CN113032597A - Power transmission equipment classification method and system based on image processing - Google Patents
Power transmission equipment classification method and system based on image processing Download PDFInfo
- Publication number
- CN113032597A CN113032597A CN202110354677.5A CN202110354677A CN113032597A CN 113032597 A CN113032597 A CN 113032597A CN 202110354677 A CN202110354677 A CN 202110354677A CN 113032597 A CN113032597 A CN 113032597A
- Authority
- CN
- China
- Prior art keywords
- image
- visible light
- infrared
- images
- classification
- 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.)
- Pending
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 63
- 238000012545 processing Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012216 screening Methods 0.000 claims abstract description 55
- 238000013145 classification model Methods 0.000 claims abstract description 38
- 230000000007 visual effect Effects 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 abstract description 9
- 239000003086 colorant Substances 0.000 description 4
- 238000002372 labelling Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000012212 insulator Substances 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/532—Query formulation, e.g. graphical querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/55—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Water Supply & Treatment (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a power transmission equipment classification method and a system based on image processing, wherein the power transmission equipment classification method based on image processing comprises the following steps: constructing an image repository; simultaneously and continuously acquiring an infrared image and a visible light image of the power transmission line; leading a plurality of groups of infrared images and visible light images into an image repository; screening infrared images in an image storage library; screening the visible light images in the image repository according to the infrared image screening result in the image repository, and recording the screened visible light images in the image repository as a visible light to-be-classified collection; and inputting the visible light images to be classified and collected into a preset visible light classification model to complete classification. According to the power transmission equipment classification method based on image processing, the interference caused by useless images and the calculation amount increased by the useless images can be effectively reduced, and the classification efficiency and accuracy are improved.
Description
Technical Field
The invention relates to the technical field of information, in particular to a power transmission equipment classification method and system based on image processing.
Background
With the continuous expansion of the scale of the power grid, image acquisition devices such as handheld image acquisition devices, fixed image acquisition devices and aerial photography devices are also increasingly put into the daily management and construction processes of the power grid. Therefore, at present, power enterprises often need to process a large amount of image data, and in the process of processing the image, classification according to the types of power transmission equipment is a link which is difficult to bypass. Traditional transmission equipment is categorised, mainly classifies and marks through the manual work, and this process need consume a large amount of manpower and materials, and categorised result and classification personnel's professional ability, the physical state when categorising are closely relevant, therefore the condition that the classification result has uncontrollable error appears easily.
For this situation, a method for classifying power transmission equipment based on image processing is beginning to appear in the market, wherein the most common method is to implement classification based on a classification model. However, in the image acquisition process, a large amount of useless images (for example, only containing a large amount of vegetation but no power transmission equipment) may be acquired, and thus the useless images cause great waste of operation resources and a situation of wrong classification.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a power transmission equipment classification method based on image processing, which solves the problems of resource waste and error-prone conclusion caused by useless images in the classification process. The invention further provides a power transmission equipment classification system based on image processing.
According to a first aspect of the present invention, a method for classifying power transmitting apparatuses based on image processing includes the steps of:
constructing an image repository;
simultaneously and continuously acquiring infrared images and visible light images of the power transmission line, wherein the actual shooting areas corresponding to each group of infrared images and visible light images are consistent;
guiding a plurality of groups of infrared images and visible light images into an image repository;
screening the infrared images in the image storage library according to the temperature area which exceeds a preset minimum temperature threshold in the infrared images;
screening the visible light images in the image repository according to the infrared image screening result in the image repository, and recording the visible light images screened in the image repository as a visible light to-be-classified collection;
and inputting the visible light images in the visible light to-be-classified collection set into a pre-established visible light classification model to complete classification, and performing classification marking.
According to the power transmission equipment classification method based on image processing, the method at least has the following technical effects: by simultaneously acquiring the infrared image and the visible light image, the consistency of the two images can be kept. By screening the infrared images, a large number of useless images which do not contain power equipment can be effectively removed, and the calculation amount of subsequently classifying the visible light images is reduced. Meanwhile, after all invalid visible light images are removed according to the infrared images, the conclusion of classification errors can be reduced. The power transmission equipment classification method based on image processing can effectively reduce interference caused by useless images and the calculation amount increased by the useless images, and improves the efficiency and accuracy of classification.
According to some embodiments of the present invention, before the screening the visible light images in the image repository according to the infrared image screening result in the image repository, the method further includes the following steps:
and inputting the infrared images after being screened in the image storage library into a pre-established infrared classification model for classification, and screening the infrared images only containing the power lines.
According to some embodiments of the present invention, the method for classifying power transmitting equipment based on image processing further includes:
comparing the classification result of the infrared image with the classification result of the visible light image;
and for each group of infrared images and visible light images, if the classification result according to the infrared classification model is inconsistent with the visible light classification result, canceling the class mark of the visible light image and transmitting the class mark to an image library to be manually identified.
According to some embodiments of the invention, the simultaneously and continuously acquiring the infrared image and the visible light image of the power transmission line comprises the following steps:
keeping the visual fields of the infrared image acquisition device and the visible light image acquisition device consistent;
and simultaneously starting the infrared image acquisition device and the visible light image acquisition device.
According to some embodiments of the present invention, the method for classifying power transmitting equipment based on image processing further includes:
naming a plurality of the infrared images and visible light images in the image repository;
and constructing an image source directory table, wherein the image source directory table comprises name information of a plurality of infrared images and visible light images and corresponding path connection information.
An image processing-based power transmission apparatus classification system according to an embodiment of a second aspect of the present invention includes:
the image acquisition module is used for simultaneously and continuously acquiring infrared images and visible light images of the power transmission line, and the actual shooting areas corresponding to each group of infrared images and visible light images are consistent;
an image repository for storing a plurality of infrared images and visible light images;
the infrared pre-screening module is used for screening the infrared images in the image storage library according to the temperature area which exceeds a preset minimum temperature threshold in the infrared images;
the visible light pre-screening module is used for screening the visible light images in the image repository according to the screening result of the infrared pre-screening module, and recording the visible light images screened in the image repository as a visible light to-be-classified collection;
and the visible light classification module is internally provided with a visible light classification model and is used for inputting the visible light images to be classified and collected into a pre-established visible light classification model to complete classification and carrying out classification marking.
According to the power transmission equipment classification system based on image processing, the power transmission equipment classification system based on image processing at least has the following technical effects: the infrared image and the visible light image are simultaneously collected through the image collecting module, and the consistency of the images of the infrared image and the visible light image can be kept. The infrared image is screened by the infrared pre-screening module, a large number of useless images without containing power equipment can be effectively removed, and the calculation amount of the subsequent visible light classification module for classifying the visible light images is reduced. Meanwhile, after all invalid visible light images are removed by the visible light pre-screening module according to the infrared images, the conclusion of classification errors can be reduced. The power transmission equipment classification system based on image processing can effectively reduce interference caused by useless images and the calculation amount increased by the useless images, and improves the efficiency and accuracy of classification.
According to some embodiments of the present invention, the power transmission equipment classification system based on image processing further includes an infrared classification module, and an infrared classification model is built in the infrared classification module and is used for classifying the infrared images screened by the infrared pre-screening module.
According to some embodiments of the present invention, the power transmission equipment classification system based on image processing further includes a classification result correction module, and the classification result correction module is configured to compare the classification result of the visible light image with the classification result of the infrared image.
According to some embodiments of the invention, the image capture module comprises an infrared image capture device and a visible image capture device, wherein the infrared image capture device and the visible image capture device have a consistent field of view.
According to some embodiments of the present invention, the above-mentioned power transmission equipment classification system based on image processing further includes an image source directory table, where the image source directory table includes name information of a plurality of infrared images and visible light maps, and corresponding path connection information.
Additional aspects and advantages 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 above and additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a simplified flowchart of a power transmission equipment classification method based on image processing according to an embodiment of the present invention;
fig. 2 is a block diagram of a power transmission equipment classification system based on image processing according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it is to be understood that the directional descriptions, such as the directions of upper, lower, front, rear, left, right, etc., are referred to only for convenience of describing the present invention and for simplicity of description, and are not intended to indicate or imply that the device or element so referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be considered as limiting the present invention.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless otherwise explicitly limited, terms such as arrangement, installation, connection and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific contents of the technical solutions.
A power transmitting apparatus classification method based on image processing according to an embodiment of a first aspect of the present invention is described below with reference to fig. 1 to 2.
According to the power transmission equipment classification method based on image processing, the method comprises the following steps:
constructing an image repository;
simultaneously and continuously acquiring infrared images and visible light images of the power transmission line, wherein the actual shooting areas corresponding to each group of infrared images and visible light images are consistent;
leading a plurality of groups of infrared images and visible light images into an image repository;
screening the infrared images in the image storage library according to the temperature area which exceeds a preset minimum temperature threshold in the infrared images;
screening the visible light images in the image repository according to the infrared image screening result in the image repository, and recording the screened visible light images in the image repository as a visible light to-be-classified collection;
and inputting the visible light images to be classified and collected into a preset visible light classification model to complete classification, and performing classification marking.
Referring to fig. 1 and 2, the infrared image includes sufficient temperature characteristics, and temperature information corresponding to the shooting area can be known through the difference of colors and the shades of the colors. For normally operating power transmission equipment, such as power lines, insulators, transformers, etc., usually carry a certain current and thus have a certain temperature, and these temperatures are greater than the ambient temperature, so that the first screening can be assisted according to this point, for example: the ambient temperature is 20 degrees, if the normal operating temperature of all power transmission equipment is higher than 40 degrees, 40 degrees can be set as the lowest temperature threshold, and if no area exceeding 40 degrees exists in an infrared image, no power equipment exists in the image by default. The visible light image contains more image information, and the classification result can be more accurately obtained by utilizing the visible light image and the visible light classification model for classification. Therefore, the visible light image and the infrared image are collected at the same time, so that the advantages of the visible light image and the infrared image can be conveniently utilized to complete subsequent classification.
The main purpose of constructing the image repository is to store visible light images and infrared images, and in actual engineering, collected visible light images and infrared images are not processed in real time, but are stored in batches and then processed in batches, so that the low utilization rate of computing resources can be avoided, and meanwhile, a power transmission classification system can serve a plurality of image collection modules.
A brief description of a general implementation of an embodiment of the present invention is provided herein. After the collected infrared images and visible light images are led into the image database, the infrared images in the image database are firstly screened, the infrared images which do not contain the temperature area higher than the lowest temperature threshold are screened, then the corresponding visible light images are found according to the screened residual infrared images, and the optical images can contain power equipment inevitably. And finally, inputting the visible light images into a light classification model to finish classification and labeling.
According to the power transmission equipment classification method based on image processing, the infrared image and the visible light image are collected simultaneously, and the consistency of the images of the infrared image and the visible light image can be kept. By screening the infrared images, a large number of useless images which do not contain power equipment can be effectively removed, and the calculation amount of subsequently classifying the visible light images is reduced. Meanwhile, after all invalid visible light images are removed according to the infrared images, the conclusion of classification errors can be reduced. According to the power transmission equipment classification method based on image processing, the interference caused by useless images and the calculation amount increased by the useless images can be effectively reduced, and the classification efficiency and accuracy are improved.
In some embodiments of the present invention, before screening the visible light images in the image repository according to the infrared image screening result in the image repository, the method further includes the following steps:
and inputting the screened infrared images in the image storage library into a pre-established infrared classification model for classification, and screening the infrared images only containing the power lines.
When the infrared image and the visible light image are collected, the image collection module automatically shoots according to a preset route in most cases, so that a large number of images which are not shot by the electric power equipment may exist, and the invalid images can be effectively removed according to the manner described above. In the shooting process, another problem may be encountered, particularly in the aerial shooting, a situation that a large number of power lines are shot may be encountered, and if the images only containing the power lines are screened by using the visible light model, on one hand, the computation amount is too large, and on the other hand, because a complex environment background may exist in the images only containing the power lines, the probability of error occurrence is also increased. In the infrared image, other regions are all at normal temperature, and only the power line region has too high temperature, so that a linear region appears in the infrared image, and the infrared image has extremely high resolution. The infrared image containing only the power line can be identified by constructing an infrared classification model, so that the part of the visible light image can be screened out. This step is also carried out, even though the labeling of the visible light image containing only the power line is completed.
In some embodiments of the present invention, the method for classifying power transmission equipment based on image processing further includes:
comparing the classification result of the infrared image with the classification result of the visible light image;
and for each group of infrared images and visible light images, if the classification result according to the infrared classification model is inconsistent with the visible light classification result, canceling the class mark of the visible light image and transmitting the class mark to an image library to be manually identified.
The result of utilizing infrared classification model to carry out transmission of electricity equipment classification can compare with the result of visible light classification model, and only the exact classification can be calculated to both unanimities, and these visible light images can keep the mark, and other nonconformities, then need eliminate the mark and lead in wait artifical discernment image storehouse, and follow-up can the manual work reinspects, can reduce the work load of artifical reinspection like this, also can improve categorised precision simultaneously. In actual engineering, the accuracy of the visible light classification model can meet the requirement generally, so that the result of the visible light classification model can not be compared with the result of the infrared classification model.
In some embodiments of the present invention, simultaneously and continuously acquiring the infrared image and the visible light image of the power transmission line comprises the steps of:
keeping the visual fields of the infrared image acquisition device and the visible light image acquisition device consistent;
and simultaneously starting the infrared image acquisition device and the visible light image acquisition device.
The visual fields of the infrared image acquisition device and the visual image acquisition device are kept consistent, the corresponding relation between the infrared image and the visual image can be better established, the visual image can be conveniently screened according to the infrared image, and the subsequent result can be compared. In order to further ensure that the acquired images are consistent, the acquisition of the images and the acquisition of the images are started at the same time, and errors caused by inconsistency of the acquisition time of the images and the acquisition time of the images are avoided.
In some embodiments of the present invention, the method for classifying power transmission equipment based on image processing further includes:
naming a plurality of infrared images and visible light images in an image repository;
and constructing an image source directory table, wherein the image source directory table comprises name information of a plurality of infrared images and visible light images and corresponding path connection information.
A plurality of infrared images and visible light images are named, and the connection relation with a source file is established through an image source directory table, so that the source of the image can be determined in time after other operations are completed according to classification results in sequence, and the operations such as obstacle removal and maintenance can be performed in time. Here, a simple example is made: for example, images acquired by the same unmanned aerial vehicle during cruise can be uniformly named, and the unmanned aerial vehicle can be directly traced through the naming.
The power transmission equipment classification system based on image processing comprises an image acquisition module, an image storage library, an infrared pre-screening module, a visible light pre-screening module and a visible light classification module.
The image acquisition module is used for simultaneously and continuously acquiring the infrared image and the visible light image of the power transmission line, and the actual shooting areas corresponding to each group of infrared image and the visible light image are consistent;
an image repository for storing a plurality of infrared images and visible light images;
the infrared pre-screening module is used for screening the infrared images in the image storage library according to the temperature area which exceeds the preset minimum temperature threshold in the infrared images;
the visible light pre-screening module is used for screening the visible light images in the image repository according to the screening result of the infrared pre-screening module and recording the visible light images screened in the image repository as a visible light to-be-classified collection;
and the visible light classification module is internally provided with a visible light classification model and is used for inputting visible light images to be classified and collected into a pre-established visible light classification model to complete classification and carrying out classification marking.
Referring to fig. 1 and 2, the image acquisition module may acquire an infrared image and a visible light image, where the infrared image includes sufficient temperature characteristics, and temperature information corresponding to a shooting area may be known through different colors and shades of the colors. For normally operating power transmission equipment, such as power lines, insulators, transformers, etc., usually carry a certain current and thus have a certain temperature, and these temperatures are greater than the ambient temperature, so that the first screening can be assisted according to this point, for example: the ambient temperature is 20 degrees, if the normal operating temperature of all power transmission equipment is higher than 40 degrees, 40 degrees can be set as the lowest temperature threshold, and if no area exceeding 40 degrees exists in an infrared image, no power equipment exists in the image by default. The visible light image contains more image information, and the classification result can be more accurately obtained by utilizing the visible light image and the visible light classification model for classification. Therefore, the visible light image and the infrared image are collected at the same time, so that the advantages of the visible light image and the infrared image can be conveniently utilized to complete subsequent classification.
The main purpose of constructing the image repository is to store visible light images and infrared images, and in actual engineering, collected visible light images and infrared images are not processed in real time, but are stored in batches and then processed in batches, so that the low utilization rate of computing resources can be avoided, and meanwhile, a power transmission classification system can serve a plurality of image collection modules.
A brief description of a general implementation of an embodiment of the present invention is provided herein. After the collected infrared images and visible light images are led into the image database by the image collecting module, the infrared images in the image database are firstly screened by the infrared pre-screening module, the infrared images which do not contain the temperature area higher than the lowest temperature threshold are screened, then the visible light pre-screening module finds the corresponding visible light images according to the remaining screened infrared images, and the visible light pre-screening module can inevitably contain power equipment in the light images. And finally, inputting the visible light images into the light classification model through the visible light classification module to finish classification and labeling.
According to the power transmission equipment classification system based on image processing, the power transmission equipment classification system based on image processing at least has the following technical effects: the infrared image and the visible light image are simultaneously collected through the image collecting module, and the consistency of the images of the infrared image and the visible light image can be kept. The infrared image is screened by the infrared pre-screening module, a large number of useless images without containing power equipment can be effectively removed, and the calculation amount of the subsequent visible light classification module for classifying the visible light images is reduced. Meanwhile, after all invalid visible light images are removed by the visible light pre-screening module according to the infrared images, the conclusion of classification errors can be reduced. The power transmission equipment classification system based on image processing can effectively reduce interference caused by useless images and the calculation amount increased by the useless images, and improves the efficiency and accuracy of classification.
In some embodiments of the present invention, the power transmission equipment classification system based on image processing further includes an infrared classification module, and an infrared classification model is built in the infrared classification module and is used for classifying the infrared images screened by the infrared pre-screening module.
When the infrared image and the visible light image are collected, the image collection module automatically shoots according to a preset route in most cases, so that a large number of images which are not shot by the electric power equipment may exist, and the invalid images can be effectively removed according to the manner described above. In the shooting process, another problem may be encountered, particularly in the aerial shooting, a situation that a large number of power lines are shot may be encountered, and if the images only containing the power lines are screened by using the visible light model, on one hand, the computation amount is too large, and on the other hand, because a complex environment background may exist in the images only containing the power lines, the probability of error occurrence is also increased. In the infrared image, other regions are all at normal temperature, and only the power line region has too high temperature, so that a linear region appears in the infrared image, and the infrared image has extremely high resolution. Here, the infrared image including only the power line may be recognized by the infrared classification module, so that the part of the visible light image is filtered out. This process, even though, completes the labeling of the visible light image containing only the power line.
In some embodiments of the present invention, the power transmission equipment classification system based on image processing further includes a classification result modification module, and the classification result modification module is configured to compare the classification result of the visible light image with the classification result of the infrared image.
The infrared classification model is utilized to classify the power transmission equipment, the classification result correction module can be utilized to compare the result of the infrared classification model with the result of the visible light classification model, accurate classification can be calculated only when the result of the infrared classification model is consistent with the result of the visible light classification model, the visible light images can be kept labeled, other images are inconsistent, the label needs to be eliminated, the images are guided into an image library to be manually identified, and subsequent manual rechecking can be carried out, so that the workload of manual rechecking can be reduced, and the classification precision can be improved. In actual engineering, the accuracy of the visible light classification model can meet the requirement generally, so that the result of the visible light classification model can not be compared with the result of the infrared classification model.
In some embodiments of the present invention, the image capturing module includes an infrared image capturing device and a visible light image capturing device, and the infrared image capturing device and the visible light image capturing device have the same visual field. The visual fields of the infrared image acquisition device and the visible light image acquisition device are kept consistent, the corresponding relation between the infrared image and the visible light image can be better established, the visible light image can be conveniently screened according to the infrared image, and the subsequent results can be compared. In order to further ensure that the acquired images are consistent, the acquisition of the images and the acquisition of the images are started at the same time, and errors caused by inconsistency of the acquisition time of the images and the acquisition time of the images are avoided.
In some embodiments of the present invention, the above-mentioned power transmission equipment classification system based on image processing further includes an image source directory table, where the image source directory table includes name information of a plurality of infrared images and visible light maps, and corresponding path connection information. A plurality of infrared images and visible light images are named, and the connection relation with a source file is established through an image source directory table, so that the source of the image can be determined in time after other operations are completed according to classification results in sequence, and the operations such as obstacle removal and maintenance can be performed in time. Here, a simple example is made: for example, images acquired by the same unmanned aerial vehicle during cruise can be uniformly named, and the unmanned aerial vehicle can be directly traced through the naming.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples" or the like mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although the embodiments of the present invention have been described in detail with reference to the accompanying drawings, the present invention is not limited to the embodiments, and those skilled in the art will understand that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (10)
1. A power transmission equipment classification method based on image processing is characterized by comprising the following steps:
constructing an image repository;
simultaneously and continuously acquiring infrared images and visible light images of the power transmission line, wherein the actual shooting areas corresponding to each group of infrared images and visible light images are consistent;
guiding a plurality of groups of infrared images and visible light images into an image repository;
screening the infrared images in the image storage library according to the temperature area which exceeds a preset minimum temperature threshold in the infrared images;
screening the visible light images in the image repository according to the infrared image screening result in the image repository, and recording the visible light images screened in the image repository as a visible light to-be-classified collection;
and inputting the visible light images in the visible light to-be-classified collection set into a pre-established visible light classification model to complete classification, and performing classification marking.
2. The image-processing-based power transmission equipment classification method according to claim 1, characterized by further comprising, before the screening of the visible light images in the image repository based on the infrared image screening results in the image repository, the following steps:
and inputting the infrared images after being screened in the image storage library into a pre-established infrared classification model for classification, and screening the infrared images only containing the power lines.
3. The image-processing-based power transmission apparatus classification method according to claim 2, characterized by further comprising the steps of:
comparing the classification result of the infrared image with the classification result of the visible light image;
and for each group of infrared images and visible light images, if the classification result according to the infrared classification model is inconsistent with the visible light classification result, canceling the class mark of the visible light image and transmitting the class mark to an image library to be manually identified.
4. The image processing-based power transmission equipment classification method according to claim 1, wherein the step of simultaneously and continuously acquiring the infrared image and the visible light image of the power transmission line comprises the following steps:
keeping the visual fields of the infrared image acquisition device and the visible light image acquisition device consistent;
and simultaneously starting the infrared image acquisition device and the visible light image acquisition device.
5. The image-processing-based power transmission apparatus classification method according to claim 1, characterized by further comprising the steps of:
naming a plurality of the infrared images and visible light images in the image repository;
and constructing an image source directory table, wherein the image source directory table comprises name information of a plurality of infrared images and visible light images and corresponding path connection information.
6. An image processing-based classification system for power transmission equipment, comprising:
the image acquisition module is used for simultaneously and continuously acquiring infrared images and visible light images of the power transmission line, and the actual shooting areas corresponding to each group of infrared images and visible light images are consistent;
an image repository for storing a plurality of infrared images and visible light images;
the infrared pre-screening module is used for screening the infrared images in the image storage library according to the temperature area which exceeds a preset minimum temperature threshold in the infrared images;
the visible light pre-screening module is used for screening the visible light images in the image repository according to the screening result of the infrared pre-screening module, and recording the visible light images screened in the image repository as a visible light to-be-classified collection;
and the visible light classification module is internally provided with a visible light classification model and is used for inputting the visible light images to be classified and collected into a pre-established visible light classification model to complete classification and carrying out classification marking.
7. The image-processing-based power transmission equipment classification system according to claim 6, further comprising an infrared classification module, wherein an infrared classification model is built in the infrared classification module and is used for classifying the infrared images screened by the infrared pre-screening module.
8. The image-processing-based power transmission equipment classification system according to claim 7, further comprising a classification result correction module configured to compare the classification result of the visible light image with the classification result of the infrared image.
9. The image processing-based power transmission equipment classification system according to claim 7, wherein the image acquisition module comprises an infrared image acquisition device and a visible light image acquisition device, and the infrared image acquisition device and the visible light image acquisition device have the same visual field.
10. The image-processing-based power transmission equipment classification system according to claim 6, characterized by further comprising an image source directory table that includes name information of a plurality of the infrared images and visible light maps, and corresponding path connection information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110354677.5A CN113032597A (en) | 2021-03-31 | 2021-03-31 | Power transmission equipment classification method and system based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110354677.5A CN113032597A (en) | 2021-03-31 | 2021-03-31 | Power transmission equipment classification method and system based on image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113032597A true CN113032597A (en) | 2021-06-25 |
Family
ID=76453524
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110354677.5A Pending CN113032597A (en) | 2021-03-31 | 2021-03-31 | Power transmission equipment classification method and system based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113032597A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570574A (en) * | 2021-07-28 | 2021-10-29 | 北京精英系统科技有限公司 | Scene feature detection device, search device and search method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009530A (en) * | 2019-04-16 | 2019-07-12 | 国网山西省电力公司电力科学研究院 | A kind of nerve network system and method suitable for portable power inspection |
| CN111523423A (en) * | 2020-04-15 | 2020-08-11 | 四川赛康智能科技股份有限公司 | Power equipment identification method and device |
| CN111754483A (en) * | 2020-06-23 | 2020-10-09 | 四川省东宇信息技术有限责任公司 | Method and system for identifying abnormal equipment based on thermal imager |
-
2021
- 2021-03-31 CN CN202110354677.5A patent/CN113032597A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009530A (en) * | 2019-04-16 | 2019-07-12 | 国网山西省电力公司电力科学研究院 | A kind of nerve network system and method suitable for portable power inspection |
| CN111523423A (en) * | 2020-04-15 | 2020-08-11 | 四川赛康智能科技股份有限公司 | Power equipment identification method and device |
| CN111754483A (en) * | 2020-06-23 | 2020-10-09 | 四川省东宇信息技术有限责任公司 | Method and system for identifying abnormal equipment based on thermal imager |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570574A (en) * | 2021-07-28 | 2021-10-29 | 北京精英系统科技有限公司 | Scene feature detection device, search device and search method |
| CN113570574B (en) * | 2021-07-28 | 2023-12-01 | 北京精英系统科技有限公司 | Scene feature detection device, scene feature search device and scene feature search method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111259892B (en) | Inspection method, inspection device, inspection equipment and inspection medium for state of indicator lamp | |
| CN105141889A (en) | Power transmission line intelligent patrol system based on image vision | |
| CN112926405A (en) | Method, system, equipment and storage medium for detecting wearing of safety helmet | |
| CN110969719A (en) | Automatic inspection method, system, terminal equipment and storage medium | |
| CN110533654A (en) | The method for detecting abnormality and device of components | |
| CN110569856B (en) | Sample labeling method and device, and damage category identification method and device | |
| CN112102443B (en) | Labeling system and labeling method suitable for substation equipment inspection image | |
| CN104392232A (en) | Method for correcting video metadata in traffic scenes | |
| CN111914767A (en) | Scattered-pollution enterprise detection method and system based on multi-source remote sensing data | |
| CN114721430A (en) | Power line safety inspection and intelligent diagnosis system based on unmanned aerial vehicle | |
| CN110766045B (en) | Underground drainage pipeline disease identification method, intelligent terminal and storage medium | |
| CN113032597A (en) | Power transmission equipment classification method and system based on image processing | |
| CN114627394A (en) | Muck vehicle fake plate identification method and system based on unmanned aerial vehicle | |
| CN114881931A (en) | Photovoltaic panel defect detection method, system and equipment based on double-light fusion and computer readable storage medium | |
| CN111241905A (en) | Power transmission line nest detection method based on improved SSD algorithm | |
| CN112966687B (en) | Image segmentation model training method and device and communication equipment | |
| CN114359552A (en) | Instrument image identification method based on inspection robot | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN113408630A (en) | Transformer substation indicator lamp state identification method | |
| CN115690807A (en) | Box number identification method based on OCR technology | |
| CN112364790B (en) | Airport work order information identification method and system based on convolutional neural network | |
| CN114283442A (en) | Intelligent identification method and device for secondary wiring diagram and storage medium | |
| CN114332630A (en) | Multi-stage accurate screening fruit tree pest and disease monitoring system and method | |
| CN113986823A (en) | Picture archiving method, device, medium and equipment for communication machine room | |
| CN112559712A (en) | Intelligent operation and maintenance method and system |
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 |