CN119150250A - Method and system for detecting quality of wall surface of building wall - Google Patents
Method and system for detecting quality of wall surface of building wall Download PDFInfo
- Publication number
- CN119150250A CN119150250A CN202411620342.3A CN202411620342A CN119150250A CN 119150250 A CN119150250 A CN 119150250A CN 202411620342 A CN202411620342 A CN 202411620342A CN 119150250 A CN119150250 A CN 119150250A
- Authority
- CN
- China
- Prior art keywords
- data point
- height
- straight line
- fitting straight
- height level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C15/00—Surveying instruments or accessories not provided for in groups G01C1/00 - G01C13/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to the field of building wall detection, in particular to a method and a system for detecting the quality of a building wall, which comprise the steps of obtaining at least one row of data points on the wall of the building wall, wherein each row of data points comprises a plurality of three-dimensional coordinate points positioned on the same row of the wall of the building wall, dividing each row of data points into a plurality of height grades, carrying out least square fitting on the data points of each height grade to obtain a fitting straight line corresponding to each height grade, calculating the importance degree of each data point according to the parameter information of the fitting straight line corresponding to the height grade and the position relation between the data points in the height grade and the corresponding fitting straight line, constructing a regression model by taking the importance degree of each data point as weight, and detecting the perpendicularity of the wall of the building wall based on the constructed regression model. The fitting result can be obtained more accurately, and the accuracy of wall quality detection is improved.
Description
Technical Field
The invention relates to the field of building wall detection, in particular to a method and a system for detecting the quality of a building wall.
Background
The perpendicularity of the wall surface of the building wall is an important part of the quality of the building engineering, and is directly related to the structural safety, the appearance and the subsequent construction efficiency of the building. If the perpendicularity of the wall surface of the building wall is unqualified, the quality of the building wall can have larger potential safety hazard, and serious injury and death can be caused. The problem of building wall face inclination can be timely found through detecting the perpendicularity of the building wall face, and the inclination hidden danger existing in the building wall face is timely checked out, so that workers can timely carry out repairing treatment on the building wall face, and further quality qualification of the building wall face is guaranteed. It can be seen that it is necessary and important to perform verticality detection on the wall surface of a building wall.
In the prior art, the real inclination condition of the wall surface of the building wall body is generally reflected by constructing a regression model so as to realize the verticality detection of the wall surface of the building wall body. However, when the regression model is constructed, some data points with relatively poor performance on the real inclination condition of the wall surface of the building wall body are interfered, so that the constructed regression model has relatively large difference with the real inclination condition of the wall surface of the building wall body, and an accurate model foundation cannot be provided for subsequent verticality detection.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a method for detecting the wall quality of a building wall, which comprises the following steps:
obtaining at least one row of data points on a wall surface of a building wall, wherein each row of data points comprises a plurality of three-dimensional coordinate points positioned on the same row of the wall surface of the building wall;
For each row of data points, dividing the plurality of data points of the row into a plurality of height levels according to the height data, and respectively carrying out least square fitting on the data points of each height level to obtain fitting straight lines respectively corresponding to each height level;
For each data point, calculating the importance degree of the data point according to the parameter information of the fitting straight line corresponding to the height level of the data point and the position relation between the data point in the height level of the data point and the corresponding fitting straight line;
And constructing a regression model by taking the importance degree of each data point as a weight and adopting a least square method, and detecting the perpendicularity of the wall surface of the building wall based on the constructed regression model.
Optionally, for each data point, calculating the importance degree of the data point according to the parameter information of the fitting straight line corresponding to the height level of the data point and the position relation between the data point in the height level of the data point and the corresponding fitting straight line, including:
Calculating the inclination abnormality degree of the wall body of each height level according to the parameter information of the corresponding fitting straight line;
For each data point, calculating the position relevance characteristic of the data point according to the position relation between the data point in the height level of the data point and the corresponding fitting straight line;
And calculating the importance degree of the data point according to the position relevance characteristics of the data point and the inclination abnormality degree of the wall body at the height level of the data point.
Optionally, the parameter information of the fitting straight line includes a parameter vector of the fitting straight line, an included angle between the fitting straight line and a horizontal direction, and a slope of the fitting straight line, and the calculating the wall inclination anomaly degree of each height level according to the parameter information of the corresponding fitting straight line includes:
for each height grade, calculating the height importance of the height grade according to the parameter vector of the fitting straight line corresponding to the height grade;
according to the height importance of the height grade, the included angle between each fitting straight line and the horizontal direction and the slope of the fitting straight line corresponding to the height grade, the wall inclination abnormality degree of the height grade is calculated.
Optionally, 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 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 fitting straight line corresponding to the height level and the parameter vector of the fitting straight line corresponding to the target height level.
Optionally, the target height level is a first height level, and the data points in the higher height level have a higher height.
Optionally, the calculating the importance degree of the data point according to the position correlation characteristic of the data point and the inclination abnormality degree of the wall body at the height level comprises the following steps:
Calculating the position abnormality significance of the data point according to the position relevance characteristics of the data point and the wall inclination abnormality degree of the height level of the data point;
the inverse of the position anomaly significance of the data point is taken as the importance degree of the data point.
Optionally, the calculating the position relevance feature of the data point according to the position relation between the data point and the corresponding fitting straight line in the height level comprises:
And calculating the ratio of the first quantity to the second quantity as the position correlation characteristic of the data point, wherein the first quantity is the quantity of the data points which are continuous with the data point and are positioned on the same side of the corresponding fitting straight line with the data point in the height grade of the data point, and the second quantity is the total number of the data points which are positioned on the same side of the corresponding fitting straight line with the data point in the height grade of the data point.
Optionally, the at least one set of data points is a set of data points, the importance degree of each data point is taken as a weight, a regression model is constructed by adopting a least square method, and the perpendicularity of the wall surface of the building wall is detected based on the constructed regression model, which comprises:
taking the importance degree of each data point as a weight, and adopting a least square method to perform fitting to obtain a final fitting straight line;
and evaluating the perpendicularity of the wall surface of the building wall according to the distance between each data point and the final fitting straight line.
Optionally, the acquiring at least one row of data points on the wall surface of the building wall includes:
At least one row of data points on the wall surface of the building wall is obtained by carrying out laser scanning on the wall surface of the building wall.
The invention also provides a system for detecting the quality of the wall surface of the building wall, which comprises:
The system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring at least one row of data points on the wall surface of a building wall, and each row of data points comprises a plurality of three-dimensional coordinate points positioned on the same row of the wall surface of the building wall;
The fitting module is used for dividing a plurality of data points of each column into a plurality of height grades according to the height data, and respectively carrying out least square fitting on the data points of each height grade to obtain fitting straight lines respectively corresponding to each height grade;
The calculating module is used for calculating the importance degree of each data point according to the parameter information of the fitting straight line corresponding to the height level of the data point and the position relation between the data point in the height level of the data point and the corresponding fitting straight line;
the detection module is used for constructing a regression model by taking the importance degree of each data point as a weight and detecting the perpendicularity of the wall surface of the building wall based on the constructed regression model.
The method has the advantages that the data points are divided into a plurality of different height grades, straight line fitting is respectively carried out based on the data points in each height grade, then the importance degree of each data point is calculated according to the parameter information of the fitting straight line corresponding to each height grade and the position condition of the data point relative to the fitting straight line corresponding to the height grade, the importance degree of each data point is used as the weight of the least square method to construct a regression model, and finally the perpendicularity of the wall surface of the building wall is detected based on the constructed regression model. Therefore, the weight of the data point is determined according to the abnormal inclination degree of the wall surface where the data point is located, a more accurate fitting result can be obtained, the accuracy of the regression model can be further improved, and the accuracy of detecting the perpendicularity of the wall surface of the building wall body is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a first schematic diagram of a method for detecting wall quality of a building wall according to an embodiment of the present invention;
fig. 2 is a second schematic diagram of a method for detecting wall quality of a building wall according to an embodiment of the present invention;
FIG. 3 is a first schematic diagram of distribution positions between data points and a straight line of fit provided by an embodiment of the present invention;
FIG. 4 is a second schematic diagram of distribution positions between data points and a straight line of fit provided by an embodiment of the present invention;
Fig. 5 is a schematic diagram of a wall quality detection system for a building wall according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of the method for detecting the quality of the wall surface of the building wall according to the invention with reference to the attached drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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.
The invention provides a method for detecting the quality of a wall surface of a building wall, and the scheme of the invention is described in detail below with reference to the accompanying drawings.
Referring to fig. 1, a first schematic diagram of a method for detecting wall quality of a building wall according to an embodiment of the present invention is shown, where the method for detecting wall quality of a building wall (hereinafter referred to as "the method") includes the following steps:
Step 101, obtaining at least one row of data points on the wall surface of the building wall, wherein each row of data points comprises a plurality of three-dimensional coordinate points positioned on the same row of the wall surface of the building wall.
In the step, the method obtains at least one row of data points on the wall surface of the building wall, wherein each row of data points comprises a plurality of three-dimensional coordinate points positioned on the same row of the wall surface of the building wall. The method can acquire the data points by receiving the data points of the wall surfaces of the building wall bodies with the quality to be detected, which are sent by other equipment, or by controlling one equipment to perform three-dimensional scanning on the wall surfaces of the building wall bodies with the quality to be detected. The data points may be three-dimensional coordinate points obtained by performing laser scanning on the wall surface of the building wall, or may be three-dimensional coordinate points obtained by other three-dimensional scanning methods, which is not particularly limited in the embodiment of the present invention.
Step 102, for each row of data points, dividing the plurality of data points of the row into a plurality of height levels according to the height data, and performing least square fitting on the data points of each height level respectively to obtain fitting straight lines corresponding to each height level respectively.
In the step, for each column of data points, the method divides the plurality of data points of the column into a plurality of height levels according to the height data of the data points, and performs least square fitting on the data points of each height level to obtain fitting straight lines corresponding to each height level. The method can determine the number of height levels according to actual conditions, for example, when the accuracy is required to be higher and the computing power is higher, a larger number of height levels can be selected. For the divided height levels, data points within a higher height level have a higher height than data points within a lower height level. The fitting of the data points by the least square method to obtain the fitted straight line belongs to the prior art category, and is not described in detail herein.
Step 103, for each data point, calculating the importance degree of the data point according to the parameter information of the fitting straight line corresponding to the height level of the data point and the position relation between the data point in the height level of the data point and the corresponding fitting straight line.
In the step, for each data point, the method calculates the importance degree of the data point according to the parameter information of the fitting straight line corresponding to the height level of the data point and the position relation between the data point in the height level of the data point and the corresponding fitting straight line. Specifically, the method can calculate the wall inclination abnormality degree of each height level according to the parameter information of the fitting straight line corresponding to the height level, then calculate the position relevance feature of each data point according to the position relation between the data point in the height level and the fitting straight line corresponding to the data point, and finally calculate the importance degree of the data point according to the position relevance feature of the data point and the wall inclination abnormality degree of the height level. The parameter information of the fitting straight line comprises a parameter vector of the fitting straight line, an included angle between the fitting straight line and the horizontal direction and a slope of the fitting straight line.
And 104, constructing a regression model by taking the importance degree of each data point as a weight and detecting the perpendicularity of the wall surface of the building wall based on the constructed regression model.
In the method, importance degree of each data point is used as weight, a regression model is built by adopting a least square method, and verticality of a wall surface of a building wall is detected based on the built regression model. Specifically, when the at least one set of data points is only one set of data points, the method may use importance degree of each data point as a weight, perform fitting by using a least square method to obtain a final fitted straight line, and then evaluate verticality of a wall surface of the building wall according to a distance between each data point and the final fitted straight line. When the at least one column of data points comprises a plurality of columns of data points, the method can adopt a least square method to perform fitting by taking importance degree of each data point as weight to obtain a final fitting plane, and then evaluate the perpendicularity and/or flatness of the wall surface of the building wall according to the distance between each data point and the final fitting plane.
According to the method, data points are divided into a plurality of different height grades, straight line fitting is conducted on the basis of the data points in each height grade, then the importance degree of each data point is calculated according to parameter information of a fitting straight line corresponding to each height grade and the position condition of the data point relative to the fitting straight line corresponding to the height grade, a regression model is built by taking the importance degree of each data point as the weight of a least square method, and finally the perpendicularity of a wall surface of a building wall is detected on the basis of the built regression model. Therefore, the weight of the data point is determined according to the abnormal inclination degree of the wall surface where the data point is located, a more accurate fitting result can be obtained, the accuracy of the regression model can be further improved, and the accuracy of detecting the perpendicularity of the wall surface of the building wall body is improved.
Optionally, the at least one set of data points is a set of data points, the regression model is built by using a least square method by taking the importance degree of each data point as a weight, and the perpendicularity of the wall surface of the building wall body is detected based on the built regression model.
In this embodiment, the at least one set of data points is a set of data points, the method uses importance degree of each data point as weight, uses a least square method to perform fitting to obtain a final fitting straight line, and then evaluates perpendicularity of the wall surface of the building wall according to the distance between each data point and the final fitting straight line. For example, the distances between each data point and the final fit line can be calculated separately, and then the perpendicularity of the wall surface of the building wall can be estimated based on the maximum deviation (i.e., the maximum difference) in these distances.
After the final fitting straight line is obtained through fitting, whether the maximum deviation of the distance from the wall surface of the building wall to the final fitting straight line is within an allowable deviation range or not can be determined through data analysis software or manual calculation, and if the maximum deviation exceeds the allowable deviation range, corresponding deviation rectifying measures need to be taken, such as reinforcing treatment on the building wall, and possible potential safety hazards are avoided in time.
Optionally, the acquiring at least one row of data points on the wall surface of the building wall comprises acquiring at least one row of data points on the wall surface of the building wall by performing laser scanning on the wall surface of the building wall.
In this embodiment, the method obtains at least one row of data points on the wall surface of the building wall by performing laser scanning on the wall surface of the building wall. For example, for a row of data points, a row of building wall surfaces can be three-dimensionally scanned by a three-dimensional laser scanner, so that three-dimensional coordinate information of each scanning point of the row can be obtained as a row of data points of the building wall surfaces. The three-dimensional laser scanner acquires three-dimensional coordinate information of the measured object through a laser ranging system and an angle measuring system, the laser ranging system emits laser to the measured object, the time from the emission to the return of the laser is recorded, the distance is calculated through the light speed and the time difference, the angle measuring system records the horizontal angle and the vertical angle between the scanning instrument and the measured object, and the three-dimensional coordinate information of the measured object can be back calculated through the data. The three-dimensional scanning of the object to be measured by the three-dimensional laser scanner to obtain three-dimensional coordinate information of the object to be measured belongs to the category of the prior art, and will not be described in detail here.
Referring to fig. 2, fig. 2 is a second schematic diagram of a method for detecting wall quality of a building wall according to an embodiment of the invention, as shown in fig. 2, the method includes the following steps:
Step 201, obtaining at least one row of data points on a wall surface of a building wall, wherein each row of data points comprises a plurality of three-dimensional coordinate points positioned on the same row of the wall surface of the building wall.
Step 202, for each row of data points, dividing the plurality of data points of the row into a plurality of height levels according to the height data, and performing least square fitting on the data points of each height level respectively to obtain fitting straight lines corresponding to each height level respectively.
Steps 201 and 202 are the same as steps 101 and 102 in the embodiment shown in fig. 1, and will not be described again here.
And 203, calculating the inclination abnormality degree of the wall body of each height level according to the parameter information of the corresponding fitting straight line.
In the step, the method calculates the wall inclination abnormality degree of each height grade according to the parameter information of the fitting straight line corresponding to the height grade. The parameter information of the fitting straight line may include a parameter vector of the fitting straight line, an included angle between the fitting straight line and a horizontal direction, and a slope of the fitting straight line, and correspondingly, for each height grade, the method may calculate the height importance of the height grade according to the parameter vector of the fitting straight line corresponding to the height grade, and then calculate the wall inclination anomaly degree of the height grade according to the height importance of the height grade, the included angle between each fitting straight line and the horizontal direction, and the slope of the fitting straight line corresponding to the height grade.
Step 204, for each data point, calculating the position relevance feature of the data point according to the position relation between the data point and the corresponding fitting straight line in the height level of the data point.
In this step, for each data point, the method calculates the position relevance feature of the data point according to the position relation between the data point and the corresponding fitting straight line in the height level of the data point. In some embodiments, for a data point, the method may determine the first number and the second number according to a positional relationship between the data point and its corresponding fit line in the height level of the data point, and then calculate a ratio of the first number and the second number as the position relevance feature of the data point. The first number is the number of the data points which are continuous with the data point and are positioned on the same side of the corresponding fitting straight line with the data point in the height level of the data point, and the second number is the total number of the data points which are positioned on the same side of the corresponding fitting straight line with the data point in the height level of the data point.
Step 205, calculating the importance degree of the data point according to the position correlation characteristic of the data point and the inclination abnormality degree of the wall body of the height level of the data point.
In the step, the method calculates the importance degree of the data point according to the position relevance characteristic of the data point and the inclination abnormality degree of the wall body of the height level where the data point is positioned. Specifically, the method can calculate the position abnormality significance of the data point according to the position relevance characteristic of the data point and the wall inclination abnormality degree of the height level of the data point, and then take the reciprocal of the position abnormality significance of the data point as the importance degree of the data point.
And 206, constructing a regression model by using the importance degree of each data point as a weight and detecting the perpendicularity of the wall surface of the building wall based on the constructed regression model.
This step 206 is the same as step 104 in the embodiment shown in fig. 1, and will not be described here again.
In this embodiment, data points are divided into a plurality of different height levels, straight line fitting is performed based on the data points in each height level, then the wall inclination anomaly degree of each height level is calculated based on the fitting straight line, the importance degree of each data point is calculated according to the position relation of the data point relative to the corresponding fitting straight line and the wall inclination anomaly degree corresponding to the height level, a regression model is constructed by taking the importance degree of each data point as the weight of a least square method, and finally the perpendicularity of the wall surface of the building wall is detected based on the constructed regression model. Therefore, the weight of the data point is determined according to the abnormal inclination degree of the wall surface where the data point is located, a more accurate fitting result can be obtained, the accuracy of the regression model can be further improved, and the accuracy of detecting the perpendicularity of the wall surface of the building wall body is improved.
Optionally, the parameter information of the fitting straight line comprises a parameter vector of the fitting straight line, an included angle between the fitting straight line and the horizontal direction and a slope of the fitting straight line, and the calculating of the wall inclination abnormality degree of each height grade according to the parameter information of the corresponding fitting straight line comprises calculating the height importance of each height grade according to the parameter vector of the fitting straight line corresponding to the height grade, and calculating the wall inclination abnormality degree of the height grade according to the height importance of the height grade, the included angle between each fitting straight line and the horizontal direction and the slope of the fitting straight line corresponding to the height grade.
One common factor that building wall appears the wall unevenness is measuring error, along with building wall height increases, and measuring error constantly accumulates and leads to the building wall to appear certain slope, and then makes the data point of different positions on building wall have great difference to the theoretical straight line expressive power that locates of true building wall. It can be understood that the wall section at the lower position on the wall surface of the building wall is not easy to incline, so that the data point at the lower position can reflect the straight line of the theoretical position of the wall surface of the building wall more, while the data point at the higher position can reflect the straight line of the theoretical position of the building wall more effectively because the thickness of the wall is usually smaller due to error accumulation and the load capacities at different positions have larger difference.
In the actual detection process, a certain inclination may occur at a position with a lower height of the building wall, although the fitting straight lines between different height grades are similar at this time, so that the data points still have higher height importance, and in fact, the building wall sections where the data points are located are inclined, which may cause inaccuracy of the finally fitted regression model. The tilt based on the building wall may be more remarkable with the feature of height, and shift occurs toward the tilt direction of the building wall. Therefore, the inclination change trend characteristic of the fitting straight line under each height grade can be utilized to determine the inclination possibility of the building wall section corresponding to the height grade. If the directions of the fitting straight lines corresponding to the height levels have higher consistency and have smaller difference with the vertical direction, the possibility of representing the straight line where the building wall theory is located is higher, and conversely, if the directions of the fitting straight lines corresponding to the height levels have obvious change trend, the possibility of tilting the building wall is higher, and the possibility of representing the straight line where the building wall theory is located is lower.
Therefore, in this embodiment, for each height level, the height importance of the height level is calculated according to the parameter vector of the fitting straight line corresponding to the height level, and then the inclination anomaly degree of the wall body of the height level is calculated according to the height importance of the height level, the included angle between each fitting straight line and the horizontal direction and the slope of the fitting straight line corresponding to the height level.
Specifically, for the firstThe height level may be calculated using the following formulaDegree of inclination abnormality of wall body of each height grade:
Wherein, Is the firstThe degree of wall inclination abnormality of each height level,Is the firstA sequence number of a level of height,Is the firstThe slope of the fitted line corresponding to the individual height levels,Is the firstThe included angle between the fitting straight line corresponding to the height grade and the horizontal direction,Is the firstThe included angle between the fitting straight line corresponding to the height grade and the horizontal direction,Is the firstThe high importance of the individual height classes,Is the firstThe high importance of the individual height classes,Is the total number of height classes.
In the above-mentioned formula(s),Represent the firstIncluded angle between fitting straight line corresponding to each height grade and horizontal direction andThe sine value of the angle difference between the fitting straight line corresponding to the height grade and the included angle of the horizontal direction, namely the firstFitting straight line and the first height levelSine values of included angles between the fitting straight lines corresponding to the height grades represent similarity between the two included angles; Represent the first Sine values of angle differences between the included angles of the fitting straight lines corresponding to the height grades and the horizontal direction and between the included angles of the vertical direction and the horizontal direction; Represent the first Level of height and thThe overall importance of the individual height levels as a weight for the differences between the angles; Represent the first Level of height and thThe greater the difference in direction between the height levels, the more indicative of the firstData points of the height classThe more pronounced the directional difference of the data points of the individual height classes; Represent the first The consistency of the difference in direction between the fitted straight line corresponding to each height level and the fitted straight lines corresponding to the remaining height levels is higher, and the greater the value is, the more representative isThe worse the consistency of the direction difference between the fitting straight line corresponding to each height level and the fitting straight lines corresponding to the rest height levels; Is the first Slope of fitting straight line corresponding to each height level reflects the firstThe relation between the fitting direction and the height of the fitting straight line corresponding to each height level is larger, and the larger the value is, the more the first isThe greater the likelihood of inclination of a building wall segment of a height class.
Optionally, 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 comprises calculating the height importance of the height level according to the height level and the difference norm between the parameter vector of the fitting straight line corresponding to the height level and the parameter vector of the fitting straight line corresponding to the target height level.
It is mentioned that the wall sections on the wall surfaces of the building walls at the lower positions of the heights are not easy to incline, and if the fitting straight line corresponding to a certain height level has higher consistency with the fitting straight line at the lower positions of the heights, the possibility that the building wall sections corresponding to the height level are obviously inclined is smaller, so that the data points in the height level should have higher importance.
In this embodiment, for each height level, the method may calculate the height importance of the height level according to the height level and a difference norm between the parameter vector of the fitting straight line corresponding to the height level and the parameter vector of the fitting straight line corresponding to the target height level. The parameter vector may be a two-dimensional vector of parameters (e.g., slope, intercept) of the fitted line. For the firstThe height level can be formulated as follows to calculate its height importance:
Wherein, Is the firstThe high importance of the individual height classes,Is the firstA sequence number of a level of height,Is the firstThe parameter vectors of the fitting straight line corresponding to the height grades,Parameter vector of fitting straight line corresponding to 1 st height level ""Is the norm operation of the vector,Is a linear normalization function used for normalization processing.
Optionally, the target height level is a first height level, and the data points in the higher height level have a higher height.
Optionally, the calculating the importance degree of the data point according to the position correlation characteristic of the data point and the inclination abnormality degree of the wall body at the height level comprises calculating the position abnormality significance of the data point according to the position correlation characteristic of the data point and the inclination abnormality degree of the wall body at the height level, and taking the reciprocal of the position abnormality significance of the data point as the importance degree of the data point.
In the embodiment, the method calculates the position abnormality significance of the data point according to the position relevance characteristics of the data point and the wall inclination abnormality degree of the height level of the data point, and takes the reciprocal of the position abnormality significance of the data point as the importance degree of the data point. Specifically, for the firstThe first of the height classesData points, the first can be calculated according to the following formulaPositional anomaly significance of data points:
Wherein, Is the firstThe first of the height classesThe unusual significance of the location of the data points,Is the firstThe degree of wall inclination abnormality of each height level,Represent the firstThe first of the height classesThe location correlation characteristics of the data points,Represent the firstThe median of the position correlation features for all data points within a height level,Is a linear normalization function used for normalization processing.
For a data point, the greater the significance of the position anomaly, the less likely the data point appears to be a straight line in which the theory of the building wall is located, and the greater the interference to the final fitted straight line. In order to improve the expressive power of the final fit line to the wall, such data points should be given less importance weight, reducing the interference to the overall regression model during the fit process. Thus, for the firstThe first of the height classesData points, the position abnormality significance of which is calculatedThereafter, the first can be calculated according to the following formulaDegree of importance of data points:
Wherein, Is the firstThe first of the height classesThe degree of importance of the data points,Is the firstThe first of the height classesThe positional anomaly significance of the data points.
Optionally, calculating the position correlation characteristic of the data point according to the position relation between the data point and the corresponding fitting straight line in the height level comprises calculating the ratio of the first quantity to the second quantity as the position correlation characteristic of the data point, wherein the first quantity is the quantity of the data points which are continuous with the data point and are positioned on the same side of the corresponding fitting straight line in the height level of the data point, and the second quantity is the total number of the data points which are positioned on the same side of the corresponding fitting straight line in the height level of the data point.
Referring to fig. 3 and 4 together, fig. 3 shows the positional relationship between the data points in a certain inclined wall section and the corresponding fitting straight lines, and fig. 4 shows the positional relationship between the data points in a certain normal building wall section and the corresponding fitting straight lines, it can be seen that, for the data points in a height level, if the randomness of the positional relationship with respect to the fitting straight lines corresponding to the height level is smaller, the inclination characteristic of the wall section corresponding to the height level is more remarkable. In this embodiment, the method calculates a ratio of a first number to a second number as a position correlation feature of the data point, where the first number is a number of data points that are continuous with the data point and are located on the same side of the corresponding fit line as the data point in a height level where the data point is located, and the second number is a total number of data points that are located on the same side of the corresponding fit line as the data point in the height level where the data point is located.
Specifically, for the firstThe first of the height classesData points, the first can be calculated according to the following formulaPosition correlation features for data points:
Wherein, Is the firstThe first of the height classesA data point location correlation characteristic is provided which,Is of a first quantity, i.e. the firstWithin the height level of the data point and the firstData points are continuous and with the firstThe number of data points on the same side of their corresponding fitted line,Is of a second quantity, i.e. the firstWithin the height level of the data point and the firstThe total number of data points with data points on the same side of their corresponding fitted line.
Note that, if none of the data points adjacent to each other above and below a data point is located on the same side of the corresponding fitting line as the data point, m=1 corresponding to the data point. For example, for data point X1 shown in fig. 3, it corresponds to m= 5,N =5, and for data point X2 shown in fig. 4, it corresponds to m=1, n=6.
Referring further to fig. 5, the embodiment of the present invention further provides a system for detecting wall quality of a building wall, where the system 500 for detecting wall quality of a building wall includes:
an obtaining module 501, configured to obtain at least one row of data points on a wall surface of a building wall, where each row of data points includes a plurality of three-dimensional coordinate points located on the same row of the wall surface of the building wall;
The fitting module 502 is configured to divide, for each column of data points, the plurality of data points of the column into a plurality of height levels according to the height data, and perform least square fitting on the data points of each height level to obtain fitting lines corresponding to each height level respectively;
a calculating module 503, configured to calculate, for each data point, a degree of importance of the data point according to parameter information of a fitting straight line corresponding to a height level where the data point is located and a positional relationship between the data point in the height level where the data point is located and the fitting straight line corresponding to the data point;
The detection module 504 is configured to construct a regression model by using the importance degree of each data point as a weight, and detect the verticality of the wall surface of the building wall based on the constructed regression model.
Optionally, for each data point, the calculating module 503 calculates the importance degree of the data point according to the parameter information of the fitting straight line corresponding to the height level of the data point and the position relation between the data point in the height level of the data point and the fitting straight line corresponding to the data point, including calculating the wall inclination abnormality degree of each height level according to the parameter information of the fitting straight line corresponding to the data point, calculating the position relevance feature of the data point according to the position relation between the data point in the height level of the data point and the fitting straight line corresponding to the data point for each data point, and calculating the importance degree of the data point according to the position relevance feature of the data point and the wall inclination abnormality degree of the height level of the data point.
Optionally, the parameter information of the fitting straight line includes a parameter vector of the fitting straight line, an included angle between the fitting straight line and a horizontal direction, and a slope of the fitting straight line, and the calculating module 503 calculates the wall inclination anomaly degree of each height level according to the parameter information of the corresponding fitting straight line, including, 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 wall inclination anomaly degree of the height level according to the height importance of the height level, the included angle between each fitting straight line and the horizontal direction, and the slope of the fitting straight line corresponding to the height level.
Optionally, for each height level, the calculating module 503 calculates the height importance of the height level according to the parameter vector of the fitting straight line corresponding to the height level, including:
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 fitting straight line corresponding to the height level and the parameter vector of the fitting straight line corresponding to the target height level.
Optionally, the target height level is a first height level, and the data points in the higher height level have a higher height.
Optionally, the calculating module 503 calculates the importance degree of the data point according to the position correlation characteristic of the data point and the inclination abnormality degree of the wall body at the height level of the data point, including calculating the position abnormality significance of the data point according to the position correlation characteristic of the data point and the inclination abnormality degree of the wall body at the height level of the data point, and taking the reciprocal of the position abnormality significance of the data point as the importance degree of the data point.
Optionally, the calculating module 503 calculates the position correlation characteristic of the data point according to the position relation between the data point and the corresponding fitting straight line in the height level, including calculating the ratio of the first number to the second number as the position correlation characteristic of the data point, where the first number is the number of data points which are continuous with the data point and are located on the same side of the corresponding fitting straight line as the data point in the height level where the data point is located, and the second number is the total number of data points which are located on the same side of the corresponding fitting straight line as the data point in the height level where the data point is located.
Optionally, the detection module 504 constructs a regression model by using the importance degree of each data point as a weight and detects the verticality of the wall surface of the building wall based on the constructed regression model, wherein the at least one data point is a set of data points, and the detection module uses the importance degree of each data point as a weight and uses a least square method to perform fitting to obtain a final fitting straight line, and evaluates the verticality of the wall surface of the building wall according to the distance between each data point and the final fitting straight line.
Optionally, the obtaining module 501 obtains at least one column of data points on the wall surface of the building wall, including obtaining at least one column of data points on the wall surface of the building wall by performing laser scanning on the wall surface of the building wall.
In this embodiment, the building wall quality detection system divides data points into a plurality of different height levels, respectively performs straight line fitting based on the data points in each height level, then calculates importance degree of each data point according to parameter information of a fitting straight line corresponding to each height level and position conditions of the data point relative to the fitting straight line corresponding to the height level, constructs a regression model by taking the importance degree of each data point as weight of a least square method, and finally detects perpendicularity of the building wall based on the constructed regression model. Therefore, the weight of the data point is determined according to the abnormal inclination degree of the wall surface where the data point is located, a more accurate fitting result can be obtained, the accuracy of the regression model can be further improved, and the accuracy of detecting the perpendicularity of the wall surface of the building wall body is improved.
It should be noted that the sequence of the 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 particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
1. A method for detecting the quality of a wall surface of a building wall, the method comprising the steps of:
obtaining at least one row of data points on a wall surface of a building wall, wherein each row of data points comprises a plurality of three-dimensional coordinate points positioned on the same row of the wall surface of the building wall;
For each row of data points, dividing the plurality of data points of the row into a plurality of height levels according to the height data, and respectively carrying out least square fitting on the data points of each height level to obtain fitting straight lines respectively corresponding to each height level;
For each data point, calculating the importance degree of the data point according to the parameter information of the fitting straight line corresponding to the height level of the data point and the position relation between the data point in the height level of the data point and the corresponding fitting straight line;
And constructing a regression model by taking the importance degree of each data point as a weight and adopting a least square method, and detecting the perpendicularity of the wall surface of the building wall based on the constructed regression model.
2. The method for detecting the quality of a wall surface of a building wall according to claim 1, wherein for each data point, calculating the importance degree of the data point according to the parameter information of the fitting straight line corresponding to the height level of the data point and the position relation between the data point in the height level of the data point and the fitting straight line corresponding to the data point comprises:
Calculating the inclination abnormality degree of the wall body of each height level according to the parameter information of the corresponding fitting straight line;
For each data point, calculating the position relevance characteristic of the data point according to the position relation between the data point in the height level of the data point and the corresponding fitting straight line;
And calculating the importance degree of the data point according to the position relevance characteristics of the data point and the inclination abnormality degree of the wall body at the height level of the data point.
3. The method for detecting the quality of the wall surface of the building wall according to claim 2, wherein the parameter information of the fitting straight line includes a parameter vector of the fitting straight line, an included angle between the fitting straight line and the horizontal direction, and a slope of the fitting straight line, and the calculating the wall inclination anomaly degree of each height level according to the parameter information of the corresponding fitting straight line includes:
for each height grade, calculating the height importance of the height grade according to the parameter vector of the fitting straight line corresponding to the height grade;
according to the height importance of the height grade, the included angle between each fitting straight line and the horizontal direction and the slope of the fitting straight line corresponding to the height grade, the wall inclination abnormality degree of the height grade is calculated.
4. A method for detecting the quality of a wall surface of a building wall according to claim 3, wherein 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 comprises:
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 fitting straight line corresponding to the height level and the parameter vector of the fitting straight line corresponding to the target height level.
5. The method of claim 4, wherein the target height level is a first height level and the data points in the higher height level have a higher height.
6. The method for detecting the quality of the wall surface of the building wall according to any one of claims 2 to 5, wherein the calculating the importance degree of the data point according to the position correlation characteristic of the data point and the inclination abnormality degree of the wall at the height level thereof comprises:
Calculating the position abnormality significance of the data point according to the position relevance characteristics of the data point and the wall inclination abnormality degree of the height level of the data point;
the inverse of the position anomaly significance of the data point is taken as the importance degree of the data point.
7. The method for detecting the quality of the wall surface of the building wall according to any one of claims 2 to 5, wherein the calculating the position correlation characteristic of the data point according to the position relation between the data point and the corresponding fitting straight line in the height level comprises:
And calculating the ratio of the first quantity to the second quantity as the position correlation characteristic of the data point, wherein the first quantity is the quantity of the data points which are continuous with the data point and are positioned on the same side of the corresponding fitting straight line with the data point in the height grade of the data point, and the second quantity is the total number of the data points which are positioned on the same side of the corresponding fitting straight line with the data point in the height grade of the data point.
8. The method for detecting the quality of a wall surface of a building wall according to any one of claims 1 to 5, wherein the at least one column of data points is a column of data points, the importance degree of each data point is used as a weight, a regression model is constructed by using a least square method, and the perpendicularity of the wall surface of the building wall is detected based on the constructed regression model, which comprises:
taking the importance degree of each data point as a weight, and adopting a least square method to perform fitting to obtain a final fitting straight line;
and evaluating the perpendicularity of the wall surface of the building wall according to the distance between each data point and the final fitting straight line.
9. The method for detecting the quality of a wall surface of a building wall according to any one of claims 1 to 5, wherein the step of obtaining at least one set of data points on the wall surface of the building wall comprises:
At least one row of data points on the wall surface of the building wall is obtained by carrying out laser scanning on the wall surface of the building wall.
10. A system for detecting the quality of a wall surface of a building wall, the system comprising:
The system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring at least one row of data points on the wall surface of a building wall, and each row of data points comprises a plurality of three-dimensional coordinate points positioned on the same row of the wall surface of the building wall;
The fitting module is used for dividing a plurality of data points of each column into a plurality of height grades according to the height data, and respectively carrying out least square fitting on the data points of each height grade to obtain fitting straight lines respectively corresponding to each height grade;
The calculating module is used for calculating the importance degree of each data point according to the parameter information of the fitting straight line corresponding to the height level of the data point and the position relation between the data point in the height level of the data point and the corresponding fitting straight line;
the detection module is used for constructing a regression model by taking the importance degree of each data point as a weight and detecting the perpendicularity of the wall surface of the building wall based on the constructed regression model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411620342.3A CN119150250B (en) | 2024-11-14 | 2024-11-14 | A method and system for detecting building wall surface quality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411620342.3A CN119150250B (en) | 2024-11-14 | 2024-11-14 | A method and system for detecting building wall surface quality |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119150250A true CN119150250A (en) | 2024-12-17 |
| CN119150250B CN119150250B (en) | 2025-02-07 |
Family
ID=93808108
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411620342.3A Active CN119150250B (en) | 2024-11-14 | 2024-11-14 | A method and system for detecting building wall surface quality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119150250B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114359654A (en) * | 2021-12-06 | 2022-04-15 | 重庆邮电大学 | YOLOv4 concrete apparent disease detection method based on position relevance feature fusion |
| CN116401734A (en) * | 2022-12-08 | 2023-07-07 | 安徽理工大学 | Brick-concrete building structure length calculation method based on point cloud |
| EP4394701A1 (en) * | 2022-11-11 | 2024-07-03 | MFTB Holdco, Inc. | Automated inter-image analysis of multiple building images for building floor plan generation |
-
2024
- 2024-11-14 CN CN202411620342.3A patent/CN119150250B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114359654A (en) * | 2021-12-06 | 2022-04-15 | 重庆邮电大学 | YOLOv4 concrete apparent disease detection method based on position relevance feature fusion |
| EP4394701A1 (en) * | 2022-11-11 | 2024-07-03 | MFTB Holdco, Inc. | Automated inter-image analysis of multiple building images for building floor plan generation |
| CN116401734A (en) * | 2022-12-08 | 2023-07-07 | 安徽理工大学 | Brick-concrete building structure length calculation method based on point cloud |
Non-Patent Citations (1)
| Title |
|---|
| 王廷银;林明贵;陈达;吴允平;: "基于北斗RDSS的核辐射监测应急通讯方法", 计算机系统应用, no. 12, 15 December 2019 (2019-12-15), pages 252 - 256 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119150250B (en) | 2025-02-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111197979B (en) | Point cloud data analysis-based building detection method and device | |
| CN107402001B (en) | Ultrahigh-rise building construction deviation digital inspection system and method based on 3D scanning | |
| CN115560690B (en) | Structure integral deformation analysis method based on three-dimensional laser scanning technology | |
| JP5204955B2 (en) | Scanning method for 3D laser scanner | |
| CN107537868A (en) | A kind of cold rolling mill window space position dimension precision online test method | |
| CN117689217B (en) | Underground construction monitoring and analyzing system based on BIM technology | |
| CN115164833B (en) | Monitoring method for subway tunnel structure protection | |
| KR20140050379A (en) | Ship resetting method and coordinate measuring system for resetting ship | |
| CN112884647A (en) | Embedded part construction positioning method based on BIM point cloud technology guidance | |
| US20240295086A1 (en) | Method of accurately measuring the topography of surfaces in civil engineering and a device for carrying out this method | |
| CN108426535A (en) | A kind of sleeve configuration structures real-time deformation monitoring system and method | |
| CN109631847A (en) | Threaded target pose calculation method based on point cloud data | |
| CN114001720A (en) | Supervision control method for building engineering measurement | |
| CN116433885A (en) | A multi-cotter pin positioning method based on sub-pixel edge | |
| CN118310478B (en) | Bridge construction settlement monitoring method and system | |
| CN112884823B (en) | Guiding rule simulation point cloud selection and calculation method for actual measurement actual quantity application | |
| CN119150250A (en) | Method and system for detecting quality of wall surface of building wall | |
| CN112857315A (en) | Steel pipe column verticality measuring method based on three-dimensional laser scanning | |
| CN115035142B (en) | Subway tunnel track line automatic identification method based on point cloud | |
| CN110648280A (en) | Data processing method for splicing large-scale karst cave mass point cloud data | |
| RU2680978C1 (en) | Method of geodesic monitoring of the deformation state of the earth surface in earthquake-prone areas using laser scanning technology | |
| CN112066893B (en) | Method and device for measuring height of key cap of keyboard | |
| CN115388867A (en) | Method for observing and broadcasting sinking attitude of open caisson in real time | |
| CN112833856B (en) | High-precision port area yard track detection method based on total station | |
| JP2012041620A (en) | Method of working matching surface of steel structure |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |