to that component, and its component code ID (e.g., "beam L-101") is extracted. If the initial coordinates fall within the boundaries of multiple components (e.g., node areas), one is selected as the matching result according to a preset priority (e.g., minimum component volume priority or closest to center priority).

[0044] After the above comparison, a clear component code ID (such as "beam L-101") is output, completing the initial component-level matching of defects.

[0045] Step S103: Based on the component code ID, obtain the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image.

[0046] In one embodiment, obtaining the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image based on the component code ID includes: retrieving the center coordinates and component size parameters of the component corresponding to the component code ID from a preset BIM component-level spatial index library based on the component code ID; correcting the initial three-dimensional spatial coordinates according to the component's center coordinates and component size parameters to obtain the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image.

[0047] The process involves correcting the initial three-dimensional spatial coordinates based on the component's center coordinates and component size parameters to obtain the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image. This includes: obtaining the proportional relationship between the actual dimensions of the component in each direction of the three-dimensional space and the corresponding component dimensions in the BIM model based on the component size parameters, and obtaining correction coefficients for each direction of the three-dimensional space; calculating the difference between the initial three-dimensional spatial coordinates and the center coordinates in each direction of the three-dimensional space, and multiplying the difference in each direction of the three-dimensional space by the corresponding correction coefficient to obtain the correction offset; and superimposing the center coordinates and the correction offset to obtain the target three-dimensional spatial coordinates.

[0048] Specifically, after obtaining the component ID, the initial three-dimensional spatial coordinates are further precisely corrected within the component to improve the positioning accuracy to within 3cm. The specific steps are as follows: Using the component code ID (e.g., "beam L-101") as the key, the center coordinates (X0, Y0, Z0) and the dimensional parameters (Length_X, Length_Y, Length_Z, i.e., the actual length, width, and height of the component) of the component are retrieved from the BIM component-level spatial index library. This data originates from the geometric information of the BIM model.

[0049] The correction process uses the following formula: X = X0 + (Xc - X0) × Kx; Y = Y0 + (Yc - Y0) × Ky; Z = Z0 + (Zc - Z0) × Kz.

[0050] Wherein, Kx, Ky, and Kz are component-specific correction coefficients, pre-calibrated based on factors such as component material, surface texture, and shooting distance, with values ​​typically ranging from 0.95 to 1.05. For example, for concrete beams, due to surface roughness causing systematic bias in visual measurements, Kx=0.98, Ky=1.02, and Kz=1.00 can be determined through calibration experiments. The correction coefficients are obtained by setting multiple control points with known three-dimensional coordinates on the component surface, acquiring their pixel coordinates through AI image acquisition, and then inversely solving for the coefficients that minimize the error.

[0051] In actual calculations, the differences between the initial coordinates and the center coordinates in each direction are first calculated (Xc-X0), (Yc-Y0), and (Zc-Z0). These differences are then multiplied by the corresponding correction coefficients to obtain the corrected offsets. Finally, the center coordinates and the corrected offsets are superimposed to obtain the target 3D spatial coordinates (X, Y, Z). These coordinates represent the precise 3D spatial coordinates of the defect at the component level in the BIM model, with a matching error ≤3cm.

[0052] Step S104: Based on the component code ID and the target three-dimensional spatial coordinates, locate the defect point corresponding to the defect area image in the BIM model.

[0053] In one embodiment, locating the defect point corresponding to the defect area image in the BIM model according to the component code ID and the target three-dimensional spatial coordinates includes: determining the corresponding target component in the BIM model according to the component code ID; and determining the defect point corresponding to the defect area image on the target component according to the target three-dimensional spatial coordinates.

[0054] In one embodiment, the method further includes: generating a visual annotation at the defect location, wherein the visual annotation includes a component code ID and coordinate information of the target three-dimensional space.

[0055] Specifically, the BIM model's application programming interface (API) is called, using the component code ID (e.g., "beam L-101") as a parameter to retrieve the corresponding component object from the BIM model. This component object contains its geometric entity, attribute information, etc., within the BIM scene.

[0056] The system maps the target's 3D spatial coordinates (X, Y, Z) to the local coordinate system of the BIM model, and precisely locates the defect points on the corresponding surface or inside the target component (beam L-101). For example, for a crack on the beam surface, the coordinates are located on the side or bottom of the beam. After location, the system can generate a visual annotation at that point. The annotation is in the form of a dot marker, with fixed colors set according to the defect level (minor - blue, moderate - yellow, severe - red), and embeds a unique defect code and component code ID, achieving precise annotation of "one defect, one marker; one marker, one component".

[0057] In one embodiment, the method further includes: constructing a linked database, wherein the linked database records the association between the unique defect code, the component code ID and the rectification and acceptance status, and the linked database is connected to the BIM model and the rectification and acceptance system through a technical interface, and all data fed back by the rectification and acceptance system carries the unique defect code.

[0058] Specifically, this application establishes a linked database that records the relationship between unique defect codes, BIM component ID codes, and rectification and acceptance status (not rectified, under rectification, passed acceptance, failed acceptance). This database interfaces with the BIM model and the rectification and acceptance system via TCP / IP protocol, and all data returned by the rectification and acceptance system carries a unique defect code.

[0059] In one embodiment, the method further includes: when the rectification and acceptance system sends a signal that the defect has passed the acceptance, the linked database matches the unique defect code to the corresponding component code ID and sends a labeling status update instruction to the BIM model so that the BIM model adjusts the color of the visual label at the defect point and adds a rectification and acceptance mark; when the rectification and acceptance system sends a signal that the defect has failed the acceptance, the labeling status of the visual label at the defect point remains unchanged and a rectification failure mark is added.

[0060] Specifically, when the rectification and acceptance system sends a "defect accepted" signal (for example, when on-site supervisors confirm rectification is satisfactory on their mobile devices), the linked database matches the unique defect code to the corresponding BIM component code ID and sends a labeling status update command to the BIM model. Upon receiving the command, the BIM model automatically changes the label color of the defect location to green and adds the text "rectified and accepted." If the rectification and acceptance system sends a "received but not accepted" signal, the label color remains unchanged (still the original blue / yellow / red) and a "rectification unsatisfactory" label is added.

[0061] The entire update process does not require manual modification of the annotations in the BIM model, achieving real-time and unique linkage between the annotation status and the actual rectification results.

[0062] This application provides a method for locating defects in building components, comprising: acquiring the two-dimensional pixel coordinates of an image of a defect area of ​​a building component; determining a component code ID that matches the two-dimensional pixel coordinates of the defect area image based on the two-dimensional pixel coordinates of the defect area image, a preset visual calibration parameter library, and a preset BIM component-level spatial index library; acquiring the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image based on the component code ID; and locating the defect point corresponding to the defect area image in the BIM model according to the component code ID and the target three-dimensional spatial coordinates. This application, based on the collaborative correction of spatial index driven by component code ID and visual calibration parameters, can control the positioning error to the centimeter level, achieving precise positioning of defects on components. This significantly improves the targeting and efficiency of defect investigation and rectification on construction sites. It eliminates the need for manual intervention to associate defect data with the BIM model, avoiding the inefficiency and error-prone problems caused by manual input and static annotation in traditional methods, thus improving positioning accuracy and efficiency.

[0063] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0064] The following are device embodiments of this application. For details not described in detail, please refer to the corresponding method embodiments described above.

[0065] Figure 2 This diagram illustrates a structural schematic of a building component defect location device according to an embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. The building component defect location device includes: The pixel coordinate acquisition module 201 is used to acquire the two-dimensional pixel coordinates of the defect area image of the building engineering component; The component code determination module 202 is used to determine the component code ID that matches the two-dimensional pixel coordinates of the defect area image based on the two-dimensional pixel coordinates of the defect area image, a preset visual calibration parameter library, and a preset BIM component-level spatial index library. The three-dimensional space mapping module 203 is used to obtain the target three-dimensional space coordinates corresponding to the two-dimensional pixel coordinates of the defect area image based on the component code ID. The defect location module 204 is used to locate the defect point corresponding to the defect area image in the BIM model based on the component code ID and the target three-dimensional spatial coordinates.

[0066] In one embodiment, the component coding determination module 202 is further configured to obtain the component type identifier carried by the defect area image; According to the component type identifier, the corresponding calibration parameters are retrieved from the preset visual calibration parameter library, and the two-dimensional pixel coordinates are converted into initial three-dimensional spatial coordinates based on the calibration parameters. The initial three-dimensional spatial coordinates are compared with the component spatial boundary coordinates of the corresponding area in the preset BIM component-level spatial index library to obtain the component code ID to which the initial three-dimensional spatial coordinates belong. The component code ID to which the initial three-dimensional spatial coordinates belong is used as the component code ID that matches the two-dimensional pixel coordinates of the defect area image.

[0067] In one embodiment, the three-dimensional space mapping module 203 is further configured to retrieve the center coordinates and component size parameters of the component corresponding to the component code ID from a preset BIM component-level spatial index library based on the component code ID. The initial three-dimensional spatial coordinates are corrected based on the center coordinates and size parameters of the component to obtain the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image.

[0068] In one embodiment, the initial three-dimensional spatial coordinates are corrected based on the center coordinates and size parameters of the component to obtain the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image, including: Based on the component size parameters, the proportional relationship between the actual size of the component in each direction in three-dimensional space and the corresponding component size in the BIM model is obtained, and the correction coefficients in each direction in three-dimensional space are obtained. Calculate the difference between the initial 3D spatial coordinates and the center coordinates in each direction of 3D space, and multiply the difference in each direction of 3D space by the corresponding correction coefficient to obtain the corrected offset; The center coordinates are superimposed with the corrected offset to obtain the target's three-dimensional spatial coordinates.

[0069] In one embodiment, the defect location module 204 is further configured to determine the corresponding target component in the BIM model based on the component code ID; Based on the target's three-dimensional spatial coordinates, determine the defect points on the target component that correspond to the defect area image.

[0070] In one embodiment, the apparatus further includes: a labeling module, which generates visual labels at defect locations, wherein the visual labels include component code ID and coordinate information of the target three-dimensional space.

[0071] In one embodiment, the device further includes a data linkage module, which is used to construct a linkage database. The linkage database records the association between the unique defect code, the component code ID, and the rectification and acceptance status. The linkage database is connected to the BIM model and the rectification and acceptance system through a technical interface. All data fed back by the rectification and acceptance system carries the unique defect code.

[0072] In one embodiment, the device further includes: a labeling status change module, which is used to link the database to match the corresponding component code ID through the unique code of the defect when the rectification and acceptance system sends a signal that the defect has been accepted, and send a labeling status update instruction to the BIM model so that the BIM model adjusts the color of the visual label at the defect point and adds a rectification and acceptance mark. When the rectification and acceptance system reports that the defect has failed the acceptance, the labeling status of the visual annotation at the defect location remains unchanged, and a rectification failure mark is added.

[0073] This application provides a device for locating defects in building components, specifically used for: acquiring the two-dimensional pixel coordinates of an image of a defect area of ​​a building component; determining a component code ID that matches the two-dimensional pixel coordinates of the defect area image based on the two-dimensional pixel coordinates of the defect area image, a preset visual calibration parameter library, and a preset BIM component-level spatial index library; acquiring the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image based on the component code ID; and locating the defect point corresponding to the defect area image in the BIM model according to the component code ID and the target three-dimensional spatial coordinates. This application, based on the collaborative correction of spatial index driven by component code ID and visual calibration parameters, can control the positioning error to the centimeter level, achieving precise positioning of defects on components. This significantly improves the targeting and efficiency of defect investigation and rectification on construction sites. It eliminates the need for manual intervention to associate defect data with the BIM model, avoiding the inefficiency and error-prone problems caused by manual input and static annotation in traditional methods, thus improving positioning accuracy and efficiency.

[0074] This application Figure 3 A schematic diagram of a computer device is provided. (Example) Figure 3 As shown, the computer device 3 in this embodiment includes a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and executable on the processor 301. When the processor 301 executes the computer program 303, it implements the steps in the various building component defect location method embodiments described above, for example... Figure 1 Steps 101 to 104 are shown. Alternatively, when processor 301 executes computer program 303, it implements the functions of each module / unit in the above embodiments of the building component defect location device, for example... Figure 2 The functions of modules / units 201 to 204 shown.

[0075] This application also provides a readable storage medium storing a computer program, which, when executed by a processor, is used to implement the building component defect location method provided in the various embodiments described above.

[0076] The readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of computer programs from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application-Specific Integrated Circuit (ASIC). Alternatively, the ASIC can be located in a user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0077] This application also provides a program product including execution instructions stored in a readable storage medium. At least one processor of the device can read the execution instructions from the readable storage medium, and the execution of the execution instructions by the at least one processor causes the device to implement the building component defect location method provided in the various embodiments described above.

[0078] In the embodiments of the above-described device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0079] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method of locating defects in a building component, characterized by, include: Obtain the two-dimensional pixel coordinates of the defect area image of a building component; Based on the two-dimensional pixel coordinates of the defect area image, a preset visual calibration parameter library, and a preset BIM component-level spatial index library, a component code ID that matches the two-dimensional pixel coordinates of the defect area image is determined. Based on the component code ID, obtain the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image; Based on the component code ID and the target three-dimensional spatial coordinates, locate the defect point corresponding to the defect area image in the BIM model.

2. The method of claim 1, wherein The step of determining a component code ID that matches the two-dimensional pixel coordinates of the defect area image based on the two-dimensional pixel coordinates of the defect area image, a preset visual calibration parameter library, and a preset BIM component-level spatial index library includes: Obtain the component type identifier carried by the defect area image; According to the component type identifier, the corresponding calibration parameters are retrieved from the preset visual calibration parameter library, and the two-dimensional pixel coordinates are converted into initial three-dimensional spatial coordinates based on the calibration parameters; The initial three-dimensional spatial coordinates are compared with the component spatial boundary coordinates of the corresponding area in the preset BIM component-level spatial index library to obtain the component code ID to which the initial three-dimensional spatial coordinates belong. The component code ID to which the initial three-dimensional spatial coordinates belong is used as the component code ID that matches the two-dimensional pixel coordinates of the defect area image.

3. The method of claim 1, wherein The step of obtaining the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect region image based on the component code ID includes: Based on the component code ID, retrieve the center coordinates and component size parameters of the component corresponding to the component code ID from the preset BIM component-level spatial index library; The initial three-dimensional spatial coordinates are corrected based on the center coordinates and size parameters of the component to obtain the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image.

4. The method for locating defects in building components as described in claim 3, characterized in that, The step of correcting the initial three-dimensional spatial coordinates based on the center coordinates and size parameters of the component to obtain the target three-dimensional spatial coordinates corresponding to the two-dimensional pixel coordinates of the defect area image includes: Based on the component size parameters, the proportional relationship between the actual size of the component in each direction of the three-dimensional space and the corresponding component size in the BIM model is obtained, and the correction coefficients in each direction of the three-dimensional space are obtained. Calculate the difference between the initial three-dimensional spatial coordinates and the center coordinates in each direction of the three-dimensional space, and multiply the difference in each direction of the three-dimensional space by the corresponding correction coefficient to obtain the correction offset; The center coordinates are superimposed with the corrected offset to obtain the target's three-dimensional spatial coordinates.

5. The method of claim 1, wherein the step of locating the defect in the building component is performed by a computer. The step of locating the defect point corresponding to the defect area image in the BIM model based on the component code ID and the target three-dimensional spatial coordinates includes: Based on the component code ID, determine the corresponding target component in the BIM model; Based on the target's three-dimensional spatial coordinates, the defect points corresponding to the defect region image are determined on the target component.

6. The method for locating defects in building components as described in claim 5, characterized in that, The method further includes: A visual annotation is generated at the defect location, wherein the visual annotation contains the component code ID and the coordinate information of the target three-dimensional space.

7. The method of claim 1, wherein The method further includes: A linked database is constructed, wherein the linked database records the unique defect code, the component code ID and the relationship between the rectification and acceptance status, the linked database is connected to the BIM model and the rectification and acceptance system through a technical interface, and all data fed back by the rectification and acceptance system carries the unique defect code.

8. The method for locating defects in building components as described in claim 7, characterized in that, The method further includes: When the rectification and acceptance system sends a signal that the defect has been accepted, the linkage database matches the unique defect code to the corresponding component code ID and sends a label status update instruction to the BIM model so that the BIM model can adjust the color of the visual label at the defect point and add a rectification and acceptance mark. When the rectification and acceptance system reports that the defect fails the acceptance, the labeling status of the visual annotation at the defect location remains unchanged, and a rectification failure mark is added.

9. A building component defect location apparatus, characterized by, include: The pixel coordinate acquisition module is used to acquire the two-dimensional pixel coordinates of the defect area image of the building engineering component; The component coding determination module is used to determine the component code ID that matches the two-dimensional pixel coordinates of the defect area image based on the two-dimensional pixel coordinates of the defect area image, a preset visual calibration parameter library, and a preset BIM component-level spatial index library. The three-dimensional space mapping module is used to obtain the target three-dimensional space coordinates corresponding to the two-dimensional pixel coordinates of the defect area image based on the component code ID. The defect location module is used to locate the defect point corresponding to the defect area image in the BIM model based on the component code ID and the target three-dimensional spatial coordinates.

10. A computer device, comprising: Includes a memory, and one or more processors communicatively connected to the memory; The memory stores instructions that can be executed by the one or more processors to enable the one or more processors to implement the building component defect location method as described in any one of claims 1 to 8.

Images