Method for identifying potential dangerous area in constructional engineering

Abstract

The invention provides a method for identifying a potential dangerous area in constructional engineering, and relates to the technical field of constructional engineering monitoring, and the method comprises the steps: carrying out the collection and image processing of a camera image arranged in a constructional engineering area; segmenting a target monitoring area by using an image segmentation technology; constructing a building matrix surface model in the target monitoring area by adopting a multilevel function; the method comprises the following steps: extracting feature points of a building matrix surface model, monitoring position deviation of feature points of a matched standard building matrix surface model, timely discovering tiny changes of a building matrix in a construction process, and judging whether the building matrix has risks or not.

Description

Technical Field

[0001] The invention proposes a method for identifying potential dangerous areas in a construction project, and relates to the technical field of construction project monitoring. Background Art

[0002] At construction sites, large numbers of workers perform complex tasks such as working at height, lifting heavy objects, and excavating deep foundation pits. Potentially hazardous area identification can proactively identify areas at risk of tilt or collapse, such as foundation pit slopes, building foundations, and unstable scaffolding.

[0003] Identification of potential danger areas helps to discover risk factors that may affect building quality, so that measures can be taken in advance.

[0004] However, the existing modeling methods for identifying potential hazardous areas in construction projects are too simple and cannot accurately describe the complex surface of the building matrix, monitor the dynamic changes of the building matrix during construction, and cannot be accurately used to identify potential hazardous areas. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention proposes a method for identifying potential dangerous areas in construction projects, comprising the following steps:

[0006] S1. Collect and process camera images arranged in the construction project area;

[0007] S2. Use image segmentation technology to segment the target monitoring area;

[0008] S3, using a multi-level function to construct a building base surface model within the target monitoring area;

[0009] S4. Extract feature points of the building matrix surface model, monitor the position deviation of the feature points with the matched standard building matrix surface model, and determine whether there is a risk in the building matrix.

[0010] In a preferred embodiment, the multi-level function includes: a distance correlation function, a linear superposition function and a distribution function; step S3 includes the following steps:

[0011] S31, constructing a distance correlation function for each surface point of the building matrix using multiple equations;

[0012] S32, superimposing the distance correlation functions of all surface points using a linear superposition function to obtain an initial building base surface model;

[0013] S33. Filter the surface points of the initial building matrix surface model using the distribution function and the constraint conditions, select the optimal surface points, and repeat steps S31 and S32 to form a final building matrix surface model.

[0014] In a preferred embodiment, in step S31, the distance correlation function of the i-th surface point is:

[0015]

[0016] Among them, c is the shape parameter, β is the exponential parameter, r i is the distance between the i-th surface point and the center of gravity of the building base, γ i is the angle parameter between the i-th surface point and the center of gravity.

[0017] In a preferred embodiment, in step S32, the distance correlation functions of all surface points are superimposed using a linear superposition function, and the formula of the linear superposition function f(r) is:

[0018]

[0019] Where i is the i-th surface point, m is the total number of surface points, and w i is the weight, is the distance correlation function of the i-th surface point.

[0020] In a preferred embodiment, in step S33, the distribution function E(f) of the linear superposition function f(r) is defined as:

[0021]

[0022] This distribution function reflects the sum of the rates of change of the linear superposition function f(r) in the x, y, z directions and the angle parameter γ;

[0023] Using the control point algorithm, a final set of control points is obtained as input parameters of the re-determined multiple equations, and the re-determined multiple equations are used to calculate the linear superposition function to form the final building matrix surface model.

[0024] In a preferred embodiment, the distribution function term and the interpolation term are constructed, and the interpolation value J(f) is minimized by the control point algorithm:

[0025]

[0026] Among them, ρ is the weight parameter, r j is the distance value of the j-th control point, γ j is the angle parameter of the jth control point, n is the number of control points;

[0027] Output a set of control points that minimize the interpolation value J(f), use the distance values ​​and angle parameters corresponding to this set of control points as input parameters of the multiple equations, recalculate the linear superposition function, and construct the final building base surface model.

[0028] In a preferred embodiment, step S4 includes:

[0029] S41, taking the final control point obtained in step S33 as the feature point of the final building matrix surface model, and calculating feature information of the feature point;

[0030] S42, matching the feature points of the final building base surface model with the feature points of the standard building base surface model according to the feature information of the feature points;

[0031] S43. Monitor the position deviation between the feature points of the final building matrix surface model and the feature points of the matched standard building matrix surface model, and determine whether there is a risk of tilting of the building matrix by comparing with a set position deviation threshold.

[0032] In a preferred embodiment, in step S41, with feature point k as the center, the pixel coordinates corresponding to feature point k are (x′ k ,y′ k ), calculate the gradient amplitude H(k) with the gray value L of the adjacent pixel:

[0033]

[0034] The gradient direction T(k) of the gray value L is:

[0035]

[0036] The feature information of each feature point is: the gradient amplitude and gradient direction T(k) of the corresponding pixel gray value L.

[0037] In a preferred embodiment, in step S42, matching is performed by calculating the similarity of the feature information between the feature points. Assume that the feature information D of the feature point k in the building base surface model A is A (k) is:

[0038] D A (k)=(H A (k),T A (k))

[0039] Assume that the feature information D of the feature point k′ in the standard building base surface model B is B (k′) is:

[0040] D B (k′)=(H B (k′),T B (k′))

[0041] Then the similarity G(k) is:

[0042]

[0043] The two feature points with the smallest similarity are the matching points.

[0044] In a preferred embodiment, in step S43, the spatial coordinates of the kth feature point in the building base surface model A are set to (x k ,y k ,z k ), the coordinates of the kth feature point corresponding to the standard building base surface model B are (X k ,Y k ,Z k ), then the distance deviation between matching feature points is ΔR k for:

[0045]

[0046] By matching the distance deviation ΔR between feature points k Compare with the distance deviation threshold to determine whether the building base has a risk of tilting. k If the distance deviation threshold is exceeded, the building matrix is ​​defined as a dangerous area.

[0047] Compared with the prior art, the present invention has the following beneficial technical effects:

[0048] 1. By collecting and processing images from cameras deployed in the construction area, existing monitoring equipment resources can be fully utilized. This method can obtain visual information of the construction site in real time, eliminating the need for additional manpower for on-site inspections.

[0049] 2. Using image segmentation technology to segment the target monitoring area is very beneficial. This allows subsequent analysis to focus on the actual construction activity area, avoiding unnecessary analysis of non-construction areas and improving the efficiency and accuracy of identifying potential danger areas.

[0050] 3. Using multi-level functions to construct a surface model of the building substrate within the target monitoring area can more accurately depict the shape and structure of the building substrate. This model more realistically reflects the actual conditions of the building substrate and can better adapt to the complex surface shapes of the building substrate compared to simple geometric models. For example, for buildings with complex curved surfaces, such as the dome of a large stadium, a model constructed using multi-level functions can accurately represent its surface features.

[0051] 4. Extract feature points from the building matrix surface model and monitor positional deviations from the matching standard building matrix surface model to determine if the building matrix presents risks. This method can promptly detect subtle changes to the building matrix during construction. If positional deviations exceed the normal range, it can quickly identify potential risks such as subsidence or deformation. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] 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 description of 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 creative work.

[0053] Figure 1 A flow chart of a method for identifying potential hazardous areas in a construction project according to the present invention;

[0054] Figure 2 Flowchart of the present invention using multi-level functions to construct a building base surface model within a target monitoring area;

[0055] Figure 3 A flow chart of the present invention for determining whether a building matrix is ​​at risk;

[0056] Figure 4 Schematic diagram of characteristic points in the standard building substrate surface model of the present invention. DETAILED DESCRIPTION

[0057] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0058] In the drawings of the specific embodiments of the present invention, in order to better and more clearly describe the working principles of the various components in the system, the connection relationship of the various parts in the device is shown, which only clearly distinguishes the relative position relationship between the various components, and does not constitute a limitation on the signal transmission direction, connection sequence and size, dimension and shape of the components or structures.

[0059] like Figure 1 FIG. 1 is a flow chart of a method for identifying a potential hazardous area in a construction project according to the present invention. The method for identifying a potential hazardous area in a construction project comprises the following steps:

[0060] S1. Collect and process camera images arranged in the construction project area.

[0061] S11. Multiple cameras are strategically placed at construction sites to ensure coverage of key locations within the construction area, such as excavation areas, elevated work areas, hazardous building foundations, and lifting areas. The cameras continuously capture on-site images, providing raw data for subsequent analysis.

[0062] S12: Processing the collected image to improve image quality and accuracy of subsequent processing. The image processing operation includes image denoising.

[0063] Preferably, a filtering algorithm is used to remove noise interference in the image to make the image clearer.

[0064] Preferably, image enhancement operations are performed, such as adjusting image contrast, brightness, etc., to highlight key information in the image, thereby facilitating subsequent image segmentation and feature extraction.

[0065] S2. Use image segmentation technology to segment the target monitoring area.

[0066] Threshold segmentation divides an image into different regions based on the threshold of pixel values. It is suitable for scenes with high image contrast and obvious differences between the target and the background. Region-based segmentation combines regions with similar attributes. Preferably, algorithms such as region growing and region merging are used. Edge-based segmentation performs segmentation based on edge information in the image, and gradient operators are often used to detect edges.

[0067] The target monitoring area in this embodiment is mainly a plurality of building base areas.

[0068] S3. Use multi-level functions to construct the building base surface model in the target monitoring area.

[0069] The multi-level functions for constructing the building matrix surface model include: distance correlation function, linear superposition function and distribution function.

[0070] S31. Use multiple equations to construct the distance correlation function of each surface point of the building matrix.

[0071] The distance correlation function can be used to describe the distance relationship between each surface point of a building matrix and a reference point. This description, based on a mathematical model, can accurately depict the surface shape of the building matrix. By defining the distance correlation function, complex three-dimensional surfaces can be converted into computable mathematical expressions, thus delineating the surface shape of the building matrix.

[0072] The distance correlation function of the i-th surface point is:

[0073]

[0074] Among them, γ i is the angle parameter between the i-th surface point and the center of gravity. This angle can be selected as any angle that can measure the positional relationship between the surface point and the center of gravity according to the measurement needs. i is the distance between the i-th surface point and the center of gravity of the building base. Associating the tangent function with this distance better reflects the positional relationship between the surface point and the center of gravity. c is the shape parameter, which controls the width or range of influence of the function. A larger value of c results in a slower decay of the function and a wider range of influence. β is the exponential parameter, which determines the shape of the function. Here, β is a negative number.

[0075] S32. Superimpose the distance correlation functions of all surface points using a linear superposition function to obtain an initial building base surface model.

[0076] The formula for the linear superposition function f(r) is:

[0077]

[0078] i is the i-th surface point, m is the total number of surface points, w i is the weight, is the distance correlation function of the i-th surface point.

[0079] S33. Filter the surface points of the initial building matrix surface model using the distribution function and the constraint conditions, select the optimal surface points, and repeat steps S31 and S32 to form a final building matrix surface model.

[0080] The distribution function E(f) of the linear superposition function f(r) is defined as:

[0081]

[0082] This distribution function reflects the smoothness of the linear superposition function f(r) on the surface of the building matrix. (x, y, z) represents the x, y, and z directions of the spatial coordinate system. What needs to be explained is r i is the distance between the i-th surface point and the center of gravity of the building base. The i-th surface point has a corresponding coordinate value (x i ,y i ,z i ), so the rate of change of the linear superposition function f(r) in the x, y, z directions and the angular direction is different.

[0083] Use the control point algorithm to remove non-smooth surface points, specifically:

[0084] The goal of the control point algorithm is to minimize the interpolation value J(f), and to achieve this, an algorithm is constructed that includes a distribution function term and an interpolation term:

[0085]

[0086] Among them, ρ is the weight parameter used to balance the distribution function term and the interpolation term, r j is the distance to the jth control point, γ j is the angle parameter of the jth control point. The control points are the basis of the building base surface. The shape and characteristics of the building base surface are largely determined by these points. i is the i-th surface point and n is the number of control points.

[0087] The output of a set of control points that minimizes the interpolation value J(f) is used as the input parameters of the re-determined multiple equations. Finally, the re-determined multiple equations are used to output the linear superposition function f(r) to form the final building base surface model.

[0088] S4. Extract feature points of the building matrix surface model, monitor the position deviation of the feature points with the matched standard building matrix surface model, and determine whether there is a risk in the building matrix.

[0089] The specific method is as follows:

[0090] S41 , taking the final control points obtained in step S33 as feature points of the final building base surface model, and calculating feature information of the feature points.

[0091] With feature point k as the center, the pixel coordinates corresponding to feature point k are (x′ k ,y′ k ), calculate the gradient amplitude H(k) between it and the gray value L of the adjacent pixel.

[0092] The gradient amplitude H(k) of the gray value L is:

[0093]

[0094] The gradient direction T(k) of the gray value L is:

[0095]

[0096] In this way, each feature point has feature information, and the feature information of each feature point is: the gradient amplitude and gradient direction T(k) corresponding to the grayscale value L of the pixel point.

[0097] S42. Matching the feature points of the final building base surface model with the feature points of the standard building base surface model according to the feature information of the feature points.

[0098] Matching is performed by calculating the similarity of the feature information between feature points. Suppose the feature information D of feature point k in the building base surface model A is A (k) is:

[0099] D A (k)=(H A (k),T A (k))

[0100] Assume that the feature information D of the feature point k′ in the standard building base surface model B is B (k′) is:

[0101] D B (k′)=(H B (k′),T B (k′))

[0102] Then the similarity G(k) between them is:

[0103]

[0104] The two feature points with the smallest similarity are selected for matching to form the matching points.

[0105] S43. Monitor the position deviation between the feature points of the final building matrix surface model and the feature points of the matched standard building matrix surface model, and determine whether there is a risk of tilting of the building matrix by comparing with a set position deviation threshold.

[0106] Assume that the coordinates of the kth feature point in the building base surface model A are (x k ,y k ,z k ), the coordinates of the kth feature point corresponding to the standard building base surface model B are (X k ,Y k ,Z k ), then the position deviation between matching feature points is ΔR k for:

[0107]

[0108] By matching the position deviation of the feature points ΔR k Compare with the position deviation threshold to determine whether the building matrix has a tilt risk. If the position deviation of the matching feature point ΔR k If the position deviation threshold is exceeded, the building matrix is ​​considered to be in an unsafe state and is defined as a dangerous area.

[0109] like Figure 4 As shown in FIG, a schematic diagram of corresponding feature points in the standard building base surface model.

[0110] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0111] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above-mentioned method embodiments when executed by a processor.

[0112] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of each of the above-described method embodiments.

[0113] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. The database involved in the embodiments provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited to this. The processor involved in the embodiments provided in this application may be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, etc., but is not limited to this.

[0114] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0115] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for identifying potential dangerous areas in a construction project, characterized in that: The steps include: S1. Collect and process camera images arranged in the construction project area; S2. Use image segmentation technology to segment the target monitoring area; S3, using a multi-level function to construct a building base surface model within the target monitoring area; S4. Extract feature points of the building matrix surface model, monitor the position deviation of the feature points with the matched standard building matrix surface model, and determine whether there is a risk in the building matrix.

2. The method for identifying potential dangerous areas in construction projects according to claim 1, characterized in that: The step S3 comprises: S31, constructing a distance correlation function for each surface point of the building matrix using multiple equations; S32, superimposing the distance correlation functions of all surface points using a linear superposition function to obtain an initial building base surface model; S33. Filter the surface points of the initial building matrix surface model using the distribution function and the constraint conditions, select the optimal surface points, and repeat steps S31 and S32 to form a final building matrix surface model.

3. The method for identifying potential dangerous areas in construction projects according to claim 2, characterized in that: In step S31, the distance correlation function of the i-th surface point for: Among them, c is the shape parameter, β is the exponential parameter, r i is the distance between the i-th surface point and the center of gravity of the building base, γ i is the angle parameter between the i-th surface point and the center of gravity.

4. The method for identifying potential dangerous areas in construction projects according to claim 3, characterized in that: In step S32, the distance correlation functions of all surface points are superimposed using a linear superposition function. The formula of the linear superposition function f(r) is: Where i is the i-th surface point, m is the total number of surface points, and w i is the weight, is the distance correlation function of the i-th surface point.

5. The method for identifying potential dangerous areas in construction projects according to claim 4, characterized in that: In step S33, the distribution function E(f) of the linear superposition function f(r) is defined as: The distribution function reflects the sum of the rates of change of the linear superposition function f(r) in the x, y, z directions and the angle parameter γ; Using the control point algorithm, a final set of control points is obtained as input parameters of the re-determined multiple equations, and the re-determined multiple equations are used to calculate the linear superposition function to form the final building matrix surface model.

6. The method for identifying potential dangerous areas in construction projects according to claim 5, characterized in that: Construct the distribution function term and interpolation term, and minimize the interpolation value J(f) through the control point algorithm: Among them, ρ is the weight parameter, r j is the distance value of the j-th control point, γ j is the angle parameter of the jth control point, n is the number of control points; Output a set of control points that minimize the interpolation value J(f), use the distance values ​​and angle parameters corresponding to this set of control points as input parameters of the multiple equations, recalculate the linear superposition function, and construct the final building base surface model.

7. The method for identifying potential dangerous areas in construction projects according to claim 5, characterized in that: Step S4 includes: S41, taking the final control point obtained in step S33 as the feature point of the final building matrix surface model, and calculating feature information of the feature point; S42, matching the feature points of the final building base surface model with the feature points of the standard building base surface model according to the feature information of the feature points; S43. Monitor the position deviation between the feature points of the final building matrix surface model and the feature points of the matched standard building matrix surface model, and determine whether there is a risk of tilting of the building matrix by comparing with a set position deviation threshold.

8. The method for identifying potential dangerous areas in construction projects according to claim 7, characterized in that: In step S41, with feature point k as the center, the pixel coordinates corresponding to feature point k are (x′ k ,y′ k ), calculate the gradient amplitude H(k) with the gray value L of the adjacent pixel: The gradient direction T(k) of the gray value L is: The feature information of each feature point is: the gradient amplitude and gradient direction T(k) of the corresponding pixel gray value L.

9. The method for identifying potential dangerous areas in construction projects according to claim 8, characterized in that: In step S42, matching is performed by calculating the similarity of the feature information between the feature points. Suppose the feature information D of the feature point k in the building base surface model A is A (k) is: D A (k)=(H A (k),T A (k)) Assume that the feature information D of the feature point k′ in the standard building base surface model B is B (k′) is: D B (k′)=(H B (k′),T B (k′)) Then the similarity G(k) is: The two feature points with the smallest similarity are the matching points.

10. The method for identifying potential dangerous areas in construction projects according to claim 9, characterized in that: In step S43, the spatial coordinates of the kth feature point in the building base surface model A are set to (x k ,y k ,z k ), the coordinates of the kth feature point corresponding to the standard building base surface model B are (X k ,Y k ,Z k ), then the distance deviation between matching feature points is ΔR k for: By matching the distance deviation ΔR between feature points k Compare with the distance deviation threshold to determine whether the building base has a tilt risk. If the distance deviation ΔR k If the distance deviation threshold is exceeded, the building matrix is ​​defined as a dangerous area.

Images