CN118536881B - Dynamic evaluation method, system and storage medium for engineering construction quality - Google Patents
Dynamic evaluation method, system and storage medium for engineering construction quality Download PDFInfo
- Publication number
- CN118536881B CN118536881B CN202411008128.2A CN202411008128A CN118536881B CN 118536881 B CN118536881 B CN 118536881B CN 202411008128 A CN202411008128 A CN 202411008128A CN 118536881 B CN118536881 B CN 118536881B
- Authority
- CN
- China
- Prior art keywords
- image
- construction
- determining
- pixel
- target
- 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.)
- Active
Links
- 238000010276 construction Methods 0.000 title claims abstract description 277
- 238000011156 evaluation Methods 0.000 title claims abstract description 27
- 239000000463 material Substances 0.000 claims abstract description 93
- 238000012545 processing Methods 0.000 claims abstract description 87
- 238000000034 method Methods 0.000 claims abstract description 41
- 230000011218 segmentation Effects 0.000 claims abstract description 40
- 238000003709 image segmentation Methods 0.000 claims abstract description 32
- 239000013077 target material Substances 0.000 claims abstract description 23
- 238000013441 quality evaluation Methods 0.000 claims abstract description 13
- 238000013507 mapping Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000002372 labelling Methods 0.000 claims description 6
- 238000013145 classification model Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 description 9
- 230000008859 change Effects 0.000 description 8
- 238000007689 inspection Methods 0.000 description 8
- 238000007726 management method Methods 0.000 description 8
- 238000001303 quality assessment method Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 238000003708 edge detection Methods 0.000 description 6
- 238000003908 quality control method Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 230000002349 favourable effect Effects 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a dynamic evaluation method, a system and a storage medium for engineering construction quality, belonging to the technical field of data processing. The method comprises the following steps: obtaining a first image of a target construction object at a first moment and a second image at a second moment; performing contour recognition on the first image to obtain a first contour line, and performing contour recognition on the second image to obtain a second contour line; determining a first construction area of the target construction object between a first moment and a second moment according to the first contour line and the second contour line; performing region segmentation on the first construction region by using an image segmentation model to obtain a plurality of second construction regions of the first construction region; respectively carrying out image classification on the plurality of second construction areas to obtain required material information of the second construction areas; determining target material information according to the required material information and the second construction area; and obtaining the consumption material information, and determining a quality evaluation result of the target construction object according to the target material information and the consumption material information.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a dynamic evaluation method, a system and a storage medium for engineering construction quality.
Background
Information engineering refers to a discipline or technical field for acquiring, transmitting, storing, processing and managing information by using knowledge of computer science, electronic engineering, communication technology and the like. It covers all links from the acquisition and processing of information to the transmission and storage, and is an important component in the information process of modern society.
The information system engineering supervision effectively ensures the implementation quality of the project by carrying out the works of quality control, progress control, investment control, change control, information management, safety management, contract management, coordination of the relationships of all parties and the like. The core of the quality control of the information system engineering is to accurately and efficiently calculate the implementation quality of the information system engineering. The key links of quality control are equipment arrival inspection, hidden engineering inspection, installation and debugging inspection and the like in the project implementation process.
Information system engineering because of the complex technical integration and equipment deployment involved, any quality problems arising in the construction of information system engineering can have a significant impact on the functionality and safety of the system. Therefore, construction quality assessment is a key to ensuring that engineering is smoothly performed and operated.
However, in the prior art, a lot of manpower, material resources and financial resources are required for performing engineering construction quality evaluation, which may increase the total cost of the project. In addition, the prior art generally adopts a manual method with lower efficiency and relies on a manual sampling inspection mode, which increases the probability of missed inspection.
Disclosure of Invention
The embodiment of the invention mainly aims to provide a dynamic evaluation method, a dynamic evaluation system and a dynamic evaluation storage medium for engineering construction quality, and aims to solve the problems that a large amount of manpower, material resources and financial resources are required to be input to evaluate engineering construction quality in related technologies, the total cost of projects is increased, and the efficiency of evaluating the engineering construction quality is low.
In a first aspect, an embodiment of the present invention provides a method for dynamically evaluating engineering construction quality, including:
Obtaining a first image corresponding to a target construction object at a first moment and a second image corresponding to the target construction object at a second moment;
Performing contour recognition on the first image to obtain a first contour line, and performing contour recognition on the second image to obtain a second contour line;
determining a first construction area of the target construction object between the first moment and the second moment according to the first contour line and the second contour line;
performing region segmentation on the first construction region by using an image segmentation model to obtain a plurality of second construction regions corresponding to the first construction region;
Respectively carrying out image classification on a plurality of second construction areas to obtain required material information corresponding to the second construction areas;
Determining target material information of the target construction object between the first moment and the second moment according to the required material information and the second construction area;
And obtaining the consumption material information corresponding to the first time and the second time, and determining a quality evaluation result corresponding to the target construction object according to the target material information and the consumption material information.
In a second aspect, an embodiment of the present invention provides a dynamic evaluation system for engineering construction quality, including:
the data acquisition module is used for acquiring a first image corresponding to a target construction object at a first moment and a second image corresponding to the target construction object at a second moment;
the contour determination module is used for carrying out contour recognition on the first image to obtain a first contour line and carrying out contour recognition on the second image to obtain a second contour line;
the area determining module is used for determining a first construction area of the target construction object between the first moment and the second moment according to the first contour line and the second contour line;
The region segmentation module is used for carrying out region segmentation on the first construction region by utilizing an image segmentation model to obtain a plurality of second construction regions corresponding to the first construction region;
The data classification module is used for respectively carrying out image classification on the plurality of second construction areas to obtain required material information corresponding to the second construction areas;
a material determining module, configured to determine target material information of the target construction object between the first time and the second time according to the required material information and the second construction area;
And the quality evaluation module is used for obtaining the consumption material information corresponding to the first time and the second time and determining a quality evaluation result corresponding to the target construction object according to the target material information and the consumption material information.
In a third aspect, an embodiment of the present invention further provides a storage medium, for storing a computer readable storage, where the storage medium stores one or more programs, and the one or more programs are executable by one or more processors to implement the steps of any one of the dynamic assessment methods for engineering construction quality provided in the specification of the present invention.
The embodiment of the invention provides a dynamic evaluation method, a system and a storage medium for engineering construction quality, according to the method, the progress and the change of the target construction object can be accurately monitored and compared by acquiring the first image corresponding to the target construction object and the second image corresponding to the target construction object at the second moment. The method is favorable for finding possible problems in time, and further, the first contour line and the second contour line are obtained by utilizing a contour recognition technology, so that the shape and the position of a target construction object at different time points can be accurately positioned and described, and a foundation is provided for subsequent region segmentation and material information extraction. Determining a first construction area of the target construction object between the first moment and the second moment according to the first contour line and the second contour line; the first construction area is segmented through the image segmentation model, each part of the construction site can be known more carefully, material information is acquired and analyzed for each second construction area, and required material information corresponding to a plurality of second construction areas is obtained; thereby combining the target material information and the consumption material information, the construction quality can be evaluated. The evaluation is based on actual image data and material use conditions, is more objective and accurate, and is beneficial to improving the efficiency and quality of construction projects. And the problems that a large amount of manpower, material resources and financial resources are required to be invested in project construction quality assessment in the related technology, the total cost of projects is increased, and the efficiency of adopting manual quality assessment is low are solved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a dynamic evaluation method for engineering construction quality according to an embodiment of the present invention;
fig. 2 is a schematic block diagram of a dynamic evaluation system for engineering construction quality according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations.
It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
Information engineering refers to a discipline or technical field for acquiring, transmitting, storing, processing and managing information by using knowledge of computer science, electronic engineering, communication technology and the like. It covers all links from the acquisition and processing of information to the transmission and storage, and is an important component in the information process of modern society.
The information system engineering supervision effectively ensures the implementation quality of the project by carrying out the works of quality control, progress control, investment control, change control, information management, safety management, contract management, coordination of the relationships of all parties and the like. The core of the quality control of the information system engineering is to accurately and efficiently calculate the implementation quality of the information system engineering. The key links of quality control are equipment arrival inspection, hidden engineering inspection, installation and debugging inspection and the like in the project implementation process.
Information system engineering because of the complex technical integration and equipment deployment involved, any quality problems arising in the construction of information system engineering can have a significant impact on the functionality and safety of the system. Therefore, construction quality assessment is a key to ensuring that engineering is smoothly performed and operated.
The embodiment of the invention provides a dynamic evaluation method, a system and a storage medium for engineering construction quality. The dynamic evaluation method for the engineering construction quality can be applied to terminal equipment, and the terminal equipment can be electronic equipment such as tablet computers, notebook computers, desktop computers, personal digital assistants, wearable equipment and the like. The terminal device may be a server or a server cluster.
Some embodiments of the invention are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic flow chart of a dynamic evaluation method for engineering construction quality according to an embodiment of the present invention.
As shown in fig. 1, the engineering construction quality dynamic evaluation method includes steps S101 to S107.
Step S101, a first image corresponding to a target construction object at a first moment and a second image corresponding to the target construction object at a second moment are obtained.
Illustratively, a target construction object is determined, and then a first image of the target construction object at a first time (e.g., a certain point in time) is obtained using a camera or an image acquisition device, and then a second image at a second time (another point in time) is obtained. The first time and the second time have preset time intervals, which may be set according to actual requirements, for example, the preset time intervals are 10 hours, 15 hours, and so on.
Step S102, performing contour recognition on the first image to obtain a first contour line, and performing contour recognition on the second image to obtain a second contour line.
Illustratively, a first contour pixel in the first image is detected using a contour detection algorithm provided in the image processing library, such as an edge detection algorithm (e.g., canny edge detection), and the first contour pixel is curve-fitted to obtain a first contour line. Likewise, the steps of contour detection and contour extraction are performed on the second image so that a second contour corresponding to the second image can be obtained.
In some embodiments, the performing contour recognition on the first image to obtain a first contour line, and performing contour recognition on the second image to obtain a second contour line, includes: performing edge pixel identification on the first image by using an edge identification algorithm to obtain a first edge pixel corresponding to the first image; performing pixel gradient calculation on two adjacent first edge pixels to obtain first gradient values, and dividing the first edge pixels according to the first gradient values to obtain a plurality of first pixel sets; performing curve fitting on the first pixel set to obtain a first fitted curve, and performing curve connection on all the first fitted curves to obtain the first contour line; performing edge pixel identification on the second image by using the edge identification algorithm to obtain a second edge pixel corresponding to the second image; performing pixel gradient calculation on two adjacent second edge pixels to obtain second gradient values, and dividing the second edge pixels according to the second gradient values to obtain a plurality of second pixel sets; and performing curve fitting on the second pixel set to obtain a second fitted curve, and performing curve connection on all the second fitted curves to obtain the second contour line.
Illustratively, an edge detection algorithm (e.g., canny edge detection) is used to identify edge pixels of the first image, thereby generating a binarized image, wherein the edge pixels are white and the background pixels are black, so as to determine the pixel points with the pixel values of white as the first edge pixels.
The pixel gradient calculation is performed on any two adjacent first edge pixels to obtain a first gradient value, and when the adjacent first gradient value meets a preset gradient value, the first edge pixels corresponding to the first gradient value are determined to be a pixel set, and then the first edge pixels are segmented to obtain the first pixel set.
Illustratively, the first pixel set is curve-fitted using polynomial fitting or other suitable curve-fitting method to obtain a first fitted curve, and all the first fitted curves are further connected together, so as to obtain a complete first contour line.
Illustratively, edge detection algorithms (e.g., canny edge detection) are used to identify edge pixels of the second image, thereby generating a binarized image in which the edge pixels are white and the background pixels are black, and thereby determining pixel points with white pixel values as the second edge pixels.
The pixel gradient calculation is performed on any two adjacent second edge pixels to obtain a second gradient value, and when the adjacent second gradient value meets a preset gradient value, the second edge pixels corresponding to the second gradient value are determined to be a pixel set, and then the second edge pixels are segmented to obtain a second pixel set.
Illustratively, the second pixel set is curve-fitted using polynomial fitting or other suitable curve-fitting method to obtain a second fitted curve, and all the second fitted curves are further connected together, so as to obtain a complete second contour line.
Specifically, edge pixels in the first image and the second image can be accurately identified through an edge identification algorithm, the edge pixels generally represent edge contours of target construction objects and are the basis of subsequent analysis, and further, calculating pixel gradient values of each edge pixel can provide specific information about edge changes. These gradient values can be used in subsequent segmentation and fitting steps to help describe more accurately the shape and characteristics of the object edges. And finally, by performing curve fitting and connection on each pixel set, accurate contour line description can be obtained. These contours not only reflect the shape changes of the target construction object in the first and second images, but also provide a basis for subsequent region segmentation and material information extraction. The change and progress of the construction site can be better understood and managed, thereby improving the quality management level.
In some embodiments, the performing curve connection on all the first fitted curves to obtain the first contour line and performing curve connection on all the second fitted curves to obtain the second contour line includes: determining two first fitting curves which are arbitrarily adjacent and have first crossing points, and further calculating first crossing coordinates corresponding to the first crossing points of the two first fitting curves; connecting the two first fitting curves according to the first cross coordinates to obtain the first contour line; determining two second fitting curves which are arbitrarily adjacent and have second crossing points, and further calculating second crossing coordinates corresponding to the second crossing points of the two second fitting curves; and connecting the two second fitting curves according to the second cross coordinates to obtain the second contour line.
The first pixel set corresponding to the first fitting curve is obtained, all the first fitting curves are ordered according to the pixel coordinates corresponding to the first pixel set, so that first cross coordinates corresponding to two first fitting curves which are arbitrarily adjacent and have the first cross points are obtained, the two first fitting curves are connected according to the first cross coordinates, all the first cross points are sequentially obtained, and all the first fitting curves are connected, so that a first contour line is obtained.
The second fitting curves are obtained by the first fitting curves, the second fitting curves are obtained by the second fitting curves, the second fitting curves are all ordered according to the pixel coordinates corresponding to the second fitting curves, and therefore second intersection coordinates corresponding to any two adjacent second fitting curves with the second intersection points are obtained, the two second fitting curves are connected according to the second intersection coordinates, all the second intersection points are obtained in sequence, and all the second fitting curves are connected, so that a second contour line is obtained.
Specifically, the first and second contour lines generated based on the calculated first and second intersection coordinates ensure that the generated first and second contour lines can be smooth and continuous, reflect the actual shape of the edge of the object, and further, the accurate first and second contour lines can be used as the basis of subsequent analysis, such as measurement of the shape of a building, monitoring of structural change and evaluation of construction progress, so as to help better monitor the shape change of a target construction object.
And step S103, determining a first construction area of the target construction object between the first moment and the second moment according to the first contour line and the second contour line.
The first contour line is mapped in the second image, and the content between the first contour line and the second contour line in the second image is determined as a first construction area of the target construction object between the first time and the second time.
In some embodiments, the determining a first construction area of the target construction object between the first time and the second time according to the first contour line and the second contour line includes: determining a reference object, determining first position information of the reference object corresponding to the first image and determining second position information of the reference object corresponding to the second image; performing alignment processing on the first image and the second image by using the first position information and the second position information according to the reference object to obtain alignment information; labeling the first contour line in the second image according to the alignment information, and labeling the second contour line in the second image to obtain a labeled third image; and cutting the third image according to the first contour line and the second contour line to obtain the first construction area.
For example, a reference object, for example a marker or a specific landmark, which can be clearly identified in both the first image and the second image, is selected, and the first position information of the reference object in the first image and the corresponding second position information in the second image are determined.
The alignment process is illustratively performed on the two images using the first position information of the reference object in the first image and the second position information in the second image. This includes translation, rotation, and scaling, etc., to ensure that the first image and the second image match in position and size in space, thereby obtaining alignment information. For example, the alignment information includes a translation size, a scaling size, a rotation size, and the like.
The alignment processing is performed on the first contour line according to the alignment information, so that the processed first contour line is marked in the second image, meanwhile, the second contour line is also marked in the second image, a third image with the first contour line and the second contour line is obtained, the third image is cut according to the position information of the first contour line and the second contour line in the aligned third image, and the image information of the first contour line and the second contour line in the third image is determined to be a first construction area. I.e. the first construction area is the area enclosed by the first contour line and the second contour line.
In particular, by determining the reference object and using its position information in both images, an accurate alignment of the first image and the second image in space can be ensured. This is critical for subsequent contour marking and region cutting, ensuring accuracy and reliability of operation. Based on the alignment information, the first contour line and the second contour line can be correctly marked on the second image so as to obtain the third image, thereby providing an accurate data basis for subsequent analysis and further providing an important basis for management and supervision of projects.
And step S104, carrying out region segmentation on the first construction region by using an image segmentation model to obtain a plurality of second construction regions corresponding to the first construction region.
Illustratively, an image segmentation model is selected that is appropriate for the task. Common image segmentation models include semantic segmentation models (e.g., FCN, U-Net), instance segmentation models (e.g., mask R-CNN), and contour segmentation models (e.g., HED network), and further the selected image segmentation models are trained or fine-tuned to accurately segment the first construction region.
The first construction area is illustratively segmented using a trained or fine-tuned image segmentation model, which will generate a plurality of second construction areas, the segmentation of the second construction areas being based on the differences in materials required for actually constructing the area, i.e. the differences in materials required for constructing the different second construction areas.
In some embodiments, the performing region segmentation on the first construction region by using an image segmentation model to obtain a plurality of second construction regions corresponding to the first construction region includes: denoising the first construction area by using a noise processing layer of the image segmentation model to obtain a denoised image; performing fuzzy processing on the denoising image by using a fuzzy processing layer of the image segmentation model to obtain a fuzzy image; and carrying out region segmentation on the blurred image by utilizing a segmentation processing layer of the image segmentation model to obtain a plurality of second construction regions.
Illustratively, the noise processing layer in the image segmentation model is used for denoising the first construction region, so that noise in the first construction region is eliminated, and subsequent processing is more accurate and stable.
Illustratively, the de-noised image is blurred with a blurring layer of the image segmentation model, which helps to smooth details in the image so that subsequent region segmentation is easier and more accurate.
The fuzzy image after the fuzzy processing is subjected to region segmentation by using a segmentation processing layer of the image segmentation model, and the first construction region is segmented into a plurality of second construction regions, and materials required for constructing each second construction region are different.
Specifically, the noise processing layer performs denoising processing to eliminate noise in the image, improve accuracy and stability of subsequent processing steps, and perform blurring processing in the blurring processing layer is helpful to smooth details in the image, so that high-frequency noise and unnecessary details in the image are reduced, and a segmentation model is easier to identify and segment. Finally, the first construction area can be more accurately divided into a plurality of second construction areas by utilizing the division processing layer for area division, so that a more reliable data basis is provided for subsequent analysis and application.
In some embodiments, the blurring processing layer using the image segmentation model performs blurring processing on the denoised image to obtain a blurred image, including: determining first distance information between any two first pixel points in the first construction area by utilizing the fuzzy processing layer; determining the segmentation quantity corresponding to the first construction area by utilizing the fuzzy processing layer, and determining the area center corresponding to the segmentation quantity; determining second distance information between the first pixel point and the center of the area in the first construction area by using the blurring processing layer; determining a first association degree between the first pixel point and the region center by using the first distance information and the second distance information by using the blurring processing layer; constructing a target matrix corresponding to the first construction area according to the first association degree and the first distance information by utilizing the fuzzy processing layer; determining a second association degree corresponding to the first pixel point and the region center according to the target matrix by utilizing the fuzzy processing layer; performing blurring processing on the denoising image according to the second association degree by using the blurring processing layer to obtain the blurred image; wherein the first degree of association is obtained according to the following formula:
。
Representing the first association degree between the ith pixel point and the jth region center; m represents the number of the first pixel points corresponding to the first construction area, First distance information representing an ith said first pixel point and a kth said first pixel point,Representing the second distance information between the j-th center of the region and the k-th first pixel point,Representing the second association degree of the first pixel point and the center of the area in the history record, m represents the degree of blurring set during blurring processing.
Illustratively, the blur handling layer is used to determine first distance information between any two first pixel points in the first construction area by calculating euclidean distances between pixels or other suitable distance measures. And determining the number of divisions corresponding to the first construction area, that is, the number corresponding to the second construction area, by using the fuzzy processing layer, and further determining the center position of each division area, where the center position may be randomly designated, and further continuously adjusted by a subsequent error.
For example, the blurring layer is used to determine second distance information between each pixel point in the first construction area and the center of the area to which the pixel point belongs. This helps to measure the positional relationship of each pixel point relative to the center of the area in which it is located.
The first degree of association between each pixel point in the first construction area and the center of the area is calculated using the first distance information and the second distance information according to the following formula:
。
Representing a first degree of association between the ith first pixel point and the center of the jth region; m represents the number of first pixel points corresponding to the first construction area, First distance information representing a distance between the i-th first pixel point and the k-th first pixel point,Second distance information representing a distance between a center of the jth region and the kth first pixel point,Representing a second degree of association of the first pixel point in the history record with the center of the region, m represents the degree of blurring set during blurring processing. The calculation of the first association degree depends on the second association degree, and the second association degree can be initialized when the first association degree is calculated, so that after the second association degree is calculated by using the first association degree, the first association degree is continuously updated to enable the first association degree and the second association degree to meet the preset condition.
The first distance information is weighted by using the first association degree to obtain an association relationship between each first pixel point and the center of the area, so as to construct a target matrix corresponding to the first construction area. The target matrix describes the relation between each first pixel point and the center of the area where the first pixel point is located, and is the basis of the subsequent blurring processing.
The second association degree corresponding to the center of the area where each first pixel point is located is determined according to the target matrix, so that weight distribution of the first pixel points in fuzzy processing is further optimized. And the de-noised image is subjected to blurring processing according to the second association degree, so that the blurring degree is adjusted according to the relation between the first pixel point and the center of the area where the first pixel point is positioned, the image is smoothed, and important area characteristics are reserved.
Specifically, by determining the first distance information between the pixel points and the second distance information between the pixel points and the center of the region, the relationship between the first pixel point and the region where the first pixel point is located can be accurately known. This helps preserve details and structure within the region during blurring processing. And the boundary and structure of the region can be optimized by using the first association degree and the target matrix calculated by the fuzzy processing layer. The method is favorable for more accurately dividing different parts of the region, reduces errors and missed division, further carries out fuzzy processing according to the second association degree, can better smooth details in the denoising image, ensures that region features in the image are more obvious and clear, and is favorable for the accuracy and reliability of subsequent division processing.
And step 105, respectively carrying out image classification on the plurality of second construction areas to obtain the required material information corresponding to the second construction areas.
The method includes the steps that an initial construction image and associated material information corresponding to the initial construction image are obtained, similarity calculation is conducted on a second construction area and the initial construction image, accordingly, the initial construction image corresponding to the second construction area when the similarity is maximum is determined to be a target construction image corresponding to the second construction area, and finally the associated material information corresponding to the target construction image is determined to be required material information corresponding to the second construction area.
In some embodiments, the image classifying the plurality of second construction areas to obtain the required material information corresponding to the second construction areas includes: respectively carrying out image classification on the second construction areas by using an image classification model to obtain target image types corresponding to each second construction area; and determining the required material information corresponding to the second construction area by using the target image type and a material mapping table.
The image classification model may be a deep learning based Convolutional Neural Network (CNN) or a deep learning based recurrent neural network for classifying images into different image types, for example.
Illustratively, a material mapping table is prepared that maps each target image type to specific desired material information. For example, the target image type is type 1, the required material is wood, glass; the target image type is type 2 and the desired material is cement, tile, etc.
The second construction regions are illustratively type predicted using a trained image classification model to determine to which target image type each second construction region belongs. And determining the required material information corresponding to each second construction area through the material mapping table according to the predicted target image type.
Specifically, the method can realize automatic image classification of a plurality of second construction areas, accurately acquire the material information required by each area, not only improve the efficiency, but also provide important decision support and basis for projects.
And step S106, determining target material information of the target construction object between the first moment and the second moment according to the required material information and the second construction area.
The actual size corresponding to the second construction area is determined, the quantity information required by each consumable in the required material information is determined according to the actual size, and the target material information of the target construction object between the first moment and the second moment is determined according to the quantity information.
In some embodiments, the determining the target material information of the target construction object between the first time and the second time according to the required material information and the second construction area includes: determining a mapping proportion between the second image and the target construction object, and determining a real construction area corresponding to the second construction area according to the mapping proportion; and predicting material parameters of the real construction area by using the required material information by using a data prediction model, and obtaining the target material information of the target construction object between the first moment and the second moment.
The mapping ratio between the target construction object and the real target construction object in the second image is determined, for example, by means of image processing techniques, such as feature matching or geometry-based methods. And then mapping the second construction area to the real construction area in the actual construction project by using the mapping proportion.
The data prediction model is determined based on a statistical method, machine learning or deep learning model, so that material parameters are predicted for a real construction area in combination with required material information, detailed parameters such as the material quantity corresponding to each material in the required material information are obtained, and a prediction result is determined as target material information of a target construction object between a first moment and a second moment.
Specifically, by determining the mapping ratio between the second image and the target construction object, the second construction area can be accurately mapped to the position and the proportional relation in the actual construction site. This ensures the accuracy of subsequent analysis and prediction. Therefore, the material parameter prediction is carried out on the real construction area by utilizing the data prediction model, and the material use change of the target construction object at different time points can be intelligently analyzed, so that support is provided for the subsequent dynamic evaluation of the engineering construction quality.
Step S107, obtaining consumption material information corresponding to the first time and the second time, and determining a quality evaluation result corresponding to the target construction object according to the target material information and the consumption material information.
Illustratively, first material information corresponding to the construction site at the first moment is counted, and second material information corresponding to the construction site at the second moment is counted, so that a difference between the first material information and the second material information is determined as consumption material information corresponding to the first moment and the second moment.
The method includes the steps that the difference quantity between each material in target material information and consumption material information is determined, and then quality assessment results corresponding to a target construction object are determined to be qualified when the difference quantity is in a preset range; and when the difference quantity is not in the preset range, determining that the quality evaluation result corresponding to the target construction object is unqualified, and carrying out cause analysis on a second construction area constructed between the first moment and the second moment, thereby ensuring the quality of the target construction object.
The embodiment of the invention provides a dynamic evaluation method, a system and a storage medium for engineering construction quality, according to the method, the progress and the change of the target construction object can be accurately monitored and compared by acquiring the first image corresponding to the target construction object and the second image corresponding to the target construction object at the second moment. The method is favorable for finding possible problems in time, and further, the first contour line and the second contour line are obtained by utilizing a contour recognition technology, so that the shape and the position of a target construction object at different time points can be accurately positioned and described, and a foundation is provided for subsequent region segmentation and material information extraction. Determining a first construction area of the target construction object between the first moment and the second moment according to the first contour line and the second contour line; the first construction area is segmented through the image segmentation model, each part of the construction site can be known more carefully, material information is acquired and analyzed for each second construction area, and required material information corresponding to a plurality of second construction areas is obtained; thereby combining the target material information and the consumption material information, the construction quality can be evaluated. The evaluation is based on actual image data and material use conditions, is more objective and accurate, and is beneficial to improving the efficiency and quality of construction projects. And the problems that a large amount of manpower, material resources and financial resources are required to be invested in project construction quality assessment in the related technology, the total cost of projects is increased, and the efficiency of adopting manual quality assessment is low are solved.
Referring to fig. 2, fig. 2 is a schematic diagram of an engineering construction quality dynamic evaluation system 200 according to an embodiment of the present application, where the engineering construction quality dynamic evaluation system 200 includes a data acquisition module 201, a contour determination module 202, a region determination module 203, a region segmentation module 204, a data classification module 205, a material determination module 206, and a quality evaluation module 207, where the data acquisition module 201 is configured to obtain a first image corresponding to a target construction object at a first moment and a second image corresponding to the target construction object at a second moment; the contour determination module 202 is configured to perform contour recognition on the first image to obtain a first contour line, and perform contour recognition on the second image to obtain a second contour line; a region determining module 203, configured to determine a first construction region of the target construction object between the first time and the second time according to the first contour line and the second contour line; the region segmentation module 204 is configured to segment the first construction region by using an image segmentation model, so as to obtain a plurality of second construction regions corresponding to the first construction region; the data classification module 205 is configured to perform image classification on the plurality of second construction areas to obtain required material information corresponding to the second construction areas; a material determining module 206, configured to determine target material information of the target construction object between the first time and the second time according to the required material information and the second construction area; and the quality evaluation module 207 is configured to obtain consumption material information corresponding to the first time and the second time, and determine a quality evaluation result corresponding to the target construction object according to the target material information and the consumption material information.
In some embodiments, the contour determination module 202 performs, in the process of performing contour recognition on the first image to obtain a first contour line and performing contour recognition on the second image to obtain a second contour line:
Performing edge pixel identification on the first image by using an edge identification algorithm to obtain a first edge pixel corresponding to the first image;
performing pixel gradient calculation on two adjacent first edge pixels to obtain first gradient values, and dividing the first edge pixels according to the first gradient values to obtain a plurality of first pixel sets;
Performing curve fitting on the first pixel set to obtain a first fitted curve, and performing curve connection on all the first fitted curves to obtain the first contour line;
Performing edge pixel identification on the second image by using the edge identification algorithm to obtain a second edge pixel corresponding to the second image;
performing pixel gradient calculation on two adjacent second edge pixels to obtain second gradient values, and dividing the second edge pixels according to the second gradient values to obtain a plurality of second pixel sets;
And performing curve fitting on the second pixel set to obtain a second fitted curve, and performing curve connection on all the second fitted curves to obtain the second contour line.
In some embodiments, the profile determination module 202 performs, in the process of performing curve connection on all the first fitted curves to obtain the first profile line and performing curve connection on all the second fitted curves to obtain the second profile line:
determining two first fitting curves which are arbitrarily adjacent and have first crossing points, and further calculating first crossing coordinates corresponding to the first crossing points of the two first fitting curves;
Connecting the two first fitting curves according to the first cross coordinates to obtain the first contour line;
Determining two second fitting curves which are arbitrarily adjacent and have second crossing points, and further calculating second crossing coordinates corresponding to the second crossing points of the two second fitting curves;
And connecting the two second fitting curves according to the second cross coordinates to obtain the second contour line.
In some embodiments, the area determining module 203 performs, in the determining the first construction area of the target construction object between the first time and the second time according to the first contour line and the second contour line:
Determining a reference object, determining first position information of the reference object corresponding to the first image and determining second position information of the reference object corresponding to the second image;
Performing alignment processing on the first image and the second image by using the first position information and the second position information according to the reference object to obtain alignment information;
Labeling the first contour line in the second image according to the alignment information, and labeling the second contour line in the second image to obtain a labeled third image;
And cutting the third image according to the first contour line and the second contour line to obtain the first construction area.
In some embodiments, the region segmentation module 204 performs, in the process of performing region segmentation on the first construction region using the image segmentation model to obtain a plurality of second construction regions corresponding to the first construction region:
Denoising the first construction area by using a noise processing layer of the image segmentation model to obtain a denoised image;
performing fuzzy processing on the denoising image by using a fuzzy processing layer of the image segmentation model to obtain a fuzzy image;
and carrying out region segmentation on the blurred image by utilizing a segmentation processing layer of the image segmentation model to obtain a plurality of second construction regions.
In some embodiments, the region segmentation module 204 performs, in the blurring process of the denoised image using the blurring process layer of the image segmentation model, performing:
determining first distance information between any two first pixel points in the first construction area by utilizing the fuzzy processing layer;
Determining the segmentation quantity corresponding to the first construction area by utilizing the fuzzy processing layer, and determining the area center corresponding to the segmentation quantity;
determining second distance information between the first pixel point and the center of the area in the first construction area by using the blurring processing layer;
determining a first association degree between the first pixel point and the region center by using the first distance information and the second distance information by using the blurring processing layer;
constructing a target matrix corresponding to the first construction area according to the first association degree and the first distance information by utilizing the fuzzy processing layer;
Determining a second association degree corresponding to the first pixel point and the region center according to the target matrix by utilizing the fuzzy processing layer;
Performing blurring processing on the denoising image according to the second association degree by using the blurring processing layer to obtain the blurred image;
Wherein the first degree of association is obtained according to the following formula:
。
Representing the first association degree between the ith pixel point and the jth region center; m represents the number of the first pixel points corresponding to the first construction area, First distance information representing an ith said first pixel point and a kth said first pixel point,Representing the second distance information between the j-th center of the region and the k-th first pixel point,Representing the second association degree of the first pixel point and the center of the area in the history record, m represents the degree of blurring set during blurring processing.
In some embodiments, the data classifying module 205 performs, in the process of performing image classification on the plurality of second construction areas to obtain the required material information corresponding to the second construction areas, respectively:
respectively carrying out image classification on the second construction areas by using an image classification model to obtain target image types corresponding to each second construction area;
and determining the required material information corresponding to the second construction area by using the target image type and a material mapping table.
In some embodiments, the material determination module 206 performs, in the determining the target material information of the target construction object between the first time and the second time according to the required material information and the second construction area:
Determining a mapping proportion between the second image and the target construction object, and determining a real construction area corresponding to the second construction area according to the mapping proportion;
And predicting material parameters of the real construction area by using the required material information by using a data prediction model, and obtaining the target material information of the target construction object between the first moment and the second moment.
In some embodiments, the engineering construction quality dynamic assessment system 200 may be applied to a terminal device.
It should be noted that, for convenience and brevity of description, a person skilled in the art can clearly understand that, for the specific working process of the above-described dynamic evaluation system 200 for engineering construction quality, reference may be made to the corresponding process in the foregoing embodiment of the dynamic evaluation method for engineering construction quality, which is not described herein again.
The embodiment of the invention also provides a storage medium which is used for being stored in a computer readable mode, one or more programs are stored in the storage medium, and the one or more programs can be executed by one or more processors so as to realize the steps of any engineering construction quality dynamic evaluation method provided by the specification of the embodiment of the invention.
The storage medium may be an internal storage unit of the terminal device of the foregoing embodiment, for example, a hard disk or a memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk provided on the terminal device, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like.
Those of ordinary skill in the art will appreciate that all or some of the steps, systems, functional modules/units in the apparatus, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware embodiment, the division between the functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed cooperatively by several physical components. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
It should be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments. The present invention is not limited to the above embodiments, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the scope of the present invention, and these modifications and substitutions are intended to be included in the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (5)
1. The dynamic evaluation method for the engineering construction quality is characterized by comprising the following steps:
Obtaining a first image corresponding to a target construction object at a first moment and a second image corresponding to the target construction object at a second moment;
Performing edge pixel identification on the first image by using an edge identification algorithm to obtain a first edge pixel corresponding to the first image;
performing pixel gradient calculation on two adjacent first edge pixels to obtain first gradient values, and dividing the first edge pixels according to the first gradient values to obtain a plurality of first pixel sets;
performing curve fitting on the first pixel set to obtain a first fitting curve, determining two first fitting curves which are arbitrarily adjacent and have first crossing points, and further calculating first crossing coordinates of the two first fitting curves corresponding to the first crossing points;
connecting the two first fitting curves according to the first cross coordinates to obtain a first contour line;
Performing edge pixel identification on the second image by using the edge identification algorithm to obtain a second edge pixel corresponding to the second image;
performing pixel gradient calculation on two adjacent second edge pixels to obtain second gradient values, and dividing the second edge pixels according to the second gradient values to obtain a plurality of second pixel sets;
performing curve fitting on the second pixel set to obtain a second fitting curve, determining two second fitting curves which are arbitrarily adjacent and have second crossing points, and further calculating second crossing coordinates corresponding to the second crossing points of the two second fitting curves;
Connecting the two second fitting curves according to the second cross coordinates to obtain a second contour line;
determining a first construction area of the target construction object between the first moment and the second moment according to the first contour line and the second contour line;
Denoising the first construction area by using a noise processing layer of the image segmentation model to obtain a denoised image;
performing fuzzy processing on the denoising image by using a fuzzy processing layer of the image segmentation model to obtain a fuzzy image;
Performing region segmentation on the blurred image by using a segmentation processing layer of the image segmentation model to obtain a plurality of second construction regions;
Respectively carrying out image classification on a plurality of second construction areas to obtain required material information corresponding to the second construction areas;
Determining a mapping proportion between the second image and the target construction object, and determining a real construction area corresponding to the second construction area according to the mapping proportion;
Material parameter prediction is carried out on the real construction area by utilizing the required material information by utilizing a data prediction model, and target material information of the target construction object between the first moment and the second moment is obtained;
obtaining consumption material information corresponding to the first time and the second time, and determining a quality evaluation result corresponding to the target construction object according to the target material information and the consumption material information;
The blurring processing layer for blurring the denoised image by using the image segmentation model, to obtain a blurred image, includes:
determining first distance information between any two first pixel points in the first construction area by utilizing the fuzzy processing layer;
Determining the segmentation quantity corresponding to the first construction area by utilizing the fuzzy processing layer, and determining the area center corresponding to the segmentation quantity;
determining second distance information between the first pixel point and the center of the area in the first construction area by using the blurring processing layer;
determining a first association degree between the first pixel point and the region center by using the first distance information and the second distance information by using the blurring processing layer;
constructing a target matrix corresponding to the first construction area according to the first association degree and the first distance information by utilizing the fuzzy processing layer;
Determining a second association degree corresponding to the first pixel point and the region center according to the target matrix by utilizing the fuzzy processing layer;
Performing blurring processing on the denoising image according to the second association degree by using the blurring processing layer to obtain the blurred image;
Wherein the first degree of association is obtained according to the following formula:
；
Representing the first association degree between the ith pixel point and the jth region center; m represents the number of the first pixel points corresponding to the first construction area, First distance information representing an ith said first pixel point and a kth said first pixel point,Representing the second distance information between the j-th center of the region and the k-th first pixel point,Representing the second association degree of the first pixel point and the center of the area in the history record, m represents the degree of blurring set during blurring processing.
2. The method of claim 1, wherein the determining a first construction area of the target construction object between the first time and the second time from the first contour line and the second contour line comprises:
Determining a reference object, determining first position information of the reference object corresponding to the first image and determining second position information of the reference object corresponding to the second image;
Performing alignment processing on the first image and the second image by using the first position information and the second position information according to the reference object to obtain alignment information;
Labeling the first contour line in the second image according to the alignment information, and labeling the second contour line in the second image to obtain a labeled third image;
And cutting the third image according to the first contour line and the second contour line to obtain the first construction area.
3. The method according to claim 1, wherein the image classifying the plurality of second construction areas to obtain the required material information corresponding to the second construction areas, respectively, includes:
respectively carrying out image classification on the second construction areas by using an image classification model to obtain target image types corresponding to each second construction area;
and determining the required material information corresponding to the second construction area by using the target image type and a material mapping table.
4. The utility model provides an engineering construction quality dynamic evaluation system which characterized in that includes:
the data acquisition module is used for acquiring a first image corresponding to a target construction object at a first moment and a second image corresponding to the target construction object at a second moment;
The contour determining module is used for carrying out edge pixel identification on the first image by utilizing an edge identification algorithm to obtain a first edge pixel corresponding to the first image; performing pixel gradient calculation on two adjacent first edge pixels to obtain first gradient values, and dividing the first edge pixels according to the first gradient values to obtain a plurality of first pixel sets; performing curve fitting on the first pixel set to obtain a first fitting curve, determining two first fitting curves which are arbitrarily adjacent and have first crossing points, and further calculating first crossing coordinates of the two first fitting curves corresponding to the first crossing points; connecting the two first fitting curves according to the first cross coordinates to obtain a first contour line; performing edge pixel identification on the second image by using the edge identification algorithm to obtain a second edge pixel corresponding to the second image; performing pixel gradient calculation on two adjacent second edge pixels to obtain second gradient values, and dividing the second edge pixels according to the second gradient values to obtain a plurality of second pixel sets; performing curve fitting on the second pixel set to obtain a second fitting curve, determining two second fitting curves which are arbitrarily adjacent and have second crossing points, and further calculating second crossing coordinates corresponding to the second crossing points of the two second fitting curves; connecting the two second fitting curves according to the second cross coordinates to obtain a second contour line;
the area determining module is used for determining a first construction area of the target construction object between the first moment and the second moment according to the first contour line and the second contour line;
The region segmentation module is used for carrying out denoising treatment on the first construction region by utilizing a noise treatment layer of the image segmentation model to obtain a denoised image; performing fuzzy processing on the denoising image by using a fuzzy processing layer of the image segmentation model to obtain a fuzzy image; performing region segmentation on the blurred image by using a segmentation processing layer of the image segmentation model to obtain a plurality of second construction regions; the blurring processing layer for blurring the denoised image by using the image segmentation model, to obtain a blurred image, includes: determining first distance information between any two first pixel points in the first construction area by utilizing the fuzzy processing layer; determining the segmentation quantity corresponding to the first construction area by utilizing the fuzzy processing layer, and determining the area center corresponding to the segmentation quantity; determining second distance information between the first pixel point and the center of the area in the first construction area by using the blurring processing layer; determining a first association degree between the first pixel point and the region center by using the first distance information and the second distance information by using the blurring processing layer; constructing a target matrix corresponding to the first construction area according to the first association degree and the first distance information by utilizing the fuzzy processing layer; determining a second association degree corresponding to the first pixel point and the region center according to the target matrix by utilizing the fuzzy processing layer; performing blurring processing on the denoising image according to the second association degree by using the blurring processing layer to obtain the blurred image;
Wherein the first degree of association is obtained according to the following formula:
；
Representing the first association degree between the ith pixel point and the jth region center; m represents the number of the first pixel points corresponding to the first construction area, First distance information representing an ith said first pixel point and a kth said first pixel point,Representing the second distance information between the j-th center of the region and the k-th first pixel point,The second association degree corresponding to the first pixel point and the center of the area in the history record is represented, and m represents the blurring degree set in the blurring processing process;
The data classification module is used for respectively carrying out image classification on the plurality of second construction areas to obtain required material information corresponding to the second construction areas;
The material determining module is used for determining the mapping proportion between the second image and the target construction object, and determining a real construction area corresponding to the second construction area according to the mapping proportion; material parameter prediction is carried out on the real construction area by utilizing the required material information by utilizing a data prediction model, and target material information of the target construction object between the first moment and the second moment is obtained;
And the quality evaluation module is used for obtaining the consumption material information corresponding to the first time and the second time and determining a quality evaluation result corresponding to the target construction object according to the target material information and the consumption material information.
5. A computer storage medium for computer storage, characterized in that the computer storage medium stores one or more programs executable by one or more processors to implement the steps of the engineering construction quality dynamic assessment method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411008128.2A CN118536881B (en) | 2024-07-26 | 2024-07-26 | Dynamic evaluation method, system and storage medium for engineering construction quality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411008128.2A CN118536881B (en) | 2024-07-26 | 2024-07-26 | Dynamic evaluation method, system and storage medium for engineering construction quality |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118536881A CN118536881A (en) | 2024-08-23 |
| CN118536881B true CN118536881B (en) | 2024-10-15 |
Family
ID=92392401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411008128.2A Active CN118536881B (en) | 2024-07-26 | 2024-07-26 | Dynamic evaluation method, system and storage medium for engineering construction quality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118536881B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705576A (en) * | 2019-09-29 | 2020-01-17 | 慧影医疗科技（北京）有限公司 | Region contour determining method and device and image display equipment |
| CN114049499A (en) * | 2021-11-18 | 2022-02-15 | 南昌黑鲨科技有限公司 | Target object detection method, apparatus and storage medium for continuous contour |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114764853A (en) * | 2020-12-30 | 2022-07-19 | 华为技术有限公司 | Method and device for determining occupation information |
| CN113160257B (en) * | 2021-04-23 | 2024-01-16 | 深圳市优必选科技股份有限公司 | Image data labeling method, device, electronic equipment and storage medium |
| EP4209995A4 (en) * | 2021-11-23 | 2023-12-27 | Contemporary Amperex Technology Co., Limited | Image recognition method and apparatus, and computer-readable storage medium |
| CN114708216A (en) * | 2022-03-31 | 2022-07-05 | 国网福建省电力有限公司经济技术研究院 | Construction progress intelligent identification method and system based on image identification |
| CN116051973A (en) * | 2022-09-30 | 2023-05-02 | 联想(北京)有限公司 | Region identification method and device |
| CN116342076B (en) * | 2023-05-30 | 2023-08-01 | 山东建筑大学设计集团有限公司 | Engineering information management system and management method |
-
2024
- 2024-07-26 CN CN202411008128.2A patent/CN118536881B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705576A (en) * | 2019-09-29 | 2020-01-17 | 慧影医疗科技（北京）有限公司 | Region contour determining method and device and image display equipment |
| CN114049499A (en) * | 2021-11-18 | 2022-02-15 | 南昌黑鲨科技有限公司 | Target object detection method, apparatus and storage medium for continuous contour |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118536881A (en) | 2024-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113705478B (en) | Mangrove single wood target detection method based on improved YOLOv5 | |
| Lee et al. | Automated image processing technique for detecting and analysing concrete surface cracks | |
| CN111444921A (en) | Scratch defect detection method and device, computing equipment and storage medium | |
| TWI716012B (en) | Sample labeling method, device, storage medium and computing equipment, damage category identification method and device | |
| Fujita et al. | A method based on machine learning using hand-crafted features for crack detection from asphalt pavement surface images | |
| WO2024002187A1 (en) | Defect detection method, defect detection device, and storage medium | |
| CN111626295B (en) | Training method and device for license plate detection model | |
| CN116596875B (en) | Wafer defect detection method and device, electronic equipment and storage medium | |
| CN111126393A (en) | Vehicle appearance refitting judgment method and device, computer equipment and storage medium | |
| CN113393454A (en) | Method and device for segmenting pathological target examples in biopsy tissues | |
| Jahanshahi et al. | Vision-based quantitative assessment of microcracks on reactor internal components of nuclear power plants | |
| CN116434266A (en) | Automatic extraction and analysis method for data information of medical examination list | |
| CN109711441A (en) | Image classification method, device, storage medium and electronic equipment | |
| CN108154513A (en) | Cell based on two photon imaging data detects automatically and dividing method | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| Zhang et al. | A YOLOv3‐Based Industrial Instrument Classification and Reading Recognition Method | |
| CN109190489A (en) | A kind of abnormal face detecting method based on reparation autocoder residual error | |
| CN109598712A (en) | Quality determining method, device, server and the storage medium of plastic foam cutlery box | |
| CN118536881B (en) | Dynamic evaluation method, system and storage medium for engineering construction quality | |
| CN116205918B (en) | Multi-mode fusion semiconductor detection method, device and medium based on graph convolution | |
| CN109191452B (en) | Peritoneal transfer automatic marking method for abdominal cavity CT image based on active learning | |
| CN117593420A (en) | Plane drawing labeling method, device, medium and equipment based on image processing | |
| CN116385957A (en) | X-ray image contraband detection method, device, equipment and medium | |
| CN115601655A (en) | Water body information identification method and device based on satellite remote sensing and readable medium | |
| CN114663760A (en) | Model training method, target detection method, storage medium and computing device |
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 |