Construction monitoring method, device and storage medium based on three-dimensional point cloud

Abstract

The present invention provides a construction monitoring method, equipment and storage medium based on 3D point cloud, which relates to the technical field of information-based supervision of construction projects, including: generating a 3D point cloud of a building to be constructed, fitting the basic shape of the building based on the 3D point cloud of the building to be constructed, there being a point cloud subset in the 3D point cloud of the building to be constructed that obeys the distribution of the basic shape of the building, detecting that the ratio of the number of points occupied by the point cloud subset in the 3D point cloud of the building to be constructed is not less than a preset threshold, generating a construction elevation index and a construction elevation index respectively, and then analyzing whether the horizontal deviation of the building under construction exceeds the standard. Compared with some existing construction monitoring methods, there is no need to remove point clouds under manual intervention, eliminating the extremely complex fully automated point cloud alignment process, eliminating the need to process alternative data operations, greatly improving the compatibility and simplicity of monitoring construction, and helping to reduce monitoring costs and promote application.

Description

[0001] This application is a divisional application of Chinese invention patent application 202211062396.3, filed on September 1, 2022, with the invention name of “Construction monitoring methods, devices, equipment and products based on three-dimensional point cloud”. Technical Field

[0002] The present invention relates to the technical field of information-based supervision of construction projects, and in particular to a method, device and storage medium for monitoring construction based on three-dimensional point clouds. Background Art

[0003] Usually, at a construction site, a building entity that has been constructed but not yet completed is a building under construction. The underground building part (for example, foundation and underground parking lot, etc.) and the above-ground building part (for example, walls, columns, floor slabs, beams and roof, etc.) are constructed in stages. Taking into account the construction period, safety and stability, it is particularly important to supervise the progress and quality of the construction. Relying on intelligent measuring instruments and information processing programs to monitor buildings under construction saves time and effort, and helps to rationalize the construction progress and / or discover construction quality problems early.

[0004] Some construction monitoring methods focus on construction progress or construction quality. Among them, the construction progress monitoring method generally requires at least two of three-dimensional point clouds, images, BIM models and construction plan charts, focusing on the time dimension and / or height and / or indoor and outdoor progress differences, for example, identifying whether the construction progress is ahead of schedule, behind schedule or normal, or whether it is not yet planned for construction and has been completed; the construction quality monitoring method uses instruments and procedures that are very different from the construction progress monitoring method, focusing on the tilt or offset of the building. For example, the tilt detection device is vertically installed on the building wall to automatically measure the tilt of the building under construction and alarm when the tilt is excessive, or, after measuring the offset distance of the building with radar, the offset distance is compared with the benchmark distance value to obtain the building offset.

[0005] However, existing construction monitoring methods have many defects: first, the construction site may be extremely complex. For example, due to interference from debris, it is difficult for the three-dimensional point cloud to fully reflect the building under construction. The interference of debris is obvious, and it is easy to make mistakes and inefficient to remove the debris under manual intervention. The use of a fully automatic point cloud registration algorithm is extremely complex and the monitoring difficulty is relatively large. Second, the construction progress and quality are monitored separately, which lacks compatibility, increases the complexity and cost of monitoring, and is not conducive to promotion and application. Summary of the invention

[0006] The present invention aims to solve the technical problems in the related art at least to a certain extent. To achieve the above purpose, the present invention provides a construction monitoring method based on three-dimensional point cloud, a computing device and a computer-readable storage medium.

[0007] In a first aspect, the present invention provides a construction monitoring method based on three-dimensional point cloud, comprising:

[0008] generating a three-dimensional point cloud of a proposed building suitable for indicating a building under construction;

[0009] Fitting the basic shape of the building under construction based on the three-dimensional point cloud of the building to be simulated, wherein there is a point cloud subset in the three-dimensional point cloud of the building to be simulated that obeys the distribution of the basic shape of the building;

[0010] After detecting that the ratio of the number of points occupied by the point cloud subset in the three-dimensional point cloud of the proposed building is not less than a preset threshold, generating a construction elevation index and a construction elevation index for the basic form of the building under construction respectively;

[0011] If the construction offset index is greater than a preset offset threshold, the horizontal offset of the building under construction exceeds the standard; otherwise, the horizontal offset of the building under construction is qualified.

[0012] In a second aspect, the present invention provides a computing device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the three-dimensional point cloud-based construction monitoring method described in the first aspect is implemented.

[0013] In a third aspect, the present invention provides a computer-readable storage medium, which includes a computer program executable by a processor, and when the computer program is executed, the three-dimensional point cloud-based construction monitoring method described in the first aspect is implemented.

[0014] By using the above-mentioned three-dimensional point cloud-based construction monitoring method, computing equipment and computer-readable storage medium, there is no need to eliminate point clouds under human intervention, which eliminates the extremely complex fully automated point cloud alignment process and the processing of alternative data operations, greatly improving the compatibility and simplicity of monitoring construction, and helping to reduce monitoring costs and promote application. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of a flow chart of a construction monitoring method based on three-dimensional point cloud according to an embodiment of the present invention;

[0016] Figure 2 A schematic diagram of a flow chart of another method for monitoring construction based on three-dimensional point clouds according to an embodiment of the present invention;

[0017] Figure 3 It is a geometric diagram of three points projected onto the axis in an embodiment of the present invention;

[0018] Figure 4 A schematic diagram of a flow chart of another method for monitoring construction based on three-dimensional point clouds according to an embodiment of the present invention;

[0019] Figure 5 A schematic diagram of a flow chart of another method for monitoring construction based on three-dimensional point clouds according to an embodiment of the present invention;

[0020] Figure 6 It is a geometric schematic diagram of the pre-designed cylinder and the basic shape of the building under construction in the point cloud coordinate system of an embodiment of the present invention;

[0021] Figure 7 A schematic diagram of the architecture of a building construction monitoring device based on three-dimensional point cloud according to an embodiment of the present invention;

[0022] Figure 8 The present invention is a circuit diagram of a computing device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings. When describing the drawings, unless otherwise indicated, the same figures in different drawings represent the same or similar elements. It should be noted that the embodiments described in the following exemplary embodiments do not represent all embodiments of the present invention. They are only examples of devices and methods consistent with some aspects disclosed in the present invention as detailed in the claims, and the scope of the present invention is not limited to this. The features of the various embodiments of the present invention can be combined with each other without contradiction.

[0024] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "estimated" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0025] See also Figure 1 , a construction monitoring method based on three-dimensional point cloud according to an embodiment of the present invention includes S1 to S3.

[0026] S1, generating a three-dimensional point cloud of a proposed building suitable for indicating a building under construction.

[0027] Optionally, S1 includes: inputting a three-dimensional point cloud of a measured building obtained by three-dimensional point cloud measurement of the building under construction, and performing de-centroiding conversion on the three-dimensional point cloud of the measured building to obtain a three-dimensional point cloud of the building to be simulated.

[0028] In some embodiments, specific methods for implementing three-dimensional point cloud measurement for buildings under construction may include, but are not limited to: using at least one of three-dimensional point cloud acquisition devices such as a three-dimensional laser scanner, a binocular depth camera, and a stereo camera. At least one three-dimensional point cloud acquisition device can be mounted on a drone or a ground walking mechanism. For example, the ground walking mechanism can be a cart or an AGV cart or other walking mechanism. The embodiments of the present application do not limit the specific form of obtaining three-dimensional point clouds for buildings under construction.

[0029] Determine the coordinates of the centroid point of the 3D point cloud and subtract the coordinates of the centroid point from the coordinates of each point in the 3D point cloud. This is called de-centroiding. In addition to hiding the true coordinates of the 3D point cloud, it also reduces the coordinates of any two points in the 3D point cloud while maintaining their relative positions, which facilitates subsequent processing of the 3D point cloud and helps reduce the computing volume of the point cloud.

[0030] S2, fitting the basic shape of the building under construction based on the three-dimensional point cloud of the building to be simulated, so as to obtain the association result between the building shape and the point cloud.

[0031] The basic shape of the building under construction can be any one of a cube, a sphere, a cone and a cylinder, and the result of associating the building shape with the point cloud is suitable for indicating that there is a point cloud subset in the three-dimensional point cloud of the building to be simulated that obeys the distribution of the basic building shape.

[0032] Optionally, S2 includes: combining a preset cylinder detection model and the three-dimensional point cloud of the building to be constructed, iteratively fitting the cylinder to obtain a cylinder fitting index set suitable for indicating that the basic shape of the building under construction is a cylinder and a point cloud subset with the largest number of points.

[0033] In some embodiments, some parameters suitable for iteratively fitting a cylinder may be pre-placed in a random sampling consensus algorithm (RANSAC) to form a preset cylinder detection model. For example, n may be 3 or other values, k may be 10,000 or other values, t may be 1 cm or other values, and the numerical combination form is not limited. See the table below.

[0034] In some embodiments, the three-dimensional point cloud of the building to be simulated is input into a preset cylinder detection model. After multiple fittings, the optimal cylinder and the point cloud subset that obeys its distribution have the largest i. For example, i can be 43521 or other values. The point cloud subset with the largest i and the cylinder fitting index set that best matches it can be output together. In addition, i can also be output together to form the association result of the building shape and the point cloud.

[0035] In some embodiments, the cylindrical fitting index set includes at least a point P0 passing through the axis and an axis vector. In addition, it may also include r. For example, P0 can be expressed as (48.8258, 17.7809, 2.73465), the axis vector can be expressed as (-0.0052, -0.0184, 0.9998), r can be 3.3707 or other values, and P0 and Ad can each be other forms of expression and other specific values, which are not limited here.

[0036]

[0037] For example, for any point in the point cloud, if the vertical distance of its projection on the axis of the cylinder is marked as d, d, r and t should satisfy |dr| less than or equal to t, then it can be regarded as an internal point, otherwise, it should be regarded as an external point.

[0038] Compared with any of the cubes, spheres and cones, the cylinder requires fewer fitting parameters, so that the three-dimensional point cloud of the building to be simulated is divided into a point cloud subset that obeys the cylindrical distribution (which can be called the inner point subset) and a point cloud subset that does not obey the cylindrical distribution (which can be called the outer point subset), which helps to strike a balance between the simplicity and accuracy of point cloud segmentation.

[0039] S3, identifying at least one construction elevation index based on the association result between the building shape and the point cloud.

[0040] Alternatively, see Figure 2 , another embodiment of the present invention is a construction monitoring method based on three-dimensional point cloud, wherein S3 includes: S31 to S34.

[0041] S31, detecting whether the ratio of the number of points of the point cloud subset that obeys the cylinder to the three-dimensional point cloud of the proposed building is lower than a preset threshold, if so, executing S32, if not, executing S33.

[0042] In some embodiments, the result of associating the building form with the point cloud may include a subset of inner points with the largest number of points and a set of cylinder fitting indicators that is optimal for indicating the cylinder to which the inner point subset obeys, and the number of points i in the inner point subset and the number of points m in the three-dimensional point cloud of the building to be simulated are counted, where i / m is the point ratio. Alternatively, the result of associating the building form with the point cloud may further include i, which helps to improve the efficiency of point ratio detection compared to the lack of i in the result of associating the building form with the point cloud.

[0043] In some embodiments, the preset threshold is between 0.5 and 1, for example, 0.55 or 0.7 or other values.

[0044] In practice, when the height of the building under construction has been constructed at a relatively low level, the base plane is more prominent than the building height, and it is more likely to have many miscellaneous points. The three-dimensional point cloud shows that most points are distributed on a certain horizontal plane and its vicinity, and the angle between the axis of the cylinder and the vertical line is greater than the angle between the axis and the horizontal plane (which can be called a biased horizontal state); when the height of the building under construction has been constructed at a relatively high level, the building height is more prominent than the base plane, the proportion of miscellaneous points is reduced, and the three-dimensional point cloud shows that most points are distributed vertically, and the angle between the axis of the cylinder and the vertical line is smaller than the angle between the axis and the horizontal plane (which can be called a biased vertical state).

[0045] When the point ratio is lower than the preset threshold, it can reflect that the proportion of noise is high, the inner point subset is smaller than the outer point subset, and the cylinder is in a horizontal state; when the point ratio is greater than or equal to the preset threshold, it can reflect that the proportion of noise is low, the inner point subset is larger than the outer point subset, and the cylinder is in a vertical state.

[0046] S32, using a preset indicator suitable for indicating that the building under construction does not exceed the base elevation as a construction elevation indicator.

[0047] For some buildings under construction, such as one-story houses or buildings, the height between the foundation and a reference point above the foundation can be called the base elevation. The base elevation can be proportional to the design elevation to be achieved after the completion of the building under construction. For example, the proportion of the base elevation to the design elevation can be 8.5% or 30% or 40% or other values. The proportion can be adaptively changed according to the type of building. The base elevation can also be unrelated to the design elevation, for example, fixed at 2.5 meters.

[0048] In some embodiments, the preset indicator can be in the form of "the height of the building under construction that has been constructed is lower than or equal to the base elevation" or "2.5 meters" or "the height of the building under construction that has been constructed is lower than or equal to the base elevation, 2.5 meters", etc., which can be distinguished from the estimated column height described below.

[0049] S33, combining the cylinder fitting index set and the point cloud subset to respectively determine an estimated column top center and an estimated column bottom center belonging to the basic shape of the building under construction.

[0050] Among them, the estimated column height is suitable for indicating that the building under construction has exceeded the base elevation, the pre-designed cylinder is suitable for indicating the basic shape of the building under construction after completion, and the column height difference is suitable for indicating the remaining elevation for subsequent construction of the building under construction.

[0051] Controlled by the point count ratio detection method, when the cylinder is in a vertically oriented state, it is necessary to combine the cylinder fitting index set with the point cloud subset to locate the center of the top and the center of the bottom of the cylinder respectively. This not only makes up for the defect of lack of center positioning performance suitable for locating the center of the top and the center of the bottom of the cylinder respectively in the cylinder fitting process, but also prevents the aforementioned center positioning performance from being mistakenly triggered when the cylinder is in a horizontally oriented state.

[0052] Optionally, S33 includes: determining, according to the cylinder fitting index set, projection points of each point in the point cloud subset onto the axis to which the basic shape of the building under construction belongs, and identifying the two projection points with the largest distance as the estimated center of the top of the column and the estimated center of the bottom of the column.

[0053] In some embodiments, according to the above P0 and the above axis vector, in the point cloud coordinate system, the axis of the cylinder is positioned, and each point in the inner point subset is projected onto the aforementioned axis, wherein along the vertical direction represented by the Z coordinate axis, the projection point with the largest coordinate is the estimated center of the top of the cylinder, and the projection point with the smallest coordinate is the estimated center of the bottom of the cylinder.

[0054] For example, see Figure 3 In the point cloud coordinate system represented by XYZ, the three points in the inner point subset are marked as P1, P2 and P3 respectively. The three points are projected onto the axis Axis of the cylinder respectively, and the three projection points are marked as P1 and P2 respectively. ＇ 、P2 ＇ and P3 ＇ , projection point P1 ＇ The vertical distance d1 between point P1 and projection point P2 is less than r. ＇ The vertical distance d2 between point P2 is greater than r, |d1-r| and |d2-r| are both less than t, and the projection point P3 ＇ The vertical distance d3 from point P3 is equal to r.

[0055] Using point projection to synchronously locate the estimated column top center and the estimated column bottom center on the axis helps to balance the accuracy and simplicity of locating the two centers.

[0056] S34, detecting the estimated column height between the estimated column bottom circle center and the estimated column top circle center to serve as a construction elevation index.

[0057] Alternatively, see Figure 4 In another embodiment of the present invention, a construction monitoring method based on three-dimensional point cloud is provided, wherein S3 further includes: S35, obtaining a pre-designed cylinder; S36, detecting a column height difference between a design column height H2 of the pre-designed cylinder and an estimated column height H1 as a construction elevation indicator.

[0058] Alternatively, see Figure 5In another embodiment of the present invention, a construction monitoring method based on three-dimensional point cloud is provided, wherein the two construction elevation indicators are estimated column height and column height difference.

[0059] For example, see Figure 6 , the column height difference can be expressed as: designed column height H2-estimated column height H1.

[0060] Compared with some existing construction progress monitoring methods, it relies on three-dimensional point clouds to identify elevation indicators suitable for reflecting construction progress. There is no need to remove clutter from the point cloud under human intervention, which eliminates the extremely complex fully automated point cloud registration process and the operation of processing at least one type of alternative data in the image / three-dimensional building model / construction schedule, greatly improving the simplicity of monitoring construction progress.

[0061] Alternatively, see Figure 5 ,After S35, the construction monitoring method based on three-dimensional point cloud also includes S4A.

[0062] S4A, detect the center distance between the design column bottom center and the estimated column bottom center of the pre-designed cylinder as a construction offset indicator.

[0063] For example, see Figure 6 , the estimated center of the column base is represented by P2 ＇ , the center of the design column bottom circle is represented as Pb, and S=|P2 ＇ Pb|, let the center distance S be the construction offset index. If the construction offset index is greater than the preset offset threshold, it reflects that the horizontal offset of the building under construction exceeds the standard and needs to be rectified. Otherwise, it reflects that the horizontal offset of the building under construction is qualified and no rectification is required.

[0064] Alternatively, see Figure 5 ,After S35, the construction monitoring method based on three-dimensional point cloud also includes S4B.

[0065] S4B, detect the axis angle between the axis of the pre-designed cylinder and the axis of the basic shape of the building under construction as a construction inclination indicator.

[0066] In some embodiments, see Figure 6 , we can estimate the center of the top circle P1 ＇ The three-dimensional coordinates minus the estimated column base center P2 ＇ The three-dimensional coordinates of the axis vector 1. Similarly, the axis vector can be obtained by subtracting the three-dimensional coordinates of the center of the design column bottom Pb from the three-dimensional coordinates of the center of the design column top Pa. 2. Then, find the axis vector 1 and axis vector 2, or the axis vector in the result of associating the building shape with the point cloud can be directly used as 1. It helps to improve the efficiency of angle measurement.

[0067] Exemplarily, the axis angle θ can be expressed as follows:

[0068] θ = arccos[( 1. 2) / (| 1|×| 2|], or, θ = arctan[|(Κ1-Κ2) / (1+Κ1×Κ2)|]

[0069] Among them, K1 represents the slope of the axis located on the basic shape of the building under construction, and K2 represents the slope of the axis located on the pre-designed cylinder.

[0070] Compared with some existing construction quality monitoring methods, the distance measurement method is used to achieve the purpose of construction offset detection, or / and the angle measurement method is used to achieve the purpose of construction inclination detection. Some data required for detecting construction elevation are retained, which helps to improve the compatibility and simplicity of monitoring construction progress and quality, and helps to reduce monitoring costs and promote application.

[0071] See also Figure 7 Another embodiment of the present invention is a three-dimensional point cloud-based building construction monitoring device, which includes a building point cloud generation module, a building shape fitting module and a construction index detection module.

[0072] The building point cloud generation module is used to generate a three-dimensional point cloud of a proposed building suitable for indicating a building under construction.

[0073] The building shape fitting module is used to fit the basic shape of the building under construction based on the three-dimensional point cloud of the building to be simulated, so as to obtain the association result between the building shape and the point cloud.

[0074] The construction index detection module is used to identify the construction elevation index based on the association results between the building shape and the point cloud.

[0075] See also Figure 8 , a computing device according to another embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the above-mentioned construction monitoring method based on three-dimensional point cloud is implemented, wherein the processor can be connected to the memory via a universal serial bus. It can be understood that the computing device can be a server or a terminal device.

[0076] A computer-readable storage medium according to another embodiment of the present invention includes a computer program executable by a processor, and when the computer program is executed, the above-mentioned three-dimensional point cloud-based construction monitoring method is implemented.

[0077] In the embodiments of the present application, the specific form of the computer program product is not limited, and may include but not be limited to: software / demo / applet / program class / macros that can implement building information application software, and may also be in the form of a computer program product implemented on one or more computer-storable media containing computer-usable program codes.

[0078] A computer program product may include one or more computer executable components configured to perform an embodiment when the program is run. The one or more computer executable components may be at least one software code or a portion thereof. In addition, any box of the logic flow in the figure may represent program steps, or interconnected logic circuits, boxes and functions, or a combination of program steps and logic circuits, boxes and functions.

[0079] Generally speaking, computer instructions for implementing the method of the present invention may be carried by any combination of one or more computer-readable storage media, any of which may be temporary or non-temporary, and may include but are not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or components, or any combination of the above.

[0080] A computer readable storage medium may be any tangible medium containing a stored program, more specific examples (a non-exhaustive list) include: an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0081] The program can be used by or in combination with an instruction execution system, device or device to write a computer program code for performing the operation of the present invention in one or more programming languages ​​or a combination thereof, wherein the programming language includes an object-oriented programming language such as Java, Smalltalk, C++, and also includes a conventional procedural programming language such as "C" language or a similar programming language, in particular, Python language suitable for neural network calculations and platform frameworks based on TensorFlow, PyTorch, etc. can be used. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or connected to an external computer (for example, connected through the Internet according to an Internet service provider).

[0082] The above-mentioned three-dimensional point cloud-based construction monitoring device, computing equipment and computer-readable storage medium can refer to the specific description of the above-mentioned three-dimensional point cloud-based construction monitoring method and its beneficial effects, which will not be repeated here.

[0083] Although the embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A construction monitoring method based on three-dimensional point cloud, characterized in that: include: generating a three-dimensional point cloud of a proposed building suitable for indicating a building under construction; Fitting the basic shape of the building under construction based on the three-dimensional point cloud of the building to be simulated, wherein there is a point cloud subset in the three-dimensional point cloud of the building to be simulated that obeys the distribution of the basic shape of the building, the basic shape of the building under construction is a cylinder, and the cylinder is suitable for being represented by a cylinder fitting index set; After detecting that the ratio of the number of points occupied by the point cloud subset to the three-dimensional point cloud of the proposed building is not less than a preset threshold, generating a construction elevation index and a construction offset index respectively; If the construction offset index is greater than the preset offset threshold, the horizontal offset of the building under construction exceeds the standard; otherwise, the horizontal offset of the building under construction is qualified; The generating of the construction elevation index and the construction offset index respectively comprises: Determine the estimated column top center and the estimated column bottom center belonging to the basic form of the building under construction respectively by combining the cylinder fitting index set and the point cloud subset; Detecting the estimated column height between the estimated column bottom circle center and the estimated column top circle center as the construction elevation index; After the pre-designed cylinder is obtained, the center distance between the center of the designed column bottom to which the pre-designed cylinder belongs and the estimated column bottom center is detected to serve as a construction offset indicator.

2. The construction monitoring method based on three-dimensional point cloud according to claim 1 is characterized in that: The method of respectively determining the estimated column top center and the estimated column bottom center belonging to the basic form of the building under construction by combining the cylinder fitting index set and the point cloud subset comprises: determining, according to the cylinder fitting index set, the projection points of each point in the point cloud subset onto the axis to which the basic form of the building under construction belongs; and respectively identifying the two projection points with the largest distance as the estimated column top center and the estimated column bottom center.

3. The construction monitoring method based on three-dimensional point cloud according to claim 1 or 2, characterized in that: After obtaining the pre-designed cylinder, the method further includes: detecting an axis angle between an axis to which the pre-designed cylinder belongs and an axis to which the basic form of the building under construction belongs, to serve as a construction inclination indicator.

4. A computing device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the three-dimensional point cloud-based construction monitoring method as described in any one of claims 1 to 3.

5. A computer-readable storage medium comprising a computer program executable by a processor, characterized in that: When the computer program is executed, the three-dimensional point cloud-based construction monitoring method as described in any one of claims 1 to 3 is implemented.

Images