CN116228774A - Substation inspection image defect identification method and system based on image quality evaluation - Google Patents
Substation inspection image defect identification method and system based on image quality evaluation Download PDFInfo
- Publication number
- CN116228774A CN116228774A CN202310517319.0A CN202310517319A CN116228774A CN 116228774 A CN116228774 A CN 116228774A CN 202310517319 A CN202310517319 A CN 202310517319A CN 116228774 A CN116228774 A CN 116228774A
- Authority
- CN
- China
- Prior art keywords
- substation inspection
- substation
- image
- inspection
- quality evaluation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G06N3/08—Learning methods
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Entrepreneurship & Innovation (AREA)
- Water Supply & Treatment (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of substation inspection, and provides a substation inspection image defect identification method and system based on image quality evaluation, which aim to solve the problem that an inspection image with poor quality seriously affects the inspection effect. The substation inspection image defect identification method based on image quality evaluation comprises the steps of downsampling and aggregating each frame of image in substation inspection video information to a preset feature size to obtain a corresponding substation inspection feature map, and extracting global features of each substation inspection feature map to obtain a substation inspection global feature map; performing quality evaluation on the substation inspection global feature map according to a preset rule to obtain quality scores of all frames of substation inspection images, and screening out substation inspection images with the quality scores larger than a preset score threshold; and processing the screened substation inspection image to obtain a defect identification result. The defect identification effect of the substation robot on the inspection image can be improved.
Description
Technical Field
The invention belongs to the technical field of substation inspection, and particularly relates to a substation inspection image defect identification method and system based on image quality evaluation.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
At present, a substation inspection robot acquires a lot of inspection data in the inspection process. However, in the process of acquisition and transmission of an image, degradation of image quality is inevitably caused, which may cause insufficient prominence of the object in the image and increase the processing difficulty. The quality of the image plays an increasingly important role in inspection of substation equipment, and the acquired inspection image may be less than ideal in imagination for various reasons. For example, due to factors such as shooting angle, weather condition and distance between the patrol equipment and the patrol equipment when the images are acquired, the acquired patrol images have a larger gap from ideal conditions, and the quality of the patrol images can not be used for identifying defects of the patrol images. In addition, the collected image is subjected to certain compression and storage processes, such as JPG 2000 compression and JPG compression, and transmission of a network channel, and the quality and resolution of the image are distorted to different degrees. In the process of equipment inspection and defect diagnosis, the quality of an image determines the quality of an identification result to a great extent, the inspection effect is seriously influenced by an inspection image with poor quality, and the existing inspection technology directly carries out identification processing on the inspection image and does not consider the influence of the quality of the inspection image on the inspection effect.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides a substation inspection image defect identification method and system based on image quality evaluation, which can improve the defect identification effect of a substation robot on an inspection image and enable the robot to accurately perform equipment positioning and defect identification of an inspection target in real time.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the first aspect of the invention provides a substation inspection image defect identification method based on image quality evaluation.
A substation inspection image defect identification method based on image quality evaluation comprises the following steps:
obtaining inspection video information of a transformer substation;
downsampling and aggregating each frame of image in the substation inspection video information to a preset feature size to obtain a corresponding substation inspection feature map, and extracting global features of each substation inspection feature map to obtain a substation inspection global feature map;
performing quality evaluation on the substation inspection global feature map according to a preset rule to obtain quality scores of all frames of substation inspection images, and screening out substation inspection images with the quality scores larger than a preset score threshold;
and processing the screened substation inspection image by using a pre-trained defect recognition model to obtain a defect recognition result.
As an implementation manner, before downsampling and aggregating each frame of image in the substation inspection video information, the method further comprises:
and filtering the inspection video information of the transformer substation by adopting a bilateral filtering method.
As one implementation mode, each frame of image in the substation inspection video information is downsampled and aggregated to a preset feature size by utilizing a downsampling aggregation operation module.
As one embodiment, global features of the input feature map are extracted using a global feature extraction module.
As one embodiment, each global feature extraction module includes a residual connection unit, and a first convolution layer, a depth convolution layer, a second convolution layer, and a nonlinear operation layer that are sequentially connected in series, where the residual connection unit is configured to connect an input of the first convolution layer and an output of the nonlinear operation layer.
As an embodiment, the convolution kernel sizes of the first convolution layer and the second convolution layer are each 1×1, so that the result of the corresponding convolution layer is the same as the size of the input layer feature map.
The second aspect of the invention provides a substation inspection image defect identification system based on image quality evaluation.
A substation inspection image defect identification system based on image quality evaluation, comprising:
the information acquisition module is used for acquiring the inspection video information of the transformer substation;
the feature extraction module is used for downsampling and aggregating each frame of image in the substation inspection video information to a preset feature size to obtain a corresponding substation inspection feature map, and extracting global features of each substation inspection feature map to obtain a substation inspection global feature map;
the quality evaluation module is used for performing quality evaluation on the substation inspection global feature map according to a preset rule to obtain the quality scores of all frames of substation inspection images, and screening out substation inspection images with the quality scores larger than a preset score threshold;
and the defect identification module is used for processing the screened substation inspection images by utilizing the pre-trained defect identification model to obtain a defect identification result.
As an implementation manner, in the feature extraction module, before downsampling and aggregating each frame of image in the substation inspection video information, the method further includes:
and filtering the inspection video information of the transformer substation by adopting a bilateral filtering method.
A third aspect of the present invention provides a computer-readable storage medium.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps in a substation inspection image defect identification method based on image quality assessment as described above.
A fourth aspect of the invention provides a computer device.
The substation robot comprises a robot body, a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes the steps in the substation inspection image defect identification method based on the image quality evaluation when executing the program.
Compared with the prior art, the invention has the beneficial effects that:
the innovation provides a substation inspection image defect identification technology integrating image quality evaluation, which utilizes a deep learning technology to realize the quality evaluation of substation inspection images, filters low-quality inspection data according to an evaluation result, solves the problem that the inspection image with poor quality seriously affects the inspection effect, improves the accuracy of carrying out target detection and defect identification on inspection equipment, and can be practically applied to intelligent inspection equipment identification tasks in a substation scene.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
Fig. 1 is a flowchart of a substation inspection image defect identification method based on image quality evaluation according to an embodiment of the present invention;
FIG. 2 is a KL_Module structure of an embodiment of the invention;
fig. 3 is a schematic structural diagram of a substation inspection image defect recognition system based on image quality evaluation according to an embodiment of the present invention.
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Example 1
Referring to fig. 1, the present embodiment provides a substation inspection image defect identification method based on image quality evaluation, which includes:
step 1: and obtaining inspection video information of the transformer substation.
In the specific implementation process, the substation robot can be used for shooting the inspection video by carrying a visible light camera.
It can be understood that the inspection video information of the transformer substation can also be acquired in other manners, such as a camera with a preset acquisition position point, etc.
Step 2: and downsampling and aggregating each frame of image in the substation inspection video information to a preset feature size to obtain a corresponding substation inspection feature map, and extracting global features of each substation inspection feature map to obtain a substation inspection global feature map.
In the implementation process, before downsampling and aggregating each frame of image in the substation inspection video information, the method further comprises the following steps:
and filtering the inspection video information of the transformer substation by adopting a bilateral filtering method. Therefore, the contrast and definition of the video picture can be improved, and a foundation is laid for the following intelligent identification.
The Bilateral filtering (bilinear filtering) is a nonlinear filtering method, is a compromise process combining the spatial proximity of the image and the pixel value similarity, and simultaneously considers the spatial domain information and the gray level similarity to achieve the purpose of edge protection and denoising, and has the characteristics of simplicity, non-iteration and locality. The bilateral filter has the advantages that the bilateral filter can be used for edge preservation (edge preservation), and the edge can be obviously obscured by wiener filtering or Gaussian filtering for denoising in the past, so that the protection effect on high-frequency details is not obvious.
In order to realize real-time quality evaluation of substation inspection images, a lightweight image quality evaluation network Iqa _Net is constructed. The lightweight image quality evaluation network Iqa _Net consists of a downsampling aggregation operation module and a plurality of global feature extraction modules. As shown in fig. 2, the downsampling aggregation operation module adopts a Stem operation module. The global feature extraction Module adopts a KL_Module Module.
In the implementation process, each frame of image in the substation inspection video information is downsampled and aggregated to a preset feature size by using a downsampling aggregation operation module. Due to the information redundancy of natural images, common Stem is aggregated to the appropriate feature size by downsampling the input image. The Stem operation here uses a convolution kernel and a non-overlapping convolution of step size 4, which downsamples the input image by a factor of 4.
And extracting global features of the input feature map by using a global feature extraction module.
Each global feature extraction module comprises a residual connection unit, a first convolution layer, a depth convolution layer (such as a Depthwise convolution layer with a convolution kernel size of 7×7), a second convolution layer and a nonlinear operation layer, which are sequentially connected in series, wherein the residual connection unit is used for connecting an input of the first convolution layer and an output of the nonlinear operation layer (such as a relu6 nonlinear operation layer), as shown in fig. 2.
As an embodiment, the convolution kernel sizes of the first convolution layer and the second convolution layer are each 1×1. In the convolution layer of 1×1, the step length is unified to be 1, and zero filling with the size of 2 is performed on the feature map, so that the result of the convolution layer is the same as the size of the feature map of the input layer, and the result cannot be gradually reduced along with the convolution process.
The KL_Module Module mainly comprises a depth separable convolution based on a large convolution kernel, the depth separable convolution can reduce the calculated amount of a model, and the large convolution kernel can improve the enhanced global feature representation.
The operation process of the KL_Module Module comprises the following steps:
1) First, a Depthwise convolution (deep convolution, i.e., spatial convolution) operation performs a convolution operation on each channel of the previous layer output using a 7×7 large convolution kernel alone, thereby expanding the receptive field and enhancing the global feature extraction capability.
2) The information for the multiple channels is then linearly combined.
3) And a residual structure is introduced, the dimension is increased and then reduced, the gradient propagation is enhanced, and the memory occupation required in the reasoning period is obviously reduced.
4) Adopting Concat operation to replace Add operation, thereby achieving the purpose of reducing complexity; the depth separable convolution and the grouping convolution, while being capable of coordinating the capacity and the calculation amount of the model, are found to occupy a great calculation amount by point convolution, so in the residual structure, the Add operation is replaced by the Concat operation, so that more characteristic channels can be mapped under the specific calculation complexity, and the encoding of more information is facilitated.
Wherein, concat operation: tensor stitching expands the dimension of the two tensors.
Add operation: tensors are added, and the tensors are directly added, so that the dimension cannot be expanded.
5) The network is fully convoluted, so that the model can adapt to images with different sizes; the use of Relu6 (highest output of 6) activates the function, making the model more robust with low accuracy calculations.
Step 3: and performing quality evaluation on the substation inspection global feature map according to a preset rule to obtain the quality scores (for example, between 0 and 1) of each frame of substation inspection image, and screening out substation inspection images with the quality scores larger than a preset score threshold.
In the specific implementation process, the substation inspection global feature map has a pre-association relation with the quality score, and the quality evaluation can be performed on the substation inspection global feature map according to the pre-determined relation.
If the mass fraction of the substation inspection image between 0 and 1 is output, judging that the substation inspection image is high-quality when the mass fraction is larger than 0.5, and using the substation inspection image for subsequent defect identification. When the mass fraction is less than or equal to 0.5, the image is directly filtered, and defect identification is not carried out on the image.
Step 4: and processing the screened substation inspection image by using a pre-trained defect recognition model to obtain a defect recognition result.
The defect recognition model may be a multi-target detection algorithm based on deep learning, such as YOLOv series algorithm, and the like.
According to the method, the quality evaluation is carried out on the inspection image data, the inspection image with poor quality is filtered, the high-quality inspection image is input into the pre-trained defect identification model for reasoning, the accuracy of defect identification is improved, early warning of faults of abnormal equipment of the transformer substation is guaranteed, and the intelligent level of the transformer substation is further improved.
Example two
As shown in fig. 3, the present embodiment provides a substation inspection image defect identification system based on image quality evaluation, which includes:
(1) And the information acquisition module is used for acquiring the inspection video information of the transformer substation.
(2) The feature extraction module is used for downsampling and aggregating each frame of image in the substation inspection video information to a preset feature size to obtain a corresponding substation inspection feature map, and extracting global features of each substation inspection feature map to obtain a substation inspection global feature map.
In the feature extraction module, before downsampling and aggregating each frame of image in the substation inspection video information, the method further comprises the following steps:
and filtering the inspection video information of the transformer substation by adopting a bilateral filtering method.
(3) The quality evaluation module is used for performing quality evaluation on the substation inspection global feature map according to a preset rule to obtain the quality scores of all frames of substation inspection images, and screening out substation inspection images with the quality scores larger than a preset score threshold.
(4) And the defect identification module is used for processing the screened substation inspection images by utilizing the pre-trained defect identification model to obtain a defect identification result.
It should be noted that, each module in the embodiment corresponds to each step in the first embodiment one to one, and the implementation process is the same, which is not described here.
Example III
The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps in the substation inspection image defect identification method based on image quality evaluation as described above.
Example IV
The embodiment provides a substation robot, which comprises a robot body, a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the steps in the substation inspection image defect identification method based on image quality evaluation are realized when the processor executes the program.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The substation inspection image defect identification method based on image quality evaluation is characterized by comprising the following steps of:
obtaining inspection video information of a transformer substation;
downsampling and aggregating each frame of image in the substation inspection video information to a preset feature size to obtain a corresponding substation inspection feature map, and extracting global features of each substation inspection feature map to obtain a substation inspection global feature map;
performing quality evaluation on the substation inspection global feature map according to a preset rule to obtain quality scores of all frames of substation inspection images, and screening out substation inspection images with the quality scores larger than a preset score threshold;
and processing the screened substation inspection image by using a pre-trained defect recognition model to obtain a defect recognition result.
2. The substation inspection image defect identification method based on image quality evaluation according to claim 1, further comprising, before downsampling and aggregating each frame of image in the substation inspection video information:
and filtering the inspection video information of the transformer substation by adopting a bilateral filtering method.
3. The substation inspection image defect identification method based on image quality evaluation according to claim 1, wherein each frame of image in the substation inspection video information is downsampled and aggregated to a preset feature size by utilizing a downsampling aggregation operation module.
4. The substation inspection image defect identification method based on image quality evaluation according to claim 1, wherein global features of the input feature map are extracted by a global feature extraction module.
5. The substation inspection image defect identification method based on image quality evaluation according to claim 4, wherein each global feature extraction module comprises a residual connection unit and a first convolution layer, a depth convolution layer, a second convolution layer and a nonlinear operation layer which are sequentially connected in series, and the residual connection unit is used for connecting an input of the first convolution layer and an output of the nonlinear operation layer.
6. The substation inspection image defect identification method based on image quality evaluation according to claim 5, wherein the convolution kernel sizes of the first convolution layer and the second convolution layer are 1×1, so that the result of the corresponding convolution layer is the same as the size of the input layer feature map.
7. The substation inspection image defect identification system based on image quality evaluation is characterized by comprising:
the information acquisition module is used for acquiring the inspection video information of the transformer substation;
the feature extraction module is used for downsampling and aggregating each frame of image in the substation inspection video information to a preset feature size to obtain a corresponding substation inspection feature map, and extracting global features of each substation inspection feature map to obtain a substation inspection global feature map;
the quality evaluation module is used for performing quality evaluation on the substation inspection global feature map according to a preset rule to obtain the quality scores of all frames of substation inspection images, and screening out substation inspection images with the quality scores larger than a preset score threshold;
and the defect identification module is used for processing the screened substation inspection images by utilizing the pre-trained defect identification model to obtain a defect identification result.
8. The substation inspection image defect identification system based on image quality evaluation according to claim 7, wherein the feature extraction module, before downsampling and aggregating each frame of image in the substation inspection video information, further comprises:
and filtering the inspection video information of the transformer substation by adopting a bilateral filtering method.
9. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps in the substation inspection image defect identification method based on image quality evaluation according to any one of claims 1-6.
10. A substation robot comprising a robot body, a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the substation inspection image defect identification method based on image quality evaluation according to any one of claims 1-6 when the program is executed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310517319.0A CN116228774B (en) | 2023-05-10 | 2023-05-10 | Substation inspection image defect identification method and system based on image quality evaluation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310517319.0A CN116228774B (en) | 2023-05-10 | 2023-05-10 | Substation inspection image defect identification method and system based on image quality evaluation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116228774A true CN116228774A (en) | 2023-06-06 |
CN116228774B CN116228774B (en) | 2023-09-08 |
Family
ID=86571692
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310517319.0A Active CN116228774B (en) | 2023-05-10 | 2023-05-10 | Substation inspection image defect identification method and system based on image quality evaluation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116228774B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110006435A (en) * | 2019-04-23 | 2019-07-12 | 西南科技大学 | A kind of Intelligent Mobile Robot vision navigation system method based on residual error network |
CN112131936A (en) * | 2020-08-13 | 2020-12-25 | 华瑞新智科技(北京)有限公司 | Inspection robot image identification method and inspection robot |
CN113870143A (en) * | 2021-10-11 | 2021-12-31 | 国网智能科技股份有限公司 | Distribution line inspection image enhancement method and system |
US20220189008A1 (en) * | 2020-12-16 | 2022-06-16 | Hon Hai Precision Industry Co., Ltd. | Method for detecting data defects and computing device utilizing method |
CN114663352A (en) * | 2022-02-24 | 2022-06-24 | 国网通用航空有限公司 | High-precision detection method and system for defects of power transmission line and storage medium |
CN115187519A (en) * | 2022-06-21 | 2022-10-14 | 上海市计量测试技术研究院 | Image quality evaluation method, system and computer readable medium |
CN115272284A (en) * | 2022-08-17 | 2022-11-01 | 广东电网有限责任公司 | Power transmission line defect identification method based on image quality evaluation |
CN115937121A (en) * | 2022-11-28 | 2023-04-07 | 福州大学 | Non-reference image quality evaluation method and system based on multi-dimensional feature fusion |
CN115937675A (en) * | 2022-11-29 | 2023-04-07 | 广西电网有限责任公司电力科学研究院 | Target and defect identification method in substation inspection environment |
-
2023
- 2023-05-10 CN CN202310517319.0A patent/CN116228774B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110006435A (en) * | 2019-04-23 | 2019-07-12 | 西南科技大学 | A kind of Intelligent Mobile Robot vision navigation system method based on residual error network |
CN112131936A (en) * | 2020-08-13 | 2020-12-25 | 华瑞新智科技(北京)有限公司 | Inspection robot image identification method and inspection robot |
US20220189008A1 (en) * | 2020-12-16 | 2022-06-16 | Hon Hai Precision Industry Co., Ltd. | Method for detecting data defects and computing device utilizing method |
CN113870143A (en) * | 2021-10-11 | 2021-12-31 | 国网智能科技股份有限公司 | Distribution line inspection image enhancement method and system |
CN114663352A (en) * | 2022-02-24 | 2022-06-24 | 国网通用航空有限公司 | High-precision detection method and system for defects of power transmission line and storage medium |
CN115187519A (en) * | 2022-06-21 | 2022-10-14 | 上海市计量测试技术研究院 | Image quality evaluation method, system and computer readable medium |
CN115272284A (en) * | 2022-08-17 | 2022-11-01 | 广东电网有限责任公司 | Power transmission line defect identification method based on image quality evaluation |
CN115937121A (en) * | 2022-11-28 | 2023-04-07 | 福州大学 | Non-reference image quality evaluation method and system based on multi-dimensional feature fusion |
CN115937675A (en) * | 2022-11-29 | 2023-04-07 | 广西电网有限责任公司电力科学研究院 | Target and defect identification method in substation inspection environment |
Non-Patent Citations (1)
Title |
---|
李宁;郑仟;谢贵文;陈炜;: "基于无人机图像识别技术的输电线路缺陷检测", 电子设计工程, no. 10 * |
Also Published As
Publication number | Publication date |
---|---|
CN116228774B (en) | 2023-09-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhang et al. | A dense u-net with cross-layer intersection for detection and localization of image forgery | |
CN110009622B (en) | Display panel appearance defect detection network and defect detection method thereof | |
CN111080600A (en) | Fault identification method for split pin on spring supporting plate of railway wagon | |
Fan et al. | Multiscale cross-connected dehazing network with scene depth fusion | |
CN115439804A (en) | Monitoring method and device for high-speed rail maintenance | |
CN104700405A (en) | Foreground detection method and system | |
CN105405153A (en) | Intelligent mobile terminal anti-noise interference motion target extraction method | |
Liu et al. | Low-quality license plate character recognition based on CNN | |
Li et al. | Fabric defect segmentation system based on a lightweight GAN for industrial Internet of Things | |
KR101615479B1 (en) | Method and apparatus for processing super resolution image using adaptive pre/post-filtering | |
CN116228774B (en) | Substation inspection image defect identification method and system based on image quality evaluation | |
CN116596792B (en) | Inland river foggy scene recovery method, system and equipment for intelligent ship | |
CN110728692A (en) | Image edge detection method based on Scharr operator improvement | |
Peng et al. | MND-GAN: A Research on Image Deblurring Algorithm Based on Generative Adversarial Network | |
CN116071392A (en) | Moving target detection method and system combined with foreground contour extraction | |
CN112446292B (en) | 2D image salient object detection method and system | |
CN115049901A (en) | Small target detection method and device based on feature map weighted attention fusion | |
CN114463379A (en) | Dynamic capturing method and device for video key points | |
CN114612907A (en) | License plate recognition method and device | |
Hu et al. | Rain-density squeeze-and-excitation residual network for single image rain-removal | |
Chebbi et al. | An improvement of structural similarity index for image quality assessment | |
CN114511591B (en) | Track tracking method and device, electronic equipment and storage medium | |
Liu et al. | A Lightweight Denoising Method Based on Noise2Void for X-ray Pseudo-Color Images in X-ray Security Inspection | |
Chen et al. | Contrast Restoration of Hazy Image in HSV Space | |
Zhang et al. | Digital image forensics of non-uniform deblurring |
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 |