CN113807722B - Method and system for analyzing field quality of electric power engineering project based on image analysis - Google Patents
Method and system for analyzing field quality of electric power engineering project based on image analysis Download PDFInfo
- Publication number
- CN113807722B CN113807722B CN202111122395.9A CN202111122395A CN113807722B CN 113807722 B CN113807722 B CN 113807722B CN 202111122395 A CN202111122395 A CN 202111122395A CN 113807722 B CN113807722 B CN 113807722B
- Authority
- CN
- China
- Prior art keywords
- pixel information
- pixel
- information
- quality
- division
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000010191 image analysis Methods 0.000 title claims abstract description 23
- 239000013598 vector Substances 0.000 claims abstract description 57
- 238000004458 analytical method Methods 0.000 claims abstract description 46
- 238000003709 image segmentation Methods 0.000 claims description 19
- 230000004927 fusion Effects 0.000 claims description 16
- 238000010586 diagram Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000004870 electrical engineering Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000005728 strengthening Methods 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an on-site quality analysis method and an on-site quality analysis system for an electric power engineering project based on image analysis, wherein the method comprises the steps of extracting feature vectors of first pixel information to obtain first pixel feature vectors; inputting the first pixel feature vector into a pixel analysis model to obtain pixel information of candidate target contours to which at least one quality problem belongs; acquiring the pixel information of a candidate target contour area to which each quality problem belongs in the first pixel information according to the candidate target contour pixel information, and taking the pixel information as second pixel information; extracting the feature vector of the second pixel information to obtain a second pixel feature vector; and acquiring the specific problem of the quality problem based on the second pixel characteristic vector. The invention enables analysis of at least one quality problem in a project image and at least one specific problem of the at least one quality problem.
Description
Technical Field
The invention relates to the technical field of power engineering project supervision, in particular to a method and a system for analyzing the field quality of a power engineering project based on image analysis.
Background
Proper supervision of electric power construction engineering is that government supervises and manages electric power engineering quality. The quality supervision work of the electric power construction engineering is very important to promote the continuous and healthy development of electric power and national economy. In recent years, the social and economic development is rapid, the rapid development of the power industry is promoted, and new requirements are put forward for the quality supervision and management of the power engineering. How to improve the quality supervision and management level of engineering projects, and to adopt effective intelligent dynamic management measures to carry out multidimensional management on the quality of engineering projects, wherein the means of strengthening the prevention and the treatment are auxiliary are important problems to be solved in the quality management work of engineering projects.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a method and a system for analyzing the field quality of an electric power engineering project based on image analysis, wherein the technical scheme is as follows:
in a first aspect, an on-site quality analysis method for an electric power engineering project based on image analysis is provided, which is characterized by comprising the following steps:
extracting the feature vector of the first pixel information to obtain a first pixel feature vector; wherein the first pixel information characterizes a set of pixel information of the project image when the project image has a quality problem;
Inputting the first pixel feature vector into a pixel analysis model to obtain pixel information of candidate target contours to which at least one quality problem belongs;
acquiring the pixel information of a candidate target contour area to which each quality problem belongs in the first pixel information according to the candidate target contour pixel information, and taking the pixel information as second pixel information;
Extracting the feature vector of the second pixel information to obtain a second pixel feature vector;
And carrying out operation processing on the second pixel characteristic vector, and inputting the result after the operation processing into the pixel analysis model to obtain the specific problem of the quality problem.
In one possible implementation manner, the extracting the feature vector of the first pixel information to obtain a first pixel feature vector, inputting the first pixel feature vector into a pixel analysis model, and obtaining the pixel information of the candidate target contour to which the at least one quality problem belongs includes:
Performing region division on the first pixel information through a plurality of preset image segmentation methods, and acquiring the credibility of each divided region of each preset image segmentation method;
Determining a division area fused by a plurality of preset image segmentation methods based on the credibility of each divided area of each preset image segmentation method, and marking the division area as a first fusion division result;
Fusing the first division result information into first pixel information, and carrying out region division on the fused first pixel information by a plurality of preset image segmentation methods to obtain a second division result;
and determining a second fusion division result based on the plurality of second division results and the credibility of each divided region of each preset image division method.
In one possible implementation manner, the determining the second fusion partition result includes:
Fusing each second division result with a reference division result of the same division area to obtain a second division result middle area diagram;
And fusing the second division result middle region map information into the first pixel information, and performing region division on the fused first pixel information to obtain a second fusion division result.
In one possible implementation manner, the fusing based on each second division result and the reference division result of the same division area to obtain a second division result middle area diagram includes:
Determining a difference graph of each second division result and a reference division result for the same division region based on the difference of each second division result and the reference division result of the same division region;
The second division result middle area diagram information is fused into the first pixel information, and comprises the following steps:
and fusing the difference map information corresponding to each divided area into first pixel information.
In one possible implementation, the reference division result of the same division area is determined based on each second division result.
In one possible implementation, the method further comprises analyzing a distribution of different quality problems based on the first pixel information.
In one possible implementation manner, the analyzing the distribution of the different quality problems based on the first pixel information includes:
Acquiring a first pixel information set corresponding to a plurality of project blocks;
acquiring the duty ratio information of different types of project quality problems of a first pixel information set in the first pixel information set, and determining the distribution of different quality problems based on the duty ratio information;
wherein the obtaining the duty ratio information of the different kinds of item quality problems in the first pixel information set includes:
Acquiring first duty ratio information of second pixel information in a first pixel information set, wherein the second pixel information represents the project quality problem pixel information of a project block which belongs to the second pixel information in the first pixel information set;
And acquiring second duty ratio information of third pixel information in the first pixel information set, wherein the third pixel information represents the pixel information of the quality problem of the same category item in the second pixel information.
In a second aspect, there is provided an image analysis-based power engineering project field quality analysis system, comprising: the first pixel characteristic vector acquisition unit is used for extracting characteristic vectors of the first pixel information to obtain first pixel characteristic vectors; wherein the first pixel information characterizes a set of pixel information of the project image when the project image has a quality problem;
the first pixel information acquisition unit is used for inputting the first pixel characteristic vector into a pixel analysis model to acquire pixel information of candidate target contours to which at least one quality problem belongs;
A second pixel information obtaining unit, configured to obtain, according to the candidate target contour pixel information, the pixel information of a candidate target contour region to which each quality problem in the first pixel information belongs, and use the pixel information as second pixel information;
the second pixel characteristic vector acquisition unit is used for extracting the characteristic vector of the second pixel information to obtain a second pixel characteristic vector;
and the quality problem analysis unit is used for carrying out operation processing on the second pixel characteristic vector, inputting the result after the operation processing into the pixel analysis model and obtaining the specific problem of the quality problem.
In a third aspect, an electronic device is provided, the electronic device comprising:
A processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to implement the method according to the first aspect by executing the executable instructions.
In a fourth aspect, there is provided a computer readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the steps of the method as described in the first aspect above.
The method and the system for analyzing the field quality of the power engineering project based on the image analysis have the following beneficial effects: the analysis of at least one quality problem and at least one specific problem of the at least one quality problem in the project image is achieved by acquiring a plurality of candidate target contours existing for the project image with the quality problem, and by unified second pixel feature extraction and pixel analysis model of the candidate target contours.
Drawings
FIG. 1 is a flow chart of a method for on-site quality analysis of an electrical engineering project based on image analysis in an embodiment of the application;
fig. 2 is a block diagram of an on-site quality analysis system for an electrical engineering project based on image analysis in an embodiment of the present application.
Detailed Description
The present invention will be further described in detail with reference to the accompanying drawings, for the purpose of making the objects, technical solutions and advantages of the present invention more apparent, and the described embodiments should not be construed as limiting the present invention, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present invention.
The embodiment of the application provides an on-site quality analysis method for an electric power engineering project based on image analysis, which comprises the following steps:
extracting the feature vector of the first pixel information to obtain a first pixel feature vector; wherein the first pixel information characterizes a set of pixel information of the project image when the project image has a quality problem;
Inputting the first pixel feature vector into a pixel analysis model to obtain pixel information of candidate target contours to which at least one quality problem belongs; the pixel analysis network is used for analyzing target contour pixel information corresponding to the quality problem;
acquiring the pixel information of a candidate target contour area to which each quality problem belongs in the first pixel information according to the candidate target contour pixel information, and taking the pixel information as second pixel information;
Extracting the feature vector of the second pixel information to obtain a second pixel feature vector;
And carrying out operation processing on the second pixel characteristic vector, and inputting the result after the operation processing into the pixel analysis model to obtain the specific problem of the quality problem.
The candidate object outline to which the at least one quality problem belongs means that one or more quality problems can exist in the project image with the quality problem, the existing quality problems can be one or more, and each quality problem can exist one or more candidate objects to which the quality problem belongs. There may or may not be quality problems within each candidate target contour.
According to the embodiment of the invention, the plurality of candidate target contours existing in the project image with the quality problem are obtained, at least one quality problem in the project image and at least one specific problem of the at least one quality problem are analyzed through unified second pixel feature extraction and pixel analysis model of the candidate target contours, the complexity of quality problem identification in the power engineering project by adopting different image feature extraction methods and different image feature identification analysis models for different quality problems is avoided, and the quality problem identification efficiency of the power engineering project in multiple dimensions, multiple objects and multiple categories is improved under the condition that the target of the quality problem in the project image is unknown and the quality problem category of the target of the quality problem and the specific problem of the quality problem in the project image is unknown are identified by adopting a unified feature extraction method and a pixel analysis method. The method further avoids the need of adopting different feature extraction methods and pixel analysis methods for analysis when a plurality of quality problems exist in the same project image or targets to which the plurality of quality problems belong, and realizes the high-efficiency analysis when a plurality of quality problems exist in the project image and candidate targets to which the plurality of quality problems belong.
Wherein quality supervision analysis in the power engineering project includes: the quality of people, machines, objects, methods and rings can be monitored, and various targets such as people, objects and the like can be simultaneously present in the quality problem image, and various quality problems of the targets can also be simultaneously present.
The first pixel information represents a set of pixel information of an item image when the quality problem exists in the item image, and also can represent a set of pixel information of an item image frame sequence in a dynamic process when the quality problem exists in the dynamic process, and the set of pixel information is used for analyzing the quality problem existing in the process and the quality problem existing in the dynamic process.
Further, the extracting the feature vector from the first pixel information to obtain a first pixel feature vector, inputting the first pixel feature vector into a pixel analysis model, and obtaining the pixel information of the candidate target contour to which at least one quality problem belongs, including:
Performing region division on the first pixel information through a plurality of preset image segmentation methods, and acquiring the credibility of each divided region of each preset image segmentation method;
Determining a division area fused by a plurality of preset image segmentation methods based on the credibility of each divided area of each preset image segmentation method, and marking the division area as a first fusion division result;
Fusing the first division result information into first pixel information, and carrying out region division on the fused first pixel information by a plurality of preset image segmentation methods to obtain a second division result;
and determining a second fusion division result based on the plurality of second division results and the credibility of each divided region of each preset image division method.
In the embodiment of the application, a plurality of different image segmentation results are obtained through a plurality of image segmentation methods, the fusion is carried out based on the different image segmentation results to obtain the first fusion division result, the inaccuracy of a single image segmentation result is avoided, meanwhile, the first fusion division result information is fused to the first pixel information to carry out region division again, the characteristic information in the original first pixel information is increased, and the second division result is more accurate. Each divided region in each divided result represents pixel information of a candidate target contour to which a quality problem belongs.
Further, the determining the second fusion partitioning result includes:
Fusing each second division result with a reference division result of the same division area to obtain a second division result middle area diagram;
And fusing the second division result middle region map information into the first pixel information, and performing region division on the fused first pixel information to obtain a second fusion division result.
In the embodiment of the application, a plurality of second division results are obtained for the first pixel information fused with the first division result information, and in the process of fusing the plurality of second division results, the fused information of the reference division result is fused into the first pixel information so as to further divide the first pixel information into regions again, so that the first pixel information is fused with the first division result information, each region division information of different preset image division methods and difference information of the same division region in the plurality of second division results at the same time, and the characteristic information of the first pixel information is enriched.
Further, the fusing is performed based on each second division result and the reference division result of the same division area, to obtain a second division result middle area diagram, which includes:
Determining a difference graph of each second division result and a reference division result for the same division region based on the difference of each second division result and the reference division result of the same division region;
The second division result middle area diagram information is fused into the first pixel information, and comprises the following steps:
and fusing the difference map information corresponding to each divided area into first pixel information.
In the embodiment of the application, the difference between each second division result and the reference division result of the same division region is represented in the second division result middle region diagram, and the latest first pixel information is obtained after the difference diagram information corresponding to each division region is fused into the first pixel information, so that each region division difference of different preset image division methods is fused in the latest first pixel information, and the target region and the non-target region in the latest first pixel information are separated by a remarkable difference diagram region in the process of carrying out region division on the basis of the latest first pixel information to obtain the second fusion division result, thereby enabling the division of the target region in the latest first pixel information to be more accurate.
Further, the above-described reference division result of the same division area is determined based on each of the second division results.
In the embodiment of the application, the reference division result of the same division area is determined based on each second division result, and can be determined based on a common area of each second division result.
Furthermore, the method for analyzing the field quality of the electric power engineering project based on the image analysis further comprises the step of analyzing the distribution of different quality problems based on the first pixel information, wherein the distribution of the different quality problems can be the geographical position distribution or project distribution of the different quality problems or the geographical position distribution, the construction team to which the project belongs and the manager distribution.
Further, the analyzing the distribution of the different quality problems based on the first pixel information includes:
Acquiring a first pixel information set corresponding to a plurality of project blocks;
acquiring the duty ratio information of different types of project quality problems of a first pixel information set in the first pixel information set, and determining the distribution of different quality problems based on the duty ratio information;
wherein the obtaining the duty ratio information of the different kinds of item quality problems in the first pixel information set includes:
Acquiring first duty ratio information of second pixel information in a first pixel information set, wherein the second pixel information represents the project quality problem pixel information of a project block which belongs to the second pixel information in the first pixel information set;
And acquiring second duty ratio information of third pixel information in the first pixel information set, wherein the third pixel information represents the pixel information of the quality problem of the same category item in the second pixel information.
The embodiment of the application provides an on-site quality analysis system for an electric power engineering project based on image analysis, which comprises the following components:
The first pixel characteristic vector acquisition unit is used for extracting characteristic vectors of the first pixel information to obtain first pixel characteristic vectors; wherein the first pixel information characterizes a set of pixel information of the project image when the project image has a quality problem;
the first pixel information acquisition unit is used for inputting the first pixel characteristic vector into a pixel analysis model to acquire pixel information of candidate target contours to which at least one quality problem belongs;
A second pixel information obtaining unit, configured to obtain, according to the candidate target contour pixel information, the pixel information of a candidate target contour region to which each quality problem in the first pixel information belongs, and use the pixel information as second pixel information;
the second pixel characteristic vector acquisition unit is used for extracting the characteristic vector of the second pixel information to obtain a second pixel characteristic vector;
and the quality problem analysis unit is used for carrying out operation processing on the second pixel characteristic vector, inputting the result after the operation processing into the pixel analysis model and obtaining the specific problem of the quality problem.
The specific definition of the on-site quality analysis system for the electric power engineering project can be referred to as the definition of the on-site quality analysis method for the electric power engineering project hereinabove, and will not be described herein. The units in the electric power engineering project field quality analysis system can be realized in whole or in part by software, hardware and a combination thereof. The units can be embedded in hardware or independent of a processor in the computer equipment, and can also be stored in a memory in the computer equipment in a software mode, so that the processor can call and execute the operations corresponding to the units.
The embodiment of the application provides electronic equipment, which comprises:
A processor;
a memory for storing processor-executable instructions;
Wherein the processor is configured to implement the method for on-site quality analysis of an electrical engineering project based on image analysis as described above by executing the executable instructions.
Further, the electronic device provided by the embodiment of the application includes: at least one processor, memory, a user interface, and at least one network interface. The various components in the electronic device are coupled together by a bus system. It will be appreciated that a bus system is used to enable connected communications between these components. The bus system includes a power bus, a control bus, and a status signal bus in addition to the data bus. The user interface may include, among other things, a display, keyboard, mouse, trackball, click wheel, keys, buttons, touch pad, or touch screen, etc.
The embodiment of the application provides a computer readable storage medium, wherein computer instructions are stored, and the instructions are executed by a processor to realize the steps of the method for analyzing the field quality of the electric power engineering project based on image analysis. The computer readable storage medium may be read-only memory (ROM), random-access memory (random access memory, RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, optical data storage node, etc.
The present invention is not limited to the above-described specific embodiments, and various modifications may be made by those skilled in the art without inventive effort from the above-described concepts, and are within the scope of the present invention.
Claims (10)
1. The method for analyzing the field quality of the electric power engineering project based on the image analysis is characterized by comprising the following steps:
extracting the feature vector of the first pixel information to obtain a first pixel feature vector; wherein the first pixel information characterizes a set of pixel information of the project image when the project image has a quality problem;
Inputting the first pixel feature vector into a pixel analysis model to obtain pixel information of candidate target contours to which at least one quality problem belongs;
acquiring the pixel information of a candidate target contour area to which each quality problem belongs in the first pixel information according to the candidate target contour pixel information, and taking the pixel information as second pixel information;
Extracting the feature vector of the second pixel information to obtain a second pixel feature vector;
And carrying out operation processing on the second pixel characteristic vector, and inputting the result after the operation processing into the pixel analysis model to obtain the specific problem of the quality problem.
2. The method for on-site quality analysis of an electric power engineering project based on image analysis according to claim 1, wherein the extracting the feature vector of the first pixel information to obtain a first pixel feature vector, inputting the first pixel feature vector into a pixel analysis model to obtain the pixel information of a candidate target contour to which at least one quality problem belongs, comprises:
Performing region division on the first pixel information through a plurality of preset image segmentation methods, and acquiring the credibility of each divided region of each preset image segmentation method;
Determining a division area fused by a plurality of preset image segmentation methods based on the credibility of each divided area of each preset image segmentation method, and marking the division area as a first fusion division result;
Fusing the first division result information into first pixel information, and carrying out region division on the fused first pixel information by a plurality of preset image segmentation methods to obtain a second division result;
and determining a second fusion division result based on the plurality of second division results and the credibility of each divided region of each preset image division method.
3. The method for analyzing the field quality of the electric power engineering project based on the image analysis according to claim 2, wherein the determining the second fusion division result includes:
Fusing each second division result with a reference division result of the same division area to obtain a second division result middle area diagram;
And fusing the second division result middle region map information into the first pixel information, and performing region division on the fused first pixel information to obtain a second fusion division result.
4. The method for analyzing the field quality of the electric power engineering project based on the image analysis according to claim 3, wherein the fusing of each second division result with the reference division result of the same division area to obtain the second division result middle area diagram comprises the following steps:
Determining a difference graph of each second division result and a reference division result for the same division region based on the difference of each second division result and the reference division result of the same division region;
The second division result middle area diagram information is fused into the first pixel information, and comprises the following steps:
and fusing the difference map information corresponding to each divided area into first pixel information.
5. The image analysis-based power engineering project field quality analysis method according to claim 4, wherein the reference division result of the same division region is determined based on each second division result.
6. The method for on-site quality analysis of an electrical power engineering project based on image analysis according to claim 1, further comprising analyzing a distribution of different quality problems based on the first pixel information.
7. The method for analyzing the on-site quality of an electric power engineering project based on image analysis according to claim 6, wherein the analyzing the distribution of different quality problems based on the first pixel information comprises:
Acquiring a first pixel information set corresponding to a plurality of project blocks;
acquiring the duty ratio information of different types of project quality problems of a first pixel information set in the first pixel information set, and determining the distribution of different quality problems based on the duty ratio information;
wherein the obtaining the duty ratio information of the different kinds of item quality problems in the first pixel information set includes:
Acquiring first duty ratio information of second pixel information in a first pixel information set, wherein the second pixel information represents the project quality problem pixel information of a project block which belongs to the second pixel information in the first pixel information set;
And acquiring second duty ratio information of third pixel information in the first pixel information set, wherein the third pixel information represents the pixel information of the quality problem of the same category item in the second pixel information.
8. An on-site quality analysis system for an electric power engineering project based on image analysis, comprising:
The first pixel characteristic vector acquisition unit is used for extracting characteristic vectors of the first pixel information to obtain first pixel characteristic vectors; wherein the first pixel information characterizes a set of pixel information of the project image when the project image has a quality problem;
the first pixel information acquisition unit is used for inputting the first pixel characteristic vector into a pixel analysis model to acquire pixel information of candidate target contours to which at least one quality problem belongs;
A second pixel information obtaining unit, configured to obtain, according to the candidate target contour pixel information, the pixel information of a candidate target contour region to which each quality problem in the first pixel information belongs, and use the pixel information as second pixel information;
the second pixel characteristic vector acquisition unit is used for extracting the characteristic vector of the second pixel information to obtain a second pixel characteristic vector;
and the quality problem analysis unit is used for carrying out operation processing on the second pixel characteristic vector, inputting the result after the operation processing into the pixel analysis model and obtaining the specific problem of the quality problem.
9. An electronic device, the electronic device comprising:
A processor;
a memory for storing processor-executable instructions;
Wherein the processor is configured to implement the method of any of claims 1-7 by executing the executable instructions.
10. A computer readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the steps of the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111122395.9A CN113807722B (en) | 2021-09-24 | 2021-09-24 | Method and system for analyzing field quality of electric power engineering project based on image analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111122395.9A CN113807722B (en) | 2021-09-24 | 2021-09-24 | Method and system for analyzing field quality of electric power engineering project based on image analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113807722A CN113807722A (en) | 2021-12-17 |
| CN113807722B true CN113807722B (en) | 2024-06-28 |
Family
ID=78940380
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111122395.9A Active CN113807722B (en) | 2021-09-24 | 2021-09-24 | Method and system for analyzing field quality of electric power engineering project based on image analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113807722B (en) |
-
2021
- 2021-09-24 CN CN202111122395.9A patent/CN113807722B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 分层像素级图像融合中线性轮廓信息识别仿真;宋薇;;计算机仿真(06);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113807722A (en) | 2021-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Elhoseny | Multi-object detection and tracking (MODT) machine learning model for real-time video surveillance systems | |
| CN111858869B (en) | Data matching method and device, electronic equipment and storage medium | |
| CN112232293A (en) | Image processing model training method, image processing method and related equipment | |
| CN108629783B (en) | Image segmentation method, system and medium based on image feature density peak search | |
| CN113870401B (en) | Expression generation method, device, equipment, medium and computer program product | |
| CN110968712B (en) | BIM family model acquisition method, device and system | |
| CN111931809A (en) | Data processing method and device, storage medium and electronic equipment | |
| CN110807379B (en) | Semantic recognition method, semantic recognition device and computer storage medium | |
| CN108961316A (en) | Image processing method, device and server | |
| CN113838061A (en) | Method and device for image annotation and storage medium | |
| CN114330109A (en) | Interpretability method and system of deep reinforcement learning model under unmanned scene | |
| CN116168351A (en) | Inspection method and device for power equipment | |
| KR20230132350A (en) | Joint perception model training method, joint perception method, device, and storage medium | |
| CN113807722B (en) | Method and system for analyzing field quality of electric power engineering project based on image analysis | |
| CN111767419A (en) | Picture searching method, device, equipment and computer readable storage medium | |
| CN116936116A (en) | Intelligent medical data analysis method and system | |
| CN110188156B (en) | Transmission line engineering three-dimensional design result key information extraction method and system | |
| CN112270384A (en) | Loop detection method and device, electronic equipment and storage medium | |
| CN112233161A (en) | Hand image depth determination method and device, electronic equipment and storage medium | |
| CN112053394A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN114842178A (en) | Online visual interaction system and method based on electronic product | |
| CN108256077A (en) | A kind of dynamic expansion knowledge graph inference method towards China Mobile's intelligent customer service | |
| CN110909288B (en) | Service data processing method, device, platform, service end, system and medium | |
| CN113903071A (en) | Face recognition method and device, electronic equipment and storage medium | |
| US11887387B2 (en) | Mesh structure equipment detection apparatus, mesh structure equipment detection method and program |
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 |