CN116152218A - Intelligent detection method and device for construction quality - Google Patents

Abstract

The present application relates to the technical field of quality inspection, and in particular to a method and device for intelligent inspection of construction quality, wherein the method includes: based on a binocular camera, acquiring color image data and three-dimensional point cloud data of the plane to be inspected, and analyzing all information in the color image data The detection plane is divided into regional grids to calculate the pixel coordinates of the grid vertices and intersection points in the evaluation area, and the relative spatial position of each intersection point is calculated according to the mapping between the pixel coordinates of the grid vertices and intersection points in the area and the 3D point cloud data. Based on the variance value of the absolute flat plane, the flatness level of the plane to be detected is evaluated. The embodiment of the present application can be based on the three-dimensional point cloud data of the operation plane, and realize the intelligent and accurate evaluation of the flatness of the operation plane by meshing the operation plane and calculating and processing the point cloud data, and improving the detection efficiency of the flatness , more intelligent.

Description

Construction quality intelligent detection method and device

technical field

The present application relates to the technical field of quality inspection, in particular to an intelligent inspection method and device for construction quality.

Background technique

In the process of building construction, a large number of plane operations are often involved, and the flatness of the key work surface, as a key indicator to measure the construction quality, is the focus of quality control for industry practitioners.

In related technologies, manual methods such as the fixed-length ruler method, the section drawing method, and the rolling and accumulating method are mainly used to detect the flatness of the working plane. The cross-section drawing method and the bump accumulation method are mainly applicable to the concrete surface detection of road engineering. At present, there are also related programs that use laser-type flatness measuring instruments to evaluate the standard deviation of surface flatness.

However, the flatness detection of the working plane in the related technology is highly dependent on manual operation or the driving level of the detection vehicle, and it is difficult to fully cover the detected working plane, resulting in low detection efficiency and accuracy, and insufficient applicability, which needs to be solved urgently.

Contents of the invention

This application provides a method and device for intelligent detection of construction quality to solve the problem that the flatness detection of the working plane in the related art is highly dependent on manual operation or the driving level of the detection vehicle, and it is difficult to fully cover the detected working plane, resulting in the detection efficiency and The accuracy is low and the applicability is insufficient.

The embodiment of the first aspect of the present application provides an intelligent detection method for construction quality, including the following steps: based on a binocular camera, acquiring color image data and three-dimensional point cloud data of a plane to be detected; Regional grid division to calculate the pixel coordinates of the grid vertices and intersection points in the evaluation area; calculate the spatial position of each intersection point according to the mapping between the pixel coordinates of the grid vertices and intersection points in the area and the 3D point cloud data The flatness level of the plane to be detected is evaluated relative to the variance value of the absolutely flat plane.

Optionally, in an embodiment of the present application, performing area grid division on the detected plane in the color image data to calculate pixel coordinates of grid vertices and intersection points in the evaluation area includes: In the color image data, click on the vertices of the evaluation range to determine the evaluation area; set the number of rows and columns of the grid to generate a divided grid; on the basis of the divided grid, extract one by one All intersection coordinates in each grid, get the pixel coordinates.

Optionally, in an embodiment of the present application, the calculation according to the mapping between the pixel coordinates of the grid vertices and intersection points in the region and the 3D point cloud data is relative to the absolute flatness of each intersection point in the spatial position The variance value of the plane is used to evaluate the flatness level of the plane to be detected, including: extracting the spatial coordinate data of the intersection points of each row of grids, and calculating the variance value of the grid intersection points row by row. The average value of the three-dimensional coordinates of grid intersection points; calculate the variance of the evaluation area according to the variance value and the average value, so as to obtain the flatness level of the plane to be detected.

Optionally, in an embodiment of the present application, the formula for calculating the variance value of the grid intersection is:

Among them, var _rj is the variance of the jth grid intersection point, z _j is the three-dimensional coordinate of the jth grid intersection point, avg _zr is the average value of the three-dimensional coordinate z of the grid intersection point in each row, and c is the column number of the grid, r is the number of columns in the grid;

And, the formula for calculating the average value of the three-dimensional coordinates is:

Among them, avg _zr is the average value of the three-dimensional coordinate z of the grid intersection of each row, z _j is the three-dimensional coordinate of the jth grid intersection, c is the number of grid columns, and r is the number of grid columns.

Optionally, in one embodiment of the present application, the formula for calculating the variance of the evaluation area is:

Among them, var _f is the variance of the evaluation area, var _rn is the variance of the nth grid intersection, avg _f is the average value of the variance value of each grid intersection in the evaluation area, and r is the number of grid columns.

The embodiment of the second aspect of the present application provides an intelligent detection device for construction quality, including: an acquisition module, used to acquire color image data and three-dimensional point cloud data of the plane to be detected based on a binocular camera; a calculation module, used to calculate the The detected plane in the color image data is divided into regional grids to calculate the pixel coordinates of the vertices and intersection points of the grid in the evaluation area; The mapping between the cloud data calculates the variance value of each intersection point relative to the absolute flat plane in the spatial position, and evaluates the flatness level of the plane to be detected.

Optionally, in an embodiment of the present application, the calculation module includes: a clicking unit, configured to click a vertex of an evaluation range in the color image data to determine the evaluation area; a dividing unit, It is used to set the number of rows and columns of the grid to generate a divided grid; the extraction unit is used to extract all the intersection coordinates in each grid one by one on the basis of the divided grid to obtain the the pixel coordinates.

Optionally, in an embodiment of the present application, the detection module includes: a first computing unit, configured to extract the spatial coordinate data of each row of grid intersections, and calculate the variance value of the grid intersections row by row at the same time , calculating the average value of the three-dimensional coordinates of the intersection points of each row of grids; the second calculation unit is used to calculate the variance of the evaluation area according to the variance value and the average value, so as to obtain the plane to be detected flatness level.

Optionally, in an embodiment of the present application, the formula for calculating the variance value of the grid intersection is:

Among them, var _rj is the variance of the jth grid intersection point, z _j is the three-dimensional coordinate of the jth grid intersection point, avg _zr is the average value of the three-dimensional coordinate z of the grid intersection point in each row, and c is the column number of the grid, r is the number of columns in the grid;

And, the formula for calculating the average value of the three-dimensional coordinates is:

Among them, avg _zr is the average value of the three-dimensional coordinate z of the grid intersection of each row, z _j is the three-dimensional coordinate of the jth grid intersection, c is the number of grid columns, and r is the number of grid columns.

Optionally, in one embodiment of the present application, the formula for calculating the variance of the evaluation area is:

Among them, var _f is the variance of the evaluation area, var _rn is the variance of the nth grid intersection, avg _f is the average value of the variance value of each grid intersection in the evaluation area, and r is the number of grid columns.

The embodiment of the third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and operable on the processor, and the processor executes the program to realize The construction quality intelligent detection method as described in the above-mentioned embodiment.

The embodiment of the fourth aspect of the present application provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the program is executed by a processor, the above method for intelligent detection of construction quality is realized.

In this embodiment of the present application, based on a binocular camera, the color image data and 3D point cloud data of the plane to be detected can be obtained, and the area grid division of the detected plane in the color image data is performed to calculate the pixels of the vertices and intersection points of the grid in the evaluation area Coordinates, according to the mapping between the pixel coordinates of the grid vertices and intersection points in the area and the three-dimensional point cloud data, calculate the variance value of each intersection point in the spatial position relative to the absolute flat plane, and evaluate the flatness level of the plane to be detected. The grid division of the working plane and the calculation and processing of point cloud data realize the intelligent and accurate evaluation of the flatness of the working plane, improve the detection efficiency of the flatness, and make it more intelligent. Thus, it solves the problem that the flatness detection of the working plane in the related technology is highly dependent on manual operation or the driving level of the detection vehicle, and it is difficult to fully cover the detected working plane, resulting in low detection efficiency and accuracy, and insufficient applicability, etc. question. Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.

Description of drawings

The above and/or additional aspects and advantages of the present application will become apparent and easy to understand from the following description of the embodiments in conjunction with the accompanying drawings, wherein:

Fig. 1 is a flow chart of a construction quality intelligent detection method provided according to an embodiment of the present application;

Fig. 2 is a schematic diagram of determining the scope of the assessed area according to an embodiment of the present application;

FIG. 3 is a schematic diagram of grid division according to an embodiment of the present application;

Fig. 4 is a schematic diagram of the construction quality intelligent detection process of an embodiment of the present application;

Fig. 5 is a working plane flatness detection effect diagram of an embodiment of the present application;

Fig. 6 is a schematic structural diagram of a construction quality intelligent detection device according to an embodiment of the present application;

FIG. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed ways

Embodiments of the present application are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary, and are intended to explain the present application, and should not be construed as limiting the present application.

The construction quality intelligent detection method and device according to the embodiments of the present application will be described below with reference to the accompanying drawings. In view of the above-mentioned background technology center mentioned in the related technology, the flatness detection of the working plane is highly dependent on manual operation or the driving level of the detection vehicle, and it is difficult to fully cover the detected working plane, resulting in low detection efficiency and accuracy, and is applicable In order to solve the problem of lack of stability, this application provides an intelligent detection method for construction quality, which can obtain color image data and 3D point cloud data of the plane to be detected based on a binocular camera, and perform regional grid division on the detected plane in the color image data , to calculate the pixel coordinates of the grid vertices and intersection points in the evaluation area, and calculate the variance of each intersection point in the spatial position relative to the absolute flat plane according to the mapping between the pixel coordinates of the grid vertices and intersection points in the area and the 3D point cloud data value, evaluate the flatness level of the plane to be detected, and realize the intelligent and accurate evaluation of the flatness of the working plane by meshing the working plane and calculating and processing the point cloud data, improving the detection efficiency of the flatness and making it more intelligent change. Thus, it solves the problem that the flatness detection of the working plane in the related technology is highly dependent on manual operation or the driving level of the detection vehicle, and it is difficult to fully cover the detected working plane, resulting in low detection efficiency and accuracy, and insufficient applicability, etc. question.

Specifically, FIG. 1 is a schematic flowchart of a method for intelligent detection of construction quality provided by an embodiment of the present application.

As shown in Figure 1, the construction quality intelligent detection method includes the following steps:

In step S101, based on the binocular camera, the color image data and the three-dimensional point cloud data of the plane to be detected are acquired.

It can be understood that in the embodiment of the present application, binocular cameras can be used for data collection, and the unique correspondence between each pixel point and the spatial coordinates can be realized on the basis of the color image acquired by the traditional camera, and then the three-dimensional point cloud of the evaluated plane can be obtained data.

In the actual implementation process, when collecting data, the binocular camera can be placed near the detected plane to ensure that the plane is within the shooting range of the binocular camera, and then connected to the binocular camera to obtain the relevant data of the plane.

The embodiment of the present application is based on a binocular camera to obtain color image data and 3D point cloud data of the plane to be detected. By using the binocular camera to collect relevant data of the plane to be measured, intervention operations on the plane to be detected are avoided, and detection is reduced. The influence of itself on the plane has realized the intelligence of quality inspection on the construction site.

In step S102, area grid division is performed on the detected plane in the color image data to calculate pixel coordinates of grid vertices and intersection points in the evaluation area.

It can be understood that in the embodiment of the present application, the regional grid can be obtained by setting the parameters of the grid for the area to be detected and then segmented, and performing data processing on the detection area after the obtained grid division to obtain the grid vertices and intersection points The pixel coordinates of .

In the embodiment of the present application, the detected planes in the color image data can be divided into regional grids to calculate the pixel coordinates of the vertices and intersection points of the grids in the evaluation area, and the grid processing of the detected planes can be implemented to further extract the calculation results of the flatness. The required key nodes and coordinate information improve the data processing level of the flatness detection process.

Optionally, in one embodiment of the present application, the area grid division is performed on the detected plane in the color image data to calculate the pixel coordinates of the grid vertices and intersection points in the evaluation area, including: in the color image data, the point Select the vertices of the evaluation range to determine the evaluation area; set the number of rows and columns of the grid to generate a divided grid; on the basis of the divided grid, extract all the intersection coordinates in each grid one by one, Get pixel coordinates.

It can be understood that, in the embodiment of the present application, selecting the vertices of the evaluation range can be realized by determining the number of vertices and the specific positions of the vertices in the evaluation area. To generate the divided grid, the change of the four sides can be calculated according to the set row and column parameters, and then the unit length of each side after division can be calculated. The pixel coordinates can be obtained by calculating the coordinates of the intersection points in the grid.

In the actual execution process, first, as shown in Figure 2, a schematic diagram is determined for the scope of the evaluated area of an embodiment of the present application. When the area is composed of 4 vertices, the coordinates of the vertices can be respectively recorded as P ₁ (u ₁ , v ₁ ), P ₂ (u ₂ , v ₂ ), P ₃ (u ₃ , v ₃ ), P ₄ (u ₄ , v ₄ ), establish a plane coordinate system based on the color image, and place the point at the upper left corner of the color image is the origin of the coordinates, starting from the origin of the coordinates, the X-axis direction is from left to right, and the Y-axis direction is from top to bottom.

Then set the grid parameters. The number of rows and columns of the grid can be the main parameters of the set grid. The row parameters of the grid can be recorded as R, and the column parameters can be recorded as C. According to the set row and column parameters, respectively Calculate the X-axis and Y-axis changes of the four sides, which are recorded as L _x1 , L _x2 , L _x3 , L _x4 , L _y1 , L _y2 , L _y3 , and L _y4 , and the calculation formula is

L _x1 =u ₂ -u ₁

L _x2 =u ₃ -u ₂

L _x3 =u ₄ -u ₃

L _x4 =u ₄ -u ₁

L _y1 =v ₂ -v ₁

L _y2 =v ₃ -v ₂

L _y3 =v ₄ -v ₃

L _y4 =v ₄ -v ₁

Among them, L _x1 , L _x2 , L _x3 , L _x4 are the changes of the four sides of the X-axis respectively, L _y1 , L _y2 , L _y3 , and _Ly4 are the changes of the four sides of the Y-axis respectively, u ₁ , v ₁ , u ₂ , v ₂ , u ₃ , v ₃ , u ₄ , and v ₄ respectively correspond to the coordinate values corresponding to the set vertex coordinates P ₁ , P ₂ , P ₃ , and P ₄ . While calculating the X-axis and Y-axis changes of the four sides, calculate the unit length of each side after division, which is recorded as L _avg1 , L _avg2 , L _avg3 , and L _avg4 , and the calculation formula is

Among them, L _avg1 , L _avg2 , L _avg3 , and L _avg4 are the unit lengths of each edge after division, L _x4 , L _y4 , L _x2 , and _Ly2 are the change values of the corresponding sides of the X-axis and Y-axis respectively, and C is The number of columns of the grid, R is the number of columns of the grid, and the specific grid effect after division is shown in Figure 3.

Finally extract grid intersections, and on the basis of the divided grids, extract all intersection coordinates in each grid one by one, which can be recorded as P _i (u _i , v _i ), and store all intersection coordinates in the set M middle. When the number of rows is r and the number of columns is c, the two endpoints in each row are recorded as P _ro (u _ro , v _ro ), P _rc (u _rc , v _rc ), and the coordinates of P _ro and P _rc The calculation formula is

u _ro =u ₁ +L _avg1 ×r

v _ro =v ₁ +L _avg2 ×r

u _rc =u ₃ +L _avg3 ×r

v _rc =v ₃ +L _avg4 ×r

Among them, u _ro , v _ro , u _rc , and v _rc are the corresponding coordinate values of the front and rear endpoints of each row, and u ₁ , v ₁ , u ₃ , and v ₃ correspond to the set vertex coordinates P ₁ and P ₃ respectively. The coordinate values of , L _avg1 , L _avg2 , L _avg3 , and L _avg4 are the unit lengths of each edge after division, c is the number of grid columns, and r is the number of grid columns. Further, set any point in each row as P _ri (u _ri , v _ri ), and its coordinate calculation formula is:

Among them, u _ri and v _ri are the corresponding coordinate values of the i-th point in each row, u _ro , v _ro , u _rc , and v _rc are the corresponding coordinate values of the front and rear endpoints in each row, and c is the grid The number of columns, r is the number of columns of the grid, and 0≤ivc, the unit step of i is 1.

In the embodiment of the present application, in the color image data, click the vertices of the evaluation range to determine the evaluation area; set the number of rows and columns of the grid to generate a divided grid, and based on the divided grid , extracting all the intersection coordinates in each grid one by one to obtain the pixel coordinates, through the grid division and intersection extraction of the image data, the pixel coordinates of the intersection points in the grid are obtained, so as to further realize the evaluation of its spatial flatness.

In step S103, according to the mapping between the pixel coordinates of the grid vertices and intersection points in the area and the three-dimensional point cloud data, calculate the variance value of each intersection point relative to the absolute flat plane in the spatial position, and evaluate the flatness level of the plane to be detected .

It can be understood that in the embodiment of the present application, by mapping the pixel coordinates of the grid intersections to their three-dimensional coordinates in the point cloud data marked as D _i (xi _, y _i , zi ₎ , all grid intersections The spatial three-dimensional data of are all stored in the set K.

For example, Fig. 4 is a schematic diagram of the construction quality intelligent detection process of an embodiment of the present application. Through the acquisition of three-dimensional point cloud data, the final detection result is obtained by evaluating the regional grid division and the calculation of the regional flatness. Figure 5 shows.

The embodiment of the present application can calculate the variance value of each intersection point relative to the absolute flat plane in the spatial position according to the mapping between the pixel coordinates of the grid vertices and intersection points in the area and the three-dimensional point cloud data, and evaluate the flatness level of the plane to be detected , so as to realize the efficient evaluation of the flatness of the plane and improve the accuracy of the obtained detection results.

Optionally, in one embodiment of the present application, the variance value of each intersection point relative to the absolute flat plane in the spatial position is calculated according to the mapping between the pixel coordinates of the grid vertices and intersection points in the area and the three-dimensional point cloud data, Evaluate the flatness level of the plane to be detected, including: extracting the spatial coordinate data of each row of grid intersections, and calculating the average value of the three-dimensional coordinates of each row of grid intersections while calculating the variance value of each row of grid intersections; Variance and Mean Calculate the variance of the evaluation area to obtain the flatness level of the plane to be inspected.

It can be understood that in the embodiment of the present application, the spatial coordinate data of each row of grid intersections can be extracted from the set K, so as to calculate the variance of the grid intersections row by row, and then calculate the three-dimensional coordinates of each row of grid intersections The average value of z is calculated. The variance value of the evaluated area can be calculated from the variance value of each row of grid intersections and the average value of the variance value of each row of grid intersections within the evaluated area.

The embodiment of the present application can extract the spatial coordinate data of grid intersection points in each row, calculate the variance value of the grid intersection points row by row, and calculate the average value of the three-dimensional coordinates of the grid intersection points in each row, and then according to the variance value and the average Calculate the variance of the evaluation area to obtain the flatness level of the plane to be detected. Through the grid division of the data and the calculation of the variance value of the intersection, the accuracy of the flatness detection is improved, and the intelligent level of the detection is improved.

Optionally, in one embodiment of the present application, the calculation formula of the variance value of the grid intersection is:

Among them, var _rj is the variance of the jth grid intersection point, z _j is the three-dimensional coordinate of the jth grid intersection point, avg _zr is the average value of the three-dimensional coordinate z of the grid intersection point in each row, and c is the column number of the grid, r is the number of columns in the grid;

And, the calculation formula of the average value of the three-dimensional coordinates is:

Among them, avg _zr is the average value of the three-dimensional coordinate z of the grid intersection of each row, z _j is the three-dimensional coordinate of the jth grid intersection, c is the number of grid columns, and r is the number of grid columns.

It can be seen from the above formula that the variance value of the grid intersection point can be calculated by the three-dimensional coordinates of the grid intersection point and the average value of the three-dimensional coordinates of the grid intersection point in each row, and the average value of the three-dimensional coordinates of the grid intersection point in each row can be obtained through the grid The three-dimensional coordinates of the intersection point and the column value of the grid are calculated and obtained, thereby obtaining the variance value of the required grid intersection point, so as to perform further intelligent detection.

Optionally, in an embodiment of the present application, the formula for calculating the variance of the evaluation area is:

Among them, var _f is the variance of the evaluation area, var _rn is the variance of the nth grid intersection, avg _f is the average value of the variance value of each grid intersection in the evaluation area, and r is the number of grid columns.

It can be understood that, in the embodiment of the present application, avg _f is the average value of the variance value of the grid intersection of each row in the evaluated area, and its calculation formula is

Among them, avg _f is the average value of the variance value of the grid intersection of each row in the evaluated area, avg _rn is the average value of the variance of the nth grid intersection, and r is the number of columns of the grid.

In the embodiment of the present application, the detection result is obtained through the calculation formula of the variance of the evaluation area, thereby completing the numerical calculation process required by the intelligent detection process, and thus obtaining the detection effect of the flatness of the working plane.

According to the construction quality intelligent detection method proposed in the embodiment of the present application, the color image data and three-dimensional point cloud data of the plane to be detected can be obtained based on the binocular camera, and the area grid is divided into the detected plane in the color image data to calculate and evaluate The pixel coordinates of the grid vertices and intersection points in the area, according to the mapping between the pixel coordinates of the grid vertices and intersection points in the area and the three-dimensional point cloud data, calculate the variance value of each intersection point in the spatial position relative to the absolute flat plane, and evaluate the The flatness level of the detection plane, through the grid division of the operation plane and the calculation and processing of point cloud data, realizes the intelligent and accurate evaluation of the flatness of the operation plane, improves the detection efficiency of the flatness, and is more intelligent. Thus, it solves the problem that the flatness detection of the working plane in the related technology is highly dependent on manual operation or the driving level of the detection vehicle, and it is difficult to fully cover the detected working plane, resulting in low detection efficiency and accuracy, and insufficient applicability, etc. question.

Next, the construction quality intelligent detection device proposed according to the embodiment of the present application will be described with reference to the accompanying drawings.

Fig. 6 is a schematic block diagram of a construction quality intelligent detection device according to an embodiment of the present application.

As shown in FIG. 6 , the construction quality intelligent detection device 10 includes: an acquisition module 100 , a calculation module 200 and a detection module 300 .

Wherein, the obtaining module 100 is used to obtain color image data and three-dimensional point cloud data of the plane to be detected based on the binocular camera;

Calculation module 200, for carrying out area grid division to the detected plane in the color image data, to calculate the pixel coordinates of grid vertices and intersection points in the evaluation area;

The detection module 300 is used to calculate the variance value of each intersection point relative to the absolute flat plane in the spatial position according to the mapping between the pixel coordinates of the grid vertices and intersection points in the area and the three-dimensional point cloud data, and evaluate the flatness of the plane to be detected level.

Optionally, in an embodiment of the present application, the calculating module 200 includes: a clicking unit, a dividing unit and an extracting unit.

Wherein, the clicking unit is used to click the vertices of the evaluation range in the color image data to determine the evaluation area;

The division unit is used to set the number of rows and columns of the grid to generate the divided grid;

The extracting unit is configured to extract all intersection coordinates in each grid one by one on the basis of the divided grids to obtain pixel coordinates.

Optionally, in an embodiment of the present application, the detection module 300 includes: a first calculation unit and a second calculation unit.

Wherein, the first calculation unit is used to extract the spatial coordinate data of each row of grid intersections, and calculate the average value of the three-dimensional coordinates of each row of grid intersections while calculating the variance value of the grid intersections row by row;

The second calculation unit is used to calculate the variance of the evaluation area according to the variance value and the average value, so as to obtain the flatness level of the plane to be detected.

Optionally, in one embodiment of the present application, the calculation formula of the variance value of the grid intersection is:

Among them, var _rj is the variance of the jth grid intersection point, z _j is the three-dimensional coordinate of the jth grid intersection point, avg _zr is the average value of the three-dimensional coordinate z of the grid intersection point in each row, and c is the column number of the grid, r is the number of columns in the grid;

And, the calculation formula of the average value of the three-dimensional coordinates is:

Among them, avg _zr is the average value of the three-dimensional coordinate z of the grid intersection of each row, z _j is the three-dimensional coordinate of the jth grid intersection, c is the number of grid columns, and r is the number of grid columns.

Optionally, in an embodiment of the present application, the formula for calculating the variance of the evaluation area is:

Among them, var _f is the variance of the evaluation area, var _rn is the variance of the nth grid intersection, avg _f is the average value of the variance value of each grid intersection in the evaluation area, and r is the number of grid columns.

It should be noted that the foregoing explanations on the embodiment of the construction quality intelligent detection method are also applicable to the construction quality intelligent detection device of this embodiment, and will not be repeated here.

According to the construction quality intelligent detection device proposed in the embodiment of the present application, based on the binocular camera, the color image data and three-dimensional point cloud data of the plane to be detected can be obtained, and the area grid division of the detected plane in the color image data is carried out to calculate and evaluate The pixel coordinates of the grid vertices and intersection points in the area, according to the mapping between the pixel coordinates of the grid vertices and intersection points in the area and the three-dimensional point cloud data, calculate the variance value of each intersection point in the spatial position relative to the absolute flat plane, and evaluate the The flatness level of the detection plane, through the grid division of the operation plane and the calculation and processing of point cloud data, realizes the intelligent and accurate evaluation of the flatness of the operation plane, improves the detection efficiency of the flatness, and is more intelligent. Thus, it solves the problem that the flatness detection of the working plane in the related technology is highly dependent on manual operation or the driving level of the detection vehicle, and it is difficult to fully cover the detected working plane, resulting in low detection efficiency and accuracy, and insufficient applicability, etc. question.

FIG. 7 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. This electronic equipment can include:

A memory 701 , a processor 702 , and a computer program stored in the memory 701 and executable on the processor 702 .

When the processor 702 executes the program, the method for intelligent detection of construction quality provided in the above-mentioned embodiments is implemented.

Further, the electronic equipment also includes:

The communication interface 703 is used for communication between the memory 701 and the processor 702 .

The memory 701 is used to store computer programs that can run on the processor 702 .

The memory 701 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

If the memory 701, the processor 702, and the communication interface 703 are implemented independently, the communication interface 703, the memory 701, and the processor 702 may be connected to each other through a bus to complete mutual communication. The bus may be an Industry Standard Architecture (Industry Standard Architecture, ISA for short) bus, a Peripheral Component Interconnect (PCI for short) bus, or an Extended Industry Standard Architecture (EISA for short) bus. The bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in FIG. 7 , but it does not mean that there is only one bus or one type of bus.

Optionally, in specific implementation, if the memory 701, processor 702, and communication interface 703 are integrated on one chip, then the memory 701, processor 702, and communication interface 703 can communicate with each other through the internal interface.

The processor 702 may be a central processing unit (Central Processing Unit, referred to as CPU), or a specific integrated circuit (Application Specific Integrated Circuit, referred to as ASIC), or configured to implement one or more of the embodiments of the present application integrated circuit.

This embodiment also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above method for intelligent detection of construction quality is realized.

In the description of this specification, descriptions referring to the terms "one embodiment", "some embodiments", "example", "specific examples", or "some examples" mean that specific features described in connection with the embodiment or example , structure, material or characteristic is included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the described specific features, structures, materials or characteristics may be combined in any one or N embodiments or examples in an appropriate manner. In addition, those skilled in the art can combine and combine different embodiments or examples and features of different embodiments or examples described in this specification without conflicting with each other.

In addition, the terms "first" and "second" are used for descriptive purposes only, and cannot be interpreted as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of these features. In the description of the present application, "N" means at least two, such as two, three, etc., unless otherwise specifically defined.

Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or N steps of executable instructions for implementing a custom logical function or process, Also, the scope of preferred embodiments of the present application includes additional implementations in which functions may be performed out of the order shown or discussed, including substantially concurrently or in reverse order depending on the functions involved, which should be considered Those skilled in the art to which the embodiments of the present application belong can understand.

The logic and/or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium, For use with instruction execution systems, devices, or devices (such as computer-based systems, systems including processors, or other systems that can fetch instructions from instruction execution systems, devices, or devices and execute instructions), or in conjunction with these instruction execution systems, devices or equipment used. For the purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use in or in conjunction with an instruction execution system, device or device. More specific examples (non-exhaustive list) of computer readable media include the following: electrical connection with one or N wires (electronic device), portable computer disk case (magnetic device), random access memory (RAM), Read Only Memory (ROM), Erasable and Editable Read Only Memory (EPROM or Flash Memory), Fiber Optic Devices, and Portable Compact Disc Read Only Memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program can be printed, since the paper or other medium can be optically scanned and subsequently edited, interpreted, or in other suitable manner as necessary Processing is performed to obtain the program electronically and then to store it in a computer memory.

It should be understood that each part of the present application may be realized by hardware, software, firmware or a combination thereof. In the above embodiments, the N steps or methods may be implemented by software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented by any one or a combination of the following techniques known in the art: a discrete Logic circuits, ASICs with suitable combinational logic gates, Programmable Gate Arrays (PGA), Field Programmable Gate Arrays (FPGA), etc.

Those of ordinary skill in the art can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. During execution, one or a combination of the steps of the method embodiments is included.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing module, each unit may exist separately physically, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software function modules. If the integrated modules are implemented in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium.

The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, and the like. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limitations on the present application, and those skilled in the art can make the above-mentioned The embodiments are subject to changes, modifications, substitutions and variations.

Claims (12)

1. The construction quality intelligent detection method is characterized by comprising the following steps of:

based on a binocular camera, color image data and three-dimensional point cloud data of a plane to be detected are obtained;

performing region meshing on the detected plane in the color image data to calculate pixel coordinates of grid vertices and intersection points in an evaluation region; and

and calculating the variance value of each intersection point relative to an absolute flat plane in a space position according to the pixel coordinates of the grid vertexes and the intersection points in the area and the mapping between the three-dimensional point cloud data, and evaluating the flatness level of the plane to be detected.

2. The method of claim 1, wherein the region meshing of the detected planes in the color image data to calculate pixel coordinates of mesh vertices and intersections in an evaluation region comprises:

clicking a vertex of an evaluation range in the color image data to determine the evaluation area;

setting the number of rows and columns of the grid, and generating a divided grid;

and extracting all intersection point coordinates in each grid one by one on the basis of the divided grids to obtain the pixel coordinates.

3. The method according to claim 2, wherein the calculating a variance value of each intersection point in a spatial position with respect to an absolute flat plane from a mapping between pixel coordinates of grid vertices and intersection points in the region and the three-dimensional point cloud data, and evaluating a flatness level of the plane to be detected, comprises:

extracting space coordinate data of each row of grid intersection points, calculating the variance value of the grid intersection points row by row, and calculating the average value of the three-dimensional coordinates of each row of grid intersection points;

and calculating the variance of the evaluation area according to the variance value and the average value to obtain the flatness level of the plane to be detected.

4. A method according to claim 3, wherein the variance value of the grid intersection is calculated by the formula:

wherein va isr _rj Variance of the j-th grid intersection, z _j Avg, which is the three-dimensional coordinates of the j-th mesh intersection point _zr The average value of three-dimensional coordinates z of each row of grid intersection points is calculated, c is the number of columns of the grid, and r is the number of columns of the grid;

and, the calculation formula of the average value of the three-dimensional coordinates is:

wherein avg _zr For the average value of three-dimensional coordinates z of each row of grid intersection points, z _j The three-dimensional coordinate of the intersection point of the jth grid is c, the column number of the grid is c, and r is the column number of the grid.

5. The method of claim 4, wherein the variance of the assessment area is calculated as:

wherein var _f To evaluate the variance of the region, var _rn For variance, avg of nth grid intersection _f For the average value of the intersection variance values of each row of grids in the evaluation area, r is the number of columns of the grids.

6. The utility model provides a construction quality intelligent detection device which characterized in that includes:

the acquisition module is used for acquiring color image data and three-dimensional point cloud data of a plane to be detected based on the binocular camera;

the computing module is used for carrying out regional grid division on the detected plane in the color image data so as to compute pixel coordinates of grid vertexes and intersection points in an evaluation region; and

and the detection module is used for calculating the variance value of each intersection point relative to an absolute flat plane in the space position according to the pixel coordinates of the grid vertexes and the intersection points in the area and the mapping between the three-dimensional point cloud data, and evaluating the flatness level of the plane to be detected.

7. The apparatus of claim 6, wherein the computing module comprises:

a clicking unit configured to click, in the color image data, a vertex of an evaluation range to determine the evaluation area;

the dividing unit is used for setting the number of rows and the number of columns of the grid and generating a divided grid;

and the extraction unit is used for extracting all the intersection point coordinates in each grid one by one on the basis of the divided grids to obtain the pixel coordinates.

8. The apparatus of claim 7, wherein the detection module comprises:

the first calculation unit is used for extracting the space coordinate data of each row of grid intersection points, calculating the variance value of the grid intersection points row by row and calculating the average value of the three-dimensional coordinates of each row of grid intersection points;

and the second calculation unit is used for calculating the variance of the evaluation area according to the variance value and the average value so as to obtain the flatness level of the plane to be detected.

9. The apparatus of claim 8, wherein the variance value of the grid intersection is calculated by the formula:

wherein var _rj Variance of the j-th grid intersection, z _j Avg, which is the three-dimensional coordinates of the j-th mesh intersection point _zr The average value of three-dimensional coordinates z of each row of grid intersection points is calculated, c is the number of columns of the grid, and r is the number of columns of the grid;

and, the calculation formula of the average value of the three-dimensional coordinates is:

wherein avg _zr For the average value of three-dimensional coordinates z of each row of grid intersection points, z _j The three-dimensional coordinate of the intersection point of the jth grid is c, the column number of the grid is c, and r is the column number of the grid.

10. The apparatus of claim 9, wherein the variance of the evaluation area is calculated by the formula:

wherein var _f To evaluate the variance of the region, var _rn For variance, avg of nth grid intersection _f For the average value of the intersection variance values of each row of grids in the evaluation area, r is the number of columns of the grids.

11. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the construction quality intelligent detection method according to any one of claims 1-5.

12. A computer-readable storage medium having stored thereon a computer program, characterized in that the program is executed by a processor for realizing the construction quality intelligent detection method according to any one of claims 1 to 5.

Images