CN114266985A - Glass insulator spontaneous explosion identification method, device, equipment, medium and program product - Google Patents
Glass insulator spontaneous explosion identification method, device, equipment, medium and program product Download PDFInfo
- Publication number
- CN114266985A CN114266985A CN202210043777.0A CN202210043777A CN114266985A CN 114266985 A CN114266985 A CN 114266985A CN 202210043777 A CN202210043777 A CN 202210043777A CN 114266985 A CN114266985 A CN 114266985A
- Authority
- CN
- China
- Prior art keywords
- explosion
- self
- glass insulator
- glass
- insulator string
- 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
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application relates to the technical field of power grids and provides a glass insulator spontaneous explosion identification processing method, a glass insulator spontaneous explosion identification processing device, computer equipment, a storage medium and a computer program product. This application can improve glass insulator spontaneous explosion identification degree of accuracy and efficiency. The method comprises the following steps: the method comprises the steps of obtaining a power transmission line inspection picture shot by an unmanned aerial vehicle for inspecting a power transmission line, inputting the inspection picture into a glass insulator string detection model, obtaining a glass insulator string detection image output after the model detects a glass insulator string on the inspection picture, inputting the glass insulator string detection image into a self-explosion insulator single-chip detection model, obtaining an image area where each self-explosion insulator is located on the glass insulator string detection image by the model, finally determining the self-explosion number of the glass insulator according to the area number of the image area where each self-explosion insulator is located, and determining the continuous self-explosion number of the glass insulator according to the overlapping condition of the image areas where each self-explosion insulator is located.
Description
Technical Field
The application relates to the technical field of power grids, in particular to a glass insulator spontaneous explosion identification processing method, a glass insulator spontaneous explosion identification processing device, a glass insulator spontaneous explosion identification processing computer device, a storage medium and a computer program product.
Background
The transmission line is long and the coverage area is wide, and along with the rapid development of unmanned aerial vehicle technique, electric power operation and maintenance personnel adopt unmanned aerial vehicle to shoot gradually and patrol and examine the transmission line, so not only can improve the efficiency of patrolling and examining, can also improve the quality of patrolling and examining in addition to patrolling and examining more meticulously. Among them, the glass insulator is a component of equipment commonly used for power transmission, and can prevent live equipment from becoming a ground path. The glass insulator is in a severe natural environment for a long time, and the phenomenon of insulator self-explosion often occurs when the glass insulator is influenced by lightning, ice and snow and severe temperature change.
Glass insulator spontaneous explosion discernment mainly relies on the manual work to look over in patrolling and examining the picture to unmanned aerial vehicle among the conventional art, and intensity of labour is big and easy visual fatigue, leads to this kind of technique to have glass insulator spontaneous explosion discernment degree of accuracy and the lower technical problem of efficiency.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a glass insulator spontaneous explosion identification processing method, apparatus, computer device, storage medium, and computer program product for solving the above technical problems.
In a first aspect, the application provides a glass insulator spontaneous explosion identification processing method. The method comprises the following steps:
acquiring a power transmission line inspection picture obtained by the unmanned aerial vehicle inspecting and shooting the power transmission line;
inputting the power transmission line inspection picture into a pre-constructed glass insulator string detection model, and acquiring a glass insulator string detection image output by the glass insulator string detection model after the glass insulator string detection is carried out on the power transmission line inspection picture;
inputting the glass insulator string detection image into a pre-constructed single self-explosion insulator sheet detection model, and acquiring an image area where each self-explosion insulator is positioned on the glass insulator string detection image by the single self-explosion insulator sheet detection model;
and determining the self-explosion number of the glass insulators according to the number of the image areas where the self-explosion insulators are located, and determining the continuous self-explosion number of the glass insulators according to the overlapping condition of the image areas where the self-explosion insulators are located.
In one embodiment, after determining the number of auto-explosions of the glass insulator according to the number of the image areas where the respective auto-explosions are located, and determining the number of continuous auto-explosions of the glass insulator according to the overlapping condition between the image areas where the respective auto-explosions are located, the method further includes: acquiring a power transmission line voltage grade corresponding to the power transmission line inspection picture; and judging the insulator spontaneous explosion degree of the power transmission line according to the voltage grade of the power transmission line, the spontaneous explosion number of the glass insulators and the continuous spontaneous explosion number.
In one embodiment, the glass insulator string detection model is used for positioning an image area where a glass insulator string is located in the power transmission line inspection picture by adopting an S2A-Net rotation target detection algorithm and outputting a detection image of the glass insulator string; and the image area where the glass insulator string is positioned is marked by adopting a rotating rectangular frame.
In one embodiment, the inputting the glass insulator string detection image into a pre-constructed self-explosion insulator single-chip detection model includes: intercepting to obtain a mask screenshot of the glass insulator string based on the glass insulator string detection image; zooming the glass insulator string mask screenshot to a preset size in a mode of same length and width zooming ratio to obtain a zoomed glass insulator string mask screenshot; and inputting the zoomed screen shot of the glass insulator string mask to the self-explosion insulator single-chip detection model so that the self-explosion insulator single-chip detection model can position the image area where each self-explosion insulator is located on the zoomed screen shot of the glass insulator string mask.
In one embodiment, the single-chip detection model of the self-explosion insulator is used for positioning an image area where each self-explosion insulator is located in the zoomed screenshot of the glass insulator string mask by adopting a yolov4 target detection algorithm; and marking the image area where each self-explosion insulator is positioned by adopting a horizontal rectangular frame.
In one embodiment, after determining the number of auto-explosions of the glass insulator according to the number of the image areas where the respective auto-explosions are located, and determining the number of continuous auto-explosions of the glass insulator according to the overlapping condition between the image areas where the respective auto-explosions are located, the method further includes: and marking a picture area where a glass insulator string containing the self-explosion insulator is located on the power transmission line inspection picture, and displaying the self-explosion number and the continuous self-explosion number of the corresponding glass insulator.
In a second aspect, the application further provides a glass insulator spontaneous explosion recognition processing device. The device comprises:
the picture acquisition module is used for acquiring a power transmission line inspection picture obtained by the unmanned aerial vehicle inspecting and shooting the power transmission line;
the string detection module is used for inputting the power transmission line inspection picture into a pre-constructed glass insulator string detection model, and acquiring a glass insulator string detection image which is output after the glass insulator string detection is carried out on the power transmission line inspection picture by the glass insulator string detection model;
the single-chip detection module is used for inputting the glass insulator string detection image into a pre-constructed single-chip detection model of the self-explosion insulator, and acquiring an image area where each self-explosion insulator is positioned on the glass insulator string detection image by the single-chip detection model of the self-explosion insulator;
and the quantity determining module is used for determining the self-explosion quantity of the glass insulators according to the quantity of the image areas where the self-explosion insulators are located and determining the continuous self-explosion quantity of the glass insulators according to the overlapping condition of the image areas where the self-explosion insulators are located.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:
acquiring a power transmission line inspection picture obtained by the unmanned aerial vehicle inspecting and shooting the power transmission line; inputting the power transmission line inspection picture into a pre-constructed glass insulator string detection model, and acquiring a glass insulator string detection image output by the glass insulator string detection model after the glass insulator string detection is carried out on the power transmission line inspection picture; inputting the glass insulator string detection image into a pre-constructed single self-explosion insulator sheet detection model, and acquiring an image area where each self-explosion insulator is positioned on the glass insulator string detection image by the single self-explosion insulator sheet detection model; and determining the self-explosion number of the glass insulators according to the number of the image areas where the self-explosion insulators are located, and determining the continuous self-explosion number of the glass insulators according to the overlapping condition of the image areas where the self-explosion insulators are located.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring a power transmission line inspection picture obtained by the unmanned aerial vehicle inspecting and shooting the power transmission line; inputting the power transmission line inspection picture into a pre-constructed glass insulator string detection model, and acquiring a glass insulator string detection image output by the glass insulator string detection model after the glass insulator string detection is carried out on the power transmission line inspection picture; inputting the glass insulator string detection image into a pre-constructed single self-explosion insulator sheet detection model, and acquiring an image area where each self-explosion insulator is positioned on the glass insulator string detection image by the single self-explosion insulator sheet detection model; and determining the self-explosion number of the glass insulators according to the number of the image areas where the self-explosion insulators are located, and determining the continuous self-explosion number of the glass insulators according to the overlapping condition of the image areas where the self-explosion insulators are located.
In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:
acquiring a power transmission line inspection picture obtained by the unmanned aerial vehicle inspecting and shooting the power transmission line; inputting the power transmission line inspection picture into a pre-constructed glass insulator string detection model, and acquiring a glass insulator string detection image output by the glass insulator string detection model after the glass insulator string detection is carried out on the power transmission line inspection picture; inputting the glass insulator string detection image into a pre-constructed single self-explosion insulator sheet detection model, and acquiring an image area where each self-explosion insulator is positioned on the glass insulator string detection image by the single self-explosion insulator sheet detection model; and determining the self-explosion number of the glass insulators according to the number of the image areas where the self-explosion insulators are located, and determining the continuous self-explosion number of the glass insulators according to the overlapping condition of the image areas where the self-explosion insulators are located.
According to the glass insulator self-explosion recognition processing method, the device, the computer equipment, the storage medium and the computer program product, a power transmission line inspection picture obtained by the inspection shooting of the power transmission line by the unmanned aerial vehicle is obtained, then the inspection picture is input into a glass insulator string detection model, a glass insulator string detection image output by the model after the inspection picture is subjected to glass insulator string detection is obtained, then the glass insulator string detection image is input into a self-explosion insulator single-chip detection model, an image area where each self-explosion insulator is located is obtained, the number of self-explosions of the glass insulator is determined according to the number of the image area where each self-explosion insulator is located, and the number of continuous self-explosions of the glass insulator is determined according to the overlapping condition of the image areas where each self-explosion insulator is located. According to the scheme, intelligent self-explosion recognition and self-explosion information acquisition of the glass insulator in the inspection picture is realized based on the glass insulator string detection model and the self-explosion insulator single-chip detection model, the self-explosion information such as the total number of self-explosions and the continuous self-explosions of the glass insulator is accurately recognized and obtained, and the accuracy and the efficiency of the self-explosion recognition of the glass insulator are improved.
Drawings
Fig. 1 is a schematic flow chart of a glass insulator spontaneous explosion identification processing method in one embodiment;
FIG. 2 is a schematic diagram illustrating the overall process of the glass insulator spontaneous explosion identification process according to an embodiment;
FIG. 3 is a labeled diagram of a rectangular box in one embodiment;
FIG. 4 is a block diagram showing the structure of a glass insulator spontaneous explosion identification processing apparatus according to an embodiment;
FIG. 5 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The glass insulator spontaneous explosion identification processing method provided by the embodiment of the application can be applied to computer equipment such as terminals and servers. The terminal can be but is not limited to various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the portable wearable devices can be head-mounted devices and the like; the server may be implemented as a stand-alone server or as a server cluster consisting of a plurality of servers.
In one embodiment, a glass insulator spontaneous explosion identification processing method is provided, as shown in fig. 1, the method may include the steps of:
step S101, acquiring a power transmission line inspection picture obtained by the unmanned aerial vehicle inspecting and shooting the power transmission line;
in the step, an original power transmission picture (original picture) obtained by the unmanned aerial vehicle during power transmission line inspection shooting is used as a power transmission line inspection picture and also used as input data of a subsequent glass insulator string detection model. In order to clearly illustrate the relationship between the steps of the present application, reference may be made to fig. 2 in the following description of steps or embodiments.
Step S102, inputting the power transmission line inspection picture into a pre-constructed glass insulator string detection model, and acquiring a glass insulator string detection image output by the glass insulator string detection model after the glass insulator string detection is carried out on the power transmission line inspection picture;
the method mainly comprises the steps of detecting an image area where a glass insulator string is located in a power transmission line inspection picture, specifically inputting the power transmission line inspection picture obtained by unmanned aerial vehicle inspection into a pre-constructed glass insulator string detection model, wherein the glass insulator string detection model is used for detecting the glass insulator string in the picture, and then obtaining a glass insulator string detection image which is output after the glass insulator string detection is carried out on the power transmission line inspection picture by the glass insulator string detection model.
In some embodiments, the glass insulator string detection model can be used for locating the image area where the glass insulator string in the power transmission line inspection picture is located by adopting an S2A-Net rotation target detection algorithm, outputting a glass insulator string detection image, namely the glass insulator string detection model can be specifically constructed based on an S2A-Net rotation target detection algorithm, the S2A-Net rotation target detection network mainly comprises a trunk network, a Feature Pyramid Network (FPN), a Feature Alignment Module (FAM) and a direction detection module (ODM), wherein a detection head consisting of the FPN and the FAM is applied to each scale of the FPN features, in the FAM module, a feature map generates a high-quality rotation anchor through an anchor lifting network (ARN), then the anchor and the feature map are input into the alignment convolutional layer to extract the aligned features, in the ODM module, the alignment feature map extracted in the last step is used for extracting direction-sensitive features by activating A Rotation Filter (ARF), then two branches are provided, one branch directly adopts the sensitive features to regress the target position, and the other branch adopts pooling operation to extract direction-insensitive features for classifying the target category.
In the embodiment, the power transmission line inspection picture is input into the glass insulator string detection model, the glass insulator string detection model adopts the S2A-Net rotating target detection algorithm to position the image area where the glass insulator string in the power transmission line inspection picture is located and output the glass insulator string detection image, and the glass insulator string detection model marks the image area where the glass insulator string is located in the power transmission line inspection picture by adopting the rotating rectangular frame, so that the condition that the horizontal frame detection algorithm detects that the adjacent glass insulators are overlapped in a large area can be avoided. The detection image of the glass insulator string may be a transmission line inspection picture in which the image area where the glass insulator string is located is marked by a rotating rectangular frame, and the specific expression form of the rotating rectangular frame may refer to fig. 3.
Step S103, inputting the detection image of the glass insulator string into a pre-constructed single-chip detection model of the self-explosion insulator, and acquiring an image area where each self-explosion insulator is positioned on the detection image of the glass insulator string by the single-chip detection model of the self-explosion insulator;
the method mainly comprises the steps that each self-explosion insulator in a glass insulator string detection image is detected and positioned through a self-explosion insulator single-chip detection model, the glass insulator string detection image is input into the self-explosion insulator single-chip detection model, the self-explosion insulator single-chip detection model is used for independently positioning an image area where each self-explosion insulator is located in the glass insulator string detection image, the specific self-explosion insulator single-chip detection model can be used for marking each self-explosion insulator by adopting an independent rectangular frame on the glass insulator string detection image, and namely one rectangular frame only marks one self-explosion insulator.
In some embodiments, the inputting of the glass insulator string detection image into the pre-constructed self-explosion insulator monolithic detection model in step S103 specifically includes:
based on the glass insulator string detection image, intercepting to obtain a glass insulator string mask screenshot; zooming the glass insulator string mask screenshot to a preset size by adopting a mode of same length and width zooming ratio to obtain a zoomed glass insulator string mask screenshot; and inputting the zoomed screenshot of the glass insulator string mask to a self-explosion insulator single-chip detection model so that the self-explosion insulator single-chip detection model can position an image area where each self-explosion insulator is located on the zoomed screenshot of the glass insulator string mask.
In the embodiment, mainly, in order to meet the preset size requirement of the self-explosion insulator single-chip detection model on the input image data under the condition that the glass insulator string detection image is output after the glass insulator string detection model adopts the rotating rectangular frame to mark the image area where the glass insulator string is located, the image distortion is caused by carrying out rough size scaling on the glass insulator string detection image, so that the identification precision is influenced, and therefore the glass insulator string detection image needs to be correspondingly processed to ensure the identification precision.
Specifically, a screenshot of a glass insulator string mask may be captured based on a glass insulator string detection image, and coordinates of four points of a rotating rectangular frame of the glass insulator string in the glass insulator string detection image are (x1, y1), (x2, y2), (x3, y3) and (x4, y4), where xmin is min (x1, x2, x3, x4), xmax is max (x1, x2, x3, x4), ymin is min (y1, y2, y3, y4), ymax max (y1, y2, y3, y4), a screenshot area corresponding to the glass insulator string detection image may be taken out of the glass insulator string mask image area (xmin, ymax) and a screenshot area corresponding to the glass insulator string image area (i.e., a pixel area other than the rotating rectangular frame area) may be filled with a screenshot value of the glass insulator string mask, and an insulator string image value of 0 may be obtained. And after the screenshot of the glass insulator string mask is obtained, zooming the screenshot of the glass insulator string mask to the preset size (640 ) by adopting the same scaling of the length and the width, and filling (0, 0, 0) pixels around the screenshot according to the requirement to obtain the zoomed screenshot of the glass insulator string mask. And then, inputting the zoomed screenshot of the glass insulator string mask to a self-explosion insulator single-chip detection model, wherein the self-explosion insulator single-chip detection model can position an image area where each self-explosion insulator is located on the zoomed screenshot of the glass insulator string mask.
Further, in some embodiments, the single self-explosion insulator sheet detection model may be used to locate an image region where each self-explosion insulator is located in the zoomed screenshot of the glass insulator string mask by using yolov4 target detection algorithm, and the image region where each self-explosion insulator is located is marked by using a horizontal rectangular frame.
Specifically, in the single-chip detection model for the self-explosion insulator in this embodiment, a yolov4 target detection algorithm is adopted to locate an image area where each self-explosion insulator is located in a zoomed screenshot of a glass insulator string, and referring to fig. 3, the single-chip detection model for the self-explosion insulator adopts a horizontal rectangular frame to mark the image area where each self-explosion insulator is located so as to distinguish a marking form of the glass insulator string, so that each self-explosion insulator can be identified and counted more accurately. Further, in order to prevent the NMS (non-maximum suppression) from filtering out the adjacent single-chip self-explosion boxes with larger overlapping degree, the threshold of the NMS may be set to 0.7, and the confidence threshold of the defect may be set to 0.5, considering that the adjacent single-chip self-explosion detection boxes may overlap. In practical application, the structure of the yolov4 target detection algorithm mainly comprises a backbone network, a Feature Pyramid (FPN), a Path Aggregation Network (PAN) and a prediction part. Wherein, the backhaul adopts a CSPDarknet53 network, and for 608 × 608 input pictures, the characteristic diagram change rule is: 608- >304- >152- >76- >38- > 19. The FPN module is from top to bottom, and the high-level feature information is transmitted and fused in an up-sampling mode. The algorithm is characterized in that a bottom-up feature pyramid is added behind the FPN module, wherein the bottom-up feature pyramid comprises two PAN structures, and the PAN structures carry out channel dimension splicing on two feature graphs with the same width and height by means of Concat operation. The sizes of the three feature maps of the prediction output are 76 × 76, 38 × 38 and 19 × 19, which correspond to the minimum, medium and maximum anchor _ box respectively, and the channel dimension of the feature map is num _ classes + 5.
And step S104, determining the self-explosion number of the glass insulators according to the number of the image areas where the self-explosion insulators are located, and determining the continuous self-explosion number of the glass insulators according to the overlapping condition of the image areas where the self-explosion insulators are located.
In the step, specifically, the number of image areas where the self-explosion insulators are located can be used as the self-explosion number (total number of pieces) of the glass insulators in the glass insulator string, and for the continuous self-explosion glass insulator string, the image areas where the adjacent self-explosion insulators are located can be overlapped, so that the number of continuous self-explosion glass insulators (continuous self-explosion number) in the glass insulator string can be calculated according to the overlapping condition among the image areas where the self-explosion insulators are located, specifically, the image areas (detection frames) where the overlapped self-explosion insulators are located can be fused, and the number of continuous self-explosion numbers can be obtained by calculating the number of continuous self-explosion according to fusion information such as the fusion number.
The glass insulator self-explosion recognition processing method comprises the steps of obtaining a power transmission line inspection picture shot by an unmanned aerial vehicle for inspecting a power transmission line, inputting the inspection picture into a glass insulator string detection model, obtaining a glass insulator string detection image output after the model detects a glass insulator string on the inspection picture, inputting the glass insulator string detection image into a self-explosion insulator single-chip detection model, obtaining an image area where each self-explosion insulator is located, located on the glass insulator string detection image, of the model, finally determining the self-explosion number of the glass insulator according to the area number of the image area where each self-explosion insulator is located, and determining the continuous self-explosion number of the glass insulator according to the overlapping condition of the image areas where each self-explosion insulator is located. According to the scheme, intelligent self-explosion recognition and self-explosion information acquisition of the glass insulator in the inspection picture is realized based on the glass insulator string detection model and the self-explosion insulator single-chip detection model, the self-explosion information such as the total number of self-explosions and the continuous self-explosions of the glass insulator is accurately recognized and obtained, and the accuracy and the efficiency of the self-explosion recognition of the glass insulator are improved.
In some embodiments, after step S104, the method may further include the steps of:
and marking a picture area where a glass insulator string containing the self-explosion insulator is located on the power transmission line inspection picture, and displaying the self-explosion number and the continuous self-explosion number of the corresponding glass insulator.
With reference to fig. 2, in this embodiment, after the spontaneous explosion information of the glass insulator on the power transmission line inspection picture is obtained in the manner provided in each embodiment, a picture region where a glass insulator string including the spontaneous explosion insulator is located on the power transmission line inspection picture may be specifically marked, and the spontaneous explosion information such as the number of spontaneous explosions and the number of consecutive spontaneous explosions of the corresponding glass insulator is displayed on the power transmission line inspection picture, so as to present the spontaneous explosion information of the glass insulator obtained by image recognition and detection to a user.
In some embodiments, after step S104, the method may further include the steps of:
acquiring a power transmission line voltage grade corresponding to the power transmission line inspection picture; and judging the insulator spontaneous explosion degree of the power transmission line according to the voltage grade of the power transmission line, the spontaneous explosion number of the glass insulators and the continuous spontaneous explosion number.
In this embodiment, the self-explosion degree of the insulator may correspond to the degree of damage or influence of the self-explosion insulator on the power transmission line. Wherein, the number of insulator pieces of different transmission line voltage grades is different, for example, 10KV voltage is 1-2 pieces, 35KV voltage is 5 pieces, 110KV voltage is 7 pieces, 220KV voltage is 14-15 pieces, 500KV voltage is 24 pieces, the damage degree or influence degree of the glass insulator on the transmission lines with different voltage grades is different from the self-explosion number and the continuous self-explosion number, such as 2 self-explosion pieces, the method has the advantages that the 10KV line is possibly not insulated at all, but the 220KV line and the 500KV line are hardly influenced, so that the method finally judges the insulator spontaneous explosion degree of the power transmission line according to the power transmission line voltage grade corresponding to the power transmission line inspection picture, the spontaneous explosion quantity and the continuous spontaneous explosion quantity of the corresponding glass insulator, and provides richer, accurate and effective data support for the maintenance of the power transmission line.
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the application also provides a glass insulator spontaneous explosion identification processing device for realizing the glass insulator spontaneous explosion identification processing method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so that specific limitations in one or more embodiments of the glass insulator spontaneous explosion identification processing device provided below can be referred to the limitations on the glass insulator spontaneous explosion identification processing method in the foregoing, and details are not repeated herein.
In one embodiment, as shown in fig. 4, there is provided a glass insulator spontaneous explosion recognition processing apparatus, and the apparatus 400 may include:
the picture acquisition module 401 is configured to acquire a power transmission line inspection picture obtained by performing inspection shooting on a power transmission line by an unmanned aerial vehicle;
the string detection module 402 is used for inputting the power transmission line inspection picture into a pre-constructed glass insulator string detection model, and acquiring a glass insulator string detection image which is output after the glass insulator string detection is carried out on the power transmission line inspection picture by the glass insulator string detection model;
the single-chip detection module 403 is configured to input the glass insulator string detection image into a pre-constructed single-chip self-explosion insulator detection model, and obtain an image area where each self-explosion insulator is located on the glass insulator string detection image by the single-chip self-explosion insulator detection model;
the number determining module 404 is configured to determine the number of auto-explosions of the glass insulator according to the number of the image areas where the auto-explosions of the glass insulators are located, and determine the number of continuous auto-explosions of the glass insulator according to the overlapping condition between the image areas where the auto-explosions of the glass insulators are located.
In one embodiment, the apparatus 400 further comprises: the degree judgment module is used for acquiring the voltage grade of the power transmission line corresponding to the power transmission line inspection picture; and judging the insulator spontaneous explosion degree of the power transmission line according to the voltage grade of the power transmission line, the spontaneous explosion number of the glass insulators and the continuous spontaneous explosion number.
In one embodiment, the glass insulator string detection model is used for positioning an image area where a glass insulator string is located in the power transmission line inspection picture by adopting an S2A-Net rotation target detection algorithm and outputting a detection image of the glass insulator string; and the image area where the glass insulator string is positioned is marked by adopting a rotating rectangular frame.
In one embodiment, the single-chip detection module 403 is configured to capture a mask screenshot of the glass insulator string based on the glass insulator string detection image; zooming the glass insulator string mask screenshot to a preset size in a mode of same length and width zooming ratio to obtain a zoomed glass insulator string mask screenshot; and inputting the zoomed screen shot of the glass insulator string mask to the self-explosion insulator single-chip detection model so that the self-explosion insulator single-chip detection model can position the image area where each self-explosion insulator is located on the zoomed screen shot of the glass insulator string mask.
In one embodiment, the single-chip detection model of the self-explosion insulator is used for positioning an image area where each self-explosion insulator is located in the zoomed screenshot of the glass insulator string mask by adopting a yolov4 target detection algorithm; and marking the image area where each self-explosion insulator is positioned by adopting a horizontal rectangular frame.
In one embodiment, the apparatus 400 further comprises: and the picture marking module is used for marking a picture area where the glass insulator string containing the self-explosion insulator is positioned on the power transmission line inspection picture and displaying the self-explosion number and the continuous self-explosion number of the corresponding glass insulator.
All or part of each module in the glass insulator spontaneous explosion identification processing device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 5. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to realize a glass insulator spontaneous explosion identification processing method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring a power transmission line inspection picture obtained by the unmanned aerial vehicle inspecting and shooting the power transmission line; inputting the power transmission line inspection picture into a pre-constructed glass insulator string detection model, and acquiring a glass insulator string detection image output by the glass insulator string detection model after the glass insulator string detection is carried out on the power transmission line inspection picture; inputting the glass insulator string detection image into a pre-constructed single self-explosion insulator sheet detection model, and acquiring an image area where each self-explosion insulator is positioned on the glass insulator string detection image by the single self-explosion insulator sheet detection model; and determining the self-explosion number of the glass insulators according to the number of the image areas where the self-explosion insulators are located, and determining the continuous self-explosion number of the glass insulators according to the overlapping condition of the image areas where the self-explosion insulators are located.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring a power transmission line voltage grade corresponding to the power transmission line inspection picture; and judging the insulator spontaneous explosion degree of the power transmission line according to the voltage grade of the power transmission line, the spontaneous explosion number of the glass insulators and the continuous spontaneous explosion number.
In one embodiment, the glass insulator string detection model is used for positioning an image area where a glass insulator string is located in the power transmission line inspection picture by adopting an S2A-Net rotation target detection algorithm and outputting a detection image of the glass insulator string; and the image area where the glass insulator string is positioned is marked by adopting a rotating rectangular frame.
In one embodiment, the processor, when executing the computer program, further performs the steps of: intercepting to obtain a mask screenshot of the glass insulator string based on the glass insulator string detection image; zooming the glass insulator string mask screenshot to a preset size in a mode of same length and width zooming ratio to obtain a zoomed glass insulator string mask screenshot; and inputting the zoomed screen shot of the glass insulator string mask to the self-explosion insulator single-chip detection model so that the self-explosion insulator single-chip detection model can position the image area where each self-explosion insulator is located on the zoomed screen shot of the glass insulator string mask.
In one embodiment, the single-chip detection model of the self-explosion insulator is used for positioning an image area where each self-explosion insulator is located in the zoomed screenshot of the glass insulator string mask by adopting a yolov4 target detection algorithm; and marking the image area where each self-explosion insulator is positioned by adopting a horizontal rectangular frame.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and marking a picture area where a glass insulator string containing the self-explosion insulator is located on the power transmission line inspection picture, and displaying the self-explosion number and the continuous self-explosion number of the corresponding glass insulator.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring a power transmission line inspection picture obtained by the unmanned aerial vehicle inspecting and shooting the power transmission line; inputting the power transmission line inspection picture into a pre-constructed glass insulator string detection model, and acquiring a glass insulator string detection image output by the glass insulator string detection model after the glass insulator string detection is carried out on the power transmission line inspection picture; inputting the glass insulator string detection image into a pre-constructed single self-explosion insulator sheet detection model, and acquiring an image area where each self-explosion insulator is positioned on the glass insulator string detection image by the single self-explosion insulator sheet detection model; and determining the self-explosion number of the glass insulators according to the number of the image areas where the self-explosion insulators are located, and determining the continuous self-explosion number of the glass insulators according to the overlapping condition of the image areas where the self-explosion insulators are located.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring a power transmission line voltage grade corresponding to the power transmission line inspection picture; and judging the insulator spontaneous explosion degree of the power transmission line according to the voltage grade of the power transmission line, the spontaneous explosion number of the glass insulators and the continuous spontaneous explosion number.
In one embodiment, the glass insulator string detection model is used for positioning an image area where a glass insulator string is located in the power transmission line inspection picture by adopting an S2A-Net rotation target detection algorithm and outputting a detection image of the glass insulator string; and the image area where the glass insulator string is positioned is marked by adopting a rotating rectangular frame.
In one embodiment, the computer program when executed by the processor further performs the steps of: intercepting to obtain a mask screenshot of the glass insulator string based on the glass insulator string detection image; zooming the glass insulator string mask screenshot to a preset size in a mode of same length and width zooming ratio to obtain a zoomed glass insulator string mask screenshot; and inputting the zoomed screen shot of the glass insulator string mask to the self-explosion insulator single-chip detection model so that the self-explosion insulator single-chip detection model can position the image area where each self-explosion insulator is located on the zoomed screen shot of the glass insulator string mask.
In one embodiment, the single-chip detection model of the self-explosion insulator is used for positioning an image area where each self-explosion insulator is located in the zoomed screenshot of the glass insulator string mask by adopting a yolov4 target detection algorithm; and marking the image area where each self-explosion insulator is positioned by adopting a horizontal rectangular frame.
In one embodiment, the computer program when executed by the processor further performs the steps of: and marking a picture area where a glass insulator string containing the self-explosion insulator is located on the power transmission line inspection picture, and displaying the self-explosion number and the continuous self-explosion number of the corresponding glass insulator.
In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, performs the steps of:
acquiring a power transmission line inspection picture obtained by the unmanned aerial vehicle inspecting and shooting the power transmission line; inputting the power transmission line inspection picture into a pre-constructed glass insulator string detection model, and acquiring a glass insulator string detection image output by the glass insulator string detection model after the glass insulator string detection is carried out on the power transmission line inspection picture; inputting the glass insulator string detection image into a pre-constructed single self-explosion insulator sheet detection model, and acquiring an image area where each self-explosion insulator is positioned on the glass insulator string detection image by the single self-explosion insulator sheet detection model; and determining the self-explosion number of the glass insulators according to the number of the image areas where the self-explosion insulators are located, and determining the continuous self-explosion number of the glass insulators according to the overlapping condition of the image areas where the self-explosion insulators are located.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring a power transmission line voltage grade corresponding to the power transmission line inspection picture; and judging the insulator spontaneous explosion degree of the power transmission line according to the voltage grade of the power transmission line, the spontaneous explosion number of the glass insulators and the continuous spontaneous explosion number.
In one embodiment, the glass insulator string detection model is used for positioning an image area where a glass insulator string is located in the power transmission line inspection picture by adopting an S2A-Net rotation target detection algorithm and outputting a detection image of the glass insulator string; and the image area where the glass insulator string is positioned is marked by adopting a rotating rectangular frame.
In one embodiment, the computer program when executed by the processor further performs the steps of: intercepting to obtain a mask screenshot of the glass insulator string based on the glass insulator string detection image; zooming the glass insulator string mask screenshot to a preset size in a mode of same length and width zooming ratio to obtain a zoomed glass insulator string mask screenshot; and inputting the zoomed screen shot of the glass insulator string mask to the self-explosion insulator single-chip detection model so that the self-explosion insulator single-chip detection model can position the image area where each self-explosion insulator is located on the zoomed screen shot of the glass insulator string mask.
In one embodiment, the single-chip detection model of the self-explosion insulator is used for positioning an image area where each self-explosion insulator is located in the zoomed screenshot of the glass insulator string mask by adopting a yolov4 target detection algorithm; and marking the image area where each self-explosion insulator is positioned by adopting a horizontal rectangular frame.
In one embodiment, the computer program when executed by the processor further performs the steps of: and marking a picture area where a glass insulator string containing the self-explosion insulator is located on the power transmission line inspection picture, and displaying the self-explosion number and the continuous self-explosion number of the corresponding glass insulator.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. A glass insulator spontaneous explosion identification processing method is characterized by comprising the following steps:
acquiring a power transmission line inspection picture obtained by the unmanned aerial vehicle inspecting and shooting the power transmission line;
inputting the power transmission line inspection picture into a pre-constructed glass insulator string detection model, and acquiring a glass insulator string detection image output by the glass insulator string detection model after the glass insulator string detection is carried out on the power transmission line inspection picture;
inputting the glass insulator string detection image into a pre-constructed single self-explosion insulator sheet detection model, and acquiring an image area where each self-explosion insulator is positioned on the glass insulator string detection image by the single self-explosion insulator sheet detection model;
and determining the self-explosion number of the glass insulators according to the number of the image areas where the self-explosion insulators are located, and determining the continuous self-explosion number of the glass insulators according to the overlapping condition of the image areas where the self-explosion insulators are located.
2. The method according to claim 1, wherein after determining the number of spontaneous explosions of the glass insulator according to the number of the image areas where the respective self-explosion insulators are located and determining the number of continuous spontaneous explosions of the glass insulator according to the overlapping condition between the image areas where the respective self-explosion insulators are located, the method further comprises:
acquiring a power transmission line voltage grade corresponding to the power transmission line inspection picture;
and judging the insulator spontaneous explosion degree of the power transmission line according to the voltage grade of the power transmission line, the spontaneous explosion number of the glass insulators and the continuous spontaneous explosion number.
3. The method according to claim 1, wherein the glass insulator string detection model is used for positioning an image area where a glass insulator string in the power transmission line inspection picture is located by adopting an S2A-Net rotating target detection algorithm and outputting a detection image of the glass insulator string; and the image area where the glass insulator string is positioned is marked by adopting a rotating rectangular frame.
4. The method according to claim 3, wherein the inputting the glass insulator string detection image into a pre-constructed self-explosion insulator monolithic detection model comprises:
intercepting to obtain a mask screenshot of the glass insulator string based on the glass insulator string detection image;
zooming the glass insulator string mask screenshot to a preset size in a mode of same length and width zooming ratio to obtain a zoomed glass insulator string mask screenshot;
and inputting the zoomed screen shot of the glass insulator string mask to the self-explosion insulator single-chip detection model so that the self-explosion insulator single-chip detection model can position the image area where each self-explosion insulator is located on the zoomed screen shot of the glass insulator string mask.
5. The method according to claim 4, wherein the single-chip detection model of the self-explosion insulator is used for positioning an image area where each self-explosion insulator is located in the zoomed screenshot of the glass insulator string mask by adopting a yolov4 target detection algorithm; and marking the image area where each self-explosion insulator is positioned by adopting a horizontal rectangular frame.
6. The method according to any one of claims 1 to 5, wherein after determining the number of spontaneous explosions of the glass insulator according to the number of the image areas where the respective self-explosion insulators are located and determining the number of continuous spontaneous explosions of the glass insulator according to the overlapping condition between the image areas where the respective self-explosion insulators are located, the method further comprises:
and marking a picture area where a glass insulator string containing the self-explosion insulator is located on the power transmission line inspection picture, and displaying the self-explosion number and the continuous self-explosion number of the corresponding glass insulator.
7. The glass insulator spontaneous explosion recognition processing device is characterized by comprising:
the picture acquisition module is used for acquiring a power transmission line inspection picture obtained by the unmanned aerial vehicle inspecting and shooting the power transmission line;
the string detection module is used for inputting the power transmission line inspection picture into a pre-constructed glass insulator string detection model, and acquiring a glass insulator string detection image which is output after the glass insulator string detection is carried out on the power transmission line inspection picture by the glass insulator string detection model;
the single-chip detection module is used for inputting the glass insulator string detection image into a pre-constructed single-chip detection model of the self-explosion insulator, and acquiring an image area where each self-explosion insulator is positioned on the glass insulator string detection image by the single-chip detection model of the self-explosion insulator;
and the quantity determining module is used for determining the self-explosion quantity of the glass insulators according to the quantity of the image areas where the self-explosion insulators are located and determining the continuous self-explosion quantity of the glass insulators according to the overlapping condition of the image areas where the self-explosion insulators are located.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210043777.0A CN114266985A (en) | 2022-01-14 | 2022-01-14 | Glass insulator spontaneous explosion identification method, device, equipment, medium and program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210043777.0A CN114266985A (en) | 2022-01-14 | 2022-01-14 | Glass insulator spontaneous explosion identification method, device, equipment, medium and program product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114266985A true CN114266985A (en) | 2022-04-01 |
Family
ID=80832976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210043777.0A Pending CN114266985A (en) | 2022-01-14 | 2022-01-14 | Glass insulator spontaneous explosion identification method, device, equipment, medium and program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114266985A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115565118A (en) * | 2022-12-07 | 2023-01-03 | 南方电网数字电网研究院有限公司 | Method for identifying single hanging point and single string of cross crossing point of power transmission line |
-
2022
- 2022-01-14 CN CN202210043777.0A patent/CN114266985A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115565118A (en) * | 2022-12-07 | 2023-01-03 | 南方电网数字电网研究院有限公司 | Method for identifying single hanging point and single string of cross crossing point of power transmission line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11209837B2 (en) | Method and device for generating a model of a to-be reconstructed area and an unmanned aerial vehicle flight trajectory | |
| JP2012103790A (en) | Object display device and object display method | |
| CN114463637B (en) | Winter wheat remote sensing identification analysis method and system based on deep learning | |
| CN115984273B (en) | Road disease detection method, device, computer equipment and readable storage medium | |
| CN112233062A (en) | Surface feature change detection method, electronic device, and storage medium | |
| CN114037907A (en) | Detection method and device for power transmission line, computer equipment and storage medium | |
| CN115984226A (en) | Insulator defect detection method, device, medium, and program product | |
| CN111815576B (en) | Method, device, equipment and storage medium for detecting corrosion condition of metal part | |
| CN116416626B (en) | Method, device, equipment and storage medium for acquiring circular seal data | |
| CN114266985A (en) | Glass insulator spontaneous explosion identification method, device, equipment, medium and program product | |
| CN114387289B (en) | Semantic segmentation method and device for three-dimensional point cloud of power transmission and distribution overhead line | |
| CN115457408A (en) | Land monitoring method and device, electronic equipment and medium | |
| CN108268138A (en) | Processing method, device and the electronic equipment of augmented reality | |
| CN115526846A (en) | Joint detection-based crack detection method and device and computer equipment | |
| CN115809982B (en) | Method, device and system for detecting cell crush injury | |
| WO2021240327A1 (en) | Modelling georeferenced data for civil infrastructure asset management | |
| CN117011658A (en) | Image processing method, apparatus, device, storage medium, and computer program product | |
| CN116503347A (en) | Method and device for detecting leakage oil of power system and training model and computer equipment | |
| CN115908318A (en) | Power line sag determination method, device, equipment, medium and product | |
| CN114238541A (en) | Sensitive target information acquisition method and device and computer equipment | |
| CN108052585B (en) | Method for judging dynamic target in complex environment | |
| CN110503685B (en) | Data processing method and equipment | |
| CN116523803B (en) | Image processing method, shadow removing device, apparatus, and storage medium | |
| CN115359056B (en) | Method and device for detecting dividing cells and computer equipment | |
| CN116703822A (en) | Transmission line insulation damage detection method, model training method, device and equipment |
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 |