CN106599865A - Disconnecting link state recognition device and method - Google Patents
Disconnecting link state recognition device and method Download PDFInfo
- Publication number
- CN106599865A CN106599865A CN201611189903.4A CN201611189903A CN106599865A CN 106599865 A CN106599865 A CN 106599865A CN 201611189903 A CN201611189903 A CN 201611189903A CN 106599865 A CN106599865 A CN 106599865A
- Authority
- CN
- China
- Prior art keywords
- disconnecting link
- matrix
- principal component
- mapping
- real time
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a disconnecting link state recognition device and method and relates to the field of power industry dispatching. According to the disconnecting link state recognition device and method, a principal component analysis network algorithm is utilized to perform feature extraction on an object region of a real-time image of a disconnecting link; extracted features are classified according to a support vector machine obtained through training in advance; in this way, the real-time state of the disconnecting link is determined, the recognition precision of the real-time state of the disconnecting link is high, the reliability of the obtained real-time state of the disconnecting link is high, and reference value is high.
Description
Technical field
The present invention relates to power industry scheduling field, in particular to a kind of disconnecting link status identification means and method.
Background technology
With the development that State Grid Corporation of China's intelligent grid is built, existing power distribution network power scheduling, data check and auxiliary
Decision-making can not complete to support lean regulatory requirement that some scheduling means based on artificial operation and confirmation are easily produced wrong
By mistake so that there is security incident.Under the overall background that intelligent substation is built, video auxiliary monitoring system is built in transformer station,
The remote monitoring of main primary equipment in transformer station is realized, using the high-grade intelligent information monitoring technology based on machine vision
Using contributing to reducing because the equipment that personnel's carelessness brings loses, operator safety risk is reduced.
It is of the prior art to be to the analysis of disconnecting link real-time status：The disconnecting link real time imaging for collecting is utilized into convolutional Neural net
The deep learning algorithm of network is carrying out image characteristic analysis.Convolutional neural networks algorithm has the network knot of multilamellar from output is input to
Structure, needs substantial amounts of multifarious data sample, once data sample is not enough, the advantage of algorithm just cannot embody, on the contrary so
Deep network structure easily causes over-fitting and cannot obtain high differentiation rate.And in the actually located environment of disconnecting link, it is impossible to
Enough multifarious disconnecting link samples are obtained, and there is very strong homogeneity between disconnecting link sample, this causes convolutional neural networks
Shortcoming will be exaggerated so as to disconnecting link real-time status identification degree of accuracy it is low, obtain disconnecting link real-time status reliability
Difference, reference value is low.
The content of the invention
In view of this, the purpose of the embodiment of the present invention is to provide a kind of disconnecting link status identification means and method, to improve
The problems referred to above.
In a first aspect, a kind of disconnecting link status identification means are embodiments provided, the disconnecting link status identification means
Including：
Information transmit-receive unit, for receiving the disconnecting link real time imaging that an image collecting device sends；
Target area recognition unit, for being identified to the target area of disconnecting link real time imaging；
Image characteristics extraction unit, for the target area using principal component analysiss network algorithm to the disconnecting link real time imaging
Domain carries out feature extraction；
Disconnecting link real-time status determining unit, the feature for the support vector machine that obtain according to training in advance to extracting is entered
Row classification, so that it is determined that disconnecting link real-time status.
Second aspect, the embodiment of the present invention additionally provides a kind of disconnecting link state identification method, the disconnecting link state recognition side
Method includes：
Receive the disconnecting link real time imaging of image collecting device transmission；
The target area of disconnecting link real time imaging is identified；
Feature extraction is carried out to the target area of the disconnecting link real time imaging using principal component analysiss network algorithm；
Feature of the support vector machine that foundation training in advance is obtained to extracting is classified, so that it is determined that the real-time shape of disconnecting link
State.
Compared with prior art, the present invention is provided a kind of disconnecting link status identification means and method, by using main constituent
Analysis network algorithm carries out feature extraction to the target area of the disconnecting link real time imaging；The support obtained according to training in advance to
Amount machine is classified to the feature extracted, so that it is determined that disconnecting link real-time status, and so that disconnecting link real-time status is known
Other degree of accuracy is high, obtains disconnecting link real-time status reliability height, and reference value is high.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Description of the drawings
To make purpose, technical scheme and the advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
The a part of embodiment of the present invention, rather than the embodiment of whole.Present invention enforcement generally described and illustrated in accompanying drawing herein
The component of example can be arranged and designed with a variety of configurations.Therefore, reality of the invention below to providing in the accompanying drawings
The detailed description for applying example is not intended to limit the scope of claimed invention, but is merely representative of the selected enforcement of the present invention
Example.Based on the embodiment in the present invention, what those of ordinary skill in the art were obtained under the premise of creative work is not made
Every other embodiment, belongs to the scope of protection of the invention.
Fig. 1 is server difference remote terminal provided in an embodiment of the present invention, the interactive schematic diagram of intelligent terminal；
Fig. 2 is the structured flowchart of server provided in an embodiment of the present invention；
Fig. 3 is the high-level schematic functional block diagram of disconnecting link status identification means provided in an embodiment of the present invention；
Fig. 4 is the subelement schematic diagram of image characteristics extraction unit provided in an embodiment of the present invention；
Fig. 5 is the flow chart of disconnecting link state identification method provided in an embodiment of the present invention；
Fig. 6 is the flow chart of the concrete steps of step 504 provided in an embodiment of the present invention.
Icon：100- servers；200- remote terminals；300- intelligent terminal；101- disconnecting link status identification means；At 102-
Reason device；103- memorizeies；104- storage controls；105- Peripheral Interfaces；301- information transmit-receive units；302- target areas recognize
Unit；303- image characteristics extraction units；304- disconnecting link real-time status determining units；305- judging units；306- fault cues
Information generating unit；401- first goes average block matrix to obtain subelement；402- fisrt feature matrix obtains subelement；403-
Two go average block matrix to obtain subelement；404- second characteristic matrixs obtain subelement；405- Hash coded sub-units；406- blocks
Extension histogram feature obtains subelement.
Specific embodiment
Below in conjunction with accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Ground description, it is clear that described embodiment is only a part of embodiment of the invention, rather than the embodiment of whole.Generally exist
Herein the component of the embodiment of the present invention described and illustrated in accompanying drawing can be arranged and designed with a variety of configurations.Cause
This, below the detailed description of the embodiments of the invention to providing in the accompanying drawings is not intended to limit claimed invention
Scope, but it is merely representative of the selected embodiment of the present invention.Based on embodiments of the invention, those skilled in the art are not doing
The every other embodiment obtained on the premise of going out creative work, belongs to the scope of protection of the invention.
The disconnecting link status identification means that the embodiment of the present invention is provided can be applicable to applied environment as shown in Figure 1 with method
In.As shown in figure 1, server 100, remote terminal 200 and intelligent terminal 300 are located in network, by the webserver
100th, remote terminal 200 and intelligent terminal 300 carry out data interaction.As shown in Fig. 2 being that the square frame of the server 300 shows
It is intended to.
The embodiment of the present invention propose disconnecting link status identification means and method, there is provided a kind of disconnecting link status identification means with
Method, the disconnecting link status identification means are applicable to server 100 with method.The server 100 may be, but not limited to, net
Network server, database server, cloud server etc..
As shown in figure 1, being the block diagram of the server 100.The server 100 is filled including disconnecting link state recognition
Put 101, processor 102, memorizer 103, storage control 104 and Peripheral Interface 105.
The memorizer 103, storage control 104 and processor 102, each element is directly or indirectly electrical each other
Connection, to realize the transmission or interaction of data.For example, these elements each other can be by one or more communication bus or letter
Number line is realized being electrically connected with.Remote sensing image target area detection means can be with software or firmware including at least one
(firmware) form is stored in the memorizer 103 or is solidificated in the operating system of the server 100
Software function module in (operating system, OS).The processor 102 is used to perform what is stored in memorizer 103
Executable module, for example, software function module or computer journey that remote sensing image target area detection means includes
Sequence.
Wherein, memorizer 103 may be, but not limited to, random access memory 103 (Random Access Memory,
RAM), read only memory 103Read Only Memory, ROM), (Programmable of programmable read only memory 103
Read-Only Memory, PROM), (the Erasable Programmable Read-Only of erasable read-only memory 103
Memory, EPROM), (the Electric Erasable Programmable Read-Only of electricallyerasable ROM (EEROM) 103
Memory, EEPROM) etc..Wherein, memorizer 103 be used for storage program, the processor 102 after execute instruction is received,
Described program is performed, the side performed by the server 100 of the stream process definition that aforementioned embodiment of the present invention any embodiment is disclosed
Method can apply in processor 102, or be realized by processor 102.
A kind of possibly IC chip of processor 102, the disposal ability with signal.Above-mentioned processor 102 can
Being general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network processing unit
(Network Processor, abbreviation NP) etc.；Can also be digital signal processor (DSP), special IC (ASIC),
Ready-made programmable gate array (FPGA) either other PLDs, discrete gate or transistor logic, discrete hard
Part component.Can realize or perform disclosed each method in the embodiment of the present invention, step and logic diagram.General processor
Can be microprocessor or the processor 102 can also be any conventional processor 102 etc..
The Peripheral Interface 105 is by various input/output devices coupled to processor 102 and memorizer 103.At some
In embodiment, Peripheral Interface 105, processor 102 and storage control 104 can be realized in one single chip.Other one
In a little examples, they can be realized respectively by independent chip.
Refer to Fig. 3, a kind of disconnecting link status identification means 101 provided in an embodiment of the present invention, the disconnecting link state recognition
Device 101 includes information transmit-receive unit 301, target area recognition unit 302, the real-time shape of image characteristics extraction unit 303, disconnecting link
State determining unit 304, judging unit 305 and fault cues information generating unit 306.
Described information Transmit-Receive Unit 301 is additionally operable to receive the dispatch command that a remote terminal 200 sends, wherein, the tune
Degree instruction includes the disconnecting link expectation state.
For example, staff's hand-held remote control terminal 200 sends the dispatch command of closure to disconnecting link, what the dispatch command included
The disconnecting link expectation state is closure state.
Described information Transmit-Receive Unit 301 is used to receive disconnecting link real time imaging and the device body that an image collecting device sends
Part information.
Wherein, image collecting device can be high-definition camera, and the disconnecting link real-time status residing for disconnecting link real time imaging includes
But it has been not limited to separated position, closure state and ground state.
The target area recognition unit 302 is used to be identified the target area of disconnecting link real time imaging.
Specifically, the target area of disconnecting link real time imaging is identified using image recognition algorithm, wherein, disconnecting link reality
When image target area including disconnecting link knob position.
Described image feature extraction unit 303 is used for using principal component analysiss network algorithm to the disconnecting link real time imaging
Target area carries out feature extraction.
Specifically, as shown in figure 4, described image feature extraction unit 303 includes：
First goes average block matrix to obtain subelement 401, for each of the target area of the disconnecting link real time imaging
Pixel carries out block and samples and go all the first of meansigma methodss acquisition ground floor principal component analysiss mapping to remove average block matrix.
Specifically, for the target area of disconnecting link real time imagingIn each pixel, around each pixel
Carry out a k1×k2Block sampling (here sampling is that individual element is carried out, therefore is completely cover type sampling), and will be every
Individual block all carries out average value processing, collects all of piece of the target area of disconnecting link real time imaging i.e.
Average value processing is carried out to each block, matrix is obtainedAs i-th disconnecting link real time imaging
Target area IiGround floor principal component analysiss network mapping first remove average block matrix, the mesh to all disconnecting link real time imagings
Mark region carries out identical process, cascaded, and average first is gone in the target area for finally giving all disconnecting link real time imagings
Block matrix：
Fisrt feature matrix obtains subelement 402, for removing the covariance matrix of average block matrix to each described first
The first wave filter that front X main characteristic vector obtains the mapping of ground floor principal component analysiss is asked for, according to first wave filter pair
The target area of the disconnecting link real time imaging carries out process of convolution, so as to obtain the fisrt feature of ground floor principal component analysiss mapping
Matrix.
It is assumed that the wave filter quantity in i-th layer of ground floor principal component analysiss mapping is ni, due to principal component analysiss mapping
Purpose be to find series of standards orthogonal matrix to minimize reconstructed error, and solutions of this problem be exactly classics it is main into
Analysis, i.e. the covariance matrix XX of matrix XTFront niIndividual main characteristic vector, therefore the first of ground floor principal component analysiss mapping
Wave filter is expressed as follows：
Wherein,It is by vectorIt is mapped to matrixFunction, el(XXT) represent covariance
Matrix XXTL-th main characteristic vector.FormulaImplication
Exactly extract the front n of the covariance matrix of X1Individual main characteristic vector come constitute ground floor principal component analysiss mapping ground floor it is main into
Divide analysis filter, process of convolution is carried out to the target area of disconnecting link real time imaging according to first wave filter, so as to obtain
The fisrt feature matrix of ground floor principal component analysiss mapping.
Second goes average block matrix to obtain subelement 403, samples simultaneously for carrying out block to fisrt feature matrix each described
Meansigma methodss are gone, obtain the mapping of second layer principal component analysiss second removes average block matrix.
Specifically, all fisrt feature matrixes that ground floor principal component analysis are exported are carried out again into principal component analysiss to reflect
Penetrate.Each the fisrt feature matrix for exporting first passes through formula
Carry out two-dimensional convolution mapping.It should be noted that before two-dimensional convolution mapping is carried out, needing to carry out edge zero padding
Operation, to ensure equivalently-sized (because convolution operation can cause size to diminish) of mapping result and original image.To two-dimensional convolution
Each fisrt feature matrix after mapping block carries out block sampling, goes average, cascade to obtain the of the mapping of second layer principal component analysiss
Two remove average block matrix
Second characteristic matrix obtains subelement 404, for removing the covariance matrix of average block matrix to each described second
The second wave filter that front Y main characteristic vector obtains the mapping of second layer principal component analysiss is asked for, according to second wave filter pair
The fisrt feature matrix of ground floor principal component analysiss mapping carries out process of convolution, so as to obtain the mapping of second layer principal component analysiss
Second characteristic matrix.
Specifically, the second wave filter is again by selection covariance matrix YYTCorresponding main characteristic vector constituting, therefore
The second wave filter now is expressed as follows：
Hypothesis carries out having n when ground floor principal component analysiss map1Individual first wave filter, exports during ground floor principal component analysiss
n1Individual output matrix, second layer principal component analysiss are directed to each fisrt feature matrix, can all produce n2Individual output matrix.For every
Individual doubtful candidate region, second layer principal component analysiss output n1n2Individual second characteristic matrix, second characteristic matrix can be used for following formula
Represent：
Hash coded sub-units 405, for binary conversion treatment to be carried out to the second characteristic matrix and Hash coding is carried out.
Each second characteristic matrix of output is taken first, carries out binary conversion treatment, then to each after binary conversion treatment
Two eigenmatrixes utilize formulaCarry out the whole value square after Hash is encoded so as to obtain Hash coding
Battle array, coding digit is identical with the second number of filter.
Block extension histogram feature extracts subelement, for carrying out to the second characteristic matrix after each Hash coding point
Block is simultaneously counted the rectangular histogram in each block, connects the rectangular histogram in all pieces so as to extract the target of the disconnecting link real time imaging
The block extension histogram feature in region.
Second characteristic matrix after above-mentioned binaryzation, Hash coded treatment, each Hash coding is converted into whole
Value matrixNext, by each whole value matrixBe divided into B blocks, the histogram information of counting statistics each block, then by each
The histogram feature of block is cascaded, and is designated asFinally give the block extension histogram feature of all whole value matrixs
Fi, wherein,
The disconnecting link real-time status determining unit 304 is used for the support vector machine that obtain according to training in advance to extracting
Block extension rectangular histogram spy classified, so that it is determined that disconnecting link real-time status.
The disconnecting link real-time status determining unit 304 is used for the support vector machine that obtain according to training in advance to extracting
Feature is classified, so that it is determined that disconnecting link real-time status.
Specifically, the block rectangular histogram extension feature for obtaining is input into into SVM separator majorized functionsSo that it is determined that disconnecting link real-time status, wherein, f (x) represents disconnecting link real-time status
Classification results, b is classification thresholds, can be tried to achieve with any one supporting vector, or by two apoplexy due to endogenous wind, any pair supporting vector
Take intermediate value to try to achieve.
The judging unit 305 is used to judge whether the disconnecting link real-time status determined is consistent with the disconnecting link expectation state.
Fault cues information generating unit 306 be used for if it is determined that disconnecting link real-time status differ with the disconnecting link expectation state
Cause, generate fault cues information.
Specifically, if Previous work personnel's hand-held remote control terminal 200 sends the dispatch command of closure to disconnecting link, in disconnecting link just
The often situation of operation, the operation that disconnecting link should be closed according to dispatch command execution, so that disconnecting link state reaches closure state,
So that the disconnecting link real-time status determined is consistent with the disconnecting link expectation state.If it is determined that disconnecting link real-time status and disconnecting link phase
When prestige state is inconsistent, the failure occurred to the scheduling of disconnecting link, the fault cues of fault cues information generating unit 306 letter are illustrated
Breath, so as to inform staff can maintenance.
Described information Transmit-Receive Unit 301 be additionally operable to by the fault cues information send to described device identity information close
The intelligent terminal 300 of connection.
Due to the management and maintenance personnel difference of the disconnecting link of different operating rooms, therefore to gathering each figure of the image of disconnecting link
As harvester gives identity information, when the scheduling of one of disconnecting link is broken down, just described fault cues information
Send to the intelligent terminal 300 associated with described device identity information, so as to the management for reaching the disconnecting link for notifying the operating room is tieed up
Repair the purpose of personnel.
Fig. 5 is referred to, the embodiment of the present invention additionally provides a kind of disconnecting link state identification method, it should be noted that this reality
The technique effect for applying the disconnecting link state identification method that example is provided, its ultimate principle and generation is identical with above-described embodiment, is letter
Describe, the present embodiment part does not refer to part, refers to the corresponding contents in above-described embodiment.The disconnecting link state recognition side
Method includes：
Step S501：Receive the dispatch command of the transmission of a remote terminal 200.
Wherein, the dispatch command includes the disconnecting link expectation state.It is to be appreciated that being held using information transmit-receive unit 301
Row step S501.
Step S502：Receive the disconnecting link real time imaging and device identity information of image collecting device transmission.
Wherein, the disconnecting link real-time status includes separated position, closure state and ground state.It is to be appreciated that
Using execution step S502 of information transmit-receive unit 301.
Step S503：The target area of disconnecting link real time imaging is identified.
It is to be appreciated that using execution step S503 of target area recognition unit 302.
Step S504：Feature is carried out using principal component analysiss network algorithm to the target area of the disconnecting link real time imaging to carry
Take.
It is to be appreciated that using execution step S504 of image characteristics extraction unit 303.
Specifically, as shown in fig. 6, step S504 includes：
Step S5041：Carry out block to each pixel of the target area of the disconnecting link real time imaging to sample and go average
Value obtains all the first of ground floor principal component analysiss mapping and removes average block matrix.
It is to be appreciated that going average block matrix to obtain unit execution step S5041 of subelement 401 using first.
Step S5042：Go the covariance matrix of average block matrix to ask for front X main characteristic vector to each described first to obtain
The first wave filter of ground floor principal component analysiss mapping is obtained, according to target of first wave filter to the disconnecting link real time imaging
Region carries out process of convolution, so as to obtain the fisrt feature matrix of ground floor principal component analysiss mapping.
It is to be appreciated that obtaining execution step S5042 of subelement 402 using fisrt feature matrix.
Step S5043：Block is carried out to fisrt feature matrix each described to sample and go meansigma methodss, obtains second layer main constituent
The second of analysis mapping removes average block matrix.
It is to be appreciated that going average block matrix to obtain execution step S5043 of subelement 403 using second.
Step S5044：Go the covariance matrix of average block matrix to ask for front Y main characteristic vector to each described second to obtain
The second wave filter of second layer principal component analysiss mapping is obtained, ground floor principal component analysiss are mapped according to second wave filter
Fisrt feature matrix carries out process of convolution, so as to obtain the second characteristic matrix of second layer principal component analysiss mapping.
It is to be appreciated that using second characteristic matrix obtaining unit execution step S5044.
Step S5045：Binary conversion treatment is carried out to the second characteristic matrix and Hash coding is carried out.
It is to be appreciated that using execution step S5045 of Hash coded sub-units 405.
Step S5046：Second characteristic matrix after each Hash coding is carried out by piecemeal and counted in each block
Rectangular histogram, connects the rectangular histogram in all pieces so as to the block extension rectangular histogram for extracting the target area of the disconnecting link real time imaging is special
Levy.
It is to be appreciated that extracting execution step S5046 of subelement 406 using block histogram feature.
Step S505：Feature of the support vector machine that foundation training in advance is obtained to extracting is classified, so that it is determined that
Disconnecting link real-time status.
It is to be appreciated that using execution step S505 of disconnecting link real-time status determining unit 304.
Specifically, step S505 includes that block of the support vector machine obtained according to training in advance to extracting extends rectangular histogram
Spy is classified, so that it is determined that disconnecting link real-time status.
Step S506：Whether the disconnecting link real-time status that judgement is determined is consistent with the disconnecting link expectation state；If it is not, then performing
Step S507.
It is to be appreciated that using execution step S506 of judging unit 305.
Step S507：Generate fault cues information.
It is to be appreciated that using fault cues information unit execution step S507.
Step S508：The fault cues information is sent to the intelligent terminal 300 associated with described device identity information.
It is to be appreciated that using execution step S508 of information transmit-receive unit 301.
In sum, a kind of disconnecting link status identification means provided in an embodiment of the present invention and method, by using main constituent
Analysis network algorithm carries out feature extraction to the target area of the disconnecting link real time imaging；The support obtained according to training in advance to
Amount machine is classified to the feature extracted, so that it is determined that disconnecting link real-time status, and so that disconnecting link real-time status is known
Other degree of accuracy is high, obtains disconnecting link real-time status reliability height, and reference value is high.
In several embodiments provided herein, it should be understood that disclosed apparatus and method, it is also possible to pass through
Other modes are realized.Device embodiment described above is only schematic, for example, the flow chart and block diagram in accompanying drawing
Show the device of multiple embodiments of the invention, the architectural framework in the cards of method and computer program product,
Function and operation.At this point, each square frame in flow chart or block diagram can represent the one of module, program segment or a code
Part a, part for the module, program segment or code is used to realize holding for the logic function of regulation comprising one or more
Row instruction.It should also be noted that at some as in the implementations replaced, the function of being marked in square frame can also be being different from
The order marked in accompanying drawing occurs.For example, two continuous square frames can essentially be performed substantially in parallel, and they are sometimes
Can perform in the opposite order, this is depending on involved function.It is also noted that every in block diagram and/or flow chart
The combination of individual square frame and block diagram and/or the square frame in flow chart, can be with the special base of the function or action for performing regulation
Realize in the system of hardware, or can be realized with the combination of computer instruction with specialized hardware.
In addition, each functional module in each embodiment of the invention can integrate to form an independent portion
Divide, or modules individualism, it is also possible to which two or more modules are integrated to form an independent part.
If the function is realized and as independent production marketing or when using using in the form of software function module, can be with
In being stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be individual
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the invention.
And aforesaid storage medium includes：USB flash disk, portable hard drive, read only memory (ROM, Read-Only Memory), random access memory are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.Need
Illustrate, herein, such as first and second or the like relational terms be used merely to by an entity or operation with
Another entity or operation make a distinction, and not necessarily require or imply these entities or there is any this reality between operating
The relation or order on border.And, term " including ", "comprising" or its any other variant are intended to the bag of nonexcludability
Contain, so that a series of process, method, article or equipment including key elements is not only including those key elements, but also including
Other key elements being not expressly set out, or also include the key element intrinsic for this process, method, article or equipment.
In the absence of more restrictions, the key element for being limited by sentence "including a ...", it is not excluded that including the key element
Process, method, article or equipment in also there is other identical element.
The preferred embodiments of the present invention are the foregoing is only, the present invention is not limited to, for the skill of this area
For art personnel, the present invention can have various modifications and variations.It is all within the spirit and principles in the present invention, made any repair
Change, equivalent, improvement etc., should be included within the scope of the present invention.It should be noted that：Similar label and letter exists
Similar terms is represented in figure below, therefore, once being defined in a certain Xiang Yi accompanying drawing, then it is not required in subsequent accompanying drawing
It is further defined and is explained.
The above, the only specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, all should contain
Cover within protection scope of the present invention.Therefore, protection scope of the present invention described should be defined by scope of the claims.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or deposit between operating
In any this actual relation or order.And, term " including ", "comprising" or its any other variant are intended to
Nonexcludability is included, so that a series of process, method, article or equipment including key elements not only will including those
Element, but also including other key elements being not expressly set out, or also include for this process, method, article or equipment
Intrinsic key element.In the absence of more restrictions, the key element for being limited by sentence "including a ...", it is not excluded that
Also there is other identical element in process, method, article or equipment including the key element.
Claims (10)
1. a kind of disconnecting link status identification means, it is characterised in that the disconnecting link status identification means include：
Information transmit-receive unit, for receiving the disconnecting link real time imaging that an image collecting device sends；
Target area recognition unit, for being identified to the target area of disconnecting link real time imaging；
Image characteristics extraction unit, for being entered to the target area of the disconnecting link real time imaging using principal component analysiss network algorithm
Row feature extraction；
Disconnecting link real-time status determining unit, the feature for the support vector machine that obtain according to training in advance to extracting is carried out point
Class, so that it is determined that disconnecting link real-time status.
2. disconnecting link status identification means according to claim 1, it is characterised in that described image feature extraction unit bag
Include：
First goes average block matrix to obtain subelement, for entering to each pixel of the target area of the disconnecting link real time imaging
Row block is sampled and goes meansigma methodss to obtain all the first of the mapping of ground floor principal component analysiss and removes average block matrix；
Fisrt feature matrix obtains subelement, and the covariance matrix for removing average block matrix to each described first asks for front X
Individual main characteristic vector obtains the first wave filter of ground floor principal component analysiss mapping, according to first wave filter to the disconnecting link
The target area of real time imaging carries out process of convolution, so as to obtain the fisrt feature matrix of ground floor principal component analysiss mapping；
Second goes average block matrix to obtain subelement, samples and goes average for carrying out block to fisrt feature matrix each described
Value, obtain the mapping of second layer principal component analysiss second removes average block matrix；
Second characteristic matrix obtains subelement, and the covariance matrix for removing average block matrix to each described second asks for front Y
Individual main characteristic vector obtains the second wave filter of second layer principal component analysiss mapping, according to second wave filter to ground floor master
The fisrt feature matrix of component analyses mapping carries out process of convolution, so as to obtain the second feature of second layer principal component analysiss mapping
Matrix；
Hash coded sub-units, for binary conversion treatment to be carried out to the second characteristic matrix and Hash coding is carried out；
Block extension histogram feature extracts subelement, for carrying out piecemeal simultaneously to the second characteristic matrix after each Hash coding
Rectangular histogram in each block is connected the rectangular histogram in all pieces so as to extract the target area of the disconnecting link real time imaging by statistics
Block extension histogram feature；
The disconnecting link real-time status determining unit is used for the block extension of the support vector machine that obtain according to training in advance to extracting
Rectangular histogram spy classified, so that it is determined that disconnecting link real-time status.
3. disconnecting link status identification means according to claim 1, it is characterised in that described information Transmit-Receive Unit is additionally operable to connect
The dispatch command of remote terminal transmission is received, wherein, the dispatch command includes the disconnecting link expectation state；
The disconnecting link status identification means also include：
Judging unit, it is whether consistent with the disconnecting link expectation state for judging the disconnecting link real-time status determined；
Fault cues information generating unit, for if it is determined that disconnecting link real-time status it is inconsistent with the disconnecting link expectation state, generate
Fault cues information.
4. disconnecting link status identification means according to claim 3, it is characterised in that described information Transmit-Receive Unit is additionally operable to
While receiving the disconnecting link real time imaging of image collecting device transmission, the device identity that described image harvester sends is received
Information；
Described information Transmit-Receive Unit is additionally operable to the fault cues information be sent to the intelligence associated with described device identity information
Can terminal.
5. disconnecting link status identification means according to claim 1, it is characterised in that the disconnecting link real-time status is included point
Open state, closure state and ground state.
6. a kind of disconnecting link state identification method, it is characterised in that the disconnecting link state identification method includes：
Receive the disconnecting link real time imaging of image collecting device transmission；
The target area of disconnecting link real time imaging is identified；
Feature extraction is carried out to the target area of the disconnecting link real time imaging using principal component analysiss network algorithm；
Feature of the support vector machine that foundation training in advance is obtained to extracting is classified, so that it is determined that disconnecting link real-time status.
7. disconnecting link state identification method according to claim 6, it is characterised in that the utilization principal component analysiss network is calculated
The step of method carries out feature extraction to the target area of the disconnecting link real time imaging includes：
Carry out block to each pixel of the target area of the disconnecting link real time imaging to sample and go meansigma methodss to obtain ground floor master
All the first of component analyses mapping remove average block matrix；
Go the covariance matrix of average block matrix to ask for front X main characteristic vector to each described first and obtain ground floor main constituent
First wave filter of analysis mapping, is carried out at convolution according to first wave filter to the target area of the disconnecting link real time imaging
Reason, so as to obtain the fisrt feature matrix of ground floor principal component analysiss mapping；
Block is carried out to fisrt feature matrix each described to sample and go meansigma methodss, obtains the second of the mapping of second layer principal component analysiss
Remove average block matrix；
Go the covariance matrix of average block matrix to ask for front Y main characteristic vector to each described second and obtain second layer main constituent
Second wave filter of analysis mapping, enters according to second wave filter to the fisrt feature matrix that ground floor principal component analysiss map
Row process of convolution, so as to obtain the second characteristic matrix of second layer principal component analysiss mapping；
Binary conversion treatment is carried out to the second characteristic matrix and Hash coding is carried out；
Piecemeal is carried out to the second characteristic matrix after each Hash coding and is counted the rectangular histogram in each block, connection is all
Rectangular histogram in block extends histogram feature so as to the block for extracting the target area of the disconnecting link real time imaging；
Feature of the support vector machine obtained according to training in advance to extracting is classified, so that it is determined that the real-time shape of disconnecting link
The step of state, includes：The support vector machine that foundation training in advance is obtained are classified to the block extension rectangular histogram spy for extracting, from
And determine disconnecting link real-time status.
8. disconnecting link state identification method according to claim 6, it is characterised in that in one image collecting device of the reception
Before the step of disconnecting link real time imaging of transmission, the disconnecting link state identification method also includes：Receive remote terminal transmission
Dispatch command, wherein, the dispatch command includes the disconnecting link expectation state；
Feature of the support vector machine obtained according to training in advance to extracting is classified, so that it is determined that the real-time shape of disconnecting link
After the step of state, the disconnecting link state identification method also includes：
Whether the disconnecting link real-time status that judgement is determined is consistent with the disconnecting link expectation state；
If it is determined that disconnecting link real-time status it is inconsistent with the disconnecting link expectation state, generate fault cues information.
9. disconnecting link state identification method according to claim 8, it is characterised in that the disconnecting link state identification method is also wrapped
Include：While the disconnecting link real time imaging that an image collecting device sends is received, the dress that described image harvester sends is received
Put identity information；
After the step of the generation fault cues information, the disconnecting link state identification method also includes：
The fault cues information is sent to the intelligent terminal associated with described device identity information.
10. disconnecting link state identification method according to claim 6, it is characterised in that the disconnecting link real-time status is included
Separated position, closure state and ground state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611189903.4A CN106599865A (en) | 2016-12-21 | 2016-12-21 | Disconnecting link state recognition device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611189903.4A CN106599865A (en) | 2016-12-21 | 2016-12-21 | Disconnecting link state recognition device and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106599865A true CN106599865A (en) | 2017-04-26 |
Family
ID=58600147
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611189903.4A Pending CN106599865A (en) | 2016-12-21 | 2016-12-21 | Disconnecting link state recognition device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106599865A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107257161A (en) * | 2017-06-20 | 2017-10-17 | 安徽南瑞继远电网技术有限公司 | A kind of transformer station's disconnecting link remote control auxiliary check method and system based on state recognition algorithm |
| CN109543573A (en) * | 2018-11-07 | 2019-03-29 | 广东电网有限责任公司 | A kind of method of secondary screen cabinet information automatic identification |
| CN110533090A (en) * | 2019-08-21 | 2019-12-03 | 国网江苏省电力有限公司电力科学研究院 | Switch tool condition detection method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198605A (en) * | 2013-03-11 | 2013-07-10 | 成都百威讯科技有限责任公司 | Indoor emergent abnormal event alarm system |
| CN104200219A (en) * | 2014-08-20 | 2014-12-10 | 深圳供电局有限公司 | Method and device for automatically identifying substation breaker and switch indicator |
| CN105356619A (en) * | 2015-12-10 | 2016-02-24 | 国网四川省电力公司天府新区供电公司 | Anti-misoperation method for transformer station based image recognition |
| CN105404867A (en) * | 2015-11-17 | 2016-03-16 | 中国科学院自动化研究所 | Vision-based substation disconnecting switch status recognition method |
| CN105447473A (en) * | 2015-12-14 | 2016-03-30 | 江苏大学 | PCANet-CNN-based arbitrary attitude facial expression recognition method |
| CN105550709A (en) * | 2015-12-14 | 2016-05-04 | 武汉大学 | Remote sensing image power transmission line corridor forest region extraction method |
-
2016
- 2016-12-21 CN CN201611189903.4A patent/CN106599865A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198605A (en) * | 2013-03-11 | 2013-07-10 | 成都百威讯科技有限责任公司 | Indoor emergent abnormal event alarm system |
| CN104200219A (en) * | 2014-08-20 | 2014-12-10 | 深圳供电局有限公司 | Method and device for automatically identifying substation breaker and switch indicator |
| CN105404867A (en) * | 2015-11-17 | 2016-03-16 | 中国科学院自动化研究所 | Vision-based substation disconnecting switch status recognition method |
| CN105356619A (en) * | 2015-12-10 | 2016-02-24 | 国网四川省电力公司天府新区供电公司 | Anti-misoperation method for transformer station based image recognition |
| CN105447473A (en) * | 2015-12-14 | 2016-03-30 | 江苏大学 | PCANet-CNN-based arbitrary attitude facial expression recognition method |
| CN105550709A (en) * | 2015-12-14 | 2016-05-04 | 武汉大学 | Remote sensing image power transmission line corridor forest region extraction method |
Non-Patent Citations (3)
| Title |
|---|
| 刘亚梅 等: "基于KPCA的工件图像特征提取研究", 《蚌埠学院学报》 * |
| 崔河富: "《数字图像处理与通信》", 31 August 2007 * |
| 王愚: "基于图像特征提取的开关安装智能纠错系统的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107257161A (en) * | 2017-06-20 | 2017-10-17 | 安徽南瑞继远电网技术有限公司 | A kind of transformer station's disconnecting link remote control auxiliary check method and system based on state recognition algorithm |
| CN107257161B (en) * | 2017-06-20 | 2020-10-09 | 安徽南瑞继远电网技术有限公司 | Transformer substation disconnecting link remote control auxiliary checking method and system based on state recognition algorithm |
| CN109543573A (en) * | 2018-11-07 | 2019-03-29 | 广东电网有限责任公司 | A kind of method of secondary screen cabinet information automatic identification |
| CN110533090A (en) * | 2019-08-21 | 2019-12-03 | 国网江苏省电力有限公司电力科学研究院 | Switch tool condition detection method and device |
| CN110533090B (en) * | 2019-08-21 | 2022-07-08 | 国网江苏省电力有限公司电力科学研究院 | Method and device for detecting state of switch knife switch |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110135319A (en) | A kind of anomaly detection method and its system | |
| CN108537154A (en) | Transmission line of electricity Bird's Nest recognition methods based on HOG features and machine learning | |
| CN109501834A (en) | A kind of point machine failure prediction method and device | |
| CN111813997B (en) | Intrusion analysis method, device, equipment and storage medium | |
| CN109639481A (en) | A kind of net flow assorted method, system and electronic equipment based on deep learning | |
| CN107563412A (en) | A kind of infrared image power equipment real-time detection method based on deep learning | |
| CN110084165A (en) | The intelligent recognition and method for early warning of anomalous event under the open scene of power domain based on edge calculations | |
| CN106355367A (en) | Warehouse monitoring management device | |
| CN110277833B (en) | Transformer substation pressure plate state identification method and terminal equipment | |
| CN101271514A (en) | Image detection method and device for fast object detection and objective output | |
| CN111598132B (en) | Portrait recognition algorithm performance evaluation method and device | |
| CN105574544A (en) | Data processing method and device | |
| CN106599865A (en) | Disconnecting link state recognition device and method | |
| CN111382808A (en) | Vehicle detection processing method and device | |
| CN110059635A (en) | A kind of skin blemishes detection method and device | |
| CN109800712A (en) | A kind of vehicle detection method of counting and equipment based on depth convolutional neural networks | |
| CN113591393A (en) | Fault diagnosis method, device, equipment and storage medium of intelligent substation | |
| CN110503135A (en) | Deep learning model compression method and system for the identification of power equipment edge side | |
| CN114151293B (en) | Fault early warning method, system, equipment and storage medium of fan variable pitch system | |
| CN114241522A (en) | Method, system, equipment and storage medium for field operation safety wearing identification | |
| CN118038153A (en) | Method, device, equipment and medium for identifying external damage prevention of distribution overhead line | |
| CN109583396A (en) | A kind of region prevention method, system and terminal based on CNN two stages human testing | |
| CN116912774A (en) | Infrared image target identification method, electronic device and storage medium of power transmission and transformation equipment based on edge calculation | |
| CN116862867A (en) | Small sample transformer substation equipment visual defect detection method and system based on improved AnoGAN | |
| CN106714007A (en) | Video abstract method and apparatus |
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 | ||
| CB02 | Change of applicant information |
Address after: Two Lu Tian Hua high tech Zone of Chengdu City, Sichuan province 610017 No. 219 Tianfu Software Park C District 10 Building 16 layer Applicant after: Huayan Intelligent Technology (Group) Co., Ltd Address before: Two Lu Tian Hua high tech Zone of Chengdu City, Sichuan province 610017 No. 219 Tianfu Software Park C District 10 Building 16 layer Applicant before: Sichuan Whayer Information Industry Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170426 |
|
| RJ01 | Rejection of invention patent application after publication |