CN115546666A - Power equipment bolt detection method and system based on unmanned aerial vehicle inspection - Google Patents
Power equipment bolt detection method and system based on unmanned aerial vehicle inspection Download PDFInfo
- Publication number
- CN115546666A CN115546666A CN202211219560.7A CN202211219560A CN115546666A CN 115546666 A CN115546666 A CN 115546666A CN 202211219560 A CN202211219560 A CN 202211219560A CN 115546666 A CN115546666 A CN 115546666A
- Authority
- CN
- China
- Prior art keywords
- bolt
- bottom plate
- component template
- picture
- detection result
- 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
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- 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
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted 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
- G06V10/82—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)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a system for detecting a bolt of power equipment based on unmanned aerial vehicle routing inspection, wherein the method comprises the following steps: firstly, constructing a bolt data set for normal bolts, and detecting the normal bolts in a bolt database by using a target detection network to obtain a bolt detection result; constructing a bottom plate component template database according to the distribution condition of the bolts in the power equipment; then judging whether the bolt detection result picture is matched with the component template picture in the bottom plate component template database, if the matching is successful, rotating and righting the bolt bottom plate in the bolt detection result picture and aligning the bolt bottom plate with the component template picture; and finally, calculating the intersection ratio of the real frame and the detection frame of the bolt component in the component template picture, if the intersection ratio is higher than a threshold value, indicating the position of a normal bolt, otherwise, indicating the position of a missing bolt. The method can improve the detection efficiency and effect under the condition of not depending on a defect sample.
Description
Technical Field
The invention relates to the technical field of power line inspection, in particular to a method and a system for detecting a bolt of power equipment based on unmanned aerial vehicle inspection.
Background
In the transmission line, the bolt plays an important role in connection and fixation. Because the bolt is exposed outdoors, the bolt is easy to lose due to the harm and interference caused by severe environments such as strong wind, rainstorm, thunder, dust and the like for a long time, potential safety hazards are caused, and the serious harm is caused to a power transmission line. Therefore, the bolt needs to be periodically inspected. The traditional method is manual inspection, namely, inspection personnel inspect tower by tower along the power transmission line. Because the transmission line topography is complicated, the weather is abominable, and most circuit area forest coverage is high, and the manual work is patrolled and examined intensity of labour big, and is efficient, has the potential safety hazard. In addition, due to the limitation of spatial position and a detecting instrument, the circuit inspection full coverage is difficult to realize in a short time, and the inspection quality and precision are low.
Along with the development of unmanned aerial vehicle technique, utilize nimble swift, efficient characteristics of unmanned aerial vehicle, realize closely acquireing the clear image of a large amount of, the different bolt of shooting the angle fast, increased substantially and patrolled and examined efficiency, reduced outdoor intensity of labour, avoided the manual work to patrol and examine the potential safety hazard that brings, the security is better. However, the manual image-by-image inspection still has the problems of high labor intensity, low efficiency and the like.
In the prior art, the process of further processing image data is mainly divided into two methods, one is to find out missing bolts on the image by using the traditional image processing algorithm; and the other type is to use a deep learning method to realize the automatic positioning of the bolt through a training network. For the method of deep learning target detection network, a large number of training samples are required. In practice, bolt missing samples are lacking, and the background of missing bolt holes is complex, so that the convergence cannot be achieved by directly performing deep learning network training. Meanwhile, the bolt missing position is positioned by using a traditional image processing algorithm, and the problems of high complexity, poor universality and the like of artificial feature design exist.
Disclosure of Invention
The invention provides a method and a system for detecting a bolt of electrical equipment based on unmanned aerial vehicle inspection, which are used for solving or at least partially solving the technical problems of excessive dependence on a defect sample and poor detection effect in the prior art.
In order to solve the technical problem, a first aspect of the present invention provides a method for detecting a bolt of an electrical device based on unmanned aerial vehicle inspection, including:
constructing a bolt data set of normal bolts, and detecting the normal bolts in a bolt database by using a target detection network to obtain a bolt detection result, wherein the bolt detection result comprises position information, confidence coefficient and category of a detection frame;
constructing a bottom plate component template database according to the distribution condition of bolts in the power equipment, wherein the bottom plate component template database comprises component template fields of different types;
judging whether the bolt detection result picture is matched with the component template picture in the bottom plate component template database or not, and if the matching is successful, rotating and righting the bolt bottom plate in the bolt detection result picture and aligning the bolt bottom plate with the component template picture;
and calculating the intersection ratio of the real frame and the detection frame of the bolt component in the component template graph, if the intersection ratio is higher than a threshold value, indicating the position of a normal bolt, and otherwise, indicating the position of a missing bolt.
In one embodiment, the target detection network used is YOLOV5.
In one embodiment, determining whether the bolt detection result picture matches a component template picture in a backplane component template database comprises:
extracting normalized multi-order rectangular characteristics of the outer contour from the bolt detection result picture and the component die layout respectively, and constructing a characteristic vector with shape description;
solving the distribution difference between the two eigenvectors based on the Wasserstein distance;
and judging whether the matching is successful or not according to whether the distribution difference is within the range allowed by the threshold value or not.
In one embodiment, the bolt bottom plate in the bolt detection result picture is rotated and aligned with the component template picture, and the method comprises the following steps:
searching characteristic angular points corresponding to the edge outlines of the bottom plate in the bolt detection result pictures and the corresponding component template pictures;
and determining the position relation between the detection result picture and the edge profile of the bottom plate in the component template picture according to the corresponding characteristic angular points, and rotating and righting the bolt bottom plate in the bolt detection result picture and aligning the bolt bottom plate with the component template picture according to the position relation.
Based on the same inventive concept, the invention provides in a second aspect an unmanned aerial vehicle inspection-based power equipment bolt detection system, which includes:
the normal bolt detection module is used for constructing a bolt data set by using normal bolts and detecting the normal bolts in the bolt database by using a target detection network to obtain a bolt detection result, wherein the bolt detection result comprises position information, confidence coefficient and category of a detection frame;
the system comprises a bottom plate component template database construction module, a bottom plate component template database and a control module, wherein the bottom plate component template database construction module is used for constructing a bottom plate component template database according to the distribution condition of bolts in power equipment, and the bottom plate component template database comprises component template maps of different types;
the template matching module is used for judging whether the bolt detection result picture is matched with the component template picture in the bottom plate component template database or not, and if the matching is successful, the bolt bottom plate in the bolt detection result picture is rotated and aligned with the component template picture;
and the bolt detection module is used for calculating the intersection ratio of the real frame and the detection frame of the bolt part in the part template picture, if the intersection ratio is higher than a threshold value, the position is indicated as the position of a normal bolt, and if not, the position is indicated as the position of a missing bolt.
Based on the same inventive concept, a third aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed, performs the method of the first aspect.
Based on the same inventive concept, a fourth aspect of the present invention provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of the first aspect when executing the program.
Compared with the prior art, the invention has the advantages and beneficial technical effects as follows:
the application provides a power equipment bolt detection method based on unmanned aerial vehicle patrols and examines, will normally bolt construction bolt data set, use the target detection network to detect the normal bolt in the bolt database, obtain the bolt testing result, because the bolt data set that the use was constructed by normal bolt, consequently very little to defect sample dependency. Constructing a bottom plate component template database according to the distribution condition of bolts in the power equipment, wherein the bottom plate component template database comprises component template patterns of different types; the regularity that the bolt distributes on the electricity tower part is fully utilized, and the template information of the whole part can be obtained in a self-adaptive mode under different photographing angles and illumination conditions, so that the effect of indirectly positioning the bolt with deficiency is achieved by utilizing the normal bolt.
Furthermore, the target detection network is YOLOV5, the YOLOV5 network has strong advantages in rapid model deployment, and has better performance, higher accuracy, higher running speed, cleaner detection result and almost no overlapped frames when detecting small targets such as bolts.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of a method for detecting bolts of electrical equipment based on unmanned aerial vehicle inspection provided by an embodiment of the invention;
fig. 2 is a schematic diagram of a YOLOV5 network involved in a target detection module in the method provided by the embodiment of the present invention;
fig. 3 is a flowchart of matching a template of a bottom plate component and determining a defect in the method according to an embodiment of the present invention.
FIG. 4 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The invention provides a power equipment bolt detection method based on unmanned aerial vehicle inspection, which is used for detecting the position of a missing bolt so as to realize the integrity detection of a power equipment nut, the method adopts a method of combining YOLOV5 target detection and template driving to carry out bolt positioning and missing detection, a YOLOV5 target detection network is used for positioning the position of a normal bolt to obtain a detection frame, and then the detection frame is matched with a component template in a bottom plate component template database so as to obtain the missing bolt information. According to the method, detection can be completed only by using a normal bolt without depending on a defect sample, and the effect of indirectly positioning the bolt with the defect is realized by matching the detection result picture of the normal bolt with the template database.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Example one
The embodiment of the invention provides a bolt detection method for power equipment based on unmanned aerial vehicle routing inspection, which comprises the following steps:
constructing a bolt data set of normal bolts, and detecting the normal bolts in a bolt database by using a target detection network to obtain a bolt detection result, wherein the bolt detection result comprises position information, confidence coefficient and category of a detection frame;
constructing a bottom plate component template database according to the distribution condition of bolts in the power equipment, wherein the bottom plate component template database comprises component template fields of different types;
judging whether the bolt detection result picture is matched with the component template picture in the bottom plate component template database or not, and if the matching is successful, rotating and righting the bolt bottom plate in the bolt detection result picture and aligning the bolt bottom plate with the component template picture;
and calculating the intersection ratio of the real frame and the detection frame of the bolt component in the component template graph, if the intersection ratio is higher than a threshold value, indicating the position of a normal bolt, otherwise indicating the position of a missing bolt.
Fig. 1 is a flowchart of a method for detecting a bolt of an electrical device based on unmanned aerial vehicle inspection according to an embodiment of the present invention.
Specifically, the target detection network is used for detecting the normal bolts in the bolt database, the positions of the normal bolts are detected and positioned, compact detection frames (including position information, confidence coefficient and category of the detection frames) surrounding the normal bolts can be obtained, in addition, the detection frames can be visualized clearly and visually on a detection result picture, the influence of complex backgrounds of the bolts is reduced, and the signal to noise ratio is improved.
The distribution of the bolts on the electric tower part is regular, the types of the electric tower bolt bottom plate parts are only limited, and the quantity and the positions of the bolts on the same type of bottom plate part template are the same, so that the distribution condition of the bolts in the electric power equipment is analyzed, the limited types of bottom plate part type pictures are arranged, and a bottom plate part template database is built.
And matching the detection result picture with the component template picture in the bottom board component template database, finding out a picture matched with the detection result picture in the data, and adjusting the detection result picture.
And finally, judging whether the bolt position is a normal bolt position or a missing bolt position according to the intersection ratio of the real frame and the detection frame of the bolt component in the component template diagram, wherein the normal bolt position indicates that the bolt at the position is normally installed, and the bolt at the position is not missing, and the missing bolt position indicates that the bolt at the position is abnormally installed and has missing.
In one embodiment, the target detection network used is YOLOV5.
Specifically, please refer to fig. 2, which is a YOLOv5 network model structure, the YOLOv5 network is composed of four main parts: the device comprises an input end, a backbone network, a feature fusion module and an output end. Firstly, an Input end (Input) randomly cuts, zooms and splices an Input image, finds the most suitable self-adaptive anchor frame for calculation, and improves the positioning accuracy of the small target defect of the bolt; then, a Backbone network (Backbone) is aggregated on different image fine granularities, and characteristic graphs of three scales are extracted; secondly, a feature fusion module (hack) enlarges the receptive field of the feature map by adding a Spatial Pyramid Pooling Structure (SPP), uses 3 groups of multi-scale maximum Pooling layers, realizes feature fusion by splicing high and low feature layers obtained by upsampling (upsampling) to obtain a new feature map so as to improve the propagation of low-layer features, and then transmits the features from weak to strong through a Path Aggregation Network (PAN) from bottom to top, so that the feature layers realize more feature fusion, the two are combined to operate, and the capability of Network feature fusion is enhanced; the final Output (Output) is the predicted part of the network, and the target frame is screened by Non-Maximum suppression (NMS), the image features are predicted, a bounding box is generated, and the class is predicted. The YOLOV5 network is used for detection, so that the running speed is high, and the accuracy is high.
In one embodiment, determining whether the bolt detection result picture matches a component template picture in a backplane component template database comprises:
extracting normalized multi-order rectangular features of the outer contour from the bolt detection result picture and the component module layout respectively, and constructing feature vectors with shape description;
solving the distribution difference between the two eigenvectors based on the Wasserstein distance;
and judging whether the matching is successful or not according to whether the distribution difference is within the range allowed by the threshold value or not.
Specifically, this step is mainly to perform shape feature matching of the bolt base plate member.
Specifically, a shape feature matching algorithm of high-dimensional multi-order moment feature normalization expression is provided, wherein by extracting the normalized multi-order rectangular features of the outer contour of the bolt bottom plate component in two pictures, the shape description of the normalized multi-order rectangular features is established, the feature vectors of the bolt bottom plate component of a detection result picture and a component model layout are respectively described, the distribution difference between the two feature vectors is solved based on Wassertein distance, and if the difference is within the range allowed by a threshold value, the matching is completed. The image matching algorithm is high in precision and has strong robustness.
Specifically, the bolt detection result and the component template are respectively subjected to region shape description, and the description results are respectively F 1 And F M Two feature vectors. The key for realizing the regional feature matching is to solve the distribution difference between the feature vectors, and the method realizes the solution of the vector distribution difference based on the Wasserstein distance。
The Wasserstein distance is used to measure the distance between two distributions and is defined as follows:
II (F) 1 ，F M ) Is F 1 And F M And (4) all possible joint distribution sets obtained by distribution combination. For each possible joint distribution gamma, sampling (x, y) -gamma to obtain a sample x and y, and calculating the distance of the pair of samples | | | x-y | | |, so that the expected value of the samples to the distance under the joint distribution gamma can be calculated. The lower bound that can be taken for this expected value in all possible joint distributions is the Wasserstein distance, the minimum consumption under optimal path planning, at which time w (F) 1 ，F M ) Is marked as sigma (F) 1 ，F M ) Representing the difference between the two feature vectors. If the difference meets the following conditions, the image (detection result picture) representing the segmentation result is successfully matched with the bottom template picture:
σ(F 1 ，F M )＜δ (2)
wherein, delta is a set threshold parameter, which shows a certain fault-tolerant capability to the region.
In one embodiment, the bolt bottom plate in the bolt detection result picture is rotated and aligned with the component template picture, and the method comprises the following steps:
searching characteristic angular points corresponding to the edge outlines of the bottom plate in the bolt detection result pictures and the corresponding component template pictures;
and determining the position relation between the detection result picture and the edge profile of the bottom plate in the component template picture according to the corresponding characteristic angular points, and rotating and righting the bolt bottom plate in the bolt detection result picture and aligning the bolt bottom plate with the component template picture according to the position relation.
Specifically, after the template matching is successful, the characteristic corner points (such as corner points and position relations thereof) of the bottom plate edge outline and the corresponding template in the detection result picture are found, and the position relations of the bottom plate edge outlines in the two pictures are determined. And rotating and righting the bottom plate component in the detection picture, and aligning the bottom plate component with the template to ensure that the bottom plate component and the template are approximately overlapped.
Fig. 3 is a flow chart of matching a template of a bottom plate component and determining a defect in the method according to an embodiment of the present invention.
After matching is successful, the IOU of the real frame and the IOU of the detection frame of the bolt part in the template are calculated, if the IOU is higher than a threshold value, the IOU is represented as the position of a normal bolt, and if the IOU is lower than the threshold value, the IOU is represented as the position of a missing bolt. Thereby detecting the position of the missing bolt.
The method provided by the invention has the beneficial effects that:
(1) the dependence on the defect sample is small, and the estimation is mainly carried out based on a large amount of normal bolt sample data.
(2) The regularity of the distribution of the bolts on the electric tower part is fully utilized, template information of the whole part can be obtained in a self-adaptive mode under different photographing angles and illumination conditions, and therefore the effect of indirectly positioning the lost bolts is achieved by utilizing normal bolts.
(3) The YOLOV5 network has the advantages of being rapid in model deployment, better in performance when small targets such as bolts are detected, higher in accuracy rate, higher in running speed, cleaner in detection results and almost free of overlapped frames.
Example two
Based on the same inventive concept, this embodiment provides power equipment bolt detecting system based on unmanned aerial vehicle patrols and examines, includes:
the normal bolt detection module is used for constructing a bolt data set by using normal bolts and detecting the normal bolts in the bolt database by using a target detection network to obtain a bolt detection result, wherein the bolt detection result comprises position information, confidence coefficient and category of a detection frame;
the system comprises a bottom plate component template database construction module, a bottom plate component template database and a data processing module, wherein the bottom plate component template database construction module is used for constructing a bottom plate component template database according to the distribution condition of bolts in power equipment, and the bottom plate component template database comprises component template maps of different types;
the template matching module is used for judging whether the bolt detection result picture is matched with the component template picture in the bottom plate component template database or not, and if the matching is successful, the bolt bottom plate in the bolt detection result picture is rotated and aligned with the component template picture;
and the bolt detection module is used for calculating the intersection ratio of the real frame and the detection frame of the bolt part in the part template picture, if the intersection ratio is higher than a threshold value, the position is indicated as the position of a normal bolt, and if not, the position is indicated as the position of a missing bolt.
Since the system described in the second embodiment of the present invention is a system used for implementing the method for detecting the bolt of the electrical equipment based on the unmanned aerial vehicle inspection in the first embodiment of the present invention, a person skilled in the art can understand the specific structure and deformation of the system based on the method described in the first embodiment of the present invention, and thus, the details are not described herein. All systems adopted by the method in the first embodiment of the invention belong to the protection scope of the invention.
EXAMPLE III
Based on the same inventive concept, please refer to fig. 4, the present invention further provides a computer readable storage medium 300, on which a computer program 311 is stored, which when executed implements the method as described in the first embodiment.
Because the computer-readable storage medium introduced in the third embodiment of the present invention is a computer-readable storage medium used for implementing the method for detecting a bolt of an electrical device based on unmanned aerial vehicle inspection in the first embodiment of the present invention, based on the method introduced in the first embodiment of the present invention, persons skilled in the art can know the specific structure and deformation of the computer-readable storage medium, and therefore, no further description is given here. Any computer readable storage medium used in the method of the first embodiment of the present invention falls within the intended scope of the present invention.
Example four
Based on the same inventive concept, the present application further provides a computer device, as shown in fig. 5, including a memory 401, a processor 402, and a computer program 403 stored in the memory and capable of running on the processor, where the processor executes the above program to implement the method in the first embodiment.
Since the computer device introduced in the fourth embodiment of the present invention is a computer device used for implementing the method for detecting a bolt of an electrical device based on unmanned aerial vehicle inspection in the first embodiment of the present invention, based on the method introduced in the first embodiment of the present invention, a person skilled in the art can know the specific structure and deformation of the computer device, and thus, details are not described herein. All the computer devices used in the method in the first embodiment of the present invention are within the scope of the present invention.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made in the embodiments of the present invention without departing from the spirit or scope of the embodiments of the invention. Thus, if such modifications and variations of the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to encompass such modifications and variations.
Claims (7)
1. Electric power equipment bolt detection method based on unmanned aerial vehicle patrols and examines, its characterized in that includes:
constructing a bolt data set of normal bolts, and detecting the normal bolts in a bolt database by using a target detection network to obtain a bolt detection result, wherein the bolt detection result comprises position information, confidence coefficient and category of a detection frame;
constructing a bottom plate component template database according to the distribution condition of bolts in the power equipment, wherein the bottom plate component template database comprises component template fields of different types;
judging whether the bolt detection result picture is matched with the component template picture in the bottom plate component template database or not, and if the matching is successful, rotating and righting the bolt bottom plate in the bolt detection result picture and aligning the bolt bottom plate with the component template picture;
and calculating the intersection ratio of the real frame and the detection frame of the bolt component in the component template graph, if the intersection ratio is higher than a threshold value, indicating the position of a normal bolt, and otherwise, indicating the position of a missing bolt.
2. The unmanned aerial vehicle inspection-based power equipment bolt detection method according to claim 1, wherein the target detection network used is YOLOV5.
3. The unmanned aerial vehicle inspection-based power equipment bolt detection method according to claim 1, wherein judging whether the bolt detection result picture matches with the component template picture in the bottom plate component template database includes:
extracting normalized multi-order rectangular features of the outer contour from the bolt detection result picture and the component module layout respectively, and constructing feature vectors with shape description;
solving the distribution difference between the two eigenvectors based on the Wasserstein distance;
and judging whether the matching is successful or not according to whether the distribution difference is within the range allowed by the threshold value or not.
4. The unmanned aerial vehicle inspection tour-based power equipment bolt detection method of claim 1, wherein the bolt bottom plate in the bolt detection result picture is rotated and aligned with the component template picture, and the method comprises the following steps:
searching characteristic angular points corresponding to the edge outlines of the bottom plate in the bolt detection result pictures and the corresponding component template pictures;
and determining the position relation between the detection result picture and the edge profile of the bottom plate in the component template picture according to the corresponding characteristic angular points, and rotating and righting the bolt bottom plate in the bolt detection result picture and aligning the bolt bottom plate with the component template picture according to the position relation.
5. Electric power equipment bolt detecting system based on unmanned aerial vehicle patrols and examines, its characterized in that includes:
the normal bolt detection module is used for constructing a bolt data set by the normal bolts, and detecting the normal bolts in the bolt database by using a target detection network to obtain a bolt detection result, wherein the bolt detection result comprises position information, confidence coefficient and category of a detection frame;
the system comprises a bottom plate component template database construction module, a bottom plate component template database and a data processing module, wherein the bottom plate component template database construction module is used for constructing a bottom plate component template database according to the distribution condition of bolts in power equipment, and the bottom plate component template database comprises component template maps of different types;
the template matching module is used for judging whether the bolt detection result picture is matched with the component template picture in the bottom plate component template database or not, and if the matching is successful, the bolt bottom plate in the bolt detection result picture is rotated and aligned with the component template picture;
and the bolt detection module is used for calculating the intersection ratio of the real frame and the detection frame of the bolt component in the component template picture, if the intersection ratio is higher than a threshold value, the bolt is indicated as the position of a normal bolt, and if not, the bolt is indicated as the position of a missing bolt.
6. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed, implements the method of any one of claims 1 to 4.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 4 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211219560.7A CN115546666A (en) | 2022-09-30 | 2022-09-30 | Power equipment bolt detection method and system based on unmanned aerial vehicle inspection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211219560.7A CN115546666A (en) | 2022-09-30 | 2022-09-30 | Power equipment bolt detection method and system based on unmanned aerial vehicle inspection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115546666A true CN115546666A (en) | 2022-12-30 |
Family
ID=84730790
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211219560.7A Pending CN115546666A (en) | 2022-09-30 | 2022-09-30 | Power equipment bolt detection method and system based on unmanned aerial vehicle inspection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115546666A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116342485A (en) * | 2023-02-16 | 2023-06-27 | 国网江苏省电力有限公司南通供电分公司 | Protective cap missing detection system and method |
-
2022
- 2022-09-30 CN CN202211219560.7A patent/CN115546666A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116342485A (en) * | 2023-02-16 | 2023-06-27 | 国网江苏省电力有限公司南通供电分公司 | Protective cap missing detection system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107742093B (en) | Real-time detection method, server and system for infrared image power equipment components | |
| Akagic et al. | Pothole detection: An efficient vision based method using rgb color space image segmentation | |
| CN109977191B (en) | Problem map detection method, device, electronic equipment and medium | |
| CN113822247A (en) | Method and system for identifying illegal building based on aerial image | |
| CN109376580B (en) | Electric power tower component identification method based on deep learning | |
| US20230300455A1 (en) | Active camera relocation method having robustness to illumination | |
| CN112581445A (en) | Detection method and device for bolt of power transmission line, storage medium and electronic equipment | |
| CN114419007B (en) | Defect type identification method and system for multi-strategy fusion deep learning network model | |
| CN115578326A (en) | Road disease identification method, system, equipment and storage medium | |
| CN112150804A (en) | City multi-type intersection identification method based on MaskRCNN algorithm | |
| CN110909623A (en) | Three-dimensional target detection method and three-dimensional target detector | |
| CN114565842A (en) | Unmanned aerial vehicle real-time target detection method and system based on Nvidia Jetson embedded hardware | |
| CN115546666A (en) | Power equipment bolt detection method and system based on unmanned aerial vehicle inspection | |
| CN113657423A (en) | Target detection method suitable for small-volume parts and stacked parts and application thereof | |
| CN109934151B (en) | Face detection method based on movidius computing chip and Yolo face | |
| CN116958606A (en) | Image matching method and related device | |
| CN103837135B (en) | Workpiece inspection method and system thereof | |
| CN113012107B (en) | Power grid defect detection method and system | |
| CN110017998A (en) | Vehicle checking method, device and equipment | |
| Xu et al. | A deep neural network-based intelligent detection model for manufacturing defects of automobile parts | |
| CN115240092A (en) | Transmission tower patrol detection method and device, electronic equipment and storage medium | |
| CN114841980A (en) | Insulator defect detection method and system based on line patrol aerial image | |
| CN114140707A (en) | Power grid fault inspection method | |
| CN114896134A (en) | Metamorphic test method, device and equipment for target detection model | |
| CN113920450A (en) | Method and device for identifying insulator RTV coating based on intrinsic image decomposition |
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 |