CN118038278A - Intelligent detection method and system for quality of building engineering - Google Patents
Intelligent detection method and system for quality of building engineering Download PDFInfo
- Publication number
- CN118038278A CN118038278A CN202410432069.5A CN202410432069A CN118038278A CN 118038278 A CN118038278 A CN 118038278A CN 202410432069 A CN202410432069 A CN 202410432069A CN 118038278 A CN118038278 A CN 118038278A
- Authority
- CN
- China
- Prior art keywords
- building
- pixel point
- neighborhood
- gray
- pixel
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 35
- 230000007547 defect Effects 0.000 claims abstract description 77
- 238000000034 method Methods 0.000 claims abstract description 55
- 238000004364 calculation method Methods 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 19
- 238000010606 normalization Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 15
- 238000013507 mapping Methods 0.000 claims description 10
- 238000012935 Averaging Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 abstract description 15
- 238000010276 construction Methods 0.000 abstract description 15
- 230000014509 gene expression Effects 0.000 description 18
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000000739 chaotic effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000002950 deficient Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000994 depressogenic effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Probability & Statistics with Applications (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Economics (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of computer vision, in particular to an intelligent detection method and system for building engineering quality. According to the method, the building local stability degree of each pixel point is obtained according to the gray distribution characteristics in the neighborhood of each pixel point in the building engineering image; obtaining the gray level characteristics of the building background in the neighborhood according to the gray level similarity between every two adjacent pixel points in the neighborhood, and further obtaining the building background characteristics of the pixel point neighborhood; obtaining building defect characteristics of the pixel neighborhood according to the gray scale abnormal characteristics in the pixel neighborhood; further obtaining the building local gray scale characteristics of the pixel neighborhood; combining the distance between the pixel points and the building local gray feature difference to obtain the similarity between the pixel points, and further obtaining the clustering result of the image; and detecting the quality of the building engineering according to the clustering result. The invention ensures that the clustering result is more accurate and is convenient for intelligent detection of the quality of the construction engineering.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to an intelligent detection method and system for building engineering quality.
Background
The construction industry has been one of the key areas of social development, and quality management of construction engineering has been a key element of project success. The traditional quality detection method mainly relies on manual inspection and off-line detection, and has the problems of low efficiency, large blind area, high cost and the like. With the continuous development of technology, intelligent detection technology gradually provides new possibilities for improving quality management level in the field of building engineering.
When the construction image is detected, the construction works can have defect manifestations such as cracks, pits and the like; in the prior art, a clustering algorithm is generally used for carrying out clustering analysis on pixel points in a building engineering image, and different defect expressions are clustered in one cluster so as to be convenient for analysis. However, the similarity between the pixels is determined only by the distance between the pixels, so that relatively continuous defects or the same defects at different positions in the building engineering image are subjected to error in clustering, and quality detection of the building engineering is affected.
Disclosure of Invention
In order to solve the technical problem that when a building engineering image is analyzed by using a clustering algorithm, the similarity between pixel points is determined only by the distance between the pixel points, so that relatively continuous defects in the building engineering image or the same defects at different positions are caused to generate errors in clustering, and the quality detection of the building engineering is influenced, the invention aims to provide an intelligent detection method and system for the quality of the building engineering, and the adopted technical scheme is as follows:
An intelligent detection method for building engineering quality, the method comprising:
Acquiring a building engineering image;
Obtaining the building gray level confusion degree of each pixel point preset neighborhood according to the gray level distribution characteristics of each pixel point preset neighborhood in the building engineering image; according to the gray level difference characteristics of each pixel point in all preset extending directions in the preset neighborhood, obtaining the building gray level difference degree of the preset neighborhood of each pixel point; obtaining the building local stability degree of each pixel point in the building engineering image according to the building gray level confusion degree and the building gray level difference degree of the preset neighborhood of each pixel point;
According to the gray level similarity degree between every two adjacent pixel points in the preset neighborhood of each pixel point, obtaining the building background gray level characteristic of the preset neighborhood of each pixel point; correcting the gray level stability of each pixel point in the preset neighborhood by using the building background gray level characteristics to obtain building background characteristics of each pixel point in the preset neighborhood; obtaining building defect characteristics of a preset neighborhood of each pixel point according to gray distribution fluctuation characteristics of the pixel points in the preset neighborhood of each pixel point and gray distribution difference characteristics among the pixel points in each extending direction;
Obtaining a building local gray scale characteristic in a preset adjacent area of each pixel point according to the building background characteristic, the building defect characteristic and the building local stability; obtaining the similarity between any two pixel points according to the building local gray feature difference and the position distance between any two pixel points; obtaining a clustering result of the building engineering image according to the similarity;
and detecting the quality of the building engineering according to the clustering result.
Further, the method for acquiring the building gray level confusion degree comprises the following steps:
and averaging the gray value difference between the central pixel point in the preset neighborhood and each other pixel point to obtain the building gray level confusion degree of the preset neighborhood of each pixel point.
Further, the method for obtaining the building gray scale difference degree comprises the following steps:
The building gray level difference degree is obtained according to a building gray level difference degree calculation formula, and the building gray level difference degree calculation formula is as follows:
; in the/> Represents the/>Presetting the building gray scale difference degree in the adjacent area by each pixel point; /(I)Represents the/>The number of extending directions of the individual pixel points; /(I)Represents the/>A serial number of the extending direction of each pixel point; /(I)Represents the/>Presetting the number of pixel points in each extending direction in the neighborhood by each pixel point; /(I)Represents the/>Presetting a pixel sequence number in each extending direction in the neighborhood by each pixel; /(I)Represents the/>Gray values of the individual pixels; /(I)Represents the/>Each pixel is preset with the first/>, in the neighborhoodFirst/>, in the extension directionGray values of the individual pixels; /(I)Representing a maximum function; representing a minimum function.
Further, the method for obtaining the local stability of the building comprises the following steps:
And carrying out negative correlation mapping and normalization processing on the product of the building gray level confusion degree and the building gray level difference degree of each pixel point preset neighborhood to obtain the building local stability degree of each pixel point preset neighborhood.
Further, the method for acquiring the gray level characteristics of the building background comprises the following steps:
Calculating the similarity characteristic between gray values of every two adjacent pixel points in the preset neighborhood of each pixel point as the gray similarity degree between every two adjacent pixel points;
and averaging the gray level similarity degree between every two adjacent pixel points in the preset neighborhood of each pixel point to obtain the building background gray level characteristic of the preset neighborhood of each pixel point.
Further, the method for acquiring the building background feature comprises the following steps:
Carrying out negative correlation mapping and normalization processing on the gray standard deviation in the preset neighborhood of each pixel point to obtain the gray stability of the preset neighborhood of each pixel point;
And carrying out normalization processing on the product of the gray level characteristic of the building background and the gray level stability degree to obtain the building background characteristic of the preset neighborhood of each pixel point.
Further, the method for acquiring the building defect characteristics comprises the following steps:
obtaining the building defect characteristics according to a building defect characteristic calculation formula, wherein the building defect characteristic calculation formula is as follows:
; in the/> Represents the/>Presetting building defect characteristics in the neighborhood of each pixel point; /(I)Represents the/>Presetting gray standard deviation in the neighborhood of each pixel point; /(I)Represents the/>The number of extending directions of the individual pixel points; /(I)Represents the/>A serial number of the extending direction of each pixel point; /(I)Represents the/>Each pixel is preset with the first/>, in the neighborhoodGray average value of all pixel points in each extending direction; /(I)Representing the/>, within a preset neighborhoodThe gray value of each extending direction is smaller than/>Is the number of pixels; /(I)Represents the/>Each pixel is preset with the first/>, in the neighborhoodThe gray value of each extending direction is smaller than/>(1 /)Gray values of the individual pixels; /(I)Representing a normalization function; An exponential function based on a natural constant is represented.
Further, the method for acquiring the building local gray scale characteristics comprises the following steps:
The building local gray scale characteristics are obtained according to a building local gray scale characteristic calculation formula, and the building local gray scale characteristic calculation formula is as follows:
; in the/> Represents the/>Presetting building local gray scale characteristics in the neighborhood by each pixel point; /(I)Represents the/>Presetting building local stability in the neighborhood by each pixel point; /(I)Represents the/>Presetting building background characteristics in the neighborhood by each pixel point; /(I)Represents the/>Building defect characteristics in the neighborhood are preset for each pixel point.
Further, the method for obtaining the similarity comprises the following steps:
And carrying out negative correlation mapping and normalization processing on the building local gray feature difference and the Euclidean distance between any two pixel points on the building engineering image to obtain the similarity between any two pixel points on the building engineering image.
A construction quality intelligent detection system, the system comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the construction quality intelligent detection method when executing the computer program.
The invention has the following beneficial effects:
The method comprises the steps of obtaining a building engineering image; because the pixel point preset adjacent areas possibly have both a defect area and a normal area, and the building local stability degrees of gray scale characteristics in the pixel point preset adjacent areas are different, the building gray scale confusion degree of each pixel point preset adjacent area is obtained according to the gray scale distribution characteristics in each pixel point preset adjacent area in a building engineering image; according to the gray level difference characteristics of each pixel point in all preset extending directions in the preset neighborhood, obtaining the building gray level difference degree of the preset neighborhood of each pixel point; according to the building gray level confusion degree and the building gray level difference degree in the preset adjacent area of each pixel point, the building local stability degree of each pixel point in the building engineering image is obtained, and gray level expression characteristics in the preset adjacent area of each pixel point are reflected; because the gray values of the pixels in the normal area are consistent and the external environment is different, the gray values of the pixels in the defect area are often different, and therefore, the building background gray characteristics of each pixel preset neighborhood are obtained according to the gray similarity degree between every two adjacent pixels in each pixel preset neighborhood; correcting the gray level stability of each pixel point in the preset neighborhood by using the building background gray level characteristics to obtain the building background characteristics of each pixel point in the preset neighborhood, and reflecting the normal expression level of the gray level characteristics of each pixel point in the preset neighborhood; if more defect areas exist in the preset neighborhood of the pixel point, gray values of the pixel points are lower in the preset neighborhood, so that the building defect characteristics of the preset neighborhood of each pixel point are obtained according to gray distribution fluctuation characteristics of the pixel points in the preset neighborhood of each pixel point and gray distribution difference characteristics among the pixel points in each extending direction, and the abnormal expression degree of the gray characteristics of the preset neighborhood of each pixel point is reflected; obtaining a building local gray scale characteristic in a preset adjacent area of each pixel point according to the building background characteristic, the building defect characteristic and the building local stability; obtaining the similarity between any two pixel points according to the building local gray feature difference and the distance between any two pixel points; obtaining a clustering result of the building engineering image according to the similarity; and detecting the quality of all the pixel points according to the clustering result. According to the method, the gray scale characteristics in the neighborhood of the pixels are utilized to calculate the building local gray scale characteristics between any two pixels in the building engineering image, and the similarity between the pixels is obtained by combining the distances between the pixels, so that the clustering result is more accurate, and the intelligent detection of the quality of the building engineering is facilitated.
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 flow chart of a method for intelligently detecting the quality of a building engineering according to an embodiment of the invention;
Fig. 2 is a schematic surface view of a building engineering 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 intelligent detection method and system for construction engineering quality according to the invention with reference to the accompanying drawings and preferred embodiments. 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 and a system for intelligently detecting the quality of construction engineering, which are specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for intelligently detecting quality of a building engineering according to an embodiment of the present invention is shown, where the method includes:
step S1: and acquiring a building engineering image.
The embodiment of the invention provides an intelligent detection method for quality of construction engineering, which aims at quality detection of construction engineering and firstly needs to acquire an identification object, namely a construction engineering image, of the embodiment of the invention.
In one embodiment of the invention, a CCD industrial camera is used for shooting the building wall to obtain all the building engineering images.
It should be noted that, in order to ensure the image quality in the subsequent image processing process, an image preprocessing operation is required to be performed after the building engineering image is obtained, and the specific image preprocessing operation is a technical means well known to those skilled in the art, and is not repeated herein and limited. In an embodiment of the invention, the image preprocessing operation includes filtering and graying.
Step S2: according to the gray distribution characteristics in the preset neighborhood of each pixel point in the building engineering image, obtaining the building gray chaotic degree of the preset neighborhood of each pixel point; according to the gray level difference characteristics of each pixel point in all preset extending directions in the preset neighborhood, obtaining the building gray level difference degree of the preset neighborhood of each pixel point; and according to the preset building gray level confusion degree and the building gray level difference degree in the neighborhood of each pixel point, obtaining the building local stability degree of each pixel point in the building engineering image.
Fig. 2 provides a schematic illustration of a construction surface in which the gray scale of the fractured and depressed areas of the construction surface is less than the gray scale of the normal areas and the gray scale of the different defective areas of the construction surface is not the same. Because the gray scale of the pixel points in different areas are different, the preset neighborhood of each pixel point in the building engineering image should be analyzed, and the local representation of each pixel point in the neighborhood is obtained through the gray scale characteristics in the neighborhood. Since defects existing on the building surface may not be continuous and distributed irregularly, there may be both a defective area and a normal area within the preset neighborhood of each pixel, and the local stability of the building of the gray features within the preset neighborhood of each pixel is different. In the embodiment of the invention, the building gray level confusion degree of each pixel point preset neighborhood is obtained according to the gray level distribution characteristics in the preset neighborhood of each pixel point in the building engineering image; according to the gray level difference characteristics of each pixel point in all preset extending directions in the preset neighborhood, obtaining the building gray level difference degree of the preset neighborhood of each pixel point; and according to the preset building gray level confusion degree and the building gray level difference degree in the neighborhood of each pixel point, obtaining the building local stability degree of each pixel point in the building engineering image.
In one embodiment of the invention, the preset neighborhood is set to be centered on each pixel pointIf not emphasized specifically, the preset neighbors are all set in this way. It should be noted that, in other embodiments of the present invention, the preset neighborhood setting mode may be set by an implementation personnel, which is not limited herein.
Preferably, in one embodiment of the present invention, the method for obtaining the degree of confusion of the gray scale of the building includes:
And averaging the gray value difference between the central pixel point in the preset neighborhood and each other pixel point to obtain the building gray level confusion degree of the preset neighborhood of each pixel point. In one embodiment of the invention, the calculation formula of the building gray level confusion degree is as follows:
In the method, in the process of the invention, Represents the/>Presetting the building gray level confusion degree in the neighborhood by each pixel point; /(I)Represents the/>Presetting the number of other pixels in the neighborhood by each pixel; /(I)Represents the/>Presetting sequence numbers of other pixels in the neighborhood by each pixel; /(I)Represents the/>Gray values of the individual pixels; /(I)Represents the/>Each pixel is preset with the first/>, in the neighborhoodGray values of individual pixels.
In the calculation formula of the building gray level confusion degree, the firstThe larger the average value of gray value differences between the central pixel point and each other pixel point in the preset neighborhood of each pixel point is, the description of the/>The more prominent the gray level of each pixel point in a preset adjacent area, the more prominent the gray level of each pixel point in the preset adjacent areaThe worse the gray scale of each pixel point is in the preset neighborhood.
Preferably, in one embodiment of the present invention, the method for acquiring the degree of difference in gray scale of a building includes:
obtaining the building gray level difference degree according to a building gray level difference degree calculation formula, wherein the building gray level difference degree calculation formula is as follows:
In the method, in the process of the invention, Represents the/>Presetting the building gray scale difference degree in the adjacent area by each pixel point; /(I)Represents the/>The number of extending directions of the individual pixel points; /(I)Represents the/>A serial number of the extending direction of each pixel point; /(I)Represents the/>Presetting the number of pixel points in each extending direction in the neighborhood by each pixel point; /(I)Represents the/>Presetting a pixel sequence number in each extending direction in the neighborhood by each pixel; /(I)Represents the/>Gray values of the individual pixels; /(I)Represents the/>Each pixel is preset with the first/>, in the neighborhoodFirst/>, in the extension directionGray values of the individual pixels; /(I)Representing a maximum function; /(I)Representing a minimum function.
In the calculation formula of the gray scale difference degree of the building,Represents the/>Each pixel is preset with the first/>, in the neighborhoodFirst/>, in the extension directionGray value and the/>, of each pixel pointThe ratio between the maximum value and the minimum value between the gray values of the pixel points is equal to/>When the gray scale difference between the central pixel point in the preset neighborhood and each pixel point in the extending direction is larger, the gray scale difference is larger through the first/>The building gray level difference degree of gray level characteristics of each pixel point in each extending direction of the neighborhood is preset, the stability degree of gray level expression of the pixel points in each extending direction is reflected, wherein the greater the building gray level difference degree is, the smaller the stability degree of gray level expression of the pixel points in each extending direction is, the maximum value of the building gray level difference degree in all extending directions is selected, the greater the possibility that the pixel points in defect areas exist in the extending direction corresponding to the maximum value of the building gray level difference degree is, and when the extending direction corresponding to the maximum value of the building gray level difference degree also presents relatively stable gray level characteristics, the first/>The more stable the local gray scale characteristics in the preset neighborhood of each pixel point are.
In one embodiment of the present invention, the preset extending directions are set to eight neighborhood directions of the central pixel point in the preset neighborhood, and the preset extending directions all adopt the setting mode unless special emphasis is made below. It should be noted that, in other embodiments of the present invention, other extending directions may be used, which is not limited herein.
Preferably, in one embodiment of the present invention, the method for obtaining the local stability of the building includes:
And carrying out negative correlation mapping and normalization processing on the product of the building gray level confusion degree and the building gray level difference degree of each pixel point preset neighborhood to obtain the building local stability degree of each pixel point preset neighborhood. In one embodiment of the invention, the calculation formula of the building local stability is as follows:
In the method, in the process of the invention, Represents the/>Presetting building local stability in the neighborhood by each pixel point; /(I)Represents the/>Presetting the building gray level confusion degree in the neighborhood by each pixel point; /(I)Represents the/>Presetting the building gray scale difference degree in the adjacent area by each pixel point; An exponential function based on a natural constant is represented.
In the calculation formula of the local stability degree of the building, the firstThe smaller the building gray level confusion degree in the preset neighborhood of each pixel point is, the/>The greater the building local stability degree of gray scale characteristics in the preset neighborhood of each pixel point; first/>The smaller the building gray scale difference degree in the preset neighborhood of each pixel point is, namely the first/>The pixel points in the extending direction with the most serious defect in the preset neighborhood of each pixel point have smaller difference degree, and the/>Carrying out negative correlation mapping and normalization processing on the building local stability degree and the building gray level difference degree in the preset neighborhood of each pixel point, and at the moment, carrying out gray value and/>, of the pixel points in the extending directionThe gray values of the individual pixels are similar, so the/>The greater the building local stability of gray scale characteristics in the preset neighborhood of each pixel point.
So far, the building local stability degree of each pixel point in the preset adjacent area is obtained.
Step S3: according to the gray level similarity degree between every two adjacent pixel points in the preset neighborhood of each pixel point, obtaining the building background gray level characteristic of the preset neighborhood of each pixel point; correcting the gray level stability of each pixel point in the preset neighborhood by using the building background gray level characteristics to obtain building background characteristics of each pixel point in the preset neighborhood; and obtaining the building defect characteristics of the preset neighborhood of each pixel point according to the gray distribution fluctuation characteristics of the pixel points in the preset neighborhood of each pixel point and the gray distribution difference characteristics among the pixel points in each extending direction.
Since the normal region and the defect region may exist in the preset adjacent region of each pixel, and the normal expression level and the abnormal expression level of the gray scale features in the adjacent regions of different pixels are different. When the building local stability degree of gray scale characteristics in the pixel preset neighborhood is larger, the normal area occupation ratio in the pixel preset neighborhood is larger, and the defect area occupation ratio is smaller. Because the gray features of different defect areas may be different, there are situations that the preset neighborhood building local stability degrees of different pixel points are the same, but the respective normal performance degrees and the abnormal performance degrees in the two neighborhood areas may be different, in order to accurately obtain the similarity between the two pixel points, the gray performance degree of the normal pixel point belonging to the background area in the preset neighborhood of each pixel point and the gray performance degree of the abnormal pixel point belonging to the defect area need to be utilized, and the building local stability degree in the preset neighborhood of each pixel point is adjusted. Therefore, in the embodiment of the invention, the building background characteristic and the building defect characteristic of the preset neighborhood of each pixel point are obtained.
The gray level similarity between every two adjacent pixels in the preset neighborhood of the pixel can reflect the normal expression degree of the normal region in the preset neighborhood of the pixel, wherein the larger the gray level similarity between every two adjacent pixels, the more similar the gray level values of the two adjacent pixels are. In practical situations, gray values of pixel points in a normal area are consistent, and because of different external environments, gray values of pixel points in a defect area often have differences, gray characteristics of normal pixel points in a preset neighborhood can be obtained according to gray similarity between pixel points in the neighborhood.
Preferably, in one embodiment of the present invention, the method for acquiring the gray-scale feature of the building background includes:
Calculating the similarity characteristic between gray values of every two adjacent pixel points in the preset neighborhood of each pixel point as the gray similarity degree between every two adjacent pixel points; and averaging the gray level similarity degree between every two adjacent pixel points in the preset neighborhood of each pixel point to obtain the building background gray level characteristic of the preset neighborhood of each pixel point.
In one embodiment of the invention, a minimum gray value and a maximum gray value between every two adjacent pixel points in a preset neighborhood of each pixel point are obtained; taking the ratio of the minimum value of the gray value between every two adjacent pixel points to the maximum value of the gray value as the similarity between the gray values of the two adjacent pixel points, and averaging the ratio of the minimum value of the gray value between every two adjacent pixel points to the maximum value of the gray value to obtain the building background gray characteristic of the preset neighborhood of each pixel point; the closer the average value is to 1, the closer the gray value of the pixel point in the preset neighborhood of the pixel point is, the larger the gray similarity degree between two adjacent pixel points is, at the moment, the larger the normal area occupation ratio in the neighborhood is, and the more obvious the gray characteristic of the building background in the neighborhood is.
Preferably, in one embodiment of the present invention, the method for acquiring the building background feature includes:
carrying out negative correlation mapping and normalization processing on the gray standard deviation in the preset neighborhood of each pixel point to obtain the gray stability of the preset neighborhood of each pixel point; and carrying out normalization processing on the product of the gray level characteristic of the building background and the gray level stability degree to obtain the building background characteristic of the preset neighborhood of each pixel point. In one embodiment of the invention, the building background feature calculation formula is as follows:
In the method, in the process of the invention, Represents the/>Presetting building background characteristics in the neighborhood by each pixel point; /(I)Represents the/>Presetting gray standard deviation in the neighborhood of each pixel point; /(I)Represents the/>Presetting the total number of pixel points in the neighborhood by each pixel point; /(I)Represents the/>Presetting pixel sequence numbers in adjacent areas by the pixel points; /(I)Represents the/>Each pixel is preset with the first/>, in the neighborhoodGray values of the individual pixels; represents the/> Each pixel is preset with the first/>, in the neighborhoodGray values of the individual pixels; /(I)Representing a maximum function; /(I)Representing a minimum function; /(I)Representing a normalization function; /(I)Represents the/>Presetting gray level stability in the neighborhood of each pixel point; /(I)Represents the/>Each pixel point presets the gray scale characteristics of the building background in the adjacent area.
In the building background feature calculation formula,The closer to 1, the description of the/>, within the preset neighborhoodPixel dot and/>The smaller the gray level difference degree between every two adjacent pixel points in the preset neighborhood is, the smaller the gray level difference degree between every two adjacent pixel points is, namely/>The more similar the gray values of the pixel points in the preset neighborhood of each pixel point are, the larger the normal area ratio is, the larger the first/>, the larger the normal area ratio should beThe local stability degree of the building in the neighborhood is preset by each pixel point, and the first/>The larger the building background features in the preset neighborhood of each pixel point are; and/>The smaller the standard deviation of gray values of pixel points in preset neighborhood of each pixel point is, the/>The more stable the gray level of the pixel point in the preset neighborhood of the pixel point, the/>The more normal a preset neighborhood of each pixel point is likely to be, the more the second/>, the larger the preset neighborhood of each pixel point should beThe local stability degree of the building in the neighborhood is preset by each pixel point, and the first/>The larger the building background feature in the preset neighborhood of each pixel point.
If more defect areas exist in the preset neighborhood of the pixel point, a plurality of abnormal pixel points with lower gray values exist in the preset neighborhood, gray distribution fluctuation characteristics in the neighborhood of different pixel points are different, and gray distribution difference characteristics in each extending direction of the pixel point in the center of the neighborhood are different.
Preferably, in one embodiment of the present invention, the method for acquiring the building defect feature includes:
building defect characteristics are obtained according to a building defect characteristic calculation formula, and the building defect characteristic calculation formula is as follows:
In the method, in the process of the invention, Represents the/>Presetting building defect characteristics in the neighborhood of each pixel point; /(I)Represents the/>Presetting gray standard deviation in the neighborhood of each pixel point; /(I)Represents the/>The number of extending directions of the individual pixel points; /(I)Represents the/>A serial number of the extending direction of each pixel point; /(I)Represents the/>Each pixel is preset with the first/>, in the neighborhoodGray average value of all pixel points in each extending direction; /(I)Representing the/>, within a preset neighborhoodThe gray value of each extending direction is smaller than/>Is the number of pixels; represents the/>Each pixel is preset with the first/>, in the neighborhoodThe gray value of each extending direction is smaller than/>(1 /)Gray values of the individual pixels; /(I)Representing a normalization function; An exponential function based on a natural constant is represented.
In the building defect characteristic calculation formula, the firstThe smaller the gray value mean value of the pixel points in each extending direction in the preset neighborhood of each pixel point is, the/>The more the number of abnormal pixel points belonging to the defect area in each extending direction in the preset neighborhood of each pixel point, the more obvious the building defect characteristics are; in/>Each pixel is preset with the first/>, in the neighborhoodIn the extending direction, the average value of the gray values of the pixel points in the extending direction is smaller than/>, in the extending directionSum of differences between gray values of all pixels, first/>The larger the difference value and the value in the extending direction, the more the number of abnormal pixel points belonging to the defect area in the extending direction, the more obvious the gray distribution difference characteristic in the extending direction, the/>The more obvious the abnormal pixel gray scale abnormal characteristics of the defect area in each extending direction in the preset neighborhood of each pixel are, the analysis is carried out on all extending directions,Reflect the/>Each pixel is preset with the first/>, in the neighborhoodGray distribution difference features between pixel points in the extending direction, wherein the more obvious the gray distribution difference features are, the description is given in the/>The more obvious the gray scale characteristics of the abnormal pixel points belonging to the defect area in the extending direction are, the larger the average value is, the more/>, the gray scale distribution difference characteristics of all extending directions are averagedThe larger the building defect characteristics in the preset neighborhood of each pixel point are; first/>The larger the standard deviation of gray values in preset neighborhoods of the pixel points is, the more chaotic the gray distribution fluctuation characteristics in the neighborhoods are, namely/>The more obvious the gray scale anomaly characteristic of the abnormal pixel points belonging to the defect area in the preset neighborhood of each pixel point is, the/>The larger the building defect feature in the preset neighborhood of each pixel point.
So far, the building background characteristics and the building defect characteristics in the preset adjacent areas of each pixel point are obtained.
Step S4: obtaining a building local gray scale characteristic in a preset adjacent area of each pixel point according to the building background characteristic, the building defect characteristic and the building local stability; obtaining the similarity between any two pixel points according to the building local gray feature difference and the position distance between any two pixel points; and obtaining a clustering result of the building engineering image according to the similarity.
And (3) adjusting the local stability of the building in the preset adjacent area of each pixel point by utilizing the building background characteristics and the building defect characteristics obtained in the step (S3) to obtain the local gray scale characteristics of the building in the preset adjacent area of each pixel point.
Preferably, in one embodiment of the present invention, the method for acquiring the local gray scale feature of the building includes:
Obtaining the building local gray scale characteristics according to the building local gray scale characteristic calculation formula, wherein the building local gray scale characteristic calculation formula is as follows:
In the method, in the process of the invention, Represents the/>Presetting building local gray scale characteristics in the neighborhood by each pixel point; /(I)Represents the/>Presetting building local stability in the neighborhood by each pixel point; /(I)Represents the/>Presetting building background characteristics in the neighborhood by each pixel point; /(I)Represents the/>Building defect characteristics in the neighborhood are preset for each pixel point.
In the building local gray feature calculation formula, because the normal region and the defect region possibly exist in the preset neighborhood of the pixel point at the same time, the building local stability degree can reflect the gray level expression degree of the normal region and the gray level expression degree of the abnormal region in the neighborhood of the pixel point, when the proportion of the normal region in the neighborhood of the pixel point is more, the proportion of the defect region is less, so that the utilization is realizedTo represent the degree of appearance of the defective region in the neighborhood of the pixel point; so/>Can reflect the/>The final expression degree of the normal region in the adjacent region is preset by each pixel point, and/>Can reflect the/>The final expression degree of the defect area in the adjacent area is preset by each pixel point, and the final expression degree are added to reflect the first/>Each pixel point presets the local gray scale characteristics of the building in the adjacent area.
Preferably, in one embodiment of the present invention, the method for obtaining the similarity includes:
and carrying out negative correlation mapping and normalization processing on the building local gray feature difference and the Euclidean distance between any two pixel points on the building engineering image to obtain the similarity between any two pixel points on the building engineering image. In one embodiment of the present invention, the similarity calculation formula is as follows:
In the method, in the process of the invention, Represents the/>Pixel dot and/>Similarity between individual pixels; /(I)Represents the/>Presetting building local gray scale characteristics in the neighborhood by each pixel point; /(I)Represents the/>Presetting building local gray scale characteristics in the neighborhood by each pixel point; represents the/> Pixel dot and/>The Euclidean distance between the individual pixel points; /(I)An exponential function based on a natural constant is represented.
In the similarity calculation formula, the firstPixel dot and/>The smaller the building local gray scale characteristics between the pixel points, the/>Pixel dot and/>The more likely the individual pixels are those with similar gray scale characteristics, the/>Pixel dot and/>The greater the similarity between the individual pixels; first/>Pixel dot and/>The smaller the Euclidean distance between the individual pixel points, the/>Pixel dot and/>The more likely that each pixel is present in the same region, at this time, the/>Pixel dot and/>The greater the similarity between the individual pixels.
Thus, the similarity between any two pixel points is obtained.
In one embodiment of the invention, all clusters are obtained by using a clustering algorithm based on dynamic splitting of a connected graph for each pixel point on a building engineering image according to the similarity between any two pixel points. It should be noted that, the clustering algorithm based on the dynamic splitting of the connected graph is a technical means well known to those skilled in the art, and in other embodiments of the present invention, other clustering algorithms may be used to perform quality detection of the building engineering, which is not limited and described herein.
Step S5: and detecting the quality of all the pixel points according to the clustering result.
In one embodiment of the present invention, quality detection is performed on all pixel points according to a clustering result, including:
In practical situations, the normal area of the building surface is the largest, so that the cluster with the largest area can be used as the cluster of the pixel points of the normal area, and a first cluster formed by the pixel points of the normal area is obtained at the moment;
Setting a distance threshold between other clusters and the first cluster, setting the gray value of the pixel points of all clusters larger than the distance threshold to 255, setting all the cluster smaller than the distance threshold to 0, setting all the pixel points in the first cluster to 0, and obtaining a binarized building engineering image, wherein in the binarized building engineering image, the pixel point with the gray value of 255 is the pixel point of a defect area, and the pixel point with the gray value of 0 is the pixel point of a normal area, so that the defect area and the normal area in the building engineering image are distinguished;
Because different types of defect areas exist, such as wall cracks, pits and the like, in order to further distinguish different defect areas, the binarized building engineering image is input into a CNN neural network and output as a quality condition. Wherein, the acquisition method of the data set comprises the following steps: and collecting building engineering binary images of different defect types, distributing different labels (such as wall skin cracks, pits and the like) to the binary images of the different defect types, and taking all samples and corresponding labels as a data set. Training process: the neural network is trained using the data set, and the loss function used is a cross entropy loss function.
It should be noted that, the CNN neural network is a technical means well known to those skilled in the art, and in other embodiments of the present invention, other neural networks may be used to perform quality detection of building engineering, which is not limited and described herein.
In conclusion, the invention acquires the building engineering image; according to the gray distribution characteristics in the preset neighborhood of each pixel point in the building engineering image, obtaining the building gray chaotic degree of the preset neighborhood of each pixel point; according to the gray level difference characteristics of each pixel point in all preset extending directions in the preset neighborhood, obtaining the building gray level difference degree of the preset neighborhood of each pixel point; according to the preset building gray level confusion degree and building gray level difference degree in the neighborhood of each pixel point, obtaining the building local stability degree of each pixel point in the building engineering image; according to the gray level similarity degree between every two adjacent pixel points in the preset neighborhood of each pixel point, obtaining the building background gray level characteristic of the preset neighborhood of each pixel point; correcting the gray level stability of each pixel point in the preset neighborhood by using the building background gray level characteristics to obtain building background characteristics of each pixel point in the preset neighborhood; according to the gray distribution fluctuation characteristics of the pixels in each pixel preset neighborhood and the gray distribution difference characteristics among the pixels in each extending direction, building defect characteristics of each pixel preset neighborhood are obtained, and the abnormal expression degree of the gray characteristics of each pixel preset neighborhood is reflected; obtaining a building local gray scale characteristic in a preset adjacent area of each pixel point according to the building background characteristic, the building defect characteristic and the building local stability; obtaining the similarity between any two pixel points according to the building local gray feature difference and the distance between any two pixel points; obtaining a clustering result of the building engineering image according to the similarity; and detecting the quality of the building engineering image according to the clustering result. According to the method, the gray scale characteristics in the neighborhood of the pixels are utilized to calculate the building local gray scale characteristics between any two pixels in the building engineering image, and the similarity between the pixels is obtained by combining the distances between the pixels, so that the clustering result is more accurate, and the intelligent detection of the quality of the building engineering is facilitated.
The embodiment of the invention also provides an intelligent detection system for the quality of the building engineering, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor can realize the steps of the intelligent detection method for the quality of the building engineering when executing the computer program.
An embodiment of a building engineering image clustering method comprises the following steps:
In the prior art, when a clustering algorithm is used for analyzing a building engineering image, the similarity between pixel points is determined only by the distance between the pixel points, so that relatively continuous defects or the same defects at different positions in the building engineering image are caused to have errors in clustering, and therefore, the technical problem that an accurate clustering result cannot be obtained is solved.
Step S1: and acquiring a building engineering image.
Step S2: according to the gray distribution characteristics in the preset neighborhood of each pixel point in the building engineering image, obtaining the building gray chaotic degree of the preset neighborhood of each pixel point; according to the gray level difference characteristics of each pixel point in all preset extending directions in the preset neighborhood, obtaining the building gray level difference degree of the preset neighborhood of each pixel point; and according to the preset building gray level confusion degree and the building gray level difference degree in the neighborhood of each pixel point, obtaining the building local stability degree of each pixel point in the building engineering image.
Step S3: according to the gray level similarity degree between every two adjacent pixel points in the preset neighborhood of each pixel point, obtaining the building background gray level characteristic of the preset neighborhood of each pixel point; correcting the gray level stability of each pixel point in the preset neighborhood by using the building background gray level characteristics to obtain building background characteristics of each pixel point in the preset neighborhood; and obtaining the building defect characteristics of the preset neighborhood of each pixel point according to the gray distribution fluctuation characteristics of the pixel points in the preset neighborhood of each pixel point and the gray distribution difference characteristics among the pixel points in each extending direction.
Step S4: obtaining a building local gray scale characteristic in a preset adjacent area of each pixel point according to the building background characteristic, the building defect characteristic and the building local stability; obtaining the similarity between any two pixel points according to the building local gray feature difference and the position distance between any two pixel points; and obtaining a clustering result of the building engineering image according to the similarity.
Because the specific implementation process of steps S1-S4 is already described in detail in the foregoing method and system for detecting the quality of a building engineering, no further description is given.
The technical effect of this embodiment is: the method comprises the steps of obtaining a building engineering image; because the pixel point preset adjacent areas possibly have both a defect area and a normal area, and the building local stability degrees of gray scale characteristics in the pixel point preset adjacent areas are different, the building gray scale confusion degree of each pixel point preset adjacent area is obtained according to the gray scale distribution characteristics in each pixel point preset adjacent area in a building engineering image; according to the gray level difference characteristics of each pixel point in all preset extending directions in the preset neighborhood, obtaining the building gray level difference degree of the preset neighborhood of each pixel point; according to the building gray level confusion degree and the building gray level difference degree in the preset adjacent area of each pixel point, the building local stability degree of each pixel point in the building engineering image is obtained, and gray level expression characteristics in the preset adjacent area of each pixel point are reflected; because the gray values of the pixels in the normal area are consistent and the external environment is different, the gray values of the pixels in the defect area are often different, and therefore, the building background gray characteristics of each pixel preset neighborhood are obtained according to the gray similarity degree between every two adjacent pixels in each pixel preset neighborhood; correcting the gray level stability of each pixel point in the preset neighborhood by using the building background gray level characteristics to obtain the building background characteristics of each pixel point in the preset neighborhood, and reflecting the normal expression level of the gray level characteristics of each pixel point in the preset neighborhood; if more defect areas exist in the preset neighborhood of the pixel point, gray values of the pixel points are lower in the preset neighborhood, so that the building defect characteristics of the preset neighborhood of each pixel point are obtained according to gray distribution fluctuation characteristics of the pixel points in the preset neighborhood of each pixel point and gray distribution difference characteristics among the pixel points in each extending direction, and the abnormal expression degree of the gray characteristics of the preset neighborhood of each pixel point is reflected; obtaining a building local gray scale characteristic in a preset adjacent area of each pixel point according to the building background characteristic, the building defect characteristic and the building local stability; obtaining the similarity between any two pixel points according to the building local gray feature difference and the distance between any two pixel points; and obtaining a clustering result of the building engineering image according to the similarity. According to the embodiment, the gray scale characteristics in the neighborhood of the pixel points are utilized to calculate the building local gray scale characteristics between any two pixel points in the building engineering image, and the similarity between the pixel points is obtained by combining the distances between the pixel points, so that the clustering result is more accurate.
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. An intelligent detection method for building engineering quality is characterized by comprising the following steps:
Acquiring a building engineering image;
Obtaining the building gray level confusion degree of each pixel point preset neighborhood according to the gray level distribution characteristics of each pixel point preset neighborhood in the building engineering image; according to the gray level difference characteristics of each pixel point in all preset extending directions in the preset neighborhood, obtaining the building gray level difference degree of the preset neighborhood of each pixel point; obtaining the building local stability degree of each pixel point in the building engineering image according to the building gray level confusion degree and the building gray level difference degree of the preset neighborhood of each pixel point;
According to the gray level similarity degree between every two adjacent pixel points in the preset neighborhood of each pixel point, obtaining the building background gray level characteristic of the preset neighborhood of each pixel point; correcting the gray level stability of each pixel point in the preset neighborhood by using the building background gray level characteristics to obtain building background characteristics of each pixel point in the preset neighborhood; obtaining building defect characteristics of a preset neighborhood of each pixel point according to gray distribution fluctuation characteristics of the pixel points in the preset neighborhood of each pixel point and gray distribution difference characteristics among the pixel points in each extending direction;
Obtaining a building local gray scale characteristic in a preset adjacent area of each pixel point according to the building background characteristic, the building defect characteristic and the building local stability; obtaining the similarity between any two pixel points according to the building local gray feature difference and the position distance between any two pixel points; obtaining a clustering result of the building engineering image according to the similarity;
and detecting the quality of the building engineering according to the clustering result.
2. The intelligent detection method for building engineering quality according to claim 1, wherein the method for obtaining the degree of confusion of the building gray scale comprises the following steps:
and averaging the gray value difference between the central pixel point in the preset neighborhood and each other pixel point to obtain the building gray level confusion degree of the preset neighborhood of each pixel point.
3. The intelligent detection method for building engineering quality according to claim 1, wherein the method for obtaining the building gray scale difference degree comprises the following steps:
The building gray level difference degree is obtained according to a building gray level difference degree calculation formula, and the building gray level difference degree calculation formula is as follows:
; in the/> Represents the/>Presetting the building gray scale difference degree in the adjacent area by each pixel point; /(I)Represents the/>The number of extending directions of the individual pixel points; /(I)Represents the/>A serial number of the extending direction of each pixel point; represents the/> Presetting the number of pixel points in each extending direction in the neighborhood by each pixel point; /(I)Represents the/>Presetting a pixel sequence number in each extending direction in the neighborhood by each pixel; /(I)Represents the/>Gray values of the individual pixels; /(I)Represents the/>Each pixel is preset with the first/>, in the neighborhoodFirst/>, in the extension directionGray values of the individual pixels; /(I)Representing a maximum function; /(I)Representing a minimum function.
4. The intelligent detection method for building engineering quality according to claim 1, wherein the method for obtaining the local stability degree of the building comprises the following steps:
And carrying out negative correlation mapping and normalization processing on the product of the building gray level confusion degree and the building gray level difference degree of each pixel point preset neighborhood to obtain the building local stability degree of each pixel point preset neighborhood.
5. The intelligent detection method for building engineering quality according to claim 1, wherein the method for acquiring the gray scale characteristics of the building background comprises the following steps:
Calculating the similarity characteristic between gray values of every two adjacent pixel points in the preset neighborhood of each pixel point as the gray similarity degree between every two adjacent pixel points;
and averaging the gray level similarity degree between every two adjacent pixel points in the preset neighborhood of each pixel point to obtain the building background gray level characteristic of the preset neighborhood of each pixel point.
6. The intelligent detection method for building engineering quality according to claim 1, wherein the method for acquiring the building background features comprises the following steps:
Carrying out negative correlation mapping and normalization processing on the gray standard deviation in the preset neighborhood of each pixel point to obtain the gray stability of the preset neighborhood of each pixel point;
And carrying out normalization processing on the product of the gray level characteristic of the building background and the gray level stability degree to obtain the building background characteristic of the preset neighborhood of each pixel point.
7. The intelligent detection method for building engineering quality according to claim 1, wherein the method for acquiring the building defect characteristics comprises the following steps:
obtaining the building defect characteristics according to a building defect characteristic calculation formula, wherein the building defect characteristic calculation formula is as follows:
; in the/> Represents the/>Presetting building defect characteristics in the neighborhood of each pixel point; /(I)Represents the/>Presetting gray standard deviation in the neighborhood of each pixel point; /(I)Represents the/>The number of extending directions of the individual pixel points; /(I)Represents the/>A serial number of the extending direction of each pixel point; represents the/> Each pixel is preset with the first/>, in the neighborhoodGray average value of all pixel points in each extending direction; /(I)Representing the/>, within a preset neighborhoodThe gray value of each extending direction is smaller than/>Is the number of pixels; /(I)Represents the/>Each pixel is preset with the first/>, in the neighborhoodThe gray value of each extending direction is smaller than/>(1 /)Gray values of the individual pixels; /(I)Representing a normalization function; /(I)An exponential function based on a natural constant is represented.
8. The intelligent detection method for building engineering quality according to claim 1, wherein the method for acquiring the local gray scale characteristics of the building comprises the following steps:
The building local gray scale characteristics are obtained according to a building local gray scale characteristic calculation formula, and the building local gray scale characteristic calculation formula is as follows:
; in the/> Represents the/>Presetting building local gray scale characteristics in the neighborhood by each pixel point; /(I)Represents the/>Presetting building local stability in the neighborhood by each pixel point; /(I)Represents the/>Presetting building background characteristics in the neighborhood by each pixel point; /(I)Represents the/>Building defect characteristics in the neighborhood are preset for each pixel point.
9. The intelligent detection method for building engineering quality according to claim 1, wherein the method for obtaining the similarity comprises the following steps:
And carrying out negative correlation mapping and normalization processing on the building local gray feature difference and the Euclidean distance between any two pixel points on the building engineering image to obtain the similarity between any two pixel points on the building engineering image.
10. An intelligent detection system for building engineering quality, the system comprising a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the steps of the intelligent detection method for building engineering quality according to any one of claims 1-9 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410432069.5A CN118038278B (en) | 2024-04-11 | 2024-04-11 | Intelligent detection method and system for quality of building engineering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410432069.5A CN118038278B (en) | 2024-04-11 | 2024-04-11 | Intelligent detection method and system for quality of building engineering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118038278A true CN118038278A (en) | 2024-05-14 |
| CN118038278B CN118038278B (en) | 2024-06-18 |
Family
ID=90989761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410432069.5A Active CN118038278B (en) | 2024-04-11 | 2024-04-11 | Intelligent detection method and system for quality of building engineering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118038278B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118246127A (en) * | 2024-05-21 | 2024-06-25 | 武汉同创万智数字科技有限公司 | BIM technology-based chemical process building construction method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004347363A (en) * | 2003-05-20 | 2004-12-09 | Utechzone Co Ltd | Method for inspecting display quality of electronic display through degree of disorder of luminance distribution |
| CN110458064A (en) * | 2019-07-31 | 2019-11-15 | 南京理工大学 | Combined data is driving and the detection of the low target of Knowledge driving type and recognition methods |
| CN115082445A (en) * | 2022-07-25 | 2022-09-20 | 山东鲁泰防水科技有限公司 | Method for detecting surface defects of building waterproof roll |
| CN115330780A (en) * | 2022-10-13 | 2022-11-11 | 山东盛世恒机械制造有限公司 | Rapid detection method for slag inclusion defect of metal welding |
| CN115439716A (en) * | 2022-09-20 | 2022-12-06 | 广东电网有限责任公司 | Method, device and equipment for training and detecting aging detection model of distribution network insulator |
| CN117557569A (en) * | 2024-01-12 | 2024-02-13 | 吉林交通职业技术学院 | Road pavement construction quality detection method and system |
| CN117635604A (en) * | 2024-01-23 | 2024-03-01 | 华航检测认证(青岛)有限公司 | Method for detecting welding quality of constructional engineering steel structure |
-
2024
- 2024-04-11 CN CN202410432069.5A patent/CN118038278B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004347363A (en) * | 2003-05-20 | 2004-12-09 | Utechzone Co Ltd | Method for inspecting display quality of electronic display through degree of disorder of luminance distribution |
| CN110458064A (en) * | 2019-07-31 | 2019-11-15 | 南京理工大学 | Combined data is driving and the detection of the low target of Knowledge driving type and recognition methods |
| CN115082445A (en) * | 2022-07-25 | 2022-09-20 | 山东鲁泰防水科技有限公司 | Method for detecting surface defects of building waterproof roll |
| CN115439716A (en) * | 2022-09-20 | 2022-12-06 | 广东电网有限责任公司 | Method, device and equipment for training and detecting aging detection model of distribution network insulator |
| CN115330780A (en) * | 2022-10-13 | 2022-11-11 | 山东盛世恒机械制造有限公司 | Rapid detection method for slag inclusion defect of metal welding |
| CN117557569A (en) * | 2024-01-12 | 2024-02-13 | 吉林交通职业技术学院 | Road pavement construction quality detection method and system |
| CN117635604A (en) * | 2024-01-23 | 2024-03-01 | 华航检测认证(青岛)有限公司 | Method for detecting welding quality of constructional engineering steel structure |
Non-Patent Citations (2)
| Title |
|---|
| YAXIONG HUANG等: "Automatic inspection of pavement cracking distress", 《JOURNAL OF ELECTRONIC IMAGING》, vol. 15, no. 1, 31 March 2006 (2006-03-31), pages 013017 - 1 * |
| 陈庆为: "基于灰色理论的木板材表面缺陷图像分割质量评价研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 03, 15 March 2015 (2015-03-15), pages 138 - 2227 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118246127A (en) * | 2024-05-21 | 2024-06-25 | 武汉同创万智数字科技有限公司 | BIM technology-based chemical process building construction method |
| CN118246127B (en) * | 2024-05-21 | 2024-08-02 | 武汉同创万智数字科技有限公司 | BIM technology-based chemical process building construction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118038278B (en) | 2024-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118038278B (en) | Intelligent detection method and system for quality of building engineering | |
| CN116611748B (en) | Titanium alloy furniture production quality monitoring system | |
| Sergyan | Color histogram features based image classification in content-based image retrieval systems | |
| CN114418957A (en) | Global and local binary pattern image crack segmentation method based on robot vision | |
| CN101770582A (en) | Image matching system and method | |
| CN116385450B (en) | PS sheet wear resistance detection method based on image processing | |
| CN101140216A (en) | Gas-liquid two-phase flow type recognition method based on digital graphic processing technique | |
| CN113947570B (en) | Crack identification method based on machine learning algorithm and computer vision | |
| CN116452589B (en) | Intelligent detection method for surface defects of artificial board based on image processing | |
| CN117893532B (en) | Die crack defect detection method for die forging rigging based on image processing | |
| CN116721107B (en) | Intelligent monitoring system for cable production quality | |
| CN114820625B (en) | Automobile top block defect detection method | |
| CN117808796B (en) | Gear surface damage detection method based on computer vision | |
| CN116188468A (en) | HDMI cable transmission letter sorting intelligent control system | |
| CN117036737A (en) | Feature extraction and matching method based on information entropy, GMS and LC significant detection | |
| CN114881965A (en) | Wood board joint detection method based on artificial intelligence and image processing | |
| CN114049320A (en) | Device missing AI quality inspection method and device based on picture similarity | |
| CN114155226A (en) | Micro defect edge calculation method | |
| CN114065798A (en) | Visual identification method and device based on machine identification | |
| CN110349119B (en) | Pavement disease detection method and device based on edge detection neural network | |
| CN113610790B (en) | Image recognition-based gas diffusion layer fiber measurement method | |
| CN109614970A (en) | A kind of appraisal procedure and system of infrared target stealthy effectiveness | |
| CN115311287A (en) | Method for detecting production abnormity of common rail oil injector | |
| CN118072254B (en) | Intelligent detection method and system for instantaneous explosion open fire | |
| CN118587223B (en) | Textile defect detection method based on image processing |
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 |