A method and system for detecting building wall surface quality

Abstract

The present invention relates to the field of building wall detection, and specifically to a building wall surface quality detection method and system, comprising: obtaining at least one column of data points on the building wall surface, each column of data points including a plurality of three-dimensional coordinate points located in the same column on the building wall surface; for each column of data points, dividing the data points of the column into a plurality of height levels, and performing least squares fitting on the data points of each height level to obtain a fitting straight line corresponding to each height level; for each data point, calculating the importance of the data point according to the parameter information of the fitting straight line corresponding to the height level and the positional relationship between the data points in the height level and the corresponding fitting straight line; constructing a regression model with the importance of each data point as a weight, and detecting the verticality of the building wall surface based on the constructed regression model. A more accurate fitting result can be obtained, and the accuracy of wall surface quality detection can be improved.

Description

Technical Field

[0001] The present invention relates to the field of building wall detection, and in particular to a building wall surface quality detection method and system. Background Art

[0002] The verticality of the building wall is an important part of the quality of the construction project. It is directly related to the structural safety, appearance and subsequent construction efficiency of the building. If the verticality of the building wall is not up to standard, there will be great safety hazards in the quality of the building wall, and serious cases may even cause great casualties. Testing the verticality of the building wall can promptly detect the problem of the tilt of the building wall, and promptly identify the hidden dangers of the tilt of the building wall, so that the staff can promptly reinforce the building wall and other repair treatments, thereby ensuring the quality of the building wall. It can be seen that it is necessary and important to test the verticality of the building wall.

[0003] In the prior art, a regression model is usually constructed to reflect the actual tilt condition of a building wall surface, so as to realize the verticality detection of a building wall surface. However, when constructing the regression model, some data points with poor performance in representing the actual tilt condition of the building wall surface interfere, so that the constructed regression model is greatly different from the actual tilt condition of the building wall surface, and cannot provide an accurate model basis for subsequent verticality detection. Summary of the invention

[0004] In order to solve the above technical problems, the object of the present invention is to provide a method for detecting the quality of a building wall surface, comprising:

[0005] Acquire at least one column of data points on a wall surface of a building, wherein each column of data points includes a plurality of three-dimensional coordinate points located in the same column on the wall surface of the building;

[0006] For each column of data points, multiple data points in the column are divided into multiple height levels according to the height data, and the data points of each height level are fitted by least squares to obtain the fitting straight line corresponding to each height level;

[0007] For each data point, the importance of the data point is calculated based on the parameter information of the fitting line corresponding to the height level of the data point and the positional relationship between the data points in the height level of the data point and the corresponding fitting line;

[0008] The importance of each data point is used as the weight, and the least square method is used to build a regression model. The verticality of the building wall is detected based on the constructed regression model.

[0009] Optionally, for each data point, calculating the importance of the data point according to parameter information of the fitting line corresponding to the height level where the data point is located and the positional relationship between the data points within the height level where the data point is located and the fitting line corresponding to the data point, includes:

[0010] Calculate the abnormal degree of wall inclination at each height level according to the parameter information of the corresponding fitting straight line;

[0011] For each data point, the position correlation feature of the data point is calculated according to the position relationship between the data point and the corresponding fitting line within the height level;

[0012] The importance of the data point is calculated based on the location correlation characteristics of the data point and the abnormal degree of wall inclination at the height level where the data point is located.

[0013] Optionally, the parameter information of the fitting line includes a parameter vector of the fitting line, an angle between the fitting line and the horizontal direction, and a slope of the fitting line, and the calculating the abnormal degree of wall inclination at each height level according to the corresponding parameter information of the fitting line includes:

[0014] For each height level, the height importance of the height level is calculated according to the parameter vector of the fitting line corresponding to the height level;

[0015] According to the height importance of the height level, the angle between each fitting line and the horizontal direction and the slope of the fitting line corresponding to the height level, the abnormal degree of wall inclination at the height level is calculated.

[0016] Optionally, for each height level, calculating the height importance of the height level according to the parameter vector of the fitting line corresponding to the height level includes:

[0017] For each height level, the height importance of the height level is calculated according to the height level and the difference norm between the parameter vector of the fitting line corresponding to the height level and the parameter vector of the fitting line corresponding to the target height level.

[0018] Optionally, the target height level is a first height level, and data points in higher height levels have higher heights.

[0019] Optionally, calculating the importance of the data point according to the position correlation feature of the data point and the abnormal degree of wall inclination at the height level where the data point is located includes:

[0020] According to the location correlation characteristics of the data point and the abnormal degree of wall inclination at the height level where the data point is located, the significance of the location abnormality of the data point is calculated;

[0021] The inverse of the position anomaly significance of the data point is taken as the importance of the data point.

[0022] Optionally, the calculating of the position correlation feature of the data point according to the position relationship between the data point and the corresponding fitting line within the height level includes:

[0023] The ratio of the first number to the second number is calculated as the position correlation feature of the data point, wherein the first number is the number of data points that are continuous with the data point and located on the same side of the corresponding fitting line as the data point within the height level where the data point is located, and the second number is the total number of data points that are located on the same side of the corresponding fitting line as the data point within the height level where the data point is located.

[0024] Optionally, the at least one column of data points is a column of data points, and the importance of each data point is used as a weight, a regression model is constructed by using a least square method, and the verticality of a building wall is detected based on the constructed regression model, including:

[0025] The importance of each data point is used as the weight, and the least square method is used to fit the final fitting line;

[0026] The verticality of the building wall is evaluated based on the distance between each data point and the final fitting straight line.

[0027] Optionally, obtaining at least one column of data points on a wall surface of a building includes:

[0028] At least one column of data points on the wall surface of the building is obtained by laser scanning the wall surface of the building.

[0029] The present invention also provides a building wall surface quality detection system, the system comprising:

[0030] An acquisition module, used to acquire at least one column of data points on a wall surface of a building, wherein each column of data points includes a plurality of three-dimensional coordinate points located in the same column on the wall surface of the building;

[0031] A fitting module is used to divide multiple data points in each column of data points into multiple height levels according to the height data, and perform least square fitting on the data points of each height level to obtain a fitting straight line corresponding to each height level;

[0032] A calculation module, for calculating the importance of each data point according to parameter information of the fitting line corresponding to the height level of the data point and the positional relationship between the data points in the height level of the data point and the corresponding fitting line;

[0033] The detection module is used to construct a regression model using the least square method with the importance of each data point as the weight, and detect the verticality of the building wall based on the constructed regression model.

[0034] The present invention has the following beneficial effects: by dividing the data points into a plurality of different height levels and performing straight line fitting based on the data points in each height level, the importance of each data point is calculated according to the parameter information of the fitting line corresponding to each height level and the position of the data point relative to the fitting line corresponding to the height level where the data point is located, a regression model is constructed with the importance of each data point as the weight of the least square method, and finally the verticality of the wall surface of the building is detected based on the constructed regression model. In this way, the weight of the data point is determined according to the abnormal inclination degree of the wall surface where the data point is located, so that a more accurate fitting result can be obtained, thereby improving the accuracy of the regression model and the accuracy of the verticality detection of the wall surface of the building. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 A first schematic diagram of a building wall surface quality detection method provided by an embodiment of the present invention;

[0037] Figure 2 A second schematic diagram of the building wall surface quality detection method provided by an embodiment of the present invention;

[0038] Figure 3 A first schematic diagram of the distribution positions between data points and fitting straight lines provided in an embodiment of the present invention;

[0039] Figure 4 A second schematic diagram of the distribution positions between the data points and the fitting straight line provided in an embodiment of the present invention;

[0040] Figure 5 A schematic diagram of a building wall surface quality detection system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a building wall surface quality detection method proposed by the present invention, its specific implementation method, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0042] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0043] The present invention provides a method for detecting the quality of a building wall surface. The scheme of the present invention is described in detail below in conjunction with the accompanying drawings.

[0044] See also Figure 1 , which shows a first schematic diagram of a building wall surface quality detection method provided by an embodiment of the present invention, the building wall surface quality detection method (hereinafter referred to as "the method") comprises the following steps:

[0045] Step 101: Acquire at least one column of data points on a wall surface of a building, wherein each column of data points includes a plurality of three-dimensional coordinate points located in the same column on the wall surface of the building.

[0046] In this step, the method obtains at least one column of data points on the wall surface of the building, wherein each column of data points includes a plurality of three-dimensional coordinate points located in the same column on the wall surface of the building. The method obtains data points by receiving data points of the wall surface of the building to be inspected for quality sent by other devices, or by controlling a device to perform a three-dimensional scan on the wall surface of the building to be inspected for quality. The data points may be three-dimensional coordinate points obtained by laser scanning the wall surface of the building, or may be three-dimensional coordinate points obtained by other three-dimensional scanning methods, which are not specifically limited in the embodiments of the present invention.

[0047] Step 102: for each column of data points, divide the multiple data points in the column into multiple height levels according to the height data, and perform least squares fitting on the data points of each height level to obtain a fitting straight line corresponding to each height level.

[0048] In this step, for each column of data points, the method divides the multiple data points in the column into multiple height levels according to the height data of the data points, and performs least squares fitting on the data points of each height level respectively, to obtain the fitted straight lines corresponding to each height level. The method can determine the number of height levels according to actual conditions, for example, when higher accuracy and stronger computing power are required, a larger number of height levels can be selected. For the divided height levels, the data points in a higher height level have a higher height than the data points in a lower height level. The method of fitting the data points using the least squares method to obtain a fitted straight line belongs to the scope of the prior art and will not be described in detail here.

[0049] Step 103: For each data point, the importance of the data point is calculated according to the parameter information of the fitting line corresponding to the height level of the data point and the positional relationship between the data points within the height level of the data point and the corresponding fitting line.

[0050] In this step, for each data point, the method calculates the importance of the data point according to the parameter information of the fitting line corresponding to the height level of the data point and the positional relationship between the data points in the height level of the data point and the corresponding fitting line. Specifically, the method can calculate the abnormal degree of wall inclination at each height level according to the parameter information of the fitting line corresponding to the height level, and then for each data point, calculate the positional correlation feature of the data point according to the positional relationship between the data points in the height level and the corresponding fitting line, and finally calculate the importance of the data point according to the positional correlation feature of the data point and the abnormal degree of wall inclination at the height level. The parameter information of the fitting line includes the parameter vector of the fitting line, the angle between the fitting line and the horizontal direction, and the slope of the fitting line.

[0051] Step 104: Using the importance of each data point as a weight, a least square method is used to construct a regression model, and the verticality of the building wall is detected based on the constructed regression model.

[0052] In this step, the method uses the importance of each data point as a weight, uses the least squares method to construct a regression model, and detects the verticality of the building wall surface based on the constructed regression model. Specifically, when the at least one column of data points is only one column of data points, the method can use the importance of each data point as a weight, use the least squares method to fit to obtain a final fitting line, and then evaluate the verticality of the building wall surface according to the distance between each data point and the final fitting line. When the at least one column of data points includes multiple columns of data points, the method can use the importance of each data point as a weight, use the least squares method to fit to obtain a final fitting plane, and then evaluate the verticality and / or flatness of the building wall surface according to the distance between each data point and the final fitting plane.

[0053] In an embodiment of the present invention, the method divides the data points into a plurality of different height levels and performs straight line fitting based on the data points in each height level, and then calculates the importance of each data point according to the parameter information of the fitting line corresponding to each height level and the position of the data point relative to the fitting line corresponding to the height level where it is located, and constructs a regression model with the importance of each data point as the weight of the least square method, and finally detects the verticality of the wall surface of the building based on the constructed regression model. In this way, the weight of the data point is determined according to the abnormal tilt degree of the wall surface where the data point is located, and a more accurate fitting result can be obtained, thereby improving the accuracy of the regression model and the accuracy of the verticality detection of the wall surface of the building.

[0054] Optionally, the at least one column of data points is a column of data points, and the importance of each data point is used as a weight, a least squares method is used to construct a regression model, and the verticality of the building wall surface is detected based on the constructed regression model, including: taking the importance of each data point as a weight, and fitting with the least squares method to obtain a final fitting straight line; evaluating the verticality of the building wall surface according to the distance between each data point and the final fitting straight line.

[0055] In this embodiment, the at least one column of data points is a column of data points, and the method uses the importance of each data point as a weight, uses the least square method to perform fitting to obtain a final fitting line, and then evaluates the verticality of the building wall surface according to the distance between each data point and the final fitting line. For example, the distance between each data point and the final fitting line can be calculated respectively, and then the verticality of the building wall surface can be evaluated according to the maximum deviation (i.e., the maximum difference) among these distances.

[0056] After the final fitting straight line is obtained through fitting, data analysis software or manual calculation can be used to determine whether the maximum deviation of the distance from the building wall to the final fitting straight line is within the allowable deviation range. If it exceeds the allowable deviation range, corresponding correction measures need to be taken, such as reinforcing the building wall, to avoid possible safety hazards in time.

[0057] Optionally, acquiring at least one column of data points on the wall surface of the building includes: acquiring at least one column of data points on the wall surface of the building by laser scanning the wall surface of the building.

[0058] In this embodiment, the method obtains at least one column of data points on the wall surface of the building by laser scanning the wall surface of the building. For example, for a column of data points, a three-dimensional laser scanner can be used to perform a three-dimensional scan on a column of the wall surface of the building to obtain the three-dimensional coordinate information of each scanning point in the column as a column of data points on the wall surface of the building. The three-dimensional laser scanner obtains the three-dimensional coordinate information of the object to be measured through a laser ranging system and an angle measuring system. The laser ranging system emits a laser to the object to be measured and records the time from the laser emission to the return, and calculates the distance through the speed of light and the time difference. The angle measuring system records the horizontal angle and vertical angle between the scanning instrument and the object to be measured. Through these data, the three-dimensional coordinate information of the object to be measured can be inversely calculated. The three-dimensional scanning of the object to be measured by a three-dimensional laser scanner to obtain the three-dimensional coordinate information of the object to be measured belongs to the scope of the prior art and will not be described in detail here.

[0059] Please read further Figure 2 , Figure 2 is a second schematic diagram of the building wall surface quality detection method provided by an embodiment of the present invention, such as Figure 2 As shown, the method comprises the following steps:

[0060] Step 201: Acquire at least one column of data points on a wall surface of a building, wherein each column of data points includes a plurality of three-dimensional coordinate points located in the same column on the wall surface of the building.

[0061] Step 202: for each column of data points, divide the multiple data points in the column into multiple height levels according to the height data, and perform least squares fitting on the data points of each height level to obtain a fitting straight line corresponding to each height level.

[0062] Steps 201 and 202 are Figure 1 Steps 101 and 102 in the illustrated embodiment are the same and will not be described in detail herein.

[0063] Step 203: Calculate the abnormal degree of wall inclination at each height level according to the parameter information of the corresponding fitting line.

[0064] In this step, the method calculates the abnormal degree of wall tilt at each height level according to the parameter information of the fitting line corresponding to the height level. The parameter information of the fitting line may include the parameter vector of the fitting line, the angle between the fitting line and the horizontal direction, and the slope of the fitting line. Accordingly, for each height level, the method can calculate the height importance of the height level according to the parameter vector of the fitting line corresponding to the height level, and then calculate the abnormal degree of wall tilt at the height level according to the height importance of the height level, the angle between each fitting line and the horizontal direction, and the slope of the fitting line corresponding to the height level.

[0065] Step 204: For each data point, calculate the position correlation feature of the data point according to the position relationship between the data point and the corresponding fitting line within the height level.

[0066] In this step, for each data point, the method calculates the positional correlation feature of the data point based on the positional relationship between the data point and the corresponding fitted line within the height level where the data point is located. In some embodiments, for a certain data point, the method can determine the first quantity and the second quantity based on the positional relationship between the data point and the corresponding fitted line within the height level where the data point is located, and then calculate the ratio of the first quantity and the second quantity as the positional correlation feature of the data point. The first quantity is the number of data points that are continuous with the data point and located on the same side of the corresponding fitted line as the data point within the height level where the data point is located, and the second quantity is the total number of data points that are located on the same side of the corresponding fitted line as the data point within the height level where the data point is located.

[0067] Step 205: Calculate the importance of the data point based on the position correlation characteristics of the data point and the abnormal degree of wall inclination at the height level where the data point is located.

[0068] In this step, the method calculates the importance of the data point according to the position correlation characteristics of the data point and the abnormal degree of the wall tilt at the height level where the data point is located. Specifically, the method can calculate the position anomaly significance of the data point according to the position correlation characteristics of the data point and the abnormal degree of the wall tilt at the height level where the data point is located, and then use the inverse of the position anomaly significance of the data point as the importance of the data point.

[0069] Step 206: Using the importance of each data point as a weight, a least square method is used to construct a regression model, and the verticality of the building wall is detected based on the constructed regression model.

[0070] The step 206 and Figure 1 Step 104 in the illustrated embodiment is the same and will not be described again here.

[0071] In this embodiment, by dividing the data points into a plurality of different height levels and performing straight line fitting based on the data points in each height level, the degree of abnormal wall tilt at each height level is calculated based on the fitted straight line, and the importance of each data point is calculated according to the positional relationship of the data point relative to the corresponding fitting straight line and the degree of abnormal wall tilt corresponding to the height level where the data point is located, a regression model is constructed with the importance of each data point as the weight of the least square method, and finally the verticality of the building wall surface is detected based on the constructed regression model. In this way, the weight of the data point is determined according to the abnormal tilt degree of the wall surface where the data point is located, and a more accurate fitting result can be obtained, thereby improving the accuracy of the regression model and the accuracy of the verticality detection of the building wall surface.

[0072] Optionally, the parameter information of the fitting straight line includes a parameter vector of the fitting straight line, an angle between the fitting straight line and the horizontal direction, and a slope of the fitting straight line. The method of calculating the abnormal degree of wall inclination at each height level according to the corresponding parameter information of the fitting straight line includes: for each height level, calculating the height importance of the height level according to the parameter vector of the fitting straight line corresponding to the height level; and calculating the abnormal degree of wall inclination at the height level according to the height importance of the height level, the angle between each fitting straight line and the horizontal direction and the slope of the fitting straight line corresponding to the height level.

[0073] A common factor that causes uneven wall surfaces on building walls is measurement errors. As the height of building walls increases, measurement errors continue to accumulate, causing the building walls to tilt to a certain extent, which in turn causes data points at different locations on the building wall to have large differences in their ability to express the theoretical straight line of the real building wall. It is understandable that wall sections at lower heights on the building wall are not prone to tilt, so the data points at lower heights are more able to reflect the theoretical straight line of the building wall; while data points at higher heights usually have smaller wall thicknesses due to error accumulation, and there are large differences in load capacity at different locations, which makes it easier for building walls at higher heights to tilt, so the data points at higher heights cannot better reflect the theoretical straight line of the building wall.

[0074] In the actual detection process, it is also possible that a certain inclination has already appeared at a lower height of the building wall. Although the fitting lines between different height levels are similar at this time, the data points still have a high height importance. In fact, the building wall segments where these data points are located are tilted, which will lead to inaccurate final fitting regression models. Based on the fact that the inclination of the building wall will be more significant with the height characteristics, it will shift in the direction of the inclination of the building wall. Therefore, the slope change trend characteristics of the fitting lines at each height level can be used to determine the possibility of inclination of the building wall segment corresponding to the height level. If the directions of the fitting lines corresponding to each height level are highly consistent and the difference with the vertical direction is small, it means that the possibility of the straight line corresponding to the building wall theory is greater; on the contrary, if the directions of the fitting lines corresponding to each height level have an obvious change trend, it means that the possibility of the building wall being tilted is greater, and the possibility of being the straight line corresponding to the building wall theory is smaller.

[0075] Therefore, in this embodiment, for each height level, the height importance of the height level is calculated based on the parameter vector of the fitting straight line corresponding to the height level, and then the degree of abnormal wall inclination at the height level is calculated based on the height importance of the height level, the angle between each fitting straight line and the horizontal direction, and the slope of the fitting straight line corresponding to the height level.

[0076] Specifically, for the The height level can be calculated using the following formula Abnormal degree of wall tilt at each height level :

[0077]

[0078] in, For the The abnormal degree of wall tilt at each height level, For the A high level number, For the The slope of the fitted straight line corresponding to the height level, For the The angle between the fitting line corresponding to each height level and the horizontal direction, For the The angle between the fitting line corresponding to each height level and the horizontal direction, For the A high level of importance, For the A high level of importance, is the total number of height levels.

[0079] In the above formula, Indicates The angle between the fitting line corresponding to the first height level and the horizontal direction and the The sine value of the angle difference between the fitting line corresponding to the height level and the horizontal direction, that is, The fitting straight line corresponding to the height level The sine value of the angle between the fitted straight lines corresponding to the height levels indicates the similarity between the two angles; Indicates The sine value of the angle difference between the angle between the fitting line corresponding to each height level and the horizontal direction and the angle between the vertical direction and the horizontal direction; Indicates height level and The overall importance of each height level, as a weight for the differences between angles; Indicates height level and The directional difference between the height levels. The larger the value, the higher the The data points of the height level are The more obvious the directional differences of the data points at each height level; Indicates The consistency of the direction difference between the fitted straight line corresponding to the first height level and the fitted straight lines corresponding to the other height levels. The larger the value, the more consistent the direction difference between the first height level and the other height levels. The worse the consistency of the direction difference between the fitting straight line corresponding to the first height level and the fitting straight lines corresponding to the other height levels; For the The slope of the fitted straight line corresponding to the height level reflects the The relationship between the fitting direction and height of the fitting line corresponding to the height level. The larger the value, the higher the height level. The higher the height level of a building, the greater the possibility that a wall section will be tilted.

[0080] Optionally, for each height level, the height importance of the height level is calculated based on the parameter vector of the fitted straight line corresponding to the height level, including: for each height level, the height importance of the height level is calculated based on the height level and the difference norm between the parameter vector of the fitted straight line corresponding to the height level and the parameter vector of the fitted straight line corresponding to the target height level.

[0081] It is mentioned above that the wall segments at lower heights on the wall surface of a building are less likely to tilt. If the fitting straight line corresponding to a certain height level is highly consistent with the fitting straight line at a lower height, it means that the possibility of obvious tilt of the building wall segment corresponding to the height level is relatively small, and thus the data points within this height level should also have a higher importance.

[0082] In this embodiment, for each height level, the method can calculate the height importance of the height level according to the height level and the difference norm between the parameter vector of the fitted line corresponding to the height level and the parameter vector of the fitted line corresponding to the target height level. The parameter vector can be a two-dimensional vector composed of the parameters of the fitted line (such as slope and intercept). The height level can be calculated by constructing the following formula: :

[0083]

[0084] in, For the A high level of importance, For the A high level number, For the The parameter vector of the fitted line corresponding to the height level, is the parameter vector of the fitting line corresponding to the first height level, " is the norm operation of the orientation quantity, is a linear normalization function used for normalization processing.

[0085] Optionally, the target height level is a first height level, and data points in higher height levels have higher heights.

[0086] Optionally, the calculating the importance of the data point based on the position correlation characteristics of the data point and the abnormal degree of wall inclination at the height level at which the data point is located includes: calculating the significance of the position anomaly of the data point based on the position correlation characteristics of the data point and the abnormal degree of wall inclination at the height level at which the data point is located; and taking the inverse of the significance of the position anomaly of the data point as the importance of the data point.

[0087] In this embodiment, the method calculates the position anomaly significance of the data point based on the position correlation characteristics of the data point and the abnormal degree of wall inclination at the height level where the data point is located; and the inverse of the position anomaly significance of the data point is used as the importance of the data point. Within the height level data points, the first The location of the data point is abnormally significant :

[0088]

[0089] in, For the Within the height level The position of the data point is abnormally significant. For the The abnormal degree of wall tilt at each height level, Indicates Within the height level The position correlation characteristics of the data points, Indicates The median of the position correlation characteristics of all data points within the height level, is a linear normalization function used for normalization processing.

[0090] For a data point, the greater the significance of its position anomaly, the less likely it is that the data point will be the line where the building wall theory is located, and the greater the interference to the final fitting line. In order to improve the performance of the final fitting line for the wall, such data points should be given a smaller importance weight to reduce the interference to the entire regression model during the fitting process. Within the height level data points, and calculate the abnormal significance of their position Then, the first The importance of each data point :

[0091]

[0092] in, For the Within the height level The importance of each data point, For the Within the height level The location of the data point is abnormally significant.

[0093] Optionally, the method of calculating the position correlation feature of the data point based on the positional relationship between the data point and its corresponding fitted straight line within the height level includes: calculating a ratio of a first quantity to a second quantity as the position correlation feature of the data point, wherein the first quantity is the number of data points within the height level where the data point is located, which are continuous with the data point and located on the same side of the corresponding fitted straight line as the data point, and the second quantity is the total number of data points within the height level where the data point is located, which are located on the same side of the corresponding fitted straight line as the data point.

[0094] Please include the parameters Figure 3 and 4 picture, Figure 3 The position relationship between the data points and the corresponding fitting straight line in a certain inclined wall segment is shown. Figure 4 The positional relationship between the data points and the corresponding fitting straight line in a normal building wall segment is shown. It can be seen that for a data point within a height level, the smaller the randomness of its positional relationship with the fitting straight line corresponding to the height level, the more significant the tilt feature of the wall segment corresponding to the height level. In this embodiment, the method calculates the ratio of the first number to the second number as the positional correlation feature of the data point, wherein the first number is the number of data points within the height level where the data point is located, which are continuous with the data point and located on the same side of the fitting straight line corresponding to the data point, and the second number is the total number of data points within the height level where the data point is located, which are located on the same side of the fitting straight line corresponding to the data point.

[0095] Specifically, for the Within the height level data points, the first The location correlation characteristics of data points :

[0096]

[0097] in, For the Within the height level The location correlation features of data points, is the first quantity, i.e. The height level where the data point is located is the same as the data points are continuous and related to the The number of data points that lie on the same side of the fitted line as their corresponding data point. is the second quantity, i.e. The height level where the data point is located is the same as the The total number of data points that lie on the same side of the fitted line as their corresponding data point.

[0098] It should be noted that if the upper and lower adjacent data points of a data point are not on the same side of the corresponding fitting line as the data point, then M corresponding to the data point is 1. Figure 3 The data point X1 shown, its corresponding M=5, N=5; Figure 4 The data point X2 shown corresponds to M=1 and N=6.

[0099] The present invention also provides a building wall quality detection system. Figure 5 , the building wall surface quality detection system 500 comprises:

[0100] An acquisition module 501 is used to acquire at least one column of data points on a wall surface of a building, wherein each column of data points includes a plurality of three-dimensional coordinate points located in the same column on the wall surface of the building;

[0101] A fitting module 502 is used to divide the data points in each column into multiple height levels according to the height data, and perform least square fitting on the data points of each height level to obtain a fitting straight line corresponding to each height level;

[0102] A calculation module 503 is used to calculate the importance of each data point according to the parameter information of the fitting line corresponding to the height level of the data point and the positional relationship between the data points in the height level of the data point and the corresponding fitting line;

[0103] The detection module 504 is used to construct a regression model using the least square method with the importance of each data point as a weight, and detect the verticality of the building wall based on the constructed regression model.

[0104] Optionally, for each data point, the calculation module 503 calculates the importance of the data point based on the parameter information of the fitting line corresponding to the height level of the data point and the positional relationship between the data points within the height level of the data point and the corresponding fitting line, including: calculating the abnormal degree of wall inclination at each height level based on the parameter information of the corresponding fitting line; for each data point, calculating the position correlation characteristics of the data point based on the positional relationship between the data points within the height level and the corresponding fitting line; calculating the importance of the data point based on the position correlation characteristics of the data point and the abnormal degree of wall inclination at the height level.

[0105] Optionally, the parameter information of the fitting line includes a parameter vector of the fitting line, an angle between the fitting line and the horizontal direction, and a slope of the fitting line. The calculation module 503 calculates the abnormal degree of wall inclination at each height level according to the corresponding parameter information of the fitting line, including: for each height level, calculating the height importance of the height level according to the parameter vector of the fitting line corresponding to the height level; calculating the abnormal degree of wall inclination at the height level according to the height importance of the height level, the angle between each fitting line and the horizontal direction and the slope of the fitting line corresponding to the height level.

[0106] Optionally, for each height level, the calculation module 503 calculates the height importance of the height level according to the parameter vector of the fitting line corresponding to the height level, including:

[0107] For each height level, the height importance of the height level is calculated according to the height level and the difference norm between the parameter vector of the fitting line corresponding to the height level and the parameter vector of the fitting line corresponding to the target height level.

[0108] Optionally, the target height level is a first height level, and data points in higher height levels have higher heights.

[0109] Optionally, the calculation module 503 calculates the importance of the data point based on the position correlation characteristics of the data point and the abnormal degree of wall inclination at the height level at which the data point is located, including: calculating the significance of the position anomaly of the data point based on the position correlation characteristics of the data point and the abnormal degree of wall inclination at the height level at which the data point is located; and taking the inverse of the significance of the position anomaly of the data point as the importance of the data point.

[0110] Optionally, the calculation module 503 calculates the position correlation feature of the data point based on the positional relationship between the data point and its corresponding fitting line within the height level, including: calculating the ratio of a first quantity to a second quantity as the position correlation feature of the data point, wherein the first quantity is the number of data points within the height level where the data point is located, which are continuous with the data point and located on the same side of the corresponding fitting line as the data point, and the second quantity is the total number of data points within the height level where the data point is located, which are located on the same side of the corresponding fitting line as the data point.

[0111] Optionally, the at least one column of data points is a column of data points, and the detection module 504 uses the importance of each data point as a weight, adopts the least squares method to construct a regression model, and detects the verticality of the building wall surface based on the constructed regression model, including: using the importance of each data point as a weight, and adopting the least squares method to fit to obtain a final fitting straight line; and evaluating the verticality of the building wall surface according to the distance between each data point and the final fitting straight line.

[0112] Optionally, the acquisition module 501 acquires at least one column of data points on the wall surface of the building, including: acquiring at least one column of data points on the wall surface of the building by laser scanning the wall surface of the building.

[0113] In this embodiment, the building wall surface quality detection system divides the data points into multiple different height levels and performs straight line fitting based on the data points in each height level, and then calculates the importance of each data point according to the parameter information of the fitting line corresponding to each height level and the position of the data point relative to the fitting line corresponding to the height level where it is located, and constructs a regression model with the importance of each data point as the weight of the least square method, and finally detects the verticality of the building wall surface based on the constructed regression model. In this way, the weight of the data point is determined according to the abnormal tilt degree of the wall surface where the data point is located, and a more accurate fitting result can be obtained, thereby improving the accuracy of the regression model and the accuracy of the verticality detection of the building wall surface.

[0114] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0115] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for detecting the quality of a building wall surface, characterized in that: The method comprises: Acquire at least one column of data points on a wall surface of a building, wherein each column of data points includes a plurality of three-dimensional coordinate points located in the same column on the wall surface of the building; For each column of data points, multiple data points in the column are divided into multiple height levels according to the height data, and the data points of each height level are fitted by least squares to obtain the fitting straight line corresponding to each height level; For each data point, the importance of the data point is calculated based on the parameter information of the fitting line corresponding to the height level of the data point and the positional relationship between the data points in the height level of the data point and the corresponding fitting line; The importance of each data point is used as the weight, and the least square method is used to build a regression model, and the verticality of the building wall is detected based on the constructed regression model; For each data point, the importance of the data point is calculated according to the parameter information of the fitting line corresponding to the height level of the data point and the positional relationship between the data points in the height level of the data point and the corresponding fitting line, including: Calculate the abnormal degree of wall inclination at each height level according to the parameter information of the corresponding fitting straight line; For each data point, the position correlation feature of the data point is calculated according to the position relationship between the data point and the corresponding fitting line within the height level; Calculate the importance of the data point based on the location correlation characteristics of the data point and the abnormal degree of wall inclination at the height level where the data point is located; The parameter information of the fitting line includes a parameter vector of the fitting line, an angle between the fitting line and the horizontal direction, and a slope of the fitting line. The calculation of the abnormal degree of wall inclination at each height level according to the corresponding parameter information of the fitting line includes: For each height level, the height importance of the height level is calculated according to the parameter vector of the fitting line corresponding to the height level; According to the height importance of the height level, the angle between each fitting straight line and the horizontal direction and the slope of the fitting straight line corresponding to the height level, the abnormal degree of wall inclination at the height level is calculated; For each height level, calculating the height importance of the height level according to the parameter vector of the fitting line corresponding to the height level includes: For each height level, calculating the height importance of the height level according to the height level and the difference norm between the parameter vector of the fitted straight line corresponding to the height level and the parameter vector of the fitted straight line corresponding to the target height level; The calculating of the position correlation feature of the data point according to the position relationship between the data point and the corresponding fitting line in the height level includes: The ratio of the first number to the second number is calculated as the position correlation feature of the data point, wherein the first number is the number of data points that are continuous with the data point and located on the same side of the corresponding fitting line as the data point within the height level where the data point is located, and the second number is the total number of data points that are located on the same side of the corresponding fitting line as the data point within the height level where the data point is located.

2. The building wall surface quality detection method according to claim 1, characterized in that: The target height level is the first height level, and data points in higher height levels have higher heights.

3. The building wall surface quality detection method according to claim 2 is characterized in that: The calculating the importance of the data point according to the position correlation characteristics of the data point and the abnormal degree of wall inclination at the height level where the data point is located includes: According to the location correlation characteristics of the data point and the abnormal degree of wall inclination at the height level where the data point is located, the significance of the location abnormality of the data point is calculated; The inverse of the position anomaly significance of the data point is taken as the importance of the data point.

4. The building wall surface quality detection method according to claim 2 is characterized in that: The at least one column of data points is a column of data points, the importance of each data point is used as a weight, a regression model is constructed by the least square method, and the verticality of the wall surface of the building is detected based on the constructed regression model, including: The importance of each data point is used as the weight, and the least square method is used to fit the final fitting line; The verticality of the building wall is evaluated based on the distance between each data point and the final fitting straight line.

5. The building wall surface quality detection method according to claim 2, characterized in that: The step of obtaining at least one column of data points on the wall surface of the building includes: At least one column of data points on the wall surface of the building is obtained by laser scanning the wall surface of the building.

6. A building wall surface quality detection system, characterized in that: The system is used to implement the building wall surface quality detection method according to any one of claims 1 to 5, and the system comprises: An acquisition module, used to acquire at least one column of data points on a wall surface of a building, wherein each column of data points includes a plurality of three-dimensional coordinate points located in the same column on the wall surface of the building; A fitting module is used to divide multiple data points in each column of data points into multiple height levels according to the height data, and perform least square fitting on the data points of each height level to obtain a fitting straight line corresponding to each height level; A calculation module, for calculating the importance of each data point according to parameter information of the fitting line corresponding to the height level of the data point and the positional relationship between the data points in the height level of the data point and the corresponding fitting line; The detection module is used to construct a regression model using the least square method with the importance of each data point as the weight, and detect the verticality of the building wall based on the constructed regression model.

Images