CN115240092A - Transmission tower patrol detection method and device, electronic equipment and storage medium - Google Patents
Transmission tower patrol detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115240092A CN115240092A CN202210949926.XA CN202210949926A CN115240092A CN 115240092 A CN115240092 A CN 115240092A CN 202210949926 A CN202210949926 A CN 202210949926A CN 115240092 A CN115240092 A CN 115240092A
- Authority
- CN
- China
- Prior art keywords
- detection
- image
- connecting part
- part detection
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/225—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on a marking or identifier characterising the area
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a power transmission tower patrol method, a device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a patrol image of a transmission tower; inputting the inspection image into a connection part detection model for connection part detection to obtain a connection part detection target image of the transmission tower; inputting a connecting part detection target image into an annular pin detection model for annular pin detection to obtain an annular pin detection result; and mapping the detection result of the annular pin back to the inspection image to obtain the inspection result of the transmission tower. The method and the device for detecting the annular pin in the inspection image can automatically detect whether the annular pin exists in the inspection image by using the connecting part detection model and the annular pin detection model, and do not need to manually detect whether the annular pin exists in the inspection image of the transmission tower, so that the speed and the accuracy of replacing the R-shaped pin of the connecting part of the transmission tower with the annular pin are improved, and the time cost of replacing the R-shaped pin of the connecting part of the transmission tower with the annular pin is reduced.
Description
Technical Field
The embodiment of the invention relates to a target detection technology, in particular to a method and a device for detecting an annular pin of a transmission tower image, electronic equipment and a storage medium.
Background
In order to ensure normal operation of the power transmission line, the unmanned aerial vehicle is required to be used for periodically shooting in the routing inspection area to obtain images of the power transmission towers, and then the unmanned aerial vehicle is manually inspected to determine whether pins are installed on connecting parts of the power transmission towers.
The pins used by the existing transmission tower mainly comprise an R-shaped pin and an annular pin. R type round pin is less, and unmanned aerial vehicle shoots can because the angle problem obtains the transmission tower image of unable discernment R type round pin, causes the erroneous judgement whether to install R type round pin of the adapting unit of inspection transmission tower. And unmanned aerial vehicle can not shoot the shaft tower image of unable discernment ring type round pin because of the angle problem when shooing, can reduce the misjudgement rate whether the adapting unit of inspection transmission tower installs the ring type round pin in other words. Therefore, whether the annular pin exists in the inspection image of the transmission tower needs to be manually checked, and then the R-shaped pin of the connecting component of the transmission tower is replaced by the annular pin.
However, the accuracy of manually checking whether the ring pins exist in the patrol image of the transmission tower is low, the checking speed is slow, the speed of replacing the R-shaped pins of the connecting components of the transmission tower with the ring pins is reduced, and the time cost of replacing the R-shaped pins of the connecting components of the transmission tower with the ring pins is increased.
Disclosure of Invention
The embodiment of the invention provides a power transmission tower patrol inspection method, a device, electronic equipment and a storage medium, which can improve the speed and accuracy of replacing an R-shaped pin of a connecting component of a power transmission tower with an annular pin and reduce the time cost of replacing the R-shaped pin of the connecting component of the power transmission tower with the annular pin.
In a first aspect, an embodiment of the present invention provides a power transmission tower inspection method, where the method includes:
acquiring a patrol image of a transmission tower;
inputting the inspection image into a connecting part detection model for detecting a connecting part to obtain a detection target image of the connecting part of the transmission tower;
inputting the connecting part detection target image into an annular pin detection model for annular pin detection to obtain an annular pin detection result;
and mapping the detection result of the ring pin back to the inspection image to obtain the inspection result of the transmission tower.
In a second aspect, an embodiment of the present invention provides a transmission tower inspection device, where the device includes:
the inspection image acquisition module is used for acquiring an inspection image of the transmission tower;
the target image generation module is used for inputting the inspection image into a connecting part detection model for connecting part detection to obtain a connecting part detection target image of the transmission tower;
the annular pin detection result generation module is used for inputting the connection part detection target image into an annular pin detection model for annular pin detection to obtain an annular pin detection result;
and the inspection result generation module is used for mapping the detection result of the annular pin back to the inspection image to obtain the inspection result of the transmission tower.
In a third aspect, the embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the method for patrolling a transmission tower according to any one of the embodiments of the present invention is implemented.
In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the transmission tower patrol method according to any one of the embodiments of the present invention.
In the embodiment of the invention, the patrol image of the transmission tower can be obtained; inputting the inspection image into a connecting part detection model for detecting a connecting part to obtain a detection target image of the connecting part of the transmission tower; inputting a connecting part detection target image into an annular pin detection model for annular pin detection to obtain an annular pin detection result; and mapping the detection result of the annular pin back to the inspection image to obtain the inspection result of the transmission tower. The method and the device for detecting the annular pin in the inspection image can automatically detect whether the annular pin exists in the inspection image by using the connecting part detection model and the annular pin detection model, do not need to manually detect whether the annular pin exists in the inspection image of the transmission tower, solve the problems of low accuracy and low inspection speed of manually detecting whether the annular pin exists in the inspection image of the transmission tower, improve the speed and accuracy of replacing the R-shaped pin of the connecting part of the transmission tower with the annular pin, and reduce the time cost of replacing the R-shaped pin of the connecting part of the transmission tower with the annular pin.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic flowchart of a method for training a connection detection model according to an embodiment of the present invention;
FIG. 2 is a schematic view of a connection provided by an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a method for training a default cotter detection model according to an embodiment of the present invention;
FIG. 4 is a schematic view of a ring pin provided by embodiments of the present invention;
FIG. 5 is a schematic flow chart of a joint training method of a connection portion detection model and a ring pin detection model according to an embodiment of the present invention;
fig. 6 is a schematic flow chart of a transmission tower inspection method according to an embodiment of the present invention;
fig. 7 is another schematic flow chart of a transmission tower inspection method according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a transmission tower inspection device according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not construed as indicating or implying relative importance.
Because the connection part detection model and the ring pin detection model need to be used in the transmission tower inspection method provided by the embodiment of the invention, and the connection part detection model and the ring pin detection model need to be trained by the corresponding preset connection part detection model, the preset ring pin detection model and the joint training of the connection part detection model and the ring pin detection model before practical application, before explaining the transmission tower inspection method provided by the embodiment of the invention, the connection part detection model training method, the ring pin detection model training method, the connection part detection model and the ring pin detection model joint training method are further explained, and the training processes in the three stages are specifically as follows:
fig. 1 is a schematic flow chart of a training method of a connection portion detection model according to an embodiment of the present invention, and as shown in fig. 1, the training method of the connection portion detection model may specifically include the following steps:
Wherein, the connecting part can be understood as a component of a transmission tower with a ring pin installed therein, fig. 2 is a schematic view of the connecting part provided by the embodiment of the invention, as shown in fig. 2, the connecting part 2 in fig. 2 is a component with a ring pin installed therein; the preset connection part can be understood as a predetermined connection part in the inspection image; the preset connection part detection model can be understood as a training model of the connection part detection model; the first training image may be understood as an image in which the preset connection portion is artificially marked with position information.
Specifically, the first training image may be input into a preset connection portion detection model, and after the preset connection portion is detected through a target detection algorithm adopted by the preset connection portion detection model, the preset connection portion detection model may output a detection frame of the preset connection portion. In order to improve the recall rate and the model precision of the connecting part detection model, the target detection algorithm adopted by the preset connecting part detection model can be a two-stage target detection algorithm which is better in model precision, and the two-stage target detection algorithm can adopt a Faster R-CNN algorithm or a Cascade R-CNN algorithm.
Here, the Intersection-over-Union (IoU) can be understood as an overlapping ratio of a plurality of frames to each other.
Specifically, the overlap area of the mark frame and the detection frame may be calculated according to the upper left corner coordinate and the lower right corner coordinate of the overlap portion of the mark frame and the detection frame, the areas of the mark frame and the detection frame may be calculated according to the coordinates of the mark frame and the coordinates of the detection frame, and the overlap area, the area of the mark frame, and the area of the detection frame may be calculated by substituting the overlap area, the area of the mark frame, and the area of the detection frame into a calculation formula of the cross ratio, so that the cross ratio of the mark frame and the detection frame may be obtained.
And 103, determining a target frame from the detection frames based on the intersection ratio.
The target frame may be a detection frame in which the value of the intersection ratio between the detection frame and the marker frame exceeds the value of the set intersection ratio.
Specifically, whether the value of the intersection ratio of the detection frame and the mark frame exceeds the value of the set intersection ratio may be determined by comparing the magnitude of the value of the intersection ratio of the detection frame and the mark frame with the value of the set intersection ratio, and if the value of the intersection ratio of the detection frame and the mark frame exceeds the value of the set intersection ratio, the detection frame whose value of the intersection ratio of the detection frame and the mark frame exceeds the value of the set intersection ratio may be determined as the target frame.
For example, if the intersection ratio is set to 0.3 and the intersection ratio of the detection frame and the marker frame is set to 0.5, it may be determined that the intersection ratio of the detection frame and the marker frame exceeds the set intersection ratio, and the detection frame may be determined as the target frame.
And 104, determining a loss function of the prediction connection part detection model based on the target frame and the mark frame.
And 105, optimizing the model parameters of the preset connecting part detection model based on the loss function to obtain the connecting part detection model.
Specifically, the model parameters of the preset connection detection model may be continuously optimized based on the loss function, so that the model parameters of the preset connection detection model are adjusted to be optimal, and thus the preset connection detection model with the model parameters adjusted to be optimal may be determined as the connection detection model used in the power transmission tower inspection method in practical applications.
Fig. 3 is a schematic flow chart of a method for training a preset ring pin detection model according to an embodiment of the present invention, and as shown in fig. 3, the method for training the preset ring pin detection model specifically includes the following steps:
Fig. 4 is a schematic view of a ring pin according to an embodiment of the present invention, as shown in fig. 4, the ring pin in fig. 4 may be used to pass through a pin hole to prevent a nut from falling off, and a preset ring pin may be understood as a predetermined ring pin in a polling image; the preset annular pin detection model can be understood as a training model of the annular pin detection model; the second training image may be understood as an image in which the preset ring pin is marked with position information by an artificial person.
Specifically, the second training image may be input to the preset ring pin detection model, and after the preset ring pin is detected by the target detection algorithm adopted by the preset ring pin detection model, the preset ring pin detection model may output a detection frame of the preset ring pin. In order to improve the detection efficiency of the ring pin detection model, the target detection algorithm adopted by the preset ring pin detection model may be a one-stage target detection algorithm which is better in model precision, the one-stage target detection algorithm may adopt a YOLOv3 algorithm, and an image feature extraction network in the YOLOv3 may adopt a RetinaNet network structure.
And step 304, determining a loss function of the preset ring pin detection model based on the target frame and the mark frame.
And 305, optimizing model parameters of a preset ring pin detection model based on a loss function to obtain the ring pin detection model.
Specifically, the model parameters of the preset looped pin detection model may be continuously optimized based on the loss function, so that the model parameters of the preset looped pin detection model are adjusted to be optimal, and thus the preset looped pin detection model with the model parameters adjusted to be optimal may be determined as the connection part detection model used in the power transmission tower inspection method in practical applications.
Fig. 5 is a schematic flow chart of a joint training method for a connection portion detection model and a ring pin detection model according to an embodiment of the present invention, and as shown in fig. 5, the joint training method for the connection portion detection model and the ring pin detection model may specifically include the following steps:
And 502, inputting a connecting part detection training image into a preset annular pin detection model for annular pin detection to obtain a detection frame.
And step 504, determining a target frame from the detection frames based on the intersection ratio.
And 505, determining a loss function of the preset annular pin detection model based on the target frame and the mark frame, and determining a loss function of the preset connecting part detection model based on the target frame and the mark frame.
After model training in the three stages is completed, model testing can be performed on the connecting part detection model and the annular pin detection model obtained through training, the test image in the inspection image can be sequentially input into the connecting part detection model and the annular pin detection model to obtain a detection result, the detection result is manually checked and fed back to the connecting part label library and the annular pin label library to perform iterative training, model accuracy of each detection model is continuously tested, and when the model accuracy of each detection model meets the requirement of practical application, the obtained model can be put into practical application.
After the model training process and the model testing process are completed, a connection part detection model and a ring pin detection model which are practically applied in the transmission tower inspection method can be obtained. The following describes in detail how the power transmission tower inspection method provided by the embodiment of the present invention is performed using the connection portion detection model and the ring pin detection model. Fig. 6 is a schematic flow chart of a transmission tower inspection method according to an embodiment of the present invention, where the method may be executed by the transmission tower inspection device according to the embodiment of the present invention, and the device may be implemented in a software and/or hardware manner. In a particular embodiment, the apparatus may be integrated in an electronic device. The following embodiments will be described by taking as an example that the apparatus is integrated in an electronic device, and referring to fig. 6, the method may specifically include the following steps:
The inspection image can be understood as an image of the transmission tower shot by inspection shooting equipment when inspection personnel inspects.
Specifically, the unmanned aerial vehicle carrying shooting equipment can be used for shooting the inspection image of the transmission tower according to the inspection route, and then the inspection image of the transmission tower stored in the shooting equipment can be obtained.
The connection part detection target image of the transmission tower can be understood as a connection part detection image for detecting the ring pin.
Specifically, the inspection image may be input into the connection portion detection model to perform connection portion detection, so as to obtain a connection portion detection image corresponding to the connection portion detection model, and then a connection portion detection target image may be screened from the connection portion detection image based on the intersection ratio between the connection portion detection images and the confidence of the connection portion detection image.
Exemplarily, the inspection image may be input into the connection portion detection model for connection portion detection, so as to obtain 3 connection portion detection images corresponding to the connection portion detection model; the intersection ratio of 3 connecting part detection images is 0.2, 0.4, and the confidence coefficient of 0.5,3 connecting part detection images is 0.4, 0.6, and 0.7, so that the connecting part detection images with the intersection ratio greater than 0.3 and the confidence coefficient greater than 0.5 can be screened out, and the connecting part detection images with the intersection ratio greater than 0.3 and the confidence coefficient greater than 0.5 are determined as connecting part detection target images.
The ring pin detection result can comprise position information, confidence degree information and characteristic information of the target ring pin in the connecting part detection target image. The target ring pin may be understood as a ring pin in the connection portion detection target image. The characteristic information may be understood as size information of the target ring pin. The position information may be understood as coordinate information of the connection part detection target image of the target ring pin in the patrol image.
For example, if the target ring pin is a, the connection part detection target image may be input into a ring pin detection model for ring pin detection, and position information, confidence information, and feature information of the target ring pin a in the connection part detection target image are obtained.
And step 604, mapping the detection result of the ring pin back to the inspection image to obtain the inspection result of the transmission tower.
The inspection result of the transmission tower can be understood as a marked image obtained by mapping the detection result of the ring pin back to the inspection image, and the marked image can include position information, confidence information and characteristic information of a target ring pin in a target image detected by the connecting part.
Specifically, the position information, the confidence information and the characteristic information of the target ring pin in the target image detected at the connecting part can be mapped back to the inspection image, that is, the position information, the confidence information and the characteristic information of the target ring pin in the target image detected at the connecting part are marked in the inspection image, so that the inspection result of the transmission tower is obtained. The inspection personnel can determine that the annular pin is arranged in the inspection image of the transmission tower by judging whether the inspection result of the transmission tower is marked by the position information, the confidence information and the characteristic information of the target annular pin.
In the embodiment of the invention, the inspection image of the transmission tower can be obtained; inputting the inspection image into a connection part detection model for connection part detection to obtain a connection part detection target image of the transmission tower; inputting a connecting part detection target image into an annular pin detection model for annular pin detection to obtain an annular pin detection result; and mapping the detection result of the ring pin back to the inspection image to obtain the inspection result of the transmission tower. The method and the device for detecting the annular pin in the inspection image can automatically detect whether the annular pin exists in the inspection image by using the connecting part detection model and the annular pin detection model, do not need to manually detect whether the annular pin exists in the inspection image of the transmission tower, solve the problems of low accuracy and low inspection speed of manually detecting whether the annular pin exists in the inspection image of the transmission tower, improve the speed and accuracy of replacing the R-shaped pin of the connecting part of the transmission tower with the annular pin, and reduce the time cost of replacing the R-shaped pin of the connecting part of the transmission tower with the annular pin.
The detection model of the connecting part in the inspection method of the transmission tower provided by the embodiment of the invention can comprise a first connecting part detection model and a second connecting part detection model, the detection algorithm adopted by the first connecting part detection model and the detection algorithm adopted by the second connecting part detection model can be different, the detection algorithm adopted by the first connecting part detection model can be a Faster R-CNN algorithm, and the detection algorithm adopted by the second connecting part detection model can be a Cascade R-CNN algorithm. The transmission tower patrol method provided by the embodiment of the present invention is further described below, and as shown in fig. 7, fig. 7 is another schematic flow diagram of the transmission tower patrol method provided by the embodiment of the present invention, and specifically may include the following steps:
and 701, acquiring an inspection image of the transmission tower.
Specifically, the inspection image may be input into the first connection detection model for connection detection to obtain first connection detection candidate images, a first connection detection intermediate image may be determined from the first connection detection candidate images based on a cross ratio between the first connection detection candidate images, and the first connection detection image may be screened from the first connection detection intermediate image according to a target confidence of the first connection detection intermediate image.
The target confidence of the first connection part for detecting the intermediate image can be obtained according to the following method: and multiplying the original confidence coefficient of the first connection part detection intermediate image by the weight of the first connection part detection model to obtain the target confidence coefficient of the first connection part detection intermediate image. The original confidence of the first connection detection intermediate image may be understood as the confidence of the first connection detection candidate image.
Further, the inspection image may be input into a first connection detection model for connection detection to obtain first connection detection candidate images, based on the intersection ratio between the first connection detection candidate images, a first connection detection candidate image in which the intersection ratio between the first connection detection candidate images exceeds the set intersection ratio is determined from the first connection detection candidate images, and the first connection detection candidate image in which the intersection ratio between the first connection detection candidate images exceeds the set intersection ratio is determined as a first connection detection intermediate image; then, according to the target confidence of the first connection portion detection intermediate image, a first connection portion detection intermediate image with a target confidence exceeding the set confidence may be screened out from the first connection portion detection intermediate image, and the first connection portion detection intermediate image with the target confidence exceeding the set confidence may be determined as the first connection portion detection image.
Exemplarily, if the weight of the first connection portion detection model is 0.4, the set intersection ratio is 0.3, and the set confidence is 0.3, the inspection image is input into the first connection portion detection model to perform connection portion detection, and first connection portion detection candidate images are obtained, namely, A1, A2, and A3, respectively, the intersection ratio between A1 and A2 is 0.3, the intersection ratio between A2 and A3 is 0.5, and the intersection ratio between A3 and A1 is 0.6; the confidence coefficient of A1 is 0.5, the confidence coefficient of A2 is 0.6, and the confidence coefficient of A3 is 0.9; the first connection portion detection candidate images (A2, A3) whose intersection ratio between the first connection portion detection candidate images exceeds the set intersection ratio may be determined as the first connection portion detection intermediate images P1, P2 from among the first connection portion detection candidate images based on the intersection ratio between the first connection portion detection candidate images; the confidence of the original confidence level A2 of the P1 and the confidence of the original confidence level A3 of the P2 can be obtained by a target confidence calculation method, the target confidence of the P1 is 0.24, the target confidence of the P2 is 0.36, then a first connection part detection intermediate image (P2) with the target confidence exceeding the set confidence can be screened from the P1 and the P2 and is the P2, and the first connection part detection intermediate image (P2) with the target confidence exceeding the set confidence is determined to be the first connection part detection image S1.
And 703, inputting the inspection image into the second connecting part detection model for connecting part detection to obtain a second connecting part detection image corresponding to the second connecting part detection model.
Specifically, the inspection image is input into a second connecting part detection model to perform connecting part detection to obtain second connecting part detection candidate images, a second connecting part detection intermediate image is determined from the second connecting part detection candidate images based on the intersection between the second connecting part detection candidate images, and the second connecting part detection image is screened from the second connecting part detection intermediate images according to the target confidence of the second connecting part detection intermediate image.
The target confidence of the second connecting part detection intermediate image can be obtained according to the following method: and multiplying the original confidence coefficient of the second connecting part detection intermediate image by the weight of the second connecting part detection model to obtain the target confidence coefficient of the second connecting part detection intermediate image.
The sum of the weight of the first connection portion detection model and the weight of the second connection portion detection model is 1.
Further, the inspection image may be input to a second join detection model for join detection to obtain second join detection candidate images, a second join detection candidate image in which the sum of the sums of the second join detection candidate images exceeds a set sum is determined from the second join detection candidate images based on the sum of the second join detection candidate images, and the second join detection candidate image in which the sum of the sums of the second join detection candidate images exceeds the set sum is determined as a second join detection intermediate image; then, a second connecting part detection intermediate image with the target confidence degree exceeding the set confidence degree may be screened out from the second connecting part detection intermediate image according to the target confidence degree of the second connecting part detection intermediate image, and the second connecting part detection intermediate image with the target confidence degree exceeding the set confidence degree may be determined as the second connecting part detection image.
Illustratively, if the weight of the second connecting part detection model is 0.6, the set intersection ratio is 0.3, and the set confidence is 0.3, inputting the inspection image into the second connecting part detection model for connecting part detection to obtain second connecting part detection candidate images which are respectively B1, B2 and B3, the intersection ratio between B1 and B2 is 0.7, the intersection ratio between B2 and B3 is 0.3, and the intersection ratio between B3 and B1 is 0.9; the confidence coefficient of B1 is 0.5, the confidence coefficient of B2 is 0.6, and the confidence coefficient of B3 is 0.8; the second joint detection candidate images whose intersection ratio between the respective second joint detection candidate images exceeds the set intersection ratio may be determined as B1, B3 from among the second joint detection candidate images based on the intersection ratio between the respective second joint detection candidate images, and the second joint detection candidate images (B1, B3) whose intersection ratio between the second joint detection candidate images exceeds the set intersection ratio may be determined as the second joint detection intermediate images P3, P4; the original confidence of the P3, namely the confidence of the B1, and the original confidence of the P4, namely the confidence of the B3, can be obtained by a target confidence calculation method, the target confidence of the P3 is 0.3, the target confidence of the P4 is 0.48, then a second connecting part detection intermediate image (P4) with the target confidence exceeding the set confidence can be screened from the P3 and the P4, and the second connecting part detection intermediate image (P4) with the target confidence exceeding the set confidence is determined to be a second connecting part detection image S2.
Specifically, the first connection portion detection image and the second connection portion detection image may be mapped onto the same image, so as to obtain a connection portion detection mapping image; a joint detection target image is determined from the joint detection map images based on the intersection ratio of the joint detection map images. Here, the connection portion detection map image may be understood as an image of a detection frame including the first connection portion detection image and the second connection portion detection image.
Further, a connection portion detection map image in which the intersection ratio of the connection portion detection map images is larger than the set intersection ratio may be determined from the connection portion detection map images based on the intersection ratio of the connection portion detection map images, and a connection portion detection map image in which the intersection ratio is larger than the set intersection ratio may be determined as the connection portion detection target image.
For example, if the first connection portion detection image is S1, the second connection portion detection image is S2, and the set intersection ratio is 0.3, S1 and S2 may be mapped onto the same image to obtain a connection portion detection mapping image; the intersection ratio of S1 and S2 in the connection portion detection map image is 0.5, it may be determined that the intersection ratio of S1 and S2 exceeds the set intersection ratio, and S1 and S2 may be determined as the connection portion detection target image.
Because the characteristics of ring round pin compare with traditional R type pin, the ring round pin has unique circular shape characteristic, even with unmanned aerial vehicle shooting, the picture of shooting at different angles all can see circular shape. Therefore, the embodiment of the invention adds the circular feature as the prior knowledge into the feature extraction function of the feature extraction network, thereby improving the feature extraction capability of the circular feature extraction of the feature extraction network; wherein the circle extraction function is as follows:
x＝x 0 +r cosθ
y＝y 0 +r sinθ
in the above formula, r can represent radius, theta is a parameter, theta is more than or equal to 0 and less than or equal to 2 pi, and x 0 、y 0 As the circle center, x and y are independent variables.
The annular pin detection model can adopt a Yolov3 algorithm, and the Yolov3 algorithm can comprise a target detection function and a circular feature extraction function.
And step 706, mapping the position information, the confidence information and the characteristic information of the target ring pin in the connecting part detection target image back to the inspection image to obtain the position information, the confidence information and the characteristic information of the target ring pin in the inspection image.
For example, if the ring pin detection result is the position information (L), the confidence information (0.8) and the feature information (the radius of the ring pin is 2 cm) of the target ring pin a in the connection portion detection target image S1, the position information, the confidence information and the feature information of the target ring pin a in the connection portion detection target image S1 may be mapped back to the inspection image, so as to obtain the position information, the confidence information and the feature information of the target ring pin in the inspection image. And the patrol personnel can see the position information, confidence information and characteristic information marks of the target annular pin A in the patrol image of the transmission tower, and then determine that the annular pin is in the patrol image of the transmission tower.
In the embodiment of the invention, whether the annular pin exists in the inspection image can be automatically detected by using the connecting part detection model and the annular pin detection model, the inspection image of the transmission tower does not need to be manually inspected to determine whether the annular pin exists, the problems of low accuracy and low inspection speed of manually inspecting whether the annular pin exists in the inspection image of the transmission tower are solved, the speed and accuracy of replacing the R-shaped pin of the connecting part of the transmission tower with the annular pin are improved, and the time cost of replacing the R-shaped pin of the connecting part of the transmission tower with the annular pin is reduced.
Fig. 8 is a schematic structural diagram of a transmission tower inspection device provided in the embodiment of the present invention, where the device is suitable for executing the transmission tower inspection method provided in the embodiment of the present invention. As shown in fig. 8, the apparatus may specifically include:
an inspection image acquisition module 801, configured to acquire an inspection image of a transmission tower;
a target image generation module 802, configured to input the inspection image into a connection detection model for connection detection, so as to obtain a detection target image of a connection of the transmission tower;
a ring pin detection result generation module 803, configured to input the connection portion detection target image into a ring pin detection model for ring pin detection, so as to obtain a ring pin detection result;
and the inspection result generating module 804 is configured to map the ring pin detection result back to the inspection image to obtain an inspection result of the transmission tower.
Optionally, the connection portion detection model includes a first connection portion detection model and a second connection portion detection model, and a detection algorithm adopted by the first connection portion detection model is different from a detection algorithm adopted by the second connection portion detection model;
the target image generation module 802 is specifically configured to:
inputting the inspection image into the first connection part detection model for connection part detection to obtain a first connection part detection image corresponding to the first connection part detection model;
inputting the inspection image into the second connecting part detection model for connecting part detection to obtain a second connecting part detection image corresponding to the second connecting part detection model;
determining the connection portion detection target image according to the first connection portion detection image and the second connection portion detection image.
Alternatively, the first and second liquid crystal display panels may be,
target image generation module 802 will patrol and examine the image input first connecting portion detection model is the connecting portion detection, obtains first connecting portion detection image that first connecting portion detection model corresponds includes: inputting the inspection image into the first connection part detection model for connection part detection to obtain first connection part detection candidate images, determining first connection part detection intermediate images from the first connection part detection candidate images based on the intersection and comparison between the first connection part detection candidate images, and screening the first connection part detection images from the first connection part detection intermediate images according to the target confidence coefficient of the first connection part detection intermediate images;
the target image generation module 802 inputs the inspection image into the second connection portion detection model for connection portion detection, and obtains a second connection portion detection image corresponding to the second connection portion detection model, including: inputting the inspection image into the second connecting part detection model for connecting part detection to obtain second connecting part detection candidate images, determining second connecting part detection intermediate images from the second connecting part detection candidate images based on the intersection and comparison of the second connecting part detection candidate images, and screening the second connecting part detection images from the second connecting part detection intermediate images according to the target confidence coefficient of the second connecting part detection intermediate images.
Alternatively,
the target confidence of the first connection part detection intermediate image is obtained according to the following method: multiplying the original confidence coefficient of the first connection part detection intermediate image by the weight of the first connection part detection model to obtain a target confidence coefficient of the first connection part detection intermediate image;
the target confidence of the second connecting part for detecting the intermediate image is obtained according to the following method: and multiplying the original confidence coefficient of the second connecting part detection intermediate image by the weight of the second connecting part detection model to obtain the target confidence coefficient of the second connecting part detection intermediate image.
Optionally, the target image generation module 802 determines the connection portion detection target image according to the first connection portion detection image and the second connection portion detection image, including:
mapping the first connection part detection image and the second connection part detection image onto the same image to obtain a connection part detection mapping image;
the joint detection target image is determined from the joint detection map images based on the intersection ratio of the joint detection map images.
Optionally, the circular pin detection model includes a circular extraction function and a target detection function;
the ring pin detection result generation module 803 is specifically configured to:
inputting the connecting part detection target image into the annular pin detection model, so as to extract an annular pin characteristic image from the connecting part detection target image by using the circular extraction function, and performing annular pin detection on the annular pin characteristic image by using the target detection function to obtain an annular pin detection result.
Optionally, the ring pin detection result includes position information, confidence information and feature information of a target ring pin in the connection part detection target image;
the inspection result generating module 804 is specifically configured to:
and mapping the position information, the confidence coefficient information and the characteristic information of the target annular pin in the target image detected by the connecting part back to the inspection image to obtain the position information, the confidence coefficient information and the characteristic information of the target annular pin in the inspection image.
Optionally, the connection portion detection model and the ring pin detection model are obtained through the following training mode:
inputting a training image into a preset connecting part detection model for detecting a connecting part to obtain a connecting part detection training image, wherein the training image comprises a preset annular pin positioned at the preset connecting part and a mark frame of the preset annular pin;
inputting the connecting part detection training image into a preset annular pin detection model for annular pin detection to obtain a detection frame;
determining the intersection ratio of the marking frame and the detection frame;
determining a target frame from the detection frames based on the intersection ratio;
determining a loss function of the preset ring pin detection model based on the target frame and the mark frame, and determining a loss function of the preset connection part detection model based on the target frame and the mark frame;
optimizing model parameters of the preset annular pin detection model based on a loss function of the preset annular pin detection model to obtain the annular pin detection model; and optimizing the model parameters of the preset connecting part detection model based on the loss function of the preset connecting part detection model to obtain the connecting part detection model.
It is obvious to those skilled in the art that, for convenience and simplicity of description, the foregoing division of each functional module is merely used as an example, and in practical applications, the above function distribution may be performed by different functional modules as needed, that is, the internal structure of the apparatus is divided into different functional modules to perform all or part of the above described functions. For the specific working process of the functional module, reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.
The device provided by the embodiment of the invention can acquire the inspection image of the transmission tower; inputting the inspection image into a connection part detection model for connection part detection to obtain a connection part detection target image of the transmission tower; inputting a connecting part detection target image into an annular pin detection model for annular pin detection to obtain an annular pin detection result; and mapping the detection result of the annular pin back to the inspection image to obtain the inspection result of the transmission tower. The method and the device for detecting the annular pin in the inspection image can automatically detect whether the annular pin exists in the inspection image by using the connecting part detection model and the annular pin detection model, do not need to manually detect whether the annular pin exists in the inspection image of the transmission tower, solve the problems of low accuracy and low inspection speed of manually detecting whether the annular pin exists in the inspection image of the transmission tower, improve the speed and accuracy of replacing the R-shaped pin of the connecting part of the transmission tower with the annular pin, and reduce the time cost of replacing the R-shaped pin of the connecting part of the transmission tower with the annular pin.
The embodiment of the invention also provides electronic equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the program, the transmission tower patrol inspection method provided by any one of the embodiments is realized.
The embodiment of the invention further provides a computer readable medium, on which a computer program is stored, and when the program is executed by a processor, the method for inspecting the transmission tower provided by any one of the embodiments is implemented.
Referring now to FIG. 9, shown is a block diagram of a computer system 1000 suitable for use with the electronic device implementing an embodiment of the present invention. The electronic device shown in fig. 9 is only an example, and should not bring any limitation to the functions and the range of use of the embodiment of the present invention.
As shown in fig. 9, the computer system 1000 includes a Central Processing Unit (CPU) 1001 that can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 1002 or a program loaded from a storage section 1008 into a Random Access Memory (RAM) 1003. In the RAM 1003, various programs and data necessary for the operation of the computer system 1000 are also stored. The CPU 1001, ROM 1002, and RAM 1003 are connected to each other via a bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.
The following components are connected to the I/O interface 1005: an input section 1006 including a keyboard, a mouse, and the like; an output section 1007 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 1008 including a hard disk and the like; and a communication section 1009 including a network interface card such as a LAN card, a modem, or the like. The communication section 1009 performs communication processing via a network such as the internet. The driver 1010 is also connected to the I/O interface 1005 as necessary. A removable medium 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 1010 as necessary, so that a computer program read out therefrom is mounted into the storage section 1008 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication part 1009 and/or installed from the removable medium 1011. The computer program performs the above-described functions defined in the system of the present invention when executed by a Central Processing Unit (CPU) 1001.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules and/or units described in the embodiments of the present invention may be implemented by software, and may also be implemented by hardware. The described modules and/or units may also be provided in a processor, and may be described as: a processor comprises an inspection image acquisition module, a target image generation module, an annular pin detection result generation module and an inspection result generation module. Wherein the names of the modules do not in some cases constitute a limitation of the module itself.
As another aspect, the present invention also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be separate and not assembled into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise:
acquiring a patrol image of a transmission tower; inputting the inspection image into a connecting part detection model for detecting a connecting part to obtain a detection target image of the connecting part of the transmission tower; inputting a connecting part detection target image into an annular pin detection model for annular pin detection to obtain an annular pin detection result; and mapping the detection result of the annular pin back to the inspection image to obtain the inspection result of the transmission tower.
According to the technical scheme of the embodiment of the invention, the inspection image of the transmission tower can be obtained; inputting the inspection image into a connection part detection model for connection part detection to obtain a connection part detection target image of the transmission tower; inputting a connecting part detection target image into an annular pin detection model for annular pin detection to obtain an annular pin detection result; and mapping the detection result of the annular pin back to the inspection image to obtain the inspection result of the transmission tower. The method and the device for detecting the annular pin in the inspection image can automatically detect whether the annular pin exists in the inspection image by using the connecting part detection model and the annular pin detection model, do not need to manually detect whether the annular pin exists in the inspection image of the transmission tower, solve the problems of low accuracy and low inspection speed of manually detecting whether the annular pin exists in the inspection image of the transmission tower, improve the speed and accuracy of replacing the R-shaped pin of the connecting part of the transmission tower with the annular pin, and reduce the time cost of replacing the R-shaped pin of the connecting part of the transmission tower with the annular pin.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (11)
1. A power transmission tower inspection method, comprising:
acquiring a patrol image of a transmission tower;
inputting the inspection image into a connecting part detection model for detecting a connecting part to obtain a detection target image of the connecting part of the transmission tower;
inputting the connecting part detection target image into an annular pin detection model for annular pin detection to obtain an annular pin detection result;
and mapping the detection result of the annular pin back to the inspection image to obtain the inspection result of the transmission tower.
2. The method according to claim 1, wherein the connection portion detection model comprises a first connection portion detection model and a second connection portion detection model, a detection algorithm adopted by the first connection portion detection model is different from a detection algorithm adopted by the second connection portion detection model, and the step of inputting the inspection image into the connection portion detection model for connection portion detection to obtain a detection target image of the connection portion of the transmission tower comprises the following steps:
inputting the inspection image into the first connection part detection model for connection part detection to obtain a first connection part detection image corresponding to the first connection part detection model;
inputting the inspection image into the second connecting part detection model for connecting part detection to obtain a second connecting part detection image corresponding to the second connecting part detection model;
determining the connection portion detection target image according to the first connection portion detection image and the second connection portion detection image.
3. The method of claim 2,
will it inputs to patrol and examine the image first connecting portion detection model is connecting portion and detects, obtains first connecting portion detection image that first connecting portion detection model corresponds includes: inputting the inspection image into the first connection part detection model for connection part detection to obtain first connection part detection candidate images, determining first connection part detection intermediate images from the first connection part detection candidate images based on the intersection and comparison between the first connection part detection candidate images, and screening the first connection part detection images from the first connection part detection intermediate images according to the target confidence coefficient of the first connection part detection intermediate images;
the image input will patrol and examine the second connecting part detection model does the connecting part and detects, obtains the second connecting part detection image that second connecting part detection model corresponds includes: inputting the inspection image into the second connecting part detection model for connecting part detection to obtain second connecting part detection candidate images, determining second connecting part detection intermediate images from the second connecting part detection candidate images based on the intersection and comparison between the second connecting part detection candidate images, and screening the second connecting part detection images from the second connecting part detection intermediate images according to the target confidence coefficient of the second connecting part detection intermediate images.
4. The method of claim 3,
the target confidence of the first connection part detection intermediate image is obtained according to the following method: multiplying the original confidence coefficient of the first connection part detection intermediate image by the weight of the first connection part detection model to obtain a target confidence coefficient of the first connection part detection intermediate image;
the target confidence of the second connecting part detection intermediate image is obtained according to the following method: and multiplying the original confidence coefficient of the second connecting part detection intermediate image by the weight of the second connecting part detection model to obtain the target confidence coefficient of the second connecting part detection intermediate image.
5. The method according to claim 2, wherein the determining the connection detection target image from the first connection detection image and the second connection detection image includes:
mapping the first connection part detection image and the second connection part detection image onto the same image to obtain a connection part detection mapping image;
the joint detection target image is determined from the joint detection map images based on the intersection ratio of the joint detection map images.
6. The method according to claim 1, wherein the ring pin detection model includes a circle extraction function and a target detection function, and the inputting the connection portion detection target image into the ring pin detection model for ring pin detection to obtain a ring pin detection result includes:
and inputting the connecting part detection target image into the annular pin detection model, so as to extract an annular pin characteristic image from the connecting part detection target image by using the circular extraction function, and performing annular pin detection on the annular pin characteristic image by using the target detection function to obtain an annular pin detection result.
7. The method according to claim 1, wherein the ring pin detection results include position information, confidence information and feature information of a target ring pin in the target image detected at the connecting part, and the mapping of the ring pin detection results back to the inspection image to obtain inspection results of the transmission tower comprises:
and mapping the position information, the confidence coefficient information and the characteristic information of the target annular pin in the connecting part detection target image back to the inspection image to obtain the position information, the confidence coefficient information and the characteristic information of the target annular pin in the inspection image.
8. The method of claim 1, wherein the connection detection model and the ring pin detection model are obtained by training as follows:
inputting a training image into a preset connecting part detection model for detecting a connecting part to obtain a connecting part detection training image, wherein the training image comprises a preset annular pin positioned at the preset connecting part and a mark frame of the preset annular pin;
inputting the connecting part detection training image into a preset ring pin detection model for ring pin detection to obtain a detection frame;
determining the intersection ratio of the marking frame and the detection frame;
determining a target frame from the detection frames based on the intersection ratio;
determining a loss function of the preset ring pin detection model based on the target frame and the mark frame, and determining a loss function of the preset connection part detection model based on the target frame and the mark frame;
optimizing model parameters of the preset annular pin detection model based on a loss function of the preset annular pin detection model to obtain the annular pin detection model; and optimizing the model parameters of the preset connecting part detection model based on the loss function of the preset connecting part detection model to obtain the connecting part detection model.
9. The utility model provides a transmission tower inspection device which characterized in that, the device includes:
the inspection image acquisition module is used for acquiring an inspection image of the transmission tower;
the target image generation module is used for inputting the inspection image into a connecting part detection model for connecting part detection to obtain a connecting part detection target image of the transmission tower;
the annular pin detection result generation module is used for inputting the connection part detection target image into an annular pin detection model for annular pin detection to obtain an annular pin detection result;
and the inspection result generation module is used for mapping the detection result of the annular pin back to the inspection image to obtain the inspection result of the transmission tower.
10. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the program, implements the transmission tower patrol method according to any one of claims 1 to 8.
11. A computer-readable storage medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the transmission tower polling method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210949926.XA CN115240092A (en) | 2022-08-09 | 2022-08-09 | Transmission tower patrol detection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210949926.XA CN115240092A (en) | 2022-08-09 | 2022-08-09 | Transmission tower patrol detection method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115240092A true CN115240092A (en) | 2022-10-25 |
Family
ID=83679605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210949926.XA Pending CN115240092A (en) | 2022-08-09 | 2022-08-09 | Transmission tower patrol detection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115240092A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115953486A (en) * | 2022-12-30 | 2023-04-11 | 国网电力空间技术有限公司 | Automatic coding method for direct-current T-shaped tangent tower component inspection image |
-
2022
- 2022-08-09 CN CN202210949926.XA patent/CN115240092A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115953486A (en) * | 2022-12-30 | 2023-04-11 | 国网电力空间技术有限公司 | Automatic coding method for direct-current T-shaped tangent tower component inspection image |
| CN115953486B (en) * | 2022-12-30 | 2024-04-12 | 国网电力空间技术有限公司 | Automatic encoding method for inspection image of direct-current T-shaped tangent tower part |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109300119B (en) | Detection method and detection device for corrosion area on surface of steel structure and terminal equipment | |
| CN115240092A (en) | Transmission tower patrol detection method and device, electronic equipment and storage medium | |
| CN111220988A (en) | Map data processing method, device, equipment and medium | |
| CN114227717A (en) | Intelligent inspection method, device, equipment and storage medium based on inspection robot | |
| CN111136655B (en) | Method and device for acquiring inspection point | |
| CN112529836A (en) | High-voltage line defect detection method and device, storage medium and electronic equipment | |
| CN115809622B (en) | Chip simulation acceleration system with automatic configuration optimizing function | |
| CN116698874A (en) | Cable defect detection method, device, equipment and storage medium | |
| CN111047160A (en) | Pollution cause analysis method and device, readable storage medium and electronic equipment | |
| CN115546666A (en) | Power equipment bolt detection method and system based on unmanned aerial vehicle inspection | |
| CN114078234B (en) | Detection method, system, storage medium and equipment for power supply area construction process | |
| CN114964732A (en) | Off-axis reflection type collimator correction method and device, electronic equipment and medium | |
| CN116205835A (en) | Circuit board flaw detection method and device and electronic equipment | |
| CN112529829B (en) | Training method and device for burr positioning and burr detection model | |
| CN115309593A (en) | Domestic computer-oriented automatic test system and method | |
| CN113989632A (en) | Bridge detection method and device for remote sensing image, electronic equipment and storage medium | |
| CN111583176B (en) | Image-based lightning protection simulation disc element fault detection method and system | |
| CN115327497B (en) | Radar detection range determining method, radar detection range determining device, electronic equipment and readable medium | |
| CN114581890B (en) | Method and device for determining lane line, electronic equipment and storage medium | |
| CN117499621B (en) | Detection method, device, equipment and medium of video acquisition equipment | |
| KR20220152785A (en) | PCB visual inspection apparatus and method using accelerated vision processing and machine learning in heterogeneous platform | |
| CN111985497B (en) | Crane operation identification method and system under overhead transmission line | |
| CN117078095A (en) | Road construction work amount detection method, device, equipment and storage medium | |
| CN117349734B (en) | Water meter equipment identification method and device, electronic equipment and storage medium | |
| CN113435300B (en) | Real-time identification method and system for lightning arrester instrument |
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 |