CN109285309A - A kind of intrusion target real-time detecting system based on transmission system - Google Patents
A kind of intrusion target real-time detecting system based on transmission system Download PDFInfo
- Publication number
- CN109285309A CN109285309A CN201811155685.1A CN201811155685A CN109285309A CN 109285309 A CN109285309 A CN 109285309A CN 201811155685 A CN201811155685 A CN 201811155685A CN 109285309 A CN109285309 A CN 109285309A
- Authority
- CN
- China
- Prior art keywords
- target
- intrusion
- space
- protection
- module
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19608—Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06T7/85—Stereo camera calibration
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
A kind of intrusion target real-time detecting system based on transmission system, is related to technical field of electric power transmission.In order to solve the problems, such as current transmission line of electricity or equipment detection, there are mobility lagging influences to overhaul the deadline.The present invention includes: the binocular synchronous images sequence acquisition module for acquiring the image of passway for transmitting electricity, calibration obtains the demarcating module of two respective inside and outside parameters of camera, for determining the area-of-interest detection module of electric transmission line channel area-of-interest, it is determined according to the protection target position in the image of two cameras shooting and protects the 3 d space coordinate of target in the 3 d space coordinate and monitoring area of protection target and determine intrusion target and protect the space length of target, the module of target detection of movement velocity and the direction of motion, and the space length according to the opposite protection target of intrusion target, the direction of motion and movement velocity judge threat level and issue the intrusion target alarm module alarmed accordingly.The present invention is suitable for transmission system and invades target real-time detection.
Description
Technical field
The present invention relates to technical field of electric power transmission, and in particular to intrusion target real-time detecting system.
Background technique
Geology and geomorphology complexity, environment are changeable along China's transmission line of electricity, are subject to foreign matter intrusion, and intrusion target substantially may be used
It is divided into three classes, the floating material of the birds activity, transmission line of electricity that are respectively as follows: passway for transmitting electricity threatens and the external force of transmission line of electricity is broken
It is bad.Wherein bird pest multidigit is in gobi, the marsh Hu Tang and ecological wetland and nature reserve area, to the safe and stable operation of electric system
Cause great threat.According to statistics, ultra-high-tension power transmission line tripping power-off is only second to lightning stroke caused by birds activity and external force is broken
It is bad, the 3rd of line fault sum is accounted for, and in recent years in rising trend.U.S. IEEE (Institute of Electrical and Electronics Engineers) nineteen ninety
Survey report shows that the failure of transmission line of electricity about 25% is related with birds.Many electricity such as Qinghai, Tibet, Henan, the Jiangxi in China
There is the report of bird pest in power company, according to statistics Qinghai-Tibet DC power transmission line since on November 11st, 2011 puts into operation, by the end of
More than 100 line tripping accidents have occurred altogether on October in 2017 31, wherein the tripping times as caused by bird pest account for always
Number 94%.Transmission line of electricity floating material is mainly reflected in, vinyl house, film, Air Filter, billboard around transmission line of electricity,
Rubbish heap, plastics, nylon or rope etc. can be wound on transmission line of electricity or shaft tower under strong wind perhaps external force, in addition
In spring, Qiu Liangji, there is also great hidden danger to line security operation for resident's kiteflying around transmission line of electricity, such as: 2017
Year March, spirit continue ± 800kV UHVDC Transmission Lines bipolar locking event, precisely due to kite string is overlapped between the two poles of the earth, under
Rainy day generates caused by interpolar discharge.The external force destruction of transmission line of electricity is mainly manifested in, and the mountain area fried stone that cuts into a mountain causes to wound insulation
Son blows up conducting wire；The mountain fire of lower section burning crop or burst that route passes through, flame and dense smoke cause route damaged；City
Political affairs, civil engineering tie up power transmission line corridor, and crane or dump truck, which accidentally touch, leads to route；Also some criminals steal tower
The electric power facilities such as material, bracing wire；And it goes fishing under transmission line of electricity, construction etc. of breaking rules and regulations.
Electric system at present mainly still uses the detection of passway for transmitting electricity intrusion target and mainly uses manual inspection, goes straight up to
Four kinds of machine inspection, unmanned plane inspection and fixed monitoring modes.Manual inspection relies primarily on electrical power line inspector using telescope to shaft tower
And critical component carry out artificial observation, helicopter routing inspection be also by helicopter be carrier manual inspection, unmanned plane inspection and
Fixed monitoring be all by after acquisition transmission line of electricity picture and video information by artificial observation or using image processing techniques into
Row processing.But there is also deficiencies for the above method, if efficiency is lower, large labor intensity；In addition in many local circuit channels in China
Line walking it is very difficult, route invade target have very strong randomness, the interval of traditional method line walking is long, is difficult to send out in time
Now invade target；Finally, conventional inspection can not obtain spatial position, kinematic parameter and the geometric scale of target, it is difficult to highly reliable
Complete patrol task in ground.Therefore it is directed to the studies above status, exploitation designs a set of passway for transmitting electricity intrusion target real-time detection and surveys
The system and method for amount has very important engineering realistic meaning.
Summary of the invention
The present invention to be solved, and current transmission line of electricity or equipment detection are all based on greatly route or improper work occurs in equipment
It is just accordingly detected when making state or data, thus the problem of existing mobility lagging influence overhauls the deadline.
A kind of intrusion target real-time detecting system based on transmission system, comprising: binocular synchronous images sequence acquisition module,
Demarcating module, area-of-interest detection module, module of target detection, intrusion target alarm module；
The binocular synchronous images sequence acquisition module, the image based on binocular camera acquisition passway for transmitting electricity；
The demarcating module, according to the positional relationship of two cameras of binocular synchronous images sequence acquisition module, calibration is obtained
Take two respective inside and outside parameters of camera；
The area-of-interest detection module, for determining electric transmission line channel area-of-interest；
The module of target detection determines protection target according to the protection target position in the image of two cameras shooting
3 d space coordinate and monitoring area in protect target 3 d space coordinate, determine intrusion target and protect target space
Distance, movement velocity and the direction of motion；
The intrusion target alarm module, according to space length, the direction of motion and the fortune of the opposite protection target of intrusion target
Dynamic velocity estimated threat level, and issue corresponding alarm.
It is described intrusion target alarm module can by employing mode (1) or in a manner of (2) judge threat level:
(1) the intrusion target alarm module judges that the process of threat level is as follows:
Intrusion target alarm module is compared the height Z0 and safety height-limiting H of intrusion target, to intrusion target and protects
Eye protection subject distance d and safe distance D are compared, and are compared to the speed v and safe speed V of intrusion target；Simultaneously to invading
The direction of motion for entering target is judged；
Then threat level is determined according to following situations and alarmed:
If a, invade target height Z0 >=safety height-limiting H and the direction of motion towards protection target, and invade target with
Target range d < safe distance D is protected, then threat level is labeled as level-one；
If b, invading height Z0 >=safety height-limiting H of target, the direction of motion is parallel with protection target, and invades target and protect
Eye protection subject distance d >=safe distance D, then threat level is labeled as second level；
If c, invading speed v >=safe speed V of target, threat level is labeled as second level；
If d, invade target height Z0 < safety height-limiting H, and with protection target inside power grid distance d≤safe distance
D, then threat level is labeled as second level；
E, remaining situation is labeled as no threat.
Degree of danger represented by level-one threat level is higher than degree of danger represented by second level threat level；Meet simultaneously
Two or more conditions are determined by degree of danger is high.
(2) the intrusion target alarm module includes protection targeted security area computing unit, intrusion target trajectory prediction list
Member and discriminant alarm unit；
Protection targeted security area computing unit extracts the space coordinate of protection objective contour, and in the three-dimensional of image
The space coordinate of the minimal circumscribed sphere of label protection objective contour and minimal circumscribed sphere in space coordinates；If protection target is
Transmission line of electricity is carried out dividing elements first by transmission line of electricity, resolves into several units, is then based on each unit and is marked minimum
Circumsphere and space coordinate, and minimal circumscribed sphere is carried out to the connection for having overlapping space, form a circle along transmission line of electricity
Cylinder space；
The first secure threshold W is chosen, is used as the first safe space in the range of W distance on the outside of minimal circumscribed sphere, or
The first safe space is used as in the range of W distance on the outside of cylindrical space；
Target trajectory predicting unit is invaded, extracts the space coordinate of intrusion objective contour, and sit in the three-dimensional space of image
The space coordinate of the minimal circumscribed sphere of label protection objective contour and minimal circumscribed sphere in mark system；According to currently and before, the moment is invaded
Enter target trajectory motion profile and direction, using neural network model estimate intrusion target possible motion profile, and
Real-time update estimated motion track；
Discriminant alarm unit calculates the minimal circumscribed sphere of protection target and the intrusion of intrusion target trajectory predicting unit estimation
The motion profile of target corresponds to the intersection in space；The first safe space is calculated simultaneously and invades the estimation of target trajectory predicting unit
The motion profile of intrusion target corresponds to the intersection in space；
If protecting the friendship of the space coordinate of the minimal circumscribed sphere of the space coordinate of target and the motion profile of intrusion target
Collection is not sky, then the alarm of the grade that impends highest level；
If protecting the friendship of the space coordinate of the minimal circumscribed sphere of the space coordinate of target and the motion profile of intrusion target
Collect to be empty, and the first safe space space corresponding with the motion profile of intrusion target of intrusion target trajectory predicting unit estimation
Intersection be not it is empty, then the levels high level alarm such as impend；
If the first safe space and the motion profile of intrusion target of intrusion target trajectory predicting unit estimation are corresponding empty
Between intersection be sky, then be judged as safety, without alarm.
The invention has the following advantages:
Transmission system (transmission line faultlocating or transmission facility detect) is carried out using the present invention to be detected, and can set
Effective monitoring is carried out between the raw problem of preparation, is the shape to transmission system so as to avoid existing transmission system detection scheme
State signal can only be the problem of can just detect failure when equipment breaks down or after breaking down caused by being detected.?
That is the present invention can carry out effective dynamic detection according to detection device, quickly equipment or place that problem occurs are carried out
Effectively identification, to carry out the preparation of debugging in advance and reach the failure generation of faulty equipment within the most fast time
Ground.Compared to existing method, detection of the invention can guarantee that the mobility of fault detection is greatly improved.
It is detected using of the invention based on equipment such as current binocular cameras, the low cost of system is conducive to big model
Universal use is enclosed, and there is good detection effect.And it can be improved power grid intelligent measurement level using the present invention, ensure
The safe and stable operation of electric system.
Detailed description of the invention
Fig. 1 is area-of-interest target detection flow chart.
Specific embodiment
Specific embodiment 1:
A kind of intrusion target real-time detecting system based on transmission system, comprising: binocular synchronous images sequence acquisition module,
Demarcating module, area-of-interest detection module, module of target detection, intrusion target alarm module；
The binocular synchronous images sequence acquisition module, the image based on binocular camera acquisition passway for transmitting electricity；
The module mainly uses focal length binocular industrial camera, and the purpose using focal length is to adapt to passway for transmitting electricity to see more at a distance
It examines, meanwhile, which has synchronizing function, guarantees the binocular image sequence basic synchronization obtained, convenient for the later period to figure
The entire parallax of picture carries out three-dimensional reconstruction；
The demarcating module, according to the positional relationship of two cameras of binocular synchronous images sequence acquisition module, calibration is obtained
Take two respective inside and outside parameters of camera；
The area-of-interest detection module, for determining electric transmission line channel area-of-interest；
The module of target detection determines protection target according to the protection target position in the image of two cameras shooting
3 d space coordinate and monitoring area in protect target 3 d space coordinate, determine intrusion target and protect target space
Distance, movement velocity and the direction of motion；The protection target is the equipment in passway for transmitting electricity or passway for transmitting electricity；
The intrusion target alarm module judges according to the space length of the opposite protection target of intrusion target, the direction of motion
Threat level, and issue corresponding alarm.
The intrusion target can be such as bird, float object (such as: plastic cloth, the polybag blown by wind), people
To destroy corresponding people etc..
The area-of-interest detection module determines that the process of electric wire paths area-of-interest is as follows:
Based on image sequence, environmental background image is modeled using the method for Gaussian modeling, obtains background mould
Type；
For present image and background model, the intrusion target (intrusion in present image is then obtained using Background difference
Object) image information, further using morphological image technology acquisition be more clear target image information, be accurately positioned intrusion
Target in the position of image, will the corresponding region in intrusion target position and protection target area as area-of-interest,
That is monitoring area；Detailed process is as shown in Figure 1.
The treatment process of the module of target detection is as follows:
For area-of-interest, using the fine granularity image recognition algorithm based on depth convolutional neural networks, description sense is emerging
The fine-feature in interesting region；
If space any point P (XC, YC, ZC) it is the certain point monitored in region, (XC, YC, ZC) indicate point P in space
Position；At the T1 moment, plane coordinates of this o'clock on the image a that the first video camera acquires is Pa (x1,y1), in the second video camera
Plane coordinates on the image b of acquisition is Pb (x2,y2), then:
In formula, BCIt is the external parameter of video camera, the inner parameter of f video camera；The external parameter of video camera and internal ginseng
Number is the intrinsic attribute of video camera, and when video camera dispatches from the factory, the two parameters are just had determined；|Pa-Pb| it is parallax, i.e. point P is two
Positional shift in width image；
According to the above process, the 3 d space coordinate at any point in monitoring scene is obtained；
Assuming that the intrusion target any point current spatial three-dimensional coordinate calculated is (X1, Y1, Z1), the space three of previous moment
Dimension coordinate is (X2, Y2, Z2)；The 3 d space coordinate for protecting target current time is (X0, Y0, Z0), actually due to protecting mesh
Target 3 d space coordinate be it is fixed, will not generally change, so current time is identical with the coordinate of previous moment；It calculates
Current time invades the movement speed of target protection target opposite with space length, the direction of motion and the intrusion target of target is protected
Degree；
It invades target and protects the space length of target:
Invade the movement velocity of target are as follows:
Wherein, Δ t is the time interval at current time and previous moment；
The height of intrusion target is determined according to the 3 d space coordinate of the intrusion target fact simultaneously.
The intrusion target alarm module judges that the process of threat level is as follows:
Intrusion target alarm module is compared the height Z0 and safety height-limiting H of intrusion target, to intrusion target and protects
Eye protection subject distance d and safe distance D are compared, and are compared to the speed v and safe speed V of intrusion target；Simultaneously to invading
The direction of motion for entering target is judged；
Then threat level is determined according to following situations and alarmed:
If a, invading height Z0 >=safety height-limiting H of target and direction of motion direction protection target (can be power transmission line
Road corridor, the equipment being also possible in power transmission line corridor), and invade target and protection target range d < safe distance D, then prestige
Side of body grade mark is level-one (degree of danger is high)；
If b, invading height Z0 >=safety height-limiting H of target, the direction of motion is parallel with protection target, and invades target and protect
Eye protection subject distance d >=safe distance D, then threat level is labeled as second level；
If c, invading speed v >=safe speed V of target, threat level is labeled as second level；
If d, invade target height Z0 < safety height-limiting H, and with protection target inside power grid distance d≤safe distance
D, then threat level is labeled as second level；
E, remaining situation is labeled as no threat.
Degree of danger represented by level-one threat level is higher than degree of danger represented by second level threat level；Meet simultaneously
Two or more condition is determined by degree of danger is high, such as when meeting condition a and condition c simultaneously, need to be marked threat level
For level-one.
Specific embodiment 2:
A kind of intrusion target real-time detecting system based on transmission system characterized by comprising binocular synchronous images sequence
Column acquisition module, demarcating module, area-of-interest detection module, module of target detection, intrusion target alarm module；
The binocular synchronous images sequence acquisition module, the image based on binocular camera acquisition passway for transmitting electricity；
The demarcating module, according to the positional relationship of two cameras of binocular synchronous images sequence acquisition module, calibration is obtained
Take two respective inside and outside parameters of camera；
The area-of-interest detection module, for determining electric transmission line channel area-of-interest；
The module of target detection determines protection target according to the protection target position in the image of two cameras shooting
3 d space coordinate and monitoring area in protect target 3 d space coordinate, determine intrusion target and protect target space
Distance, movement velocity and the direction of motion；
The intrusion target alarm module judges according to the space length of the opposite protection target of intrusion target, the direction of motion
Threat level, and issue corresponding alarm；
Invading target alarm module includes protection targeted security area computing unit, intrusion target trajectory predicting unit and differentiation
Alarm unit；
Protection targeted security area computing unit extracts the space coordinate of protection objective contour, and in the three-dimensional of image
The space coordinate of the minimal circumscribed sphere of label protection objective contour and minimal circumscribed sphere in space coordinates；If protection target is
Transmission line of electricity is carried out dividing elements first by transmission line of electricity, resolves into several units, is then based on each unit and is marked minimum
Circumsphere and space coordinate, and minimal circumscribed sphere is carried out to the connection for having overlapping space, form a circle along transmission line of electricity
Cylinder space；
The first secure threshold W is chosen, is used as the first safe space in the range of W distance on the outside of minimal circumscribed sphere, or
The first safe space is used as in the range of W distance on the outside of cylindrical space；
Target is invaded when entering the space near protection equipment, the movement rail of invader may be made due to environmental factor etc.
Mark, which changes, hits protection target, such as polybag object showy in the air is because the effect of wind-force is not to guarantee movement rail
Mark is metastable, and motion path is probably changed or disturbed or even the direction of motion may all change, thus
Intrusion protection target.First safety zone is set, can fully consider that intrusion target has the probability of the failure of generation in pole, preferably mention
Preceding early warning work, to largely solve the problems, such as that mobility lagging influence overhauls the deadline.
Target trajectory predicting unit is invaded, extracts the space coordinate of intrusion objective contour, and sit in the three-dimensional space of image
The space coordinate of the minimal circumscribed sphere of label protection objective contour and minimal circumscribed sphere in mark system；According to currently and before, the moment is invaded
Enter target trajectory motion profile and direction, using neural network model estimate intrusion target possible motion profile, and
Real-time update estimated motion track；
Discriminant alarm unit calculates the minimal circumscribed sphere (or cylindrical body) and intrusion target trajectory predicting unit of protection target
The motion profile of the intrusion target of estimation corresponds to the intersection in space；The first safe space and intrusion target trajectory prediction are calculated simultaneously
The motion profile of the intrusion target of unit estimation corresponds to the intersection in space；
If protecting the friendship of the space coordinate of the minimal circumscribed sphere of the space coordinate of target and the motion profile of intrusion target
Collection is not sky, then the alarm of the grade that impends highest level；
If protecting the friendship of the space coordinate of the minimal circumscribed sphere of the space coordinate of target and the motion profile of intrusion target
Collect to be empty, and the first safe space space corresponding with the motion profile of intrusion target of intrusion target trajectory predicting unit estimation
Intersection be not it is empty, then the levels high level alarm such as impend；
If the first safe space and the motion profile of intrusion target of intrusion target trajectory predicting unit estimation are corresponding empty
Between intersection be sky, then be judged as safety, without alarm.
Specific embodiment two and specific embodiment one are able to achieve transmission system and are detected, in comparison, specifically
The precision of the Detection accuracy of embodiment two is relatively higher, and the calculation amount of deterministic process is bigger, wants to device hardware is calculated
It asks little higher, it is also slightly long to calculate the time；And the requirement of specific embodiment a pair of hardware is relatively low, calculating speed is also more
Fastly.
Specific embodiment two and specific embodiment one can carry out effective monitoring between equipment generation problem,
So as to avoid existing transmission system detection scheme be caused by being detected to the status signal of transmission system can only
The problem of capable of just detecting failure when equipment breaks down or after breaking down.That is the present invention can be according to detection device
Effective dynamic detection is carried out, quickly equipment or place that problem occurs effectively are identified, to carry out exclusion event in advance
The preparation of barrier and the failure spot that faulty equipment is reached within the most fast time.It is of the invention compared to existing method
Detection can guarantee that the mobility of fault detection is greatly improved.
Claims (5)
1. a kind of intrusion target real-time detecting system based on transmission system characterized by comprising binocular synchronous images sequence
Acquisition module, demarcating module, area-of-interest detection module, module of target detection, intrusion target alarm module；
The binocular synchronous images sequence acquisition module, the image based on binocular camera acquisition passway for transmitting electricity；
The demarcating module, according to the positional relationship of two cameras of binocular synchronous images sequence acquisition module, calibration obtains two
A respective inside and outside parameter of camera；
The area-of-interest detection module, for determining electric transmission line channel area-of-interest；
The module of target detection determines the sky of protection target according to the protection target position in the image of two cameras shooting
Between the 3 d space coordinate of target is protected in three-dimensional coordinate and monitoring area, determine intrusion target and protect the space of target away from
From, movement velocity and the direction of motion；
The intrusion target alarm module is threatened according to the space length of the opposite protection target of intrusion target, direction of motion judgement
Grade, and issue corresponding alarm.
2. a kind of intrusion target real-time detecting system based on transmission system according to claim 1, which is characterized in that institute
It states intrusion target alarm module and judges that the process of threat level is as follows:
Intrusion target alarm module is compared the height Z0 and safety height-limiting H of intrusion target, to intrusion target and protection mesh
Subject distance d and safe distance D are compared, and are compared to the speed v and safe speed V of intrusion target；Simultaneously to intrusion mesh
The target direction of motion is judged；
Then threat level is determined according to following situations and alarmed:
If a, invading height Z0 >=safety height-limiting H of target and the direction of motion being towards protection target, and invade target and protection
Target range d < safe distance D, then threat level is labeled as level-one；
If b, invading height Z0 >=safety height-limiting H of target, the direction of motion is parallel with protection target, and invades target and protection mesh
Subject distance d >=safe distance D, then threat level is labeled as second level；
If c, invading speed v >=safe speed V of target, threat level is labeled as second level；
If d, invade target height Z0 < safety height-limiting H, and with protection target inside power grid distance d≤safe distance D, then
Threat level is labeled as second level；
E, remaining situation is labeled as no threat.
Degree of danger represented by level-one threat level is higher than degree of danger represented by second level threat level；Meet two simultaneously
Or more condition, determine by degree of danger is high.
3. a kind of intrusion target real-time detecting system based on transmission system according to claim 1, which is characterized in that institute
Stating intrusion target alarm module includes protection targeted security area computing unit, intrusion target trajectory predicting unit and discriminant alarm list
Member；
Protection targeted security area computing unit extracts the space coordinate of protection objective contour, and in the three-dimensional space of image
The space coordinate of the minimal circumscribed sphere of label protection objective contour and minimal circumscribed sphere in coordinate system；If protecting target is transmission of electricity
Transmission line of electricity is carried out dividing elements first by route, resolves into several units, be then based on each unit mark it is minimum external
Ball and space coordinate, and minimal circumscribed sphere is carried out to the connection for having overlapping space, form a cylindrical body along transmission line of electricity
Space；
The first secure threshold W is chosen, is used as the first safe space in the range of W distance on the outside of minimal circumscribed sphere, or in circle
The first safe space is used as in the range of W distance on the outside of cylinder space；
Target trajectory predicting unit is invaded, extracts the space coordinate of intrusion objective contour, and in the three-dimensional coordinate system of image
The minimal circumscribed sphere of middle label protection objective contour and the space coordinate of minimal circumscribed sphere；According to the current and mesh of moment intrusion before
The motion profile of mark track and direction estimate the possible motion profile for invading target using neural network model, and in real time
Update estimated motion track；
Discriminant alarm unit calculates the minimal circumscribed sphere of protection target and the intrusion target of intrusion target trajectory predicting unit estimation
Motion profile correspond to the intersection in space；It calculates the first safe space simultaneously and invades the intrusion of target trajectory predicting unit estimation
The motion profile of target corresponds to the intersection in space；
If protecting the intersection of the space coordinate of the minimal circumscribed sphere of the space coordinate of target and the motion profile of intrusion target not
For sky, the then alarm of the grade that impends highest level；
If protecting the minimal circumscribed sphere of the space coordinate of target and the intersection of the space coordinate of the motion profile of intrusion target being
Sky, and the intersection in the first safe space space corresponding with the motion profile of intrusion target of intrusion target trajectory predicting unit estimation
It is not sky, then the levels high level alarm such as impend；
If the first safe space space corresponding with the motion profile of intrusion target of intrusion target trajectory predicting unit estimation
Intersection is sky, then is judged as safety, without alarm.
4. a kind of intrusion target real-time detecting system based on transmission system according to claim 1,2 or 3, feature exist
In the area-of-interest detection module determines that the process of electric wire paths area-of-interest is as follows:
Based on image sequence, environmental background image is modeled using the method for Gaussian modeling, obtains background model；
For present image and background model, the image letter of the intrusion target in present image is then obtained using Background difference
Breath, positioning intrusion target in the position of image, will the corresponding region in intrusion target position and protection target area as
Area-of-interest, i.e. monitoring area.
5. a kind of intrusion target real-time detecting system based on transmission system according to claim 4, which is characterized in that institute
The treatment process for stating module of target detection is as follows:
Region of interest is described using the fine granularity image recognition algorithm based on depth convolutional neural networks for area-of-interest
The fine-feature in domain；
If space any point P (XC, YC, ZC) it is the certain point monitored in region, (XC, YC, ZC) indicate the position of point P in space
It sets；At the T1 moment, plane coordinates of this o'clock on the image a that the first video camera acquires is Pa (x1,y1), it is adopted in the second video camera
The plane coordinates on image b integrated is Pb (x2,y2), then:
In formula, BCIt is the external parameter of video camera, the inner parameter of f video camera；|Pa-Pb| it is parallax, i.e. point P is in two images
In positional shift；
According to the above process, the 3 d space coordinate at any point in monitoring scene is obtained；
Calculate current time intrusion target protection target opposite with space length, the direction of motion and the intrusion target of target is protected
Movement velocity；
The height of intrusion target is determined according to the 3 d space coordinate of the intrusion target fact simultaneously.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811155685.1A CN109285309A (en) | 2018-09-30 | 2018-09-30 | A kind of intrusion target real-time detecting system based on transmission system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811155685.1A CN109285309A (en) | 2018-09-30 | 2018-09-30 | A kind of intrusion target real-time detecting system based on transmission system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109285309A true CN109285309A (en) | 2019-01-29 |
Family
ID=65182013
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811155685.1A Pending CN109285309A (en) | 2018-09-30 | 2018-09-30 | A kind of intrusion target real-time detecting system based on transmission system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109285309A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109794948A (en) * | 2019-03-04 | 2019-05-24 | 北京国电富通科技发展有限责任公司 | Distribution network live line work robot and recognition positioning method |
| CN109919917A (en) * | 2019-02-21 | 2019-06-21 | 国网山东省电力公司临沂供电公司 | The foreign matter detecting method of overhead transmission line based on image procossing |
| CN110136378A (en) * | 2019-05-09 | 2019-08-16 | 上海卓希智能科技有限公司 | A kind of airport circumference intrusion alarm system and intrusion alarm method |
| CN110349172A (en) * | 2019-06-28 | 2019-10-18 | 华南理工大学 | Transmission line of electricity external force damage prevention method for early warning based on image procossing and binocular solid ranging |
| CN110728812A (en) * | 2019-10-12 | 2020-01-24 | 国网新疆电力有限公司喀什供电公司 | Detection and protection device for preventing external damage of power transmission line and use method thereof |
| CN110853002A (en) * | 2019-10-30 | 2020-02-28 | 上海电力大学 | Transformer substation foreign matter detection method based on binocular vision |
| CN111238323A (en) * | 2020-03-09 | 2020-06-05 | 深圳市宏源建设工程有限公司 | Remote monitoring system for controlling blasting |
| CN111833404A (en) * | 2019-04-23 | 2020-10-27 | 鸿富锦精密电子(天津)有限公司 | Camera calibration system and camera calibration method |
| CN112509263A (en) * | 2020-11-08 | 2021-03-16 | 华能通辽风力发电有限公司 | Image analysis tracking, temperature measurement positioning system and method |
| CN113487821A (en) * | 2021-07-30 | 2021-10-08 | 重庆予胜远升网络科技有限公司 | Power equipment foreign matter intrusion identification system and method based on machine vision |
| CN113532513A (en) * | 2021-06-21 | 2021-10-22 | 沈阳达能电安全高新产业技术研究院有限公司 | Intrusion target real-time detection system and method based on power transmission system |
| CN113947731A (en) * | 2021-12-21 | 2022-01-18 | 成都中轨轨道设备有限公司 | Foreign matter identification method and system based on contact net safety inspection |
| CN113965733A (en) * | 2021-12-07 | 2022-01-21 | 中国联合网络通信集团有限公司 | Binocular video monitoring method, system, computer equipment and storage medium |
| CN114155447A (en) * | 2021-12-02 | 2022-03-08 | 北京中科智易科技有限公司 | Artificial intelligence big data acquisition system |
| CN114608441A (en) * | 2020-12-03 | 2022-06-10 | 中国科学院沈阳自动化研究所 | Method for setting up dynamic visual security fence |
| CN114783132A (en) * | 2022-03-03 | 2022-07-22 | 国网安徽省电力有限公司 | Transformer substation safety protection system based on multistage intelligence |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103065409A (en) * | 2012-12-14 | 2013-04-24 | 广州供电局有限公司 | Power transmission line monitoring and early warning system |
| US9204041B1 (en) * | 2012-07-03 | 2015-12-01 | Gopro, Inc. | Rolling shutter synchronization |
| CN105915846A (en) * | 2016-04-26 | 2016-08-31 | 成都通甲优博科技有限责任公司 | Monocular and binocular multiplexed invading object monitoring method and system |
| CN106022239A (en) * | 2016-05-13 | 2016-10-12 | 电子科技大学 | Multi-target tracking method based on recurrent neural network |
| CN107391631A (en) * | 2017-07-10 | 2017-11-24 | 国家电网公司 | A kind of electric transmission line channel solid space monitoring and fast ranging method |
| CN206757825U (en) * | 2017-05-19 | 2017-12-15 | 龙岩学院 | Scope biotic intrusion early warning system based on infrared sensor |
-
2018
- 2018-09-30 CN CN201811155685.1A patent/CN109285309A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9204041B1 (en) * | 2012-07-03 | 2015-12-01 | Gopro, Inc. | Rolling shutter synchronization |
| CN103065409A (en) * | 2012-12-14 | 2013-04-24 | 广州供电局有限公司 | Power transmission line monitoring and early warning system |
| CN105915846A (en) * | 2016-04-26 | 2016-08-31 | 成都通甲优博科技有限责任公司 | Monocular and binocular multiplexed invading object monitoring method and system |
| CN106022239A (en) * | 2016-05-13 | 2016-10-12 | 电子科技大学 | Multi-target tracking method based on recurrent neural network |
| CN206757825U (en) * | 2017-05-19 | 2017-12-15 | 龙岩学院 | Scope biotic intrusion early warning system based on infrared sensor |
| CN107391631A (en) * | 2017-07-10 | 2017-11-24 | 国家电网公司 | A kind of electric transmission line channel solid space monitoring and fast ranging method |
Non-Patent Citations (4)
| Title |
|---|
| 于浩: "输电线路防外力破坏预警***研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
| 李文娟: "三维变电站仿真培训***中设备巡视的研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 李文娟等: "三维物体碰撞检测中的包围盒算法", 《中国电力教育》 * |
| 高玉琴等: "改进的基于AABB包围盒的碰撞检测算法", 《计算机工程与设计》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919917A (en) * | 2019-02-21 | 2019-06-21 | 国网山东省电力公司临沂供电公司 | The foreign matter detecting method of overhead transmission line based on image procossing |
| CN109919917B (en) * | 2019-02-21 | 2020-10-20 | 国网山东省电力公司临沂供电公司 | Image processing-based foreign matter detection method for overhead transmission line |
| CN109794948B (en) * | 2019-03-04 | 2020-08-21 | 北京国电富通科技发展有限责任公司 | Distribution network live working robot and identification and positioning method |
| CN109794948A (en) * | 2019-03-04 | 2019-05-24 | 北京国电富通科技发展有限责任公司 | Distribution network live line work robot and recognition positioning method |
| CN111833404A (en) * | 2019-04-23 | 2020-10-27 | 鸿富锦精密电子(天津)有限公司 | Camera calibration system and camera calibration method |
| CN111833404B (en) * | 2019-04-23 | 2023-10-31 | 富联精密电子(天津)有限公司 | Camera correction system and camera correction method |
| CN110136378A (en) * | 2019-05-09 | 2019-08-16 | 上海卓希智能科技有限公司 | A kind of airport circumference intrusion alarm system and intrusion alarm method |
| CN110349172B (en) * | 2019-06-28 | 2022-12-16 | 华南理工大学 | Power transmission line external damage prevention early warning method based on image processing and binocular stereo ranging |
| CN110349172A (en) * | 2019-06-28 | 2019-10-18 | 华南理工大学 | Transmission line of electricity external force damage prevention method for early warning based on image procossing and binocular solid ranging |
| CN110728812A (en) * | 2019-10-12 | 2020-01-24 | 国网新疆电力有限公司喀什供电公司 | Detection and protection device for preventing external damage of power transmission line and use method thereof |
| CN110853002A (en) * | 2019-10-30 | 2020-02-28 | 上海电力大学 | Transformer substation foreign matter detection method based on binocular vision |
| CN111238323A (en) * | 2020-03-09 | 2020-06-05 | 深圳市宏源建设工程有限公司 | Remote monitoring system for controlling blasting |
| CN112509263A (en) * | 2020-11-08 | 2021-03-16 | 华能通辽风力发电有限公司 | Image analysis tracking, temperature measurement positioning system and method |
| CN114608441A (en) * | 2020-12-03 | 2022-06-10 | 中国科学院沈阳自动化研究所 | Method for setting up dynamic visual security fence |
| CN113532513A (en) * | 2021-06-21 | 2021-10-22 | 沈阳达能电安全高新产业技术研究院有限公司 | Intrusion target real-time detection system and method based on power transmission system |
| CN113532513B (en) * | 2021-06-21 | 2024-03-29 | 沈阳达能电安全高新产业技术研究院有限公司 | Intrusion target real-time detection system and method based on power transmission system |
| CN113487821A (en) * | 2021-07-30 | 2021-10-08 | 重庆予胜远升网络科技有限公司 | Power equipment foreign matter intrusion identification system and method based on machine vision |
| CN114155447A (en) * | 2021-12-02 | 2022-03-08 | 北京中科智易科技有限公司 | Artificial intelligence big data acquisition system |
| CN114155447B (en) * | 2021-12-02 | 2022-06-24 | 北京中科智易科技有限公司 | Artificial intelligence big data acquisition system |
| CN113965733A (en) * | 2021-12-07 | 2022-01-21 | 中国联合网络通信集团有限公司 | Binocular video monitoring method, system, computer equipment and storage medium |
| CN113947731A (en) * | 2021-12-21 | 2022-01-18 | 成都中轨轨道设备有限公司 | Foreign matter identification method and system based on contact net safety inspection |
| CN113947731B (en) * | 2021-12-21 | 2022-07-22 | 成都中轨轨道设备有限公司 | Foreign matter identification method and system based on contact net safety inspection |
| CN114783132A (en) * | 2022-03-03 | 2022-07-22 | 国网安徽省电力有限公司 | Transformer substation safety protection system based on multistage intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109285309A (en) | A kind of intrusion target real-time detecting system based on transmission system | |
| CN105915846B (en) | A kind of the invader monitoring method and system of the multiplexing of list binocular | |
| CN106157507B (en) | A kind of transmission line of electricity solid protective device based on radar and video fusion | |
| CN108709633A (en) | Distributed optical fiber vibration sensing intelligent and safe monitoring method based on deep learning | |
| CN105100757B (en) | Detector with integral structure | |
| CN110126885B (en) | Railway perimeter intrusion target monitoring method and system | |
| CN104821056A (en) | Intelligent guarding method based on radar and video integration | |
| CN106816038A (en) | A kind of inland waters abnormal behaviour ship automatic identification system and method | |
| CN106097648A (en) | Transformer station's fortune inspection working space three-dimensional security monitoring method | |
| CN102081801A (en) | Multi-feature adaptive fused ship tracking and track detecting method | |
| CN204129891U (en) | A kind of high ferro anti-intrusion system along the line | |
| CN101751744A (en) | Detection and early warning method of smoke | |
| CN112434669B (en) | Human body behavior detection method and system based on multi-information fusion | |
| KR102412862B1 (en) | Intrusion alert system | |
| CN112381778A (en) | Transformer substation safety control platform based on deep learning | |
| CN108099959A (en) | Foreign body intrusion intellectual monitoring alarm system | |
| CN106741008A (en) | Rail track method for recognizing impurities and system | |
| CN115761537B (en) | Power transmission line foreign matter intrusion identification method oriented to dynamic feature supplementing mechanism | |
| CN110246119A (en) | The recognition methods of transmission tower floods potential faults based on SAR image | |
| CN106052745B (en) | A kind of power circuit monitoring method | |
| Li et al. | Application research of artificial intelligent technology in substation inspection tour | |
| CN114998846A (en) | Method and system for realizing intelligent system of offshore drilling platform and related components | |
| Zhen et al. | Transmission tower protection system based on Internet of Things in smart grid | |
| CN108269021A (en) | Risk monitoring system and method are merged based on NB-IoT electric network informations physics | |
| CN115691018B (en) | Railway perimeter intrusion monitoring and early warning method and system based on multi-sensor fusion |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190129 |
|
| WD01 | Invention patent application deemed withdrawn after publication |