An intelligent detection and identification method and system for building construction

Abstract

The embodiment of the present invention relates to the field of building detection technology and discloses an intelligent detection method for building construction, including: solving the spatial coordinate information of the corresponding indoor laser point cloud based on the acquisition position of the laser scanner and the indoor laser point cloud; determining the clustering range according to a randomly selected coordinate on a wall and a set width, and determining the interface to be detected; determining the display reference interface according to the spatial coordinate information of the laser point cloud in the interface to be detected, and comparing the spatial coordinate information of all indoor laser point clouds at the corresponding interface to be detected with the display reference interface to determine the color value of the corresponding indoor laser point cloud. The intelligent detection method for building construction in the embodiment of the present invention constructs a corresponding point cloud model by collecting three-dimensional point clouds after each stage of building construction is completed, and finally determines the numerical value of each parameter to be measured based on the point cloud parameters; reducing the time spent on repeated detection and improving overall detection efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of building detection, and in particular to an intelligent detection and identification method and system for building construction. Background Art

[0002] At present, traditional building measurement generally adopts manual measurement, which has the following pain points: First, the overall measurement is time-consuming and labor-intensive, and manual participation and recording are required at each stage; and because there are many people involved in the entire construction process, if the data quality cannot be guaranteed, then multiple parties will have to repeatedly verify the same data, which will prolong the entire construction cycle; second, because the specific implementation is carried out in a local collection method, it is impossible to fully reflect the overall construction quality of the building; and in the subsequent sorting, a lot of data will be generated and it is impossible to achieve unified and effective management. Therefore, designing a solution that can efficiently complete the management and inspection of the construction process has become a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0003] In response to the above-mentioned defects, an embodiment of the present invention discloses an intelligent detection method for building construction, which can efficiently realize construction detection at all stages of building construction, greatly improve the overall construction efficiency, and provide users with more dimensional data for reference.

[0004] A first aspect of an embodiment of the present invention discloses an intelligent detection method for building construction, comprising:

[0005] Use a 3D laser scanner to collect 3D point clouds of the indoor environment after each stage of construction to obtain the corresponding indoor laser point clouds;

[0006] Calculating spatial coordinate information of a corresponding indoor laser point cloud based on the acquisition position information of the three-dimensional laser scanner and the indoor laser point cloud; and determining the wall surface to which the corresponding indoor laser point cloud belongs based on the spatial coordinate information;

[0007] Determine a clustering range based on a randomly selected coordinate on a wall and a set width, and perform a clustering operation on the indoor laser point cloud based on the clustering range and the spatial coordinate information to obtain a to-be-detected interface, wherein the to-be-detected interface is composed of laser point clouds within a preset range, and any one of the horizontal coordinate, vertical coordinate, or vertical coordinate of the to-be-detected interface is within the preset range;

[0008] Determine a display reference interface according to the spatial coordinate information of the laser point cloud in the interface to be detected, and compare the spatial coordinate information of all indoor laser point clouds at the corresponding interface to be detected with the display reference interface to determine the color value of the corresponding indoor laser point cloud;

[0009] The corresponding indoor laser point cloud is image displayed according to the color value and spatial coordinate information to obtain a point cloud distribution map; the flatness data of the corresponding wall is determined according to the point cloud distribution map, and the numerical value of each measurement parameter is determined according to the parameter information of each interface to be detected.

[0010] As an optional implementation manner, in the first aspect of the embodiment of the present invention, determining the display reference interface based on the spatial coordinate information of the laser point cloud in the interface to be detected, and comparing the spatial coordinate information of all indoor laser point clouds at the corresponding interface to be detected with the display reference interface to determine the color value of the corresponding indoor laser point cloud includes:

[0011] When the interface to be detected is an interface to be detected in a first direction, obtaining an azimuth coordinate set associated with the laser point cloud in the interface to be detected and the first direction according to the first direction;

[0012] Acquire the largest number of azimuth coordinate data with the same value in the azimuth coordinate set, and construct a corresponding display reference interface based on the azimuth coordinate data;

[0013] Comparing the spatial coordinate information of all indoor laser point clouds at the interface to be detected with the display reference interface, if the spatial coordinate information of the corresponding indoor laser point cloud is higher than the display reference interface, configuring a first color parameter for the corresponding laser point cloud; if the spatial coordinate information of the corresponding indoor laser point cloud is lower than the display reference interface, configuring a second color parameter for the corresponding laser point cloud;

[0014] The color depth value is determined according to the difference between the spatial coordinate information of the laser point cloud and the display reference page, and the corresponding color parameter is obtained according to the color depth value, the first color parameter and the second color parameter.

[0015] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the various stages in the building construction include a concrete stage, a masonry engineering stage, a plastering engineering stage, and a putty application stage; the determining of the flatness data of the corresponding wall surface based on the point cloud distribution map and the calculation based on the parameter information of each interface to be detected to determine the numerical value of each measurement parameter include:

[0016] Determine the wall verticality, wall flatness, squareness, top plate horizontality, external window opening range and bay depth of the corresponding structure at the concrete stage based on the point cloud distribution map and parameter information of each interface to be tested;

[0017] Determine the verticality of the masonry, the flatness of the masonry surface, and the extreme difference of the external window openings of the corresponding structure during the masonry engineering stage based on the point cloud distribution map and the parameter information of each interface to be detected;

[0018] According to the point cloud distribution map and the parameter information of each interface to be detected, the verticality of the plastered facade, the flatness of the plastered surface, the squareness of the plastered room, the straightness of the plastered inner and outer corners, the maximum width of the door opening, the net height of the plastered room, the horizontality of the plastered top plate, the large and small ends of the plastered windows, the elevation difference of the bottom box in the same room, and the depth of the bay are determined.

[0019] According to the point cloud distribution map and the parameter information of each interface to be detected, the verticality of the putty facade, the flatness of the putty surface, the horizontality / flatness of the ceiling, the three sides and two lines, the squareness of the putty corners, the straightness of the putty corners and the squareness of the putty room of the corresponding structure in the puttying stage are determined.

[0020] As an optional implementation, in the first aspect of the embodiment of the present invention, after using a three-dimensional laser scanner to collect three-dimensional point clouds of the indoor environment after each stage of construction is completed to obtain corresponding indoor laser point clouds, the method further includes:

[0021] The camera is used to capture images of the indoor environment after each stage of construction is completed to obtain indoor environment images, wherein the indoor environment images include wall images, ceiling images, and ground images;

[0022] Inputting the indoor environment image into a classification and recognition model to perform foreign object recognition, and when a foreign object is detected on the surface of the indoor environment image, performing a data clearing operation on the point cloud position associated with the foreign object, and saving the wall image, ceiling image, and ground image after the foreign object is cleared;

[0023] After determining the flatness data of the corresponding wall surface according to the point cloud distribution map and performing calculations to determine the numerical values ​​of various measurement parameters according to the parameter information of each interface to be detected, the method further includes:

[0024] The point cloud distribution map and the corresponding indoor environment image are displayed.

[0025] As an optional implementation manner, in the first aspect of the embodiment of the present invention, after determining the flatness data of the corresponding wall surface according to the point cloud distribution map and performing calculations to determine the numerical values ​​of various measurement parameters according to the parameter information of each interface to be detected, the method further includes:

[0026] The construction quality score is calculated based on a pre-set quality assessment formula to obtain a corresponding construction quality score; the quality assessment formula is:

[0027]

[0028] Among them, a i is the weight of the measurement indicator, w m is the unqualified point value of the corresponding measurement indicator; w k is the total measurement value of the corresponding measurement index, and X is the construction quality score.

[0029] As an optional implementation manner, in the first aspect of the embodiment of the present invention, after comparing the spatial coordinate information of all indoor laser point clouds at the corresponding interface to be detected with the display reference interface to determine the color value of the corresponding indoor laser point cloud, the method further includes:

[0030] Based on the preset color grading logic, the color values ​​of the laser point cloud are graded to determine the color depth level of the corresponding indoor laser point cloud; the color depth level includes 7 levels of color depth; each level of color is associated with a corresponding value range;

[0031] The image display operation is performed on the corresponding indoor laser point cloud according to the color value and the spatial coordinate information to obtain a point cloud distribution map, including:

[0032] An image display operation is performed on the corresponding indoor laser point cloud according to the color depth level and the spatial coordinate information to obtain a point cloud distribution map.

[0033] As an optional implementation manner, in the first aspect of the embodiment of the present invention, after performing an image display operation on the corresponding indoor laser point cloud according to the color depth level and spatial coordinate information to obtain a point cloud distribution map, the method further includes:

[0034] The point cloud distribution map obtained after the concrete stage is completed is input into the flash point prediction model to obtain the flash point distribution maps of the masonry engineering stage, plastering engineering stage and putty application stage; the flash point prediction model is constructed by the following steps:

[0035] Obtain images of various stages of building construction and corresponding color samples;

[0036] Based on the pre-built feature extraction module, feature extraction is performed on color sample images at various stages of construction to obtain corresponding training feature information;

[0037] The various stages of building construction, the corresponding color sample images and training feature information are input into the pre-built prediction model for training to obtain the burst point prediction model.

[0038] A second aspect of an embodiment of the present invention discloses an intelligent detection system for building construction, comprising:

[0039] 3D acquisition module: used to collect 3D point clouds of the indoor environment after each stage of construction through a 3D laser scanner to obtain the corresponding indoor laser point clouds;

[0040] A calculation module is configured to calculate the spatial coordinate information of the corresponding indoor laser point cloud based on the acquisition position information of the three-dimensional laser scanner and the indoor laser point cloud; and determine the wall surface to which the corresponding indoor laser point cloud belongs based on the spatial coordinate information;

[0041] Interface determination module: used to determine the clustering range based on a randomly selected coordinate on a wall and a set width, and perform a clustering operation on the indoor laser point cloud based on the clustering range and the spatial coordinate information to obtain a to-be-detected interface, wherein the to-be-detected interface is composed of laser point clouds within a preset range, and any one of the horizontal coordinate, vertical coordinate, or vertical coordinate of the to-be-detected interface is within the preset range;

[0042] A reference determination module is configured to determine a display reference interface based on the spatial coordinate information of the laser point cloud in the interface to be detected, and compare the spatial coordinate information of all indoor laser point clouds at the corresponding interface to be detected with the display reference interface to determine the color value of the corresponding indoor laser point cloud;

[0043] Measurement and determination module: used to perform image display operations on the corresponding indoor laser point cloud according to the color value and spatial coordinate information to obtain a point cloud distribution map; and to determine the flatness data of the corresponding wall according to the point cloud distribution map and to perform calculations based on the parameter information of each interface to be detected to determine the numerical value of each measurement parameter.

[0044] A third aspect of an embodiment of the present invention discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the intelligent detection method for construction disclosed in the first aspect of the embodiment of the present invention.

[0045] A fourth aspect of an embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the intelligent detection method for building construction disclosed in the first aspect of the embodiment of the present invention.

[0046] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0047] The intelligent detection method for building construction in the embodiment of the present invention constructs a corresponding point cloud model by collecting three-dimensional point clouds after each stage of building construction is completed, and finally determines the numerical size of each parameter to be measured based on the point cloud parameters; reduces the time spent on repeated detection and improves the overall detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 It is a flowchart of the intelligent detection method for building construction disclosed in an embodiment of the present invention;

[0050] Figure 2 is a schematic diagram of a process for determining display color disclosed in an embodiment of the present invention;

[0051] Figure 3 is a schematic diagram of a flow chart of measurement parameter calculation disclosed in an embodiment of the present invention;

[0052] Figure 4 It is a schematic diagram of the process of image acquisition and recognition disclosed in an embodiment of the present invention;

[0053] Figure 5 is a schematic diagram showing the building facade disclosed in an embodiment of the present invention;

[0054] Figure 6 It is a schematic diagram showing the calculation of indicator data disclosed in an embodiment of the present invention;

[0055] Figure 7 This is a schematic diagram showing a bedroom wall according to an embodiment of the present invention;

[0056] Figure 8 is a schematic diagram of display results of measurement parameters disclosed in an embodiment of the present invention;

[0057] Figure 9 This is a schematic structural diagram of an intelligent detection device for building construction provided by an embodiment of the present invention;

[0058] Figure 10 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0059] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0060] It should be noted that the terms "first," "second," "third," "fourth," etc. in the description and claims of the present invention are used to distinguish different objects rather than to describe a specific order. The terms "including" and "having," as well as any variations thereof, in the embodiments of the present invention, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product, or apparatus.

[0061] Traditional building measurement generally adopts manual measurement, which has the following pain points: First, the overall measurement is time-consuming and labor-intensive, and manual participation and recording are required at each stage; and since there are many people involved in the entire construction process, if the data quality cannot be guaranteed, then multiple parties will have to repeatedly verify the same data, which prolongs the entire construction period; second, since local collection is adopted during the specific implementation, it is impossible to fully reflect the overall construction quality of the building; and a large amount of data will be generated during the subsequent sorting, making it impossible to achieve unified and effective management. Based on this, the embodiment of the present invention discloses an intelligent detection method, device, electronic device and storage medium for building construction, which constructs a corresponding point cloud model by collecting three-dimensional point clouds after each stage of building construction is completed, and finally determines the numerical size of each parameter to be measured based on the point cloud parameters; reduces the time spent on repeated detection and improves the overall detection efficiency.

[0062] Example 1

[0063] See also Figure 1 , Figure 1It is a flow chart of the intelligent detection method for construction disclosed in the embodiment of the present invention. Among them, the execution subject of the method described in the embodiment of the present invention is an execution subject composed of software and / or hardware, which can receive relevant information by wired or / and wireless means, and can send certain instructions. Of course, it can also have certain processing functions and storage functions. The execution subject can control multiple devices, such as a remote physical server or cloud server and related software, or it can be a local host or server and related software that performs related operations on a device placed somewhere. In some scenarios, multiple storage devices can also be controlled, and the storage devices can be placed in the same place or different places as the devices. For example Figure 1 As shown, the intelligent detection method based on building construction includes the following steps:

[0064] S101: Using a 3D laser scanner to collect 3D point clouds of the indoor environment after each stage of construction is completed to obtain corresponding indoor laser point clouds;

[0065] In the embodiments of the present invention, 3D point clouds are primarily collected using a 3D laser scanner. This greatly improves data collection efficiency, making tasks previously impossible for a single person feasible. Furthermore, because objective data is scanned, subsequent data verification can be performed directly using the corresponding data without the need for on-site measurements, thereby improving overall construction efficiency.

[0066] More preferably, Figure 4 FIG. 1 is a flow chart of image acquisition and recognition disclosed in an embodiment of the present invention; Figure 4 As shown, after the three-dimensional point cloud acquisition of the indoor environment after each stage of the building construction is completed by the three-dimensional laser scanner to obtain the corresponding indoor laser point cloud, the method further includes:

[0067] S1011: Capturing images of the indoor environment after each stage of building construction using a camera to obtain indoor environment images, wherein the indoor environment images include wall images, ceiling images, and floor images;

[0068] S1012: Inputting the indoor environment image into a classification and recognition model to perform foreign object recognition. When a foreign object is detected on the surface of the indoor environment image, performing a data clearing operation on the point cloud position associated with the foreign object, and saving the wall image, ceiling image, and ground image after the foreign object is cleared.

[0069] The above steps are mainly for clearing foreign objects when they appear in the scene. For example, when a small stone is identified on the ground or a stone on the wall is forgotten to be cleared, the presence of the stone will reduce the overall measurement accuracy, which is also extremely detrimental to the accuracy of subsequent burst point prediction. Therefore, foreign object removal is required to clear the corresponding points.

[0070] After determining the flatness data of the corresponding wall surface according to the point cloud distribution map and performing calculations to determine the numerical values ​​of various measurement parameters according to the parameter information of each interface to be detected, the method further includes:

[0071] S106: Displaying the point cloud distribution map and the corresponding indoor environment image.

[0072] In specific implementation, it can not only provide a single display image for users to view, but also combine it with the corresponding indoor environment image for comprehensive display, so that users can have a more intuitive viewing experience; rather than just a simple point cloud heat distribution map, it can more effectively help users grasp the progress.

[0073] S102: Calculating spatial coordinate information of a corresponding indoor laser point cloud based on the acquisition position information of the 3D laser scanner and the indoor laser point cloud; and determining a wall surface to which the corresponding indoor laser point cloud belongs based on the spatial coordinate information;

[0074] S103: Determine a clustering range based on a randomly selected coordinate on a wall and a set width, and perform a clustering operation on the indoor laser point cloud based on the clustering range and the spatial coordinate information to obtain a to-be-detected interface, wherein the to-be-detected interface is composed of laser point clouds within a preset range, and any one of the horizontal coordinate, vertical coordinate, or vertical coordinate of the to-be-detected interface is within the preset range;

[0075] S104: determining a display reference interface according to the spatial coordinate information of the laser point cloud in the interface to be detected, and comparing the spatial coordinate information of all indoor laser point clouds at the corresponding interface to be detected with the display reference interface to determine the color value of the corresponding indoor laser point cloud;

[0076] More preferably, Figure 2 : is a schematic diagram of the process of determining the display color disclosed in the embodiment of the present invention; Figure 2 As shown, the display reference interface is determined according to the spatial coordinate information of the laser point cloud in the interface to be detected, and the spatial coordinate information of all indoor laser point clouds at the corresponding interface to be detected is compared with the display reference interface to determine the color value of the corresponding indoor laser point cloud, including:

[0077] S1041: When the interface to be detected is an interface to be detected in a first direction, obtain an orientation coordinate set of the laser point cloud in the interface to be detected and associated with the first direction according to the first direction; the first direction here can be horizontal or vertical, etc., which is intended to represent the laser point cloud coordinates at a certain side wall, floor or ceiling in the room. Only after knowing the coordinates of the corresponding interface can further depth judgment be made.

[0078] S1042: Obtain the azimuth coordinate data with the same value and the largest number in the azimuth coordinate set, and construct a corresponding display reference interface based on the azimuth coordinate data; that is, when performing specific implementation, it is necessary to first determine the reference plane. The reference plane here can be a set reference plane, but a more convenient measurement method is to use coordinate data with the same value to determine the reference interface; for example, when it is necessary to judge the point cloud data on the ceiling, what needs to be judged is the status of the vertical coordinate of the point cloud data associated with the ceiling; extract the surface of the ceiling point cloud with the largest number of identical vertical coordinates as the reference plane, and the reference plane can be used as the basis for subsequent data judgment. Here, the surface with the largest number of identical vertical coordinates can also be directly used as the reference coordinate for subsequent comparison and judgment.

[0079] S1043: Compare the spatial coordinate information of all indoor laser point clouds at the interface to be detected with the display reference interface; if the spatial coordinate information of the corresponding indoor laser point cloud is higher than the display reference interface, configure the first color parameter for the corresponding laser point cloud; if the spatial coordinate information of the corresponding indoor laser point cloud is lower than the display reference interface, configure the second color parameter for the corresponding laser point cloud; S1044: Determine the color depth value according to the difference between the spatial coordinate information of the laser point cloud and the display reference page, and obtain the corresponding color parameter according to the color depth value, the first color parameter and the second color parameter.

[0080] After the corresponding reference plane is determined, it can be compared and judged and then the corresponding color can be configured for it. When the corresponding coordinates are relatively concave, it is configured with blue, and when the corresponding coordinates are relatively convex, it is configured with red. And the color depth can also be adjusted in combination with the numerical difference. When adjusting the color application, there are many ways to implement it, such as using a stepless color setting method or a multi-level segmentation setting. The stepless color setting means that each depth value corresponds to a color, and different values ​​correspond to different color depths; the multi-level segmentation setting means that each numerical interval corresponds to a color, which means that although the depth values ​​are different, they may point to the same color. The stepless method can better reflect the differences; the hierarchical segmentation method can make the final rendering display faster.

[0081] S105: Perform an image display operation on the corresponding indoor laser point cloud according to the color value and spatial coordinate information to obtain a point cloud distribution map; determine the flatness data of the corresponding wall according to the point cloud distribution map, and perform calculations based on the parameter information of each interface to be detected to determine the numerical value of each measurement parameter.

[0082] like Figure 5 As shown in the figure, it is to obtain and compare the corresponding parameters of the exterior wall. When it is implemented, it only takes 2 minutes to obtain the exterior wall flatness report, and can combine the point cloud distribution map and the measurement parameter results to assist in providing rectification suggestions to improve the overall building appearance. Figure 7 As shown, it is the measurement display result of the bedroom wall, where 1 refers to the specific measurement parameter, 2 represents the wall protrusion, and the data in the box represents the protrusion number, and its value is set according to the actual situation. Although it is not clearly shown in the figure, it is known that it can be displayed with the corresponding value. It is only a schematic result; 3 represents the wall depression, and the same box has a corresponding value to indicate the specific depression depth. Even different values ​​can be highlighted to make it more convenient for users to view.

[0083] More preferably, Figure 3 Schematic diagram of the flow of measurement parameter calculation disclosed in the embodiment of the present invention; Figure 3 As shown, the various stages of the construction process include the concrete stage, the masonry stage, the plastering stage, and the puttying stage; the flatness data of the corresponding wall surface is determined based on the point cloud distribution map, and the numerical values ​​of various measurement parameters are determined based on the parameter information of each interface to be detected, including:

[0084] S1051: Determine the wall verticality, wall flatness, squareness, top plate horizontality, external window opening extremes and bay depth of the corresponding structure in the concrete stage based on the point cloud distribution map and the parameter information of each interface to be detected; the multiple parameters here have their corresponding standard ranges, such as the standard range for wall verticality is verticality less than or equal to 8mm; the standard range for wall flatness is flatness less than or equal to 8mm; the standard range for squareness is squareness less than or equal to 10mm; the standard range for top plate horizontality is horizontality less than or equal to 10mm; the standard range for external window opening extremes is opening extremes between plus or minus 15mm; the standard range for bay depth is depth less than or equal to 10mm.

[0085] S1052: Determine the verticality of the masonry, the flatness of the masonry surface, and the extreme difference of the external window openings of the corresponding structure during the masonry construction stage based on the point cloud distribution map and the parameter information of each interface to be detected; the multiple parameters here have their corresponding standard ranges, such as the standard range for the verticality of the masonry is that the verticality is less than or equal to 5mm; the standard range for the flatness of the masonry is that the flatness is less than or equal to 8mm; the standard range for the extreme difference of the external window opening is that the extreme difference of the opening is between plus or minus 15mm.

[0086] S1053: Determine the verticality of the plastering facade, the flatness of the plastering surface, the squareness of the plastering room, the straightness of the plastering corners, the extreme difference in doorway width, the net height of the plastering room, the horizontality of the plastering top plate, the big and small ends of the plastering windows, the elevation difference of the bottom box in the same room, and the depth of the bay according to the point cloud distribution map and the parameter information of each interface to be detected during the plastering engineering stage of the corresponding structure; the multiple parameters here have their corresponding standard ranges, such as the standard range of the verticality of the plastering is verticality less than or equal to 4mm; the standard range of the flatness of the plastering is flatness less than or equal to 4mm; the squareness of the plastering room (vertical plastering is measured by the reference plastering) is less than or equal to 4mm. The standard range is squareness less than or equal to 10mm; the standard range of straightness of plastered inside and outside corners is straightness less than or equal to 4mm; the standard range of width extreme difference of door opening is width extreme difference between plus or minus 5mm; the net height of plastered room (based on the one-meter line of the building) is between plus or minus 20mm; the standard range of horizontality of plastered top plate is horizontality less than or equal to 10mm; the standard range of large and small heads of plastered windows is less than or equal to 6mm; the elevation difference of base boxes in the same room is less than or equal to 5mm; the standard range of bay depth is depth less than or equal to 10mm, and the standard range of door opening height extreme difference and design value deviation is between plus or minus 10mm.

[0087] S1054: Determine the verticality of the putty facade, the flatness of the putty surface, the horizontality / flatness of the ceiling, the three sides and two lines, the squareness of the putty inner and outer corners, the straightness of the putty inner and outer corners, and the squareness of the putty room according to the point cloud distribution map and the parameter information of each interface to be detected. The standard interval for the verticality of the putty facade is less than or equal to 3mm, the standard interval for the flatness of the putty surface is less than or equal to 3mm, the standard interval for the horizontality / flatness of the ceiling is less than or equal to 10mm, the standard interval for the three sides and two lines (baseboards, door trims) is less than or equal to 2mm, the standard interval for the squareness of the putty inner and outer corners is less than or equal to 3mm, the standard interval for the straightness of the putty inner and outer corners is less than or equal to 3mm, and the standard interval for the squareness of the putty room is less than or equal to 10mm. Perform a square operation on the kitchen and bathroom to determine whether they are square, and use the Pythagorean theorem to calculate and determine whether they are square.

[0088] More preferably, after determining the flatness data of the corresponding wall surface according to the point cloud distribution map and performing calculations to determine the numerical values ​​of various measurement parameters according to the parameter information of each interface to be detected, the method further includes:

[0089] The construction quality score is calculated based on a pre-set quality assessment formula to obtain a corresponding construction quality score; the quality assessment formula is:

[0090]

[0091] Among them, a i is the weight of the measurement indicator, w m is the unqualified point value of the corresponding measurement indicator; w k is the total measurement value of the corresponding measurement index, and X is the construction quality score. Here, a1 is the weight coefficient of the wall flatness, a2 is the weight coefficient of the wall verticality, a3 is the weight coefficient of the opening size deviation, a4 is the weight coefficient of the door and window opening size extreme difference, a5 is the weight coefficient of the squareness, a6 is the weight coefficient of the top plate horizontality, a7 is the weight coefficient of the ground horizontality, a8 is the weight coefficient of the Yin-Yang angle, and a9 is the weight coefficient of the bay depth; the final score item is determined by comparing the qualified points with the unqualified points of the above indicator categories, and the weights of the above multiple parameters can be set to 25%, 25%, 5%, 10%, 5%, 5%, 10%, 20%, and 10%. The corresponding quality score can be calculated using the above parameters, and the specific results are shown as follows: Figure 6 In addition to the above result presentation methods, you can also Figure 8 The presentation method shown is shown, and the value can be presented in real time at the customer's terminal for the user to view.

[0092] More preferably, after comparing the spatial coordinate information of all indoor laser point clouds at the corresponding interface to be detected with the display reference interface to determine the color value of the corresponding indoor laser point cloud, the method further includes:

[0093] Based on the preset color grading logic, the color values ​​of the laser point cloud are graded to determine the color depth level of the corresponding indoor laser point cloud; the color depth level includes 7 levels of color depth; each level of color is associated with a corresponding value range;

[0094] The performing an image display operation on the corresponding indoor laser point cloud according to the color value and the spatial coordinate information to obtain a point cloud distribution map includes:

[0095] An image display operation is performed on the corresponding indoor laser point cloud according to the color depth level and the spatial coordinate information to obtain a point cloud distribution map.

[0096] A multi-level setting method is used here to match the colors of different intervals. This method can make the characteristics of the corresponding point cloud distribution map more obvious, and also facilitate the subsequent burst point prediction.

[0097] More preferably, after performing an image display operation on the corresponding indoor laser point cloud according to the color depth level and the spatial coordinate information to obtain a point cloud distribution map, the method further includes:

[0098] The point cloud distribution map obtained after the concrete stage is completed is input into the flash point prediction model to obtain the flash point distribution maps of the masonry engineering stage, plastering engineering stage and putty application stage; the flash point prediction model is constructed by the following steps:

[0099] Obtain images of various stages of building construction and corresponding color samples;

[0100] Based on the pre-built feature extraction module, feature extraction is performed on color sample images at various stages of construction to obtain corresponding training feature information;

[0101] The various stages of building construction, the corresponding color sample images and training feature information are input into the pre-built prediction model for training to obtain the burst point prediction model.

[0102] By inputting the obtained point cloud distribution map into the flash point prediction model, the corresponding flash point prediction is carried out, thereby predicting the flash points that may exist in the subsequent stages; it is convenient for the construction team to discover the corresponding problems in time and make timely remedies. It can improve the efficiency and speed of the overall construction from a higher level, and greatly reduce the occurrence of unqualified situations.

[0103] The intelligent detection method for building construction in the embodiment of the present invention constructs a corresponding point cloud model by collecting three-dimensional point clouds after each stage of building construction is completed, and finally determines the numerical size of each parameter to be measured based on the point cloud parameters; reduces the time spent on repeated detection and improves the overall detection efficiency.

[0104] Example 2

[0105] See also Figure 9 , Figure 9 This is a schematic diagram of the structure of the intelligent detection device for building construction disclosed in an embodiment of the present invention. Figure 9 As shown, the intelligent detection device for building construction may include:

[0106] 3D acquisition module: used to collect 3D point clouds of the indoor environment after each stage of construction through a 3D laser scanner to obtain the corresponding indoor laser point clouds;

[0107] A calculation module is configured to calculate the spatial coordinate information of the corresponding indoor laser point cloud based on the acquisition position information of the three-dimensional laser scanner and the indoor laser point cloud; and determine the wall surface to which the corresponding indoor laser point cloud belongs based on the spatial coordinate information;

[0108] Interface determination module: used to determine the clustering range based on a randomly selected coordinate on a wall and a set width, and perform a clustering operation on the indoor laser point cloud based on the clustering range and the spatial coordinate information to obtain a to-be-detected interface, wherein the to-be-detected interface is composed of laser point clouds within a preset range, and any one of the horizontal coordinate, vertical coordinate, or vertical coordinate of the to-be-detected interface is within the preset range;

[0109] A reference determination module is configured to determine a display reference interface based on the spatial coordinate information of the laser point cloud in the interface to be detected, and compare the spatial coordinate information of all indoor laser point clouds at the corresponding interface to be detected with the display reference interface to determine the color value of the corresponding indoor laser point cloud;

[0110] Measurement and determination module: used to perform image display operations on the corresponding indoor laser point cloud according to the color value and spatial coordinate information to obtain a point cloud distribution map; and to determine the flatness data of the corresponding wall according to the point cloud distribution map and to perform calculations based on the parameter information of each interface to be detected to determine the numerical value of each measurement parameter.

[0111] More preferably, the method of determining a display reference interface based on the spatial coordinate information of the laser point cloud in the interface to be detected, and comparing the spatial coordinate information of all indoor laser point clouds at the corresponding interface to be detected with the display reference interface to determine the color value of the corresponding indoor laser point cloud includes:

[0112] A direction acquisition module: when the interface to be detected is an interface to be detected in a first direction, acquires a set of direction coordinates associated with the laser point cloud in the interface to be detected and the first direction according to the first direction;

[0113] A reference acquisition module is used to acquire the largest number of azimuth coordinate data with the same value in the azimuth coordinate set, and to construct a corresponding display reference interface based on the azimuth coordinate data;

[0114] Comparison module: used to compare the spatial coordinate information of all indoor laser point clouds at the interface to be detected with the display reference interface, and if the spatial coordinate information of the corresponding indoor laser point cloud is higher than the display reference interface, configure the first color parameter for the corresponding laser point cloud; if the spatial coordinate information of the corresponding indoor laser point cloud is lower than the display reference interface, configure the second color parameter for the corresponding laser point cloud;

[0115] Depth determination module: used to determine the color depth value according to the difference between the spatial coordinate information of the laser point cloud and the display reference page, and obtain the corresponding color parameter according to the color depth value, the first color parameter and the second color parameter.

[0116] More preferably, the various stages of the building construction include a concrete stage, a masonry engineering stage, a plastering engineering stage, and a puttying stage; the determining of the flatness data of the corresponding wall surface based on the point cloud distribution map and the calculation to determine the numerical value of each measurement parameter based on the parameter information of each interface to be detected include:

[0117] A first parameter calculation module is used to determine the wall verticality, wall flatness, squareness, top plate horizontality, external window opening range and bay depth of the corresponding structure in the concrete stage based on the point cloud distribution map and parameter information of each interface to be detected;

[0118] The second parameter calculation module is used to determine the verticality of the masonry, the flatness of the masonry surface and the extreme difference of the external window openings of the corresponding structure during the masonry engineering stage based on the point cloud distribution map and the parameter information of each interface to be detected;

[0119] The third parameter calculation module is used to determine the verticality of the plastered facade, the flatness of the plastered surface, the squareness of the plastered room, the straightness of the plastered inner and outer corners, the maximum difference in doorway width, the net height of the plastered room, the horizontality of the plastered ceiling, the greater and lesser ends of the plastered windows, the elevation difference of the bottom box in the same room, and the depth of the bay during the plastering engineering stage of the corresponding structure based on the point cloud distribution map and the parameter information of each interface to be detected;

[0120] The fourth parameter calculation module is used to determine the verticality of the putty facade, the flatness of the putty surface, the horizontality / flatness of the ceiling, the three sides and two lines, the squareness of the putty corners, the straightness of the putty corners and the squareness of the putty room of the corresponding structure in the puttying stage according to the point cloud distribution map and the parameter information of each interface to be detected.

[0121] More preferably, after the three-dimensional point cloud acquisition of the indoor environment after each stage of the building construction is completed by the three-dimensional laser scanner to obtain the corresponding indoor laser point cloud, the method further includes:

[0122] Image acquisition module: used to acquire images of the indoor environment after each stage of construction is completed through a camera to obtain indoor environment images, wherein the indoor environment images include wall images, ceiling images and ground images;

[0123] Foreign object recognition module: used to input the indoor environment image into the classification recognition model to perform foreign object recognition. When a foreign object is detected on the surface of the indoor environment image, a data clearing operation is performed on the point cloud position associated with the foreign object, and the wall image, ceiling image and ground image after the foreign object is cleared are saved;

[0124] After determining the flatness data of the corresponding wall surface according to the point cloud distribution map and performing calculations to determine the numerical values ​​of various measurement parameters according to the parameter information of each interface to be detected, the method further includes:

[0125] Display module: used to display the point cloud distribution map and the corresponding indoor environment image.

[0126] More preferably, after determining the flatness data of the corresponding wall surface according to the point cloud distribution map and performing calculations to determine the numerical values ​​of various measurement parameters according to the parameter information of each interface to be detected, the method further includes:

[0127] The construction quality score is calculated based on a pre-set quality assessment formula to obtain a corresponding construction quality score; the quality assessment formula is:

[0128]

[0129] Among them, a i is the weight of the measurement indicator, w m is the unqualified point value of the corresponding measurement indicator; w k is the total measurement value of the corresponding measurement index, and X is the construction quality score.

[0130] More preferably, after comparing the spatial coordinate information of all indoor laser point clouds at the corresponding interface to be detected with the display reference interface to determine the color value of the corresponding indoor laser point cloud, the method further includes:

[0131] Grading processing module: used to grade the color values ​​of the laser point cloud based on the pre-set color grading logic to determine the color depth level of the corresponding indoor laser point cloud; the color depth level includes 7 levels of color depth; each level of color is associated with a corresponding value range;

[0132] The performing an image display operation on the corresponding indoor laser point cloud according to the color value and the spatial coordinate information to obtain a point cloud distribution map includes:

[0133] An image display operation is performed on the corresponding indoor laser point cloud according to the color depth level and the spatial coordinate information to obtain a point cloud distribution map.

[0134] More preferably, after performing an image display operation on the corresponding indoor laser point cloud according to the color depth level and the spatial coordinate information to obtain a point cloud distribution map, the method further includes:

[0135] The flash point prediction module is used to input the point cloud distribution map obtained after the concrete stage into the flash point prediction model to obtain the flash point distribution maps of the masonry engineering stage, plastering engineering stage, and puttying stage. The flash point prediction model is constructed by the following steps:

[0136] Sample acquisition module: used to obtain various stages of building construction and corresponding color sample images;

[0137] Feature extraction module: used to extract features from color sample images at various stages of building construction based on a pre-built feature extraction module to obtain corresponding training feature information;

[0138] Model building module: used to input various stages of building construction, corresponding color sample images and training feature information into a pre-built prediction model for training to obtain a flash point prediction model.

[0139] The intelligent detection method for building construction in the embodiment of the present invention constructs a corresponding point cloud model by collecting three-dimensional point clouds after each stage of building construction is completed, and finally determines the numerical size of each parameter to be measured based on the point cloud parameters; reduces the time spent on repeated detection and improves the overall detection efficiency.

[0140] Example 3

[0141] See also Figure 10 , Figure 10 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention. The electronic device can be a computer, a server, etc. Of course, in certain circumstances, it can also be a smart device such as a mobile phone, a tablet computer, a monitoring terminal, and an image acquisition device with processing functions. Figure 10 As shown, the electronic device may include:

[0142] A memory 510 storing executable program code;

[0143] a processor 520 coupled to the memory 510;

[0144] The processor 520 calls the executable program code stored in the memory 510 to execute part or all of the steps in the intelligent detection method for building construction in the first embodiment.

[0145] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute some or all of the steps in the intelligent detection method for building construction in the first embodiment.

[0146] An embodiment of the present invention further discloses a computer program product, wherein when the computer program product is run on a computer, the computer is caused to execute some or all of the steps in the intelligent detection method for building construction in the first embodiment.

[0147] An embodiment of the present invention also discloses an application publishing platform, wherein the application publishing platform is used to publish a computer program product, wherein when the computer program product runs on a computer, the computer executes some or all of the steps in the intelligent detection method for construction in embodiment one.

[0148] In various embodiments of the present invention, it should be understood that the size of the serial numbers of the processes does not necessarily mean the order of execution. The order of execution 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 the present invention.

[0149] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of these units may be selected based on actual needs to achieve the objectives of this embodiment.

[0150] In addition, the functional units in the embodiments of the present invention may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The integrated unit may be implemented in the form of hardware or software functional units.

[0151] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a memory and includes several requests for causing a computer device (which can be a personal computer, server, or network device, specifically a processor in the computer device) to execute some or all of the steps of the method described in each embodiment of the present invention.

[0152] In the embodiments provided herein, it should be understood that "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should also be understood that determining B based on A does not mean determining B based solely on A; B can also be determined based on A and / or other information.

[0153] Those skilled in the art will appreciate that some or all of the steps in the various methods of the embodiments may be performed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, such as a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0154] The above is a detailed introduction to the intelligent detection method, device, electronic device and storage medium for construction disclosed in the embodiments of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. An intelligent detection method for building construction, characterized in that: include: Use a 3D laser scanner to collect 3D point clouds of the indoor environment after each stage of construction to obtain the corresponding indoor laser point clouds; Calculating spatial coordinate information of a corresponding indoor laser point cloud based on the acquisition position information of the three-dimensional laser scanner and the indoor laser point cloud; and determining the wall surface to which the corresponding indoor laser point cloud belongs based on the spatial coordinate information; Determine a clustering range based on a randomly selected coordinate on a wall and a set width, and perform a clustering operation on the indoor laser point cloud based on the clustering range and the spatial coordinate information to obtain a to-be-detected interface, wherein the to-be-detected interface is composed of laser point clouds within a preset range, and any one of the horizontal coordinate, vertical coordinate, or vertical coordinate of the to-be-detected interface is within the preset range; Determine a display reference interface according to the spatial coordinate information of the laser point cloud in the interface to be detected, and compare the spatial coordinate information of all indoor laser point clouds at the corresponding interface to be detected with the display reference interface to determine the color value of the corresponding indoor laser point cloud; The corresponding indoor laser point cloud is image displayed according to the color value and spatial coordinate information to obtain a point cloud distribution map; the flatness data of the corresponding wall is determined according to the point cloud distribution map, and the numerical value of each measurement parameter is determined according to the parameter information of each interface to be detected.

2. The intelligent detection method for building construction according to claim 1, characterized in that: The method of determining a display reference interface according to the spatial coordinate information of the laser point cloud in the interface to be detected, and comparing the spatial coordinate information of all indoor laser point clouds at the corresponding interface to be detected with the display reference interface to determine the color value of the corresponding indoor laser point cloud, includes: When the interface to be detected is an interface to be detected in a first direction, obtaining an azimuth coordinate set associated with the laser point cloud in the interface to be detected and the first direction according to the first direction; Acquire the largest number of azimuth coordinate data with the same value in the azimuth coordinate set, and construct a corresponding display reference interface based on the azimuth coordinate data; Comparing the spatial coordinate information of all indoor laser point clouds at the interface to be detected with the display reference interface, if the spatial coordinate information of the corresponding indoor laser point cloud is higher than the display reference interface, configuring a first color parameter for the corresponding laser point cloud; if the spatial coordinate information of the corresponding indoor laser point cloud is lower than the display reference interface, configuring a second color parameter for the corresponding laser point cloud; The color depth value is determined according to the difference between the spatial coordinate information of the laser point cloud and the display reference page, and the corresponding color parameter is obtained according to the color depth value, the first color parameter and the second color parameter.

3. The intelligent detection method for building construction according to claim 2, characterized in that: The various stages of building construction include the concrete stage, the masonry engineering stage, the plastering engineering stage, and the puttying stage; the flatness data of the corresponding wall surface is determined based on the point cloud distribution map, and the numerical values ​​of various measurement parameters are determined based on the parameter information of each interface to be detected, including: Determine the wall verticality, wall flatness, squareness, top plate horizontality, external window opening range and bay depth of the corresponding structure at the concrete stage based on the point cloud distribution map and parameter information of each interface to be tested; Determine the verticality of the masonry, the flatness of the masonry surface, and the extreme difference of the external window openings of the corresponding structure during the masonry engineering stage based on the point cloud distribution map and the parameter information of each interface to be detected; According to the point cloud distribution map and the parameter information of each interface to be detected, the verticality of the plastered facade, the flatness of the plastered surface, the squareness of the plastered room, the straightness of the plastered inner and outer corners, the maximum width of the door opening, the net height of the plastered room, the horizontality of the plastered top plate, the large and small ends of the plastered windows, the elevation difference of the bottom box in the same room, and the depth of the bay are determined. According to the point cloud distribution map and the parameter information of each interface to be detected, the verticality of the putty facade, the flatness of the putty surface, the horizontality / flatness of the ceiling, the three sides and two lines, the squareness of the putty corners, the straightness of the putty corners and the squareness of the putty room of the corresponding structure in the puttying stage are determined.

4. The intelligent detection method for building construction according to claim 1, characterized in that: After the three-dimensional point cloud acquisition of the indoor environment after each stage of the building construction is completed by the three-dimensional laser scanner to obtain the corresponding indoor laser point cloud, the method further includes: The camera is used to capture images of the indoor environment after each stage of construction is completed to obtain indoor environment images, wherein the indoor environment images include wall images, ceiling images, and ground images; Inputting the indoor environment image into a classification and recognition model to perform foreign object recognition, and when a foreign object is detected on the surface of the indoor environment image, performing a data clearing operation on the point cloud position associated with the foreign object, and saving the wall image, ceiling image, and ground image after the foreign object is cleared; After determining the flatness data of the corresponding wall surface according to the point cloud distribution map and performing calculations to determine the numerical values ​​of various measurement parameters according to the parameter information of each interface to be detected, the method further includes: The point cloud distribution map and the corresponding indoor environment image are displayed.

5. The intelligent detection method for building construction according to claim 1, characterized in that: After determining the flatness data of the corresponding wall surface according to the point cloud distribution map and performing calculations to determine the numerical values ​​of various measurement parameters according to the parameter information of each interface to be detected, the method further includes: The construction quality score is calculated based on a pre-set quality assessment formula to obtain a corresponding construction quality score; the quality assessment formula is: Among them, a i is the weight of the measurement indicator, w m is the unqualified point value of the corresponding measurement indicator; w k is the total measurement value of the corresponding measurement index, and X is the construction quality score.

6. The intelligent detection method for building construction according to claim 2, characterized in that: After comparing the spatial coordinate information of all indoor laser point clouds at the corresponding interface to be detected with the display reference interface to determine the color value of the corresponding indoor laser point cloud, the method further includes: Based on the preset color grading logic, the color value of the laser point cloud is graded to determine the color depth level of the corresponding indoor laser point cloud; the color depth level includes 7 levels of color depth; each level of color is associated with a corresponding value range; The image display operation is performed on the corresponding indoor laser point cloud according to the color value and the spatial coordinate information to obtain a point cloud distribution map, including: An image display operation is performed on the corresponding indoor laser point cloud according to the color depth level and the spatial coordinate information to obtain a point cloud distribution map.

7. The intelligent detection method for building construction according to claim 6, characterized in that: After performing an image display operation on the corresponding indoor laser point cloud according to the color depth level and the spatial coordinate information to obtain a point cloud distribution map, the method further includes: The point cloud distribution map obtained after the concrete stage is completed is input into the flash point prediction model to obtain the flash point distribution maps of the masonry engineering stage, plastering engineering stage and putty application stage; the flash point prediction model is constructed by the following steps: Obtain images of various stages of building construction and corresponding color samples; Based on the pre-built feature extraction module, feature extraction is performed on color sample images at various stages of construction to obtain corresponding training feature information; The various stages of building construction, the corresponding color sample images and training feature information are input into the pre-built prediction model for training to obtain the burst point prediction model.

8. An intelligent detection system for building construction, characterized in that: include: 3D acquisition module: used to collect 3D point clouds of indoor environments after each stage of construction through a 3D laser scanner to obtain corresponding indoor laser point clouds; A calculation module is configured to calculate the spatial coordinate information of the corresponding indoor laser point cloud based on the acquisition position information of the three-dimensional laser scanner and the indoor laser point cloud; and determine the wall surface to which the corresponding indoor laser point cloud belongs based on the spatial coordinate information; Interface determination module: used to determine the clustering range based on a randomly selected coordinate on a wall and a set width, and perform a clustering operation on the indoor laser point cloud based on the clustering range and the spatial coordinate information to obtain a to-be-detected interface, wherein the to-be-detected interface is composed of laser point clouds within a preset range, and any one of the horizontal coordinate, vertical coordinate, or vertical coordinate of the to-be-detected interface is within the preset range; A reference determination module is configured to determine a display reference interface based on the spatial coordinate information of the laser point cloud in the interface to be detected, and compare the spatial coordinate information of all indoor laser point clouds at the corresponding interface to be detected with the display reference interface to determine the color value of the corresponding indoor laser point cloud; Measurement and determination module: used to perform image display operations on the corresponding indoor laser point cloud according to the color value and spatial coordinate information to obtain a point cloud distribution map; and to determine the flatness data of the corresponding wall according to the point cloud distribution map and to perform calculations based on the parameter information of each interface to be detected to determine the numerical value of each measurement parameter.

9. An electronic device, characterized in that: include: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent detection method for building construction according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein the computer program enables a computer to execute the intelligent detection method for building construction according to any one of claims 1 to 7.

Images