CN103235830A - Unmanned aerial vehicle (UAV)-based electric power line patrol method and device and UAV - Google Patents
Unmanned aerial vehicle (UAV)-based electric power line patrol method and device and UAV Download PDFInfo
- Publication number
- CN103235830A CN103235830A CN2013101756952A CN201310175695A CN103235830A CN 103235830 A CN103235830 A CN 103235830A CN 2013101756952 A CN2013101756952 A CN 2013101756952A CN 201310175695 A CN201310175695 A CN 201310175695A CN 103235830 A CN103235830 A CN 103235830A
- Authority
- CN
- China
- Prior art keywords
- power equipment
- tested power
- current
- picture
- parts
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a UAV-based electric power line patrol method and device and an UAV. The method comprises the steps of collecting a sample picture of a target tested electrical device in advance, calculating a standard grey histogram of the target tested electrical device in the sample picture, and storing the standard grey histogram in a template database; collecting a picture of a current tested electrical device in real time, and calculating a current grey histogram in the current tested electrical device in the picture; and when the current grey histogram is matched with the standard grey histogram, comparing the picture of the current tested electrical device with the sample picture of the target tested electrical device, recognizing each component of the current tested electrical device in the picture of the current tested electrical device and components which are in one-to-one correspondence in the target tested electrical device in the sample picture, calculating deviation information of components of the current tested electrical device from components which are in one-to-one correspondence in the sample picture respectively, and determining whether the current tested electrical device has a defect according to the deviation information.
Description
Technical field
The present invention relates to the power equipment detection range, relate in particular to a kind of electric power line walking disposal route, device and unmanned plane based on unmanned plane.
Background technology
At present, because domestic electrical network scale constantly enlarges, long distance transmission line increases rapidly as special (surpassing) high-tension line.And a lot of transmission lines of electricity are distributed between the high and steep mountains, cause traditional artificial line walking to be subjected to the influence of uncertain factors such as terrain environment, peopleware, weather conditions, and efficient is low, and the cycle of patrolling again is long, and it is not high to patrol and examine the data accuracy rate.
Therefore, domestic beginning in recent years progressively develops unmanned plane intelligent patrol detection technology, can not be subjected to the constraint of geographical environment, has improved efficient greatly.Simultaneously because unmanned spacecraft (Unmanned Aerial Vehicle, UAV) the unique visual field during line walking and the use of the airborne line walking equipment of multiple advanced person, can do closely observation to device of transmission line, clear collection record is the picture of circuit down, patrols and examines quality and has also obtained certain raising.
But, existing also need to handle by manually carrying out picture analyzing after gathering picture by unmanned plane, manually come identification circuit to damage, filth, defectives such as circuit relevant device will be difficult to like this promote and patrol and examine work efficiency and quality.
Summary of the invention
The object of the present invention is to provide a kind of electric power line walking disposal route, device and unmanned plane based on unmanned plane, to address the above problem.
In order to achieve the above object, technical scheme of the present invention is achieved in that
A kind of electric power line walking disposal route based on unmanned plane comprises the steps:
Gather the samples pictures of the tested power equipment of target under different resolution and the different shooting angles in advance, calculate the standard grayscale histogram of the tested power equipment of target in the described samples pictures, and described standard grayscale histogram is stored to the masterplate database;
Gather in real time the picture of the current tested power equipment under different resolution and the different shooting angles, calculate the current gray level histogram of current tested power equipment in the picture of current tested power equipment;
If the described standard grayscale histogram coupling of the described current gray level histogram of current tested power equipment and the tested power equipment of target, then the picture of current tested power equipment and the samples pictures of the tested power equipment of target are compared, identify the parts one to one of the tested power equipment of target in each parts of current tested power equipment in the picture of current tested power equipment and the samples pictures, calculate the parts of current tested power equipment and the deviation information of the parts one to one in the samples pictures respectively, and judge according to described deviation information whether described current tested power equipment defective occurs.
Correspondingly, the present invention also provides a kind of electric power line walking treating apparatus, comprises pretreatment module, acquisition processing module, matching treatment and defects detection module, wherein:
Described pretreatment module, be used for gathering in advance the samples pictures of the tested power equipment of target under different resolution and the different shooting angles, calculate the standard grayscale histogram of the tested power equipment of target in the described samples pictures, and described standard grayscale histogram is stored to the masterplate database;
Described acquisition processing module is used for gathering in real time the picture of the current tested power equipment under different resolution and the different shooting angles, calculates the current gray level histogram of current tested power equipment in the picture of current tested power equipment;
Described matching treatment and defects detection module, be used for if the described standard grayscale histogram coupling of the described current gray level histogram of current tested power equipment and the tested power equipment of target, then the picture of current tested power equipment and the samples pictures of the tested power equipment of target are compared, identify the parts one to one of the tested power equipment of target in each parts of current tested power equipment in the picture of current tested power equipment and the samples pictures, calculate the parts of current tested power equipment and the deviation information of the parts one to one in the samples pictures respectively, and judge according to described deviation information whether described current tested power equipment defective occurs.
Correspondingly, the present invention also provides a kind of unmanned plane, and comprise the unmanned plane body and be installed in camera on the unmanned plane and above-mentioned electric power line walking treating apparatus, wherein:
Described electric power line walking treating apparatus is electrically connected with camera;
Described unmanned plane body is used for carrying described camera and carries out the picture of gathering tested power equipment;
Described camera is for the picture of gathering tested power equipment;
Described camera comprises infrared camera, ultraviolet camera and visible image capturing head.
Compared with prior art, the advantage of the embodiment of the invention is:
A kind of electric power line walking disposal route based on unmanned plane provided by the invention, device and unmanned plane, wherein, method comprises the steps: that unmanned plane at first gathers the samples pictures of a large amount of tested power equipments of target (namely carrying out a large amount of shooting samplings according to the actual requirement of electric power line walking with to shaft tower equipment and related device) in advance under different resolution and differing tilt angles, samples pictures (namely comprises the image input through Digital Image Processing, pre-service, feature extraction, the steps such as standard grayscale histogram of classification and the tested power equipment of calculating target) after, the standard grayscale histogram of the tested power equipment of storage target is to the masterplate database.
(collection in real time when in real time gathering current tested power equipment, when patrolling and examining automatically), gather the picture of current equipment under test, and carry out image and handle (the current gray level histogram that namely calculates current tested power equipment in the picture of current tested power equipment), in the masterplate database, carry out masterplate coupling then, utilize current gray level histogram that the method for multimode version coupling judges current tested power equipment whether with the masterplate database in the histogrammic coupling of standard grayscale of the tested power equipment of target; If the match is successful, illustrate that then current tested power equipment is the tested power equipment of target, finished the identification step of the tested power equipment of target this moment;
Then, the picture of current tested power equipment and the samples pictures of the tested power equipment of target are compared, identify the parts one to one of the tested power equipment of target in each parts of current tested power equipment in the picture of current tested power equipment and the samples pictures, (for example: the change in location of the different time sections of more same parts), and judge according to described deviation information whether described current tested power equipment defective occurs calculate the parts of current tested power equipment and the deviation information of the parts one to one in the samples pictures respectively.
Like this, electric power line walking disposal route, device and unmanned plane based on unmanned plane provided by the invention, utilize that unmanned plane is gathered automatically, image processing, identification and analytical calculation deviation information handle, can realize patrolling and examining automatically real-time line defct (damages as circuit, filthy and distortion is aging etc.), avoid loaded down with trivial details ground artificial treatment and identification, when having ensured the line data-logging quality, also improved the work efficiency of line data-logging.
Description of drawings
The schematic flow sheet based on the electric power line walking disposal route of unmanned plane that Fig. 1 provides for the embodiment of the invention;
The structural representation of the electric power line walking treating apparatus that Fig. 2 provides for the embodiment of the invention;
The structural representation of the unmanned plane that Fig. 3 provides for the embodiment of the invention.
Embodiment
Also by reference to the accompanying drawings the present invention is described in further detail below by specific embodiment.
Referring to Fig. 1, the embodiment of the invention provides the electric power line walking disposal route based on unmanned plane, comprises the steps:
Step S100, gather the samples pictures of the tested power equipment of target under different resolution and the different shooting angles in advance, calculate the standard grayscale histogram of the tested power equipment of target in the described samples pictures, and described standard grayscale histogram is stored to the masterplate database;
Step S200, gather the picture of the current tested power equipment under different resolution and the different shooting angles in real time, calculate the current gray level histogram of current tested power equipment in the picture of current tested power equipment;
The current gray level histogram that step S300, (utilize multimode version coupling method) are judged current tested power equipment whether with the masterplate database in the standard grayscale histogram of the tested power equipment of target mate; If coupling (judging that namely identifying current tested power equipment is the tested power equipment of target), then execution in step S400; If do not match, then return the operation that step S200 carries out the picture of identifying next tested power equipment again.
Step S400, the picture of current tested power equipment and the samples pictures of the tested power equipment of target are compared, identify the parts one to one of the tested power equipment of target in each parts of current tested power equipment in the picture of current tested power equipment and the samples pictures, calculate the parts of current tested power equipment and the deviation information of the parts one to one in the samples pictures respectively, and judge according to described deviation information whether described current tested power equipment defective occurs.
Preferably, described deviation information comprises relative position side-play amount, relative rotation angle side-play amount and similarity.
Those skilled in the art are to be understood that, at first unmanned plane is gathered the samples pictures (namely carrying out a large amount of shooting samplings according to the actual requirement of electric power line walking with to shaft tower equipment and related device) of a large amount of tested power equipments of target in advance under different resolution and differing tilt angles, after the samples pictures process Digital Image Processing (steps such as standard grayscale histogram that namely comprise image input, pre-service, feature extraction, classification and the tested power equipment of calculating target), the standard grayscale histogram of the tested power equipment of storage target is to the masterplate database.
(collection in real time when in real time gathering current tested power equipment, when patrolling and examining automatically), gather the picture of current equipment under test, and carry out image and handle (the current gray level histogram that namely calculates current tested power equipment in the picture of current tested power equipment), in the masterplate database, carry out masterplate coupling then, utilize current gray level histogram that the method for multimode version coupling judges current tested power equipment whether with the masterplate database in the histogrammic coupling of standard grayscale of the tested power equipment of target; If the match is successful, illustrate that then current tested power equipment is the tested power equipment of target, finished the identification step of the tested power equipment of target this moment;
Then, the picture of current tested power equipment and the samples pictures of the tested power equipment of target are compared, identify the parts one to one of the tested power equipment of target in each parts of current tested power equipment in the picture of current tested power equipment and the samples pictures, (for example: the change in location of the different time sections of more same parts), and judge according to described deviation information whether described current tested power equipment defective occurs calculate the parts of current tested power equipment and the deviation information of the parts one to one in the samples pictures respectively.
Like this, electric power line walking disposal route, device and unmanned plane based on unmanned plane provided by the invention, utilize that unmanned plane is gathered automatically, image processing, identification and analytical calculation deviation information handle, can realize patrolling and examining automatically real-time line defct (damages as circuit, filthy and distortion is aging etc.), avoid loaded down with trivial details ground artificial treatment and identification, when having ensured the line data-logging quality, also improved the work efficiency of line data-logging.
Further, in step S100, after described samples pictures step of gathering the tested power equipment of target under different resolution and the different shooting angles in advance, and in calculating described samples pictures, before the standard grayscale histogram of the tested power equipment of target, also comprise the steps:
Step S110, the samples pictures of the tested power equipment of target is carried out filtering image strengthen, characteristics of image separates and extracts and handle.
Further, in step S200, after the picture step of the current tested power equipment under described real-time collection different resolution and different shooting angles, and calculate before the current gray level histogram of current tested power equipment in the picture of current tested power equipment, also comprise the steps:
Step S210, the picture of current tested power equipment is carried out filtering image strengthen, characteristics of image separates and extracts and handle.
Preferably, in step S400, describedly judge that according to described deviation information whether described current tested power equipment defective occurs, comprises the steps:
Step S410, if judge in parts in the picture of current tested power equipment and the samples pictures that the relative position side-play amount of parts is then judged the part displacements defective on the current tested power equipment greater than offset threshold one to one;
If judge in parts and the samples pictures in the picture of current tested power equipment that the relative rotation angle side-play amount of parts is then judged the described parts rotation defect on the current tested power equipment greater than rotating threshold value one to one;
If judge in parts in the picture of current tested power equipment and the samples pictures that the similarity of parts judges then that less than default similarity deformation defect appears in the parts on the current tested power equipment one to one.
Need to prove that the grey level histogram of the input of process image, pre-service, feature extraction, classification and the tested power equipment of calculating target is a very important step, wherein:
One, the pre-service of image
Pre-service is the effect that directly influences image recognition.Carrying out pretreated purpose is the noise of removing in the image, it is become width of cloth point and line chart clearly, so that extract correct characteristics of image.
The directionization of picture can reflect the morphological feature that image is the most basic intuitively with the form of simplifying, the crucial processing links of image recognitions such as the extraction by figure image intensifying, characteristics of image, the automatic classification of image, direction masterplate coupling.Method is as follows:
(1) image is divided into the enough little piece that gives.For example image is divided into 32 * 32 non-overlapped fritter.
(2) each point to each sub-piece utilizes the Sobel operator to calculate its x direction gradient and y direction gradient respectively
(3) according to Grad, the computing formula of each sub-piece direction is as follows:
In the following formula: the width of w presentation video piece is 32 here, it is quantified as 16 directions after obtaining again, thereby obtains the direction of image.
(4) figure image intensifying: the Enhancement Method of filtering and strengthen algorithm based on the low-quality image of Fourier filtering.The basic point of departure that Gabor filtering strengthens is based on the mathematical model of image, total definition form as shown in the formula: the Gabor wave filter is used for treatment of picture, even function need be changed into digital filter, be shown below, so the truer feature near image of wave filter that the real part of Gabor function is obtained as template.
This method has been taken all factors into consideration directivity characteristics and the frequency characteristic of image.The filter effect of this method is relatively good, but the filtering medium frequency calculates and filtering calculating takies certain hour in the preprocessing process of entire image.
Two. the feature extraction of image and classification
Directly extract feature from the original gray-scale map of image, the efficient height, but extract a large amount of pseudo-characteristic information easily.Based on the sorting technique of global structure feature, realize classification by extraction and global structure features such as analysis directions figure, singular point.Adopt the human way of carrying out the image classification of imitation, the distortion of image is had stronger robustness; But be difficult to extract reliable architectural feature when picture quality is relatively poor.
Extraction and sorting algorithm are based on the algorithm of local detail feature.The algorithm of local detail feature extraction is as follows:
Utilize one 3 * 3 masterplate to come the image after the refinement is carried out the feature extraction of end points and branch point, as shown below, M is point to be detected, along the P1 of arranged clockwise, P2, P3, P8 are its 8 neighborhood points, R (1), R (2), R (3) R (8) is respectively P1, P2, P3, the gray-scale value of P8.If M is end points, then its neighborhood point satisfies following formula:
If the M take-off point, then its neighborhood point satisfies following formula:
By image is traveled through.Can find the unique point of image, record their type and position simultaneously.
Three. image recognition
By BP (Back Propagation) neural network, i.e. the learning process of error anti-pass error backpropagation algorithm is made up of the forward-propagating of information and two processes of backpropagation of error.Each neuron of input layer is responsible for receiving the input information that comes from the outside, and passes to each neuron of middle layer; The middle layer is the internal information processing layer, is responsible for information conversion, and according to the demand of information change ability, the middle layer can be designed as single hidden layer or many hidden layers structure; Last hidden layer is delivered to each neuronic information of output layer, after further handling, finishes the once forward-propagating processing procedure of study, by output layer to extraneous output information result.When reality output is not inconsistent with desired output, enter the back-propagation phase of error.Error is by output layer, by each layer of mode correction weights of error gradient decline, to the anti-pass successively of hidden layer, input layer.The information forward-propagating that goes round and begins again and error back propagation process, it is the process that each layer weights are constantly adjusted, also be the process of neural network learning training, the error that this process is performed until network output reduces to the acceptable degree, perhaps till the predefined study number of times.
BP neural network model BP network model comprises its input, action function model, error calculating and self learning model.
(1) node output model
Latent node output model: Oj=f (∑ Wij * Xi-qj)
Output node output model: Yk=f (∑ Tjk * Oj-qk)
The non-linear action function of f-; Q-neural unit threshold value.
(2) action function model
Action function is that the function that reflection lower floor imports upper layer node boost pulse intensity claims to stimulate function again, generally is taken as continuous value Sigmoid function: f (x)=1/ (1+e) in (0,1)
(3) error calculating
Error calculating is reflection neural network desired output and the function that calculates error size between the output:
Ep=1/2×∑(tpi-Opi)
The desired output of tpi-i node; The Opi-i node calculates output valve.
(4) self learning model
The learning process of neural network namely connects setting and error correction process that the weight between lower level node and the upper layer node is refused gust Wij.BP network teacher of the having mode of learning-needs are set the branch of expectation value and a no teacher's mode of learning-need input pattern.Self learning model is
△Wij(n+1)=h×Фi×Oj+a×△Wij(n)
H-learns the factor; The error of calculation of Ф i-output node i; The calculating output of Oj-output node j; The a-factor of momentum.
In other words, utilize characteristics of image to mate, be implemented in the characteristic procedure of multi-template matching method, the parts of each tested power equipment are mated, identification.Template matches based on element-specific.This coupling can be regarded senior form fit as, and matching principle is identical with form fit.
In the detection for a destination object that comprises a plurality of parts, based on the template matches of element with this kind destination object as a large form, because relative position skew, rotation are arranged between each parts.Coupling based on shape then must adopt multi-template matching at this kind situation.Because when the sample template, the basic restriction of position relation between each parts only need search parts when coupling, the hunting zone of miscellaneous part just significantly reduces, and therefore relatively based on the multi-template matching of form fit, its matching speed is faster.Matching result is the position coordinates of each parts of destination object, the anglec of rotation of the relative form element of target component and the information such as similarity of each parts.
Based on same inventive concept, the embodiment of the invention also provides a kind of electric power line walking treating apparatus, because the principle of this device solves problem is similar to aforementioned electric power line walking disposal route based on unmanned plane, so the function of this device can repeat part and repeat no more referring to the enforcement of preceding method.
Correspondingly, the invention provides a kind of electric power line walking treating apparatus 1, referring to Fig. 2, comprise pretreatment module 10, acquisition processing module 20, matching treatment and defects detection module 30, wherein:
Described pretreatment module 10, be used for gathering in advance the samples pictures of the tested power equipment of target under different resolution and the different shooting angles, calculate the standard grayscale histogram of the tested power equipment of target in the described samples pictures, and described standard grayscale histogram is stored to the masterplate database;
Described acquisition processing module 20 is used for gathering in real time the picture of the current tested power equipment under different resolution and the different shooting angles, calculates the current gray level histogram of current tested power equipment in the picture of current tested power equipment;
Described matching treatment and defects detection module 30, be used for if the described standard grayscale histogram coupling of the described current gray level histogram of current tested power equipment and the tested power equipment of target, then the picture of current tested power equipment and the samples pictures of the tested power equipment of target are compared, identify the parts one to one of the tested power equipment of target in each parts of current tested power equipment in the picture of current tested power equipment and the samples pictures, calculate the parts of current tested power equipment and the deviation information of the parts one to one in the samples pictures respectively, and judge according to described deviation information whether described current tested power equipment defective occurs.
Further, also comprise first image processing module, wherein:
Described first image processing module, what be used for the tested power equipment of target carries out the filtering image enhancing to samples pictures, and characteristics of image separates and extracts and handle.
Further, also comprise second image processing module, wherein:
Described second image processing module is used for the picture of current tested power equipment is carried out the filtering image enhancing, and characteristics of image separates and extracts and handle.
Matching treatment and defects detection module 30 comprise the determining defects submodule, wherein:
Described determining defects submodule is used for if judge in the parts of picture of current tested power equipment and the samples pictures that the relative position side-play amount of parts is then judged the part displacements defective on the current tested power equipment greater than offset threshold one to one; If judge in parts and the samples pictures in the picture of current tested power equipment that the relative rotation angle side-play amount of parts is then judged the described parts rotation defect on the current tested power equipment greater than rotating threshold value one to one;
If judge in parts in the picture of current tested power equipment and the samples pictures that the similarity of parts judges then that less than default similarity deformation defect appears in the parts on the current tested power equipment one to one.
Correspondingly, the present invention also provides a kind of unmanned plane 100, and comprise unmanned plane body 101 and be installed in camera 102 on the unmanned plane and above-mentioned electric power line walking treating apparatus 1, referring to Fig. 3, wherein:
Described electric power line walking treating apparatus 1 is electrically connected with described camera 102;
Described unmanned plane body 101 is used for carrying described camera and carries out the picture of gathering tested power equipment;
Described camera 102 is for the picture of gathering tested power equipment.
Preferably, described camera 102 comprises infrared camera, ultraviolet camera and visible image capturing head.
Through investigation, the domestic unmanned plane that is using is patrolled and examined technology, some problems of ubiquity.For example: most electric power line walkings only are equipped with infrared detection equipment (can only find local overheating defective on the circuit) with photoelectric nacelle, and visible light camera (can only find visible defects on the circuit), lack uv detection devices.
Infrared technique has advantages such as temperature anomaly point detection sensitivity height, noncontact, but also has a series of deficiencies.Can not be too fast as test speed, after must generating heat, the trouble spot could survey, be subject to interference such as radiance, angle, light.Be equipped with highly sensitive camera, can in airborne rapid movement, detect high-tension apparatus corona, electric arc and partial discharge phenomenon, thus the insulation status of assessment apparatus and the timely defective of finding insulator arrangement; And antijamming capability is strong, is not subjected to the influence of sunshine and the restriction of detection time fully, can reach complementary advantage with infrared technique.It is higher that the unmanned plane that adopts is patrolled and examined automaticity, customer service the people estimate line facility, recording defect, easily the problem of omission has reduced the routing inspection cost height.
The above is the preferred embodiments of the present invention only, is not limited to the present invention, and for a person skilled in the art, the present invention can have various changes and variation.Within the spirit and principles in the present invention all, any modification of doing, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. the electric power line walking disposal route based on unmanned plane is characterized in that, comprises the steps:
Gather the samples pictures of the tested power equipment of target under different resolution and the different shooting angles in advance, calculate the standard grayscale histogram of the tested power equipment of target in the described samples pictures, and described standard grayscale histogram is stored to the masterplate database;
Gather in real time the picture of the current tested power equipment under different resolution and the different shooting angles, calculate the current gray level histogram of current tested power equipment in the picture of current tested power equipment;
If the described standard grayscale histogram coupling of the described current gray level histogram of current tested power equipment and the tested power equipment of target, then the picture of current tested power equipment and the samples pictures of the tested power equipment of target are compared, identify the parts one to one of the tested power equipment of target in each parts of current tested power equipment in the picture of current tested power equipment and the samples pictures, calculate the parts of current tested power equipment and the deviation information of the parts one to one in the samples pictures respectively, and judge according to described deviation information whether described current tested power equipment defective occurs.
2. the electric power line walking disposal route based on unmanned plane as claimed in claim 1 is characterized in that,
Described deviation information comprises relative position side-play amount, relative rotation angle side-play amount and similarity.
3. the electric power line walking disposal route based on unmanned plane as claimed in claim 1 is characterized in that,
After described samples pictures step of gathering the tested power equipment of target under different resolution and the different shooting angles in advance, and in calculating described samples pictures, before the standard grayscale histogram of the tested power equipment of target, also comprise the steps:
The samples pictures of the tested power equipment of target is carried out filtering image strengthen, characteristics of image separates and extracts and handle.
4. the electric power line walking disposal route based on unmanned plane as claimed in claim 3 is characterized in that,
After the picture step of the current tested power equipment under described real-time collection different resolution and different shooting angles, and calculate before the current gray level histogram of current tested power equipment in the picture of current tested power equipment, also comprise the steps:
Picture to current tested power equipment carries out the filtering image enhancing, and characteristics of image separates and extracts and handle.
5. the electric power line walking disposal route based on unmanned plane as claimed in claim 1 is characterized in that,
Describedly judge that according to described deviation information whether described current tested power equipment defective occurs, comprises the steps:
If judge in parts in the picture of current tested power equipment and the samples pictures that the relative position side-play amount of parts is then judged the part displacements defective on the current tested power equipment greater than offset threshold one to one;
If judge in parts and the samples pictures in the picture of current tested power equipment that the relative rotation angle side-play amount of parts is then judged the described parts rotation defect on the current tested power equipment greater than rotating threshold value one to one;
If judge in parts in the picture of current tested power equipment and the samples pictures that the similarity of parts judges then that less than default similarity deformation defect appears in the parts on the current tested power equipment one to one.
6. an electric power line walking treating apparatus is characterized in that, comprises pretreatment module, acquisition processing module, matching treatment and defects detection module, wherein:
Described pretreatment module, be used for gathering in advance the samples pictures of the tested power equipment of target under different resolution and the different shooting angles, calculate the standard grayscale histogram of the tested power equipment of target in the described samples pictures, and described standard grayscale histogram is stored to the masterplate database;
Described acquisition processing module is used for gathering in real time the picture of the current tested power equipment under different resolution and the different shooting angles, calculates the current gray level histogram of current tested power equipment in the picture of current tested power equipment;
Described matching treatment and defects detection module, be used for if the described standard grayscale histogram coupling of the described current gray level histogram of current tested power equipment and the tested power equipment of target, then the picture of current tested power equipment and the samples pictures of the tested power equipment of target are compared, identify the parts one to one of the tested power equipment of target in each parts of current tested power equipment in the picture of current tested power equipment and the samples pictures, calculate the parts of current tested power equipment and the deviation information of the parts one to one in the samples pictures respectively, and judge according to described deviation information whether described current tested power equipment defective occurs.
7. electric power line walking treating apparatus as claimed in claim 6 is characterized in that,
Also comprise first image processing module, wherein:
Described first image processing module is used for that the samples pictures of the tested power equipment of target is carried out filtering image and strengthens, and characteristics of image separates and extracts and handle.
8. electric power line walking treating apparatus as claimed in claim 7 is characterized in that,
Also comprise second image processing module, wherein:
Described second image processing module is used for the picture of current tested power equipment is carried out the filtering image enhancing, and characteristics of image separates and extracts and handle.
9. electric power line walking treating apparatus as claimed in claim 8 is characterized in that,
Matching treatment and defects detection module comprise the determining defects submodule, wherein:
Described determining defects submodule is used for if judge in the parts of picture of current tested power equipment and the samples pictures that the relative position side-play amount of parts is then judged the part displacements defective on the current tested power equipment greater than offset threshold one to one; If judge in parts and the samples pictures in the picture of current tested power equipment that the relative rotation angle side-play amount of parts is then judged the described parts rotation defect on the current tested power equipment greater than rotating threshold value one to one;
If judge in parts in the picture of current tested power equipment and the samples pictures that the similarity of parts judges then that less than default similarity deformation defect appears in the parts on the current tested power equipment one to one.
10. a unmanned plane is characterized in that, comprise the unmanned plane body and be installed on the unmanned plane camera and as each described electric power line walking treating apparatus of claim 6-9, wherein:
Described electric power line walking treating apparatus is electrically connected with camera;
Described unmanned plane body is used for carrying described camera and carries out the picture of gathering tested power equipment;
Described camera is for the picture of gathering tested power equipment;
Described camera comprises infrared camera, ultraviolet camera and visible image capturing head.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101756952A CN103235830A (en) | 2013-05-13 | 2013-05-13 | Unmanned aerial vehicle (UAV)-based electric power line patrol method and device and UAV |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101756952A CN103235830A (en) | 2013-05-13 | 2013-05-13 | Unmanned aerial vehicle (UAV)-based electric power line patrol method and device and UAV |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103235830A true CN103235830A (en) | 2013-08-07 |
Family
ID=48883871
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013101756952A Pending CN103235830A (en) | 2013-05-13 | 2013-05-13 | Unmanned aerial vehicle (UAV)-based electric power line patrol method and device and UAV |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103235830A (en) |
Cited By (42)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103984355A (en) * | 2014-05-19 | 2014-08-13 | 华北电力大学 | Routing inspection flying robot and overhead power line distance prediction and maintaining method |
| CN104155995A (en) * | 2014-08-11 | 2014-11-19 | 江苏恒创软件有限公司 | Unmanned helicopter-based mining subsidence monitoring method |
| CN104316538A (en) * | 2014-11-07 | 2015-01-28 | 北京凯瑞德图像技术有限责任公司 | Flickering seam detection method and device for cable cladding process |
| CN104581054A (en) * | 2014-12-22 | 2015-04-29 | 深圳供电局有限公司 | Electric transmission line inspecting method and system based on videos |
| CN105160600A (en) * | 2015-09-23 | 2015-12-16 | 上海电巴新能源科技有限公司 | Iron tower structure inspection method for power supply line |
| CN105226556A (en) * | 2015-09-23 | 2016-01-06 | 深圳奥特迅电力设备股份有限公司 | A kind of power-line patrolling device and method |
| CN105263000A (en) * | 2015-10-16 | 2016-01-20 | 广西大学 | Large-scale photovoltaic power station inspection device based on double cameras carried on unmanned aerial vehicle |
| CN106092054A (en) * | 2016-05-30 | 2016-11-09 | 广东能飞航空科技发展有限公司 | A kind of power circuit identification precise positioning air navigation aid |
| CN106101658A (en) * | 2016-08-13 | 2016-11-09 | 哈尔滨理工大学 | Shaft tower foreign body and disappearance intelligent video on-line monitoring system |
| CN106099763A (en) * | 2016-08-18 | 2016-11-09 | 天津中翔腾航科技股份有限公司 | A kind of power transmission line unmanned machine inspection device |
| CN106131501A (en) * | 2016-08-13 | 2016-11-16 | 哈尔滨理工大学 | Electric line foreign matter and disappearance intelligent video on-line monitoring system |
| CN106155071A (en) * | 2016-07-12 | 2016-11-23 | 佛山杰致信息科技有限公司 | A kind of unmanned plane for line patrolling maintenance |
| CN106326932A (en) * | 2016-08-25 | 2017-01-11 | 北京每刻风物科技有限公司 | Power line inspection image automatic identification method based on neural network and power line inspection image automatic identification device thereof |
| CN106355187A (en) * | 2016-09-07 | 2017-01-25 | 西华大学 | Application of visual information to electrical equipment monitoring |
| CN106375378A (en) * | 2016-08-25 | 2017-02-01 | 北京每刻风物科技有限公司 | Application deployment method and system based on local area network client server structure |
| CN106468918A (en) * | 2015-08-18 | 2017-03-01 | 航天图景（北京）科技有限公司 | A kind of standardized data acquisition method of line data-logging and system |
| CN106506953A (en) * | 2016-10-28 | 2017-03-15 | 山东鲁能智能技术有限公司 | The substation equipment image acquisition method of servo is focused on and is exposed based on designated area |
| US9646205B2 (en) | 2015-05-26 | 2017-05-09 | HCL Technologies, Ltd. | System and a method for facilitating testing of plurality of devices using a drone |
| CN106646137A (en) * | 2016-12-28 | 2017-05-10 | 国网通用航空有限公司 | Method of detecting defect of power transmission line, defect detecting device, and defect detecting system |
| CN106710024A (en) * | 2016-11-28 | 2017-05-24 | 广州洪森科技有限公司 | Method and device for unattended automatic inspection and alarm |
| CN108010156A (en) * | 2017-11-01 | 2018-05-08 | 北京航天福道高技术股份有限公司 | A kind of round-the-clock autonomous oil field cruising inspection system |
| CN108055003A (en) * | 2017-10-24 | 2018-05-18 | 北京利泽菲尔文化科技有限公司 | A kind of autonomous inspection device of unmanned plane based on double light intelligent loads |
| CN108345820A (en) * | 2017-01-23 | 2018-07-31 | 许继集团有限公司 | High-tension apparatus image-recognizing method and device based on variety of components and component locations |
| CN108537912A (en) * | 2018-03-06 | 2018-09-14 | 全球能源互联网研究院有限公司 | A kind of power patrol unmanned machine based on intelligent image identification |
| CN108573233A (en) * | 2018-04-18 | 2018-09-25 | 国网四川省电力公司信息通信公司 | A kind of power grid ceramic insulator recognition methods based on image processing techniques |
| CN108957250A (en) * | 2018-04-10 | 2018-12-07 | 西安理工大学 | A kind of the multichannel diversity power line corona detection system and detection method of UAV system |
| CN109164112A (en) * | 2018-09-26 | 2019-01-08 | 深圳森阳环保材料科技有限公司 | A kind of cable surface defects detection system based on unmanned plane |
| CN109344282A (en) * | 2018-09-26 | 2019-02-15 | 国网电力科学研究院武汉南瑞有限责任公司 | A kind of automatic naming method of unmanned plane electric inspection process photo |
| WO2019042067A1 (en) * | 2017-08-29 | 2019-03-07 | 深圳市大疆创新科技有限公司 | Aerial vehicle control method, aerial vehicle, program and recording medium |
| CN109447946A (en) * | 2018-09-26 | 2019-03-08 | 中睿通信规划设计有限公司 | A kind of Overhead optical cable method for detecting abnormality |
| CN109493311A (en) * | 2017-09-08 | 2019-03-19 | 上海宝信软件股份有限公司 | A kind of random defect picture mode identification and matching process and system |
| CN110505477A (en) * | 2019-09-17 | 2019-11-26 | 普联技术有限公司 | Double filter test methods, device, equipment and storage medium |
| CN110892437A (en) * | 2017-07-05 | 2020-03-17 | 松下知识产权经营株式会社 | System and method for facilitating dynamic branding using autonomous vehicles |
| CN111114780A (en) * | 2019-12-20 | 2020-05-08 | 山东大学 | Unmanned aerial vehicle steel bar detection standard part placing and recycling system and method |
| CN111604888A (en) * | 2020-05-29 | 2020-09-01 | 珠海格力电器股份有限公司 | Inspection robot control method, inspection system, storage medium and electronic device |
| CN111726571A (en) * | 2020-01-05 | 2020-09-29 | 杨文娟 | High-voltage line distribution shape detection system |
| CN111812545A (en) * | 2020-07-07 | 2020-10-23 | 苏州精濑光电有限公司 | Line defect detection method, device, equipment and medium |
| CN112445240A (en) * | 2020-11-26 | 2021-03-05 | 广东电网有限责任公司 | Automatic line patrol method and automatic line patrol unmanned aerial vehicle |
| CN112837273A (en) * | 2021-01-12 | 2021-05-25 | 云南电网有限责任公司电力科学研究院 | Image verification method, system, computer equipment and storage medium |
| CN113191336A (en) * | 2021-06-04 | 2021-07-30 | 绍兴建元电力集团有限公司 | Electric power hidden danger identification method and system based on image identification |
| CN113867406A (en) * | 2021-11-10 | 2021-12-31 | 广东电网能源发展有限公司 | Unmanned aerial vehicle-based line inspection method and system, intelligent equipment and storage medium |
| CN114460963A (en) * | 2021-12-27 | 2022-05-10 | 河南福多电力工程有限公司 | Substation unmanned aerial vehicle automatic inspection system and operation method thereof |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101957325A (en) * | 2010-10-14 | 2011-01-26 | 山东鲁能智能技术有限公司 | Substation equipment appearance abnormality recognition method based on substation inspection robot |
-
2013
- 2013-05-13 CN CN2013101756952A patent/CN103235830A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101957325A (en) * | 2010-10-14 | 2011-01-26 | 山东鲁能智能技术有限公司 | Substation equipment appearance abnormality recognition method based on substation inspection robot |
Non-Patent Citations (1)
| Title |
|---|
| 刘建友: "基于航拍图像的绝缘子状态检测", 《工程科技Ⅱ辑》, 15 May 2011 (2011-05-15) * |
Cited By (50)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103984355A (en) * | 2014-05-19 | 2014-08-13 | 华北电力大学 | Routing inspection flying robot and overhead power line distance prediction and maintaining method |
| CN104155995A (en) * | 2014-08-11 | 2014-11-19 | 江苏恒创软件有限公司 | Unmanned helicopter-based mining subsidence monitoring method |
| CN104155995B (en) * | 2014-08-11 | 2017-05-31 | 江苏恒创软件有限公司 | A kind of mining collapse monitoring method based on unmanned plane |
| CN104316538A (en) * | 2014-11-07 | 2015-01-28 | 北京凯瑞德图像技术有限责任公司 | Flickering seam detection method and device for cable cladding process |
| CN104581054A (en) * | 2014-12-22 | 2015-04-29 | 深圳供电局有限公司 | Electric transmission line inspecting method and system based on videos |
| US9646205B2 (en) | 2015-05-26 | 2017-05-09 | HCL Technologies, Ltd. | System and a method for facilitating testing of plurality of devices using a drone |
| CN106468918B (en) * | 2015-08-18 | 2020-03-20 | 航天图景（北京）科技有限公司 | Standardized data acquisition method and system for line inspection |
| CN106468918A (en) * | 2015-08-18 | 2017-03-01 | 航天图景（北京）科技有限公司 | A kind of standardized data acquisition method of line data-logging and system |
| CN105160600A (en) * | 2015-09-23 | 2015-12-16 | 上海电巴新能源科技有限公司 | Iron tower structure inspection method for power supply line |
| CN105226556A (en) * | 2015-09-23 | 2016-01-06 | 深圳奥特迅电力设备股份有限公司 | A kind of power-line patrolling device and method |
| CN105263000A (en) * | 2015-10-16 | 2016-01-20 | 广西大学 | Large-scale photovoltaic power station inspection device based on double cameras carried on unmanned aerial vehicle |
| CN106092054A (en) * | 2016-05-30 | 2016-11-09 | 广东能飞航空科技发展有限公司 | A kind of power circuit identification precise positioning air navigation aid |
| CN106155071A (en) * | 2016-07-12 | 2016-11-23 | 佛山杰致信息科技有限公司 | A kind of unmanned plane for line patrolling maintenance |
| CN106131501A (en) * | 2016-08-13 | 2016-11-16 | 哈尔滨理工大学 | Electric line foreign matter and disappearance intelligent video on-line monitoring system |
| CN106101658A (en) * | 2016-08-13 | 2016-11-09 | 哈尔滨理工大学 | Shaft tower foreign body and disappearance intelligent video on-line monitoring system |
| CN106099763A (en) * | 2016-08-18 | 2016-11-09 | 天津中翔腾航科技股份有限公司 | A kind of power transmission line unmanned machine inspection device |
| CN106375378A (en) * | 2016-08-25 | 2017-02-01 | 北京每刻风物科技有限公司 | Application deployment method and system based on local area network client server structure |
| CN106326932A (en) * | 2016-08-25 | 2017-01-11 | 北京每刻风物科技有限公司 | Power line inspection image automatic identification method based on neural network and power line inspection image automatic identification device thereof |
| CN106375378B (en) * | 2016-08-25 | 2020-08-28 | 北京每刻风物科技有限公司 | Application deployment method and system based on local area network client server structure |
| CN106355187A (en) * | 2016-09-07 | 2017-01-25 | 西华大学 | Application of visual information to electrical equipment monitoring |
| CN106506953A (en) * | 2016-10-28 | 2017-03-15 | 山东鲁能智能技术有限公司 | The substation equipment image acquisition method of servo is focused on and is exposed based on designated area |
| CN106710024A (en) * | 2016-11-28 | 2017-05-24 | 广州洪森科技有限公司 | Method and device for unattended automatic inspection and alarm |
| CN106646137A (en) * | 2016-12-28 | 2017-05-10 | 国网通用航空有限公司 | Method of detecting defect of power transmission line, defect detecting device, and defect detecting system |
| CN108345820A (en) * | 2017-01-23 | 2018-07-31 | 许继集团有限公司 | High-tension apparatus image-recognizing method and device based on variety of components and component locations |
| CN110892437A (en) * | 2017-07-05 | 2020-03-17 | 松下知识产权经营株式会社 | System and method for facilitating dynamic branding using autonomous vehicles |
| WO2019042067A1 (en) * | 2017-08-29 | 2019-03-07 | 深圳市大疆创新科技有限公司 | Aerial vehicle control method, aerial vehicle, program and recording medium |
| CN109493311B (en) * | 2017-09-08 | 2022-03-29 | 上海宝信软件股份有限公司 | Irregular defect picture pattern recognition and matching method and system |
| CN109493311A (en) * | 2017-09-08 | 2019-03-19 | 上海宝信软件股份有限公司 | A kind of random defect picture mode identification and matching process and system |
| CN108055003A (en) * | 2017-10-24 | 2018-05-18 | 北京利泽菲尔文化科技有限公司 | A kind of autonomous inspection device of unmanned plane based on double light intelligent loads |
| CN108010156A (en) * | 2017-11-01 | 2018-05-08 | 北京航天福道高技术股份有限公司 | A kind of round-the-clock autonomous oil field cruising inspection system |
| CN108537912A (en) * | 2018-03-06 | 2018-09-14 | 全球能源互联网研究院有限公司 | A kind of power patrol unmanned machine based on intelligent image identification |
| CN108957250A (en) * | 2018-04-10 | 2018-12-07 | 西安理工大学 | A kind of the multichannel diversity power line corona detection system and detection method of UAV system |
| CN108573233A (en) * | 2018-04-18 | 2018-09-25 | 国网四川省电力公司信息通信公司 | A kind of power grid ceramic insulator recognition methods based on image processing techniques |
| CN109447946B (en) * | 2018-09-26 | 2021-09-07 | 中睿通信规划设计有限公司 | Overhead communication optical cable abnormality detection method |
| CN109344282A (en) * | 2018-09-26 | 2019-02-15 | 国网电力科学研究院武汉南瑞有限责任公司 | A kind of automatic naming method of unmanned plane electric inspection process photo |
| CN109164112A (en) * | 2018-09-26 | 2019-01-08 | 深圳森阳环保材料科技有限公司 | A kind of cable surface defects detection system based on unmanned plane |
| CN109447946A (en) * | 2018-09-26 | 2019-03-08 | 中睿通信规划设计有限公司 | A kind of Overhead optical cable method for detecting abnormality |
| CN110505477A (en) * | 2019-09-17 | 2019-11-26 | 普联技术有限公司 | Double filter test methods, device, equipment and storage medium |
| CN111114780A (en) * | 2019-12-20 | 2020-05-08 | 山东大学 | Unmanned aerial vehicle steel bar detection standard part placing and recycling system and method |
| CN111114780B (en) * | 2019-12-20 | 2021-04-02 | 山东大学 | Unmanned aerial vehicle steel bar detection standard part placing and recycling system and method |
| CN111726571A (en) * | 2020-01-05 | 2020-09-29 | 杨文娟 | High-voltage line distribution shape detection system |
| CN111604888A (en) * | 2020-05-29 | 2020-09-01 | 珠海格力电器股份有限公司 | Inspection robot control method, inspection system, storage medium and electronic device |
| CN111604888B (en) * | 2020-05-29 | 2021-09-14 | 珠海格力电器股份有限公司 | Inspection robot control method, inspection system, storage medium and electronic device |
| CN111812545A (en) * | 2020-07-07 | 2020-10-23 | 苏州精濑光电有限公司 | Line defect detection method, device, equipment and medium |
| CN112445240A (en) * | 2020-11-26 | 2021-03-05 | 广东电网有限责任公司 | Automatic line patrol method and automatic line patrol unmanned aerial vehicle |
| CN112837273A (en) * | 2021-01-12 | 2021-05-25 | 云南电网有限责任公司电力科学研究院 | Image verification method, system, computer equipment and storage medium |
| CN113191336A (en) * | 2021-06-04 | 2021-07-30 | 绍兴建元电力集团有限公司 | Electric power hidden danger identification method and system based on image identification |
| CN113191336B (en) * | 2021-06-04 | 2022-01-14 | 绍兴建元电力集团有限公司 | Electric power hidden danger identification method and system based on image identification |
| CN113867406A (en) * | 2021-11-10 | 2021-12-31 | 广东电网能源发展有限公司 | Unmanned aerial vehicle-based line inspection method and system, intelligent equipment and storage medium |
| CN114460963A (en) * | 2021-12-27 | 2022-05-10 | 河南福多电力工程有限公司 | Substation unmanned aerial vehicle automatic inspection system and operation method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103235830A (en) | Unmanned aerial vehicle (UAV)-based electric power line patrol method and device and UAV | |
| CN107862705B (en) | Unmanned aerial vehicle small target detection method based on motion characteristics and deep learning characteristics | |
| US10269138B2 (en) | UAV inspection method for power line based on human visual system | |
| CN105373135B (en) | A kind of method and system of aircraft docking guidance and plane type recognition based on machine vision | |
| CN111784633B (en) | Insulator defect automatic detection algorithm for electric power inspection video | |
| CN103487729B (en) | Based on the power equipments defect detection method that ultraviolet video and infrared video merge | |
| Li et al. | Towards automatic power line detection for a UAV surveillance system using pulse coupled neural filter and an improved Hough transform | |
| Liu et al. | High precision detection algorithm based on improved RetinaNet for defect recognition of transmission lines | |
| KR20200060372A (en) | Thermography image processing using a neural network to identify the bottom corrosion (CUI) of insulation | |
| CN109961460A (en) | A kind of multiple target method for inspecting based on improvement YOLOv3 model | |
| CN103279765B (en) | Steel wire rope surface damage detection method based on images match | |
| CN107588733A (en) | A kind of abrasion of pantograph pan on-line measuring device and method based on image | |
| CN107527037A (en) | Blue-green algae identification and analysis system based on unmanned aerial vehicle remote sensing data | |
| CN115862073B (en) | Substation hazard bird species target detection and identification method based on machine vision | |
| CN112528979B (en) | Transformer substation inspection robot obstacle distinguishing method and system | |
| CN113962973A (en) | Power transmission line unmanned aerial vehicle intelligent inspection system and method based on satellite technology | |
| CN114898238A (en) | Wild animal remote sensing identification method and device | |
| Zhao et al. | Image-based comprehensive maintenance and inspection method for bridges using deep learning | |
| CN114283137A (en) | Photovoltaic module hot spot defect detection method based on multi-scale characteristic diagram inference network | |
| CN115908354A (en) | Photovoltaic panel defect detection method based on double-scale strategy and improved YOLOV5 network | |
| CN112883969B (en) | Rainfall intensity detection method based on convolutional neural network | |
| CN116485802B (en) | Insulator flashover defect detection method, device, equipment and storage medium | |
| Kähler et al. | Automating powerline inspection: A novel multisensor system for data analysis using deep learning | |
| CN117197700A (en) | Intelligent unmanned inspection contact net defect identification system | |
| House et al. | Using deep learning to identify potential roof spaces for solar panels |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 100000 Beijing city Chaoyang District Road No. 9 Fu A unit 301 Applicant after: Beijing Powervision Technology Inc. Address before: 100000 Beijing city Chaoyang District Road No. 9 Fu A unit 301 Applicant before: Beijing Zhendi Technology Co., Ltd. |
|
| COR | Change of bibliographic data | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130807 |