CN110493574A - Safety supervision visualization system based on Streaming Media and AI technology - Google Patents
Safety supervision visualization system based on Streaming Media and AI technology Download PDFInfo
- Publication number
- CN110493574A CN110493574A CN201910798218.9A CN201910798218A CN110493574A CN 110493574 A CN110493574 A CN 110493574A CN 201910798218 A CN201910798218 A CN 201910798218A CN 110493574 A CN110493574 A CN 110493574A
- Authority
- CN
- China
- Prior art keywords
- video image
- video
- image
- noise
- visualization system
- 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.)
- Granted
Links
- 238000012800 visualization Methods 0.000 title claims abstract description 23
- 238000005516 engineering process Methods 0.000 title claims abstract description 10
- 230000007547 defect Effects 0.000 claims abstract description 36
- 230000005540 biological transmission Effects 0.000 claims abstract description 8
- 238000004891 communication Methods 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims description 27
- 238000003708 edge detection Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 11
- 238000012544 monitoring process Methods 0.000 claims description 10
- 230000002708 enhancing effect Effects 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims description 2
- 238000007689 inspection Methods 0.000 abstract description 18
- 238000007726 management method Methods 0.000 description 21
- 238000004458 analytical method Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 238000000034 method Methods 0.000 description 4
- 238000011946 reduction process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of safety supervision visualization system based on Streaming Media and AI technology, the safety supervision visualization system include: video data acquiring platform, data transmitting server and the visualized management terminal computer for successively carrying out data communication connection.The safety supervision visualization system passes through the video image at the available electric operating scene of video data acquiring platform, the transmission of video images at the electric operating scene obtained video data acquiring platform by data transmitting server is to visualized management terminal computer, the handling situations and each power equipment for enabling service personnel that can remotely understand electric operating scene by the visualized management terminal computer are with the presence or absence of defect, in order to adopt an effective measure in time, remove a hidden danger；Electric operating scene is deep into without service personnel simultaneously and carries out manual inspection, improves routing inspection efficiency, is also avoided since manual inspection bring inspection is not in place, inspection is not perfect.
Description
Technical field
The present invention relates to field of artificial intelligence, and in particular to a kind of safety supervision visualization based on Streaming Media and AI technology
System.
Background technique
Electric operating and the production of people's lives and enterprise are closely bound up, and when normal work of power equipment ensures just
The necessary condition often powered is grasped route by safety supervision and electric power is set so the safety supervision to electric operating is particularly significant
Standby operation conditions finds the hidden danger of electric operating process and the hidden danger of power equipment safety, removes a hidden danger in time.
Traditional electric power safety supervision relies primarily on manually to be completed at the scene, and labour expends big in electric power safety supervision, is manually patrolled
Inspection is easy to appear situations such as inspection is not in place, inspection is not perfect, causes working efficiency low.
Summary of the invention
In view of the above-mentioned problems, the present invention provides a kind of safety supervision visualization system based on Streaming Media and AI technology.
The purpose of the present invention is realized using following technical scheme:
A kind of safety supervision visualization system based on Streaming Media and AI technology, the safety supervision visualization system include: successively to carry out
Video data acquiring platform, data transmitting server and the visualized management terminal computer of data communication connection；
The video data acquiring platform is set in electric operating scene, for acquiring the video figure at electric operating scene
Picture, and by the video image real-time Transmission of acquisition to the data transmitting server；The video image includes: to make about electric power
First video image of industry field scene and about electric operating scene in each power equipment the second video image；
The data transmitting server, for being cached the video image received；
The visualized management terminal computer, for obtaining the first video image from the data transmitting server, and
It is presented by video window；It is also used to obtain the second video image from the data transmitting server, later to described the
Two video images are handled, and judge that each power equipment whether there is defect and corresponding defect type, and pass through the view
Each defects of power equipment situation is presented in frequency window.
In an optional embodiment, the video data acquiring platform includes: to be deployed in the electric operating to show
The monitoring camera of designated position and the imaging sensor being deployed near each power equipment in.
In an optional embodiment, the safety supervision visualization system further include: with the visualized management terminal meter
The terminal control equipment of calculation machine communication connection, the terminal control equipment, for being sent out to the visualized management terminal computer
It instructs out, so that the visualized management terminal computer executes corresponding operation.
In an optional embodiment, the visualized management terminal computer is also used to obtain from meteorological publishing center
Weather information is taken, and is presented by the video window.
In an optional embodiment, the visualized management terminal computer includes: that the first video image obtains
Module, the second video image obtain module, weather information obtains module, the second video image processing module, power equipments defect
Monitoring modular and video window；
First video image obtains module and is used to obtain the first video image from the data transmitting server, and leads to
The video window is crossed to be presented；
Second video image obtains module and is used to obtain the second video image from the data transmitting server, and passes
Transport to the second video image processing module；
The weather information obtains module and is used to obtain weather information from meteorological publishing center, and passes through the video window
It is presented；
The second video image processing module obtains each power equipment for handling second video image
Characteristic；
The power equipments defect monitoring modular, for according to the characteristic of each power equipment and prestore about each electricity
The characteristic of power equipment deficiency type, judge each power equipment whether there is defect and corresponding defect type, and will
Judging result is presented by the video window.
In an optional embodiment, the second video image processing module includes image denoising unit, edge
Detection unit, image enhancing unit and feature extraction unit；
Described image denoising unit is for denoising second video image；
The edge detection unit is used to carry out edge detection to the second video image after denoising and divide, and is only wrapped
Video image containing power equipment；
Described image enhancement unit is used to carry out enhancing processing to the video image that segmentation obtains；
The feature extraction unit is used to describe power equipment in video image from extraction in enhanced video image
Characteristic.
It is described that second video image is denoised in an optional embodiment, specifically:
(1) noise measuring is carried out to the pixel in second video image, obtains making an uproar for second video image
Sound point setWith non-noise point set { Ψ }N；
(2) gray processing processing is carried out to second video image, and the gray value of each noise spot is estimated, obtained
The estimated value of each noise spot gray value；Wherein, the estimated value of the gray value of noise spot A is acquired using following formula:
In formula,For the estimated value of the gray value of noise spot A, G (A) is the gray value of noise spot A, and Γ is with noise spot A
Centered on sliding window, ZΓ、WΓNon-noise points and noise points, G in respectively sliding window Γz、GwRespectively sliding window
The gray value of the sum of the grayscale values noise spot w of non-noise point z in mouth Γ,For after gray processing in the second video image it is all non-
Noise spot gray value mean value, γ1、γ2For preset weight coefficient；
(3) set that the estimated value of each noise spot gray value and non-noise point gray value are constituted is the second view after denoising
Frequency image data.
The invention has the benefit that the present invention provides a kind of, the safety supervision based on Streaming Media and AI technology visualizes system
System, the safety supervision visualization system pass through the video image at the available electric operating scene of video data acquiring platform, pass through number
The transmission of video images at the electric operating scene for obtaining video data acquiring platform according to forwarding server is whole to visualized management
Computer is held, enables service personnel that can remotely understand electric operating scene by the visualized management terminal computer
Handling situations and each power equipment are removed a hidden danger with the presence or absence of defect in order to adopt an effective measure in time；While without
Service personnel is deep into electric operating scene and carries out manual inspection, improves routing inspection efficiency, also avoids due to manual inspection band
The inspection come is not in place, inspection is not perfect and so on.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is a kind of frame construction drawing of safety supervision visualization system provided in an embodiment of the present invention；
Fig. 2 is the frame construction drawing of the second video image processing module 340 provided in an embodiment of the present invention.
Appended drawing reference: video data acquiring platform 100, data transmitting server 200, visualized management terminal computer
300, terminal control equipment 400, the first video image obtain module 310, the second video image obtains module 320, weather information
Obtain module 330, the second video image processing module 340, power equipments defect monitoring modular 350, video window 360, image
Denoise unit 341, edge detection unit 342, image enhancing unit 343, feature extraction unit 344.
Specific embodiment
The invention will be further described with the following Examples.
Fig. 1 shows a kind of safety supervision visualization system based on Streaming Media and AI technology, which includes:
Successively carry out video data acquiring platform 100, data transmitting server 200 and the visualized management terminal meter of data communication connection
Calculation machine 300.
The video data acquiring platform 100 is set in electric operating scene, for acquiring the video at electric operating scene
Image, and by the video image real-time Transmission of acquisition to the data transmitting server 200；The video image include: about
First video image of electric operating field scene and about electric operating scene in each power equipment the second video image；
The data transmitting server 200, for being cached the video image received；
The visualized management terminal computer 300, for obtaining the first video figure from the data transmitting server 200
Picture, and presented by video window 360；It is also used to obtain the second video image from the data transmitting server 200, it
Second video image is handled afterwards, judges that each power equipment whether there is defect and corresponding defect type, and
Each defects of power equipment situation is presented by the video window 360.
The safety supervision based on Streaming Media and AI technology that bring of the embodiment of the present invention has the beneficial effect that the present invention provides a kind of
Visualization system, the safety supervision visualization system pass through the video at 100 available electric operating scene of video data acquiring platform
Image passes through the transmission of video images at the electric operating scene that data transmitting server 200 obtains video data acquiring platform
To visualized management terminal computer 300, enable service personnel can be remote by the visualized management terminal computer 300
Journey understands the handling situations at electric operating scene and each power equipment whether there is defect, effectively arranges in order to take in time
It applies, removes a hidden danger；Electric operating scene is deep into without service personnel simultaneously and carries out manual inspection, improves routing inspection efficiency,
It also avoids since manual inspection bring inspection is not in place, inspection is not perfect.
In an optional embodiment, the video data acquiring platform 100 includes: to be deployed in the electric operating
The monitoring camera of designated position and the imaging sensor being deployed near each power equipment in scene.
In an optional embodiment, the safety supervision visualization system further include: with the visualized management terminal meter
The terminal control equipment 400 that calculation machine 300 communicates to connect.The terminal control equipment 400 is used for the visualized management terminal
Computer 300 issues instruction, so that the visualized management terminal computer 300 executes corresponding operation.
In an optional embodiment, the visualized management terminal computer 300 is also used to from meteorology publication
The heart obtains weather information, and is presented by the video window 360.
In an optional embodiment, pass through the video window of the visualized management terminal computer 300
360, content can also be presented below as:
1) job information: the field operation information just carried out is shown.Geographical location and distribution situation including field operation,
The specific task of field operation and exploiting entity etc..
2) supervise and examine job information: the supervise and examine job information just carried out is shown.Geographical location and distribution including operation of superintending and checking
Situation.
3) it integrates power grid risk information: realizing and show that current electric grid risk comes into force and manage situation.
4) it defect information: realizes and shows current power equipments defect type and service personnel to its disposition.
5) video information: a. video window 360 can select specified electric operating on-site supervision camera to acquire at any time
Video checked；B. video window 360 can select specified on-site law-enforcing video to be checked at any time.
6) photo and short video information: can display scene operation photo and short video information, support looking into for multiple pictures
It sees.
7) it statisticallys analyze information: realizing that the back-end data model of support video window 360 calculates, including field operation information
Analysis model, each level security supervise and examine planning analysis model, record analysis model, power grid risk analysis model, defective data violating the regulations
Analysis model, appraisal of equipment analysis model, work data analysis model, and calculated result is graphically enterprising in large-size screen monitors
Row, which is shown, is convenient for Analysis of Policy Making, and the chart specifically shown is including including operating risk statistics, handling situations statistics, operation feelings in place
Condition statistics, equipment deficiency situation statistics, equipment state evaluation situation statistics, situation statistics violating the regulations etc..
In an optional embodiment, the visualized management terminal computer 300 can also be all kinds of by what is obtained
Data carry out unified integration, and custom interface can be used, by the business of the safety supervisions portion concerns such as field operation, supervise and examine plan, defect
Related data classification processing is replaced traditional data visualization interface, 360 content of video window is realized in a manner of 3-D graphic
Height intuitively visualize, allow uninteresting data become more with flexibility and gorgeous shock visual effect.
In an optional embodiment, the visualized management terminal computer 300 includes: that the first video image obtains
Modulus block 310, the second video image obtain module 320, weather information obtains module 330, the second video image processing module
340, power equipments defect monitoring modular 350 and video window 360；
First video image obtains module 310 and is used to obtain the first video figure from the data transmitting server 200
Picture, and presented by the video window 360；
Second video image obtains module 320 and is used to obtain the second video figure from the data transmitting server 200
Picture, and it is transmitted to the second video image processing module 340；
The weather information obtains module 330 and is used to obtain weather information from meteorological publishing center, and passes through the video
Window 360 is presented；
The second video image processing module 340 obtains each electric power for handling second video image
The characteristic of equipment；
The power equipments defect monitoring modular 350, for according to the characteristic of each power equipment and prestore about
The characteristic of each power equipments defect type, judge each power equipment whether there is defect and corresponding defect type,
And judging result is presented by the video window 360.
In an optional embodiment, referring to fig. 2, the second video image processing module 340 is gone including image
It makes an uproar unit 341, edge detection unit 342, image enhancing unit 343 and feature extraction unit 344；
Described image denoising unit 341 is for denoising second video image；
The edge detection unit 342 is used to carry out edge detection to the second video image after denoising and divide, and obtains
It only include the video image of power equipment；
Described image enhancement unit 343 is used to carry out enhancing processing to the video image that segmentation obtains；
The feature extraction unit 344 is used to describe power equipment in video image from extraction in enhanced video image
Characteristic.
It is described that second video image is denoised in an optional embodiment, specifically:
(1) noise measuring is carried out to the pixel in second video image, obtains making an uproar for second video image
Sound point setWith non-noise point set { Ψ }N；
(2) gray processing processing is carried out to second video image, and the gray value of each noise spot is estimated, obtained
The estimated value of each noise spot gray value；Wherein, the estimated value of the gray value of noise spot A is acquired using following formula:
In formula,For the estimated value of the gray value of noise spot A, G (A) is the gray value of noise spot A, and Γ is with noise spot A
Centered on sliding window, ZΓ、WΓNon-noise points and noise points, G in respectively sliding window Γz、GwRespectively sliding window
The gray value of the sum of the grayscale values noise spot w of non-noise point z in mouth Γ,For after gray processing in the second video image it is all non-
Noise spot gray value mean value, γ1、γ2For preset weight coefficient；
(3) set that the estimated value of each noise spot gray value and non-noise point gray value are constituted is the second view after denoising
Frequency image data.
The utility model has the advantages that due to environment, imaging sensor itself damage, transmission of video images process the factors such as packet loss shadow
It rings, so that obtaining in the second video image, there are noises, it is therefore desirable to noise reduction process be carried out to the second video image, be somebody's turn to do with improving
The picture quality of second video image is based on this convenient for accurately identifying for the subsequent all kinds of defects to power equipment, applicant's wound
It proposes above embodiment to new property, in the above-described embodiment, first noise spot is detected, to distinguish noise spot and non-
Then noise spot is estimated using gray value of the customized formula to noise spot, and then realize the noise reduction to noise spot
Processing, when solving noise spot gray value estimated value, it is contemplated that in the above-described embodiment, the noise spot gray value, non-noise
Gray value and noise spot gray value mean valueWith the influence of the absolute difference of noise spot gray value each in sliding window, from
And can the gray value to noise spot accurately estimated, improve denoising effect, improve the picture quality of the image, reduce
Environment, imaging sensor itself damage, transmission of video images process the factors bring such as packet loss influence, in favor of subsequent right
The image is handled.
In an optional embodiment, the pixel in the second video image carries out noise measuring, obtains
To the noise point set of second video imageWith non-noise point set { Ψ }N, specifically:
(1) relative difference of other pixel brightness values in the brightness value and its neighborhood of pixel p is calculated using following formula,
In, pixel p (xp, yp) with its neighborhood in other pixel brightness values relative difference calculating formula are as follows:
In formula, QqIt (p) is the relative difference of pixel q brightness value in pixel p and its neighborhood, L (p), L (q) are respectively
The brightness value of pixel p, pixel q, LmaxFor the maximum value of other pixel brightness values in neighborhood, σ1、σ2For the adjusting of setting
The factor, ΘpFor centered on pixel p, size is to remove pixel p, residual pixel point in the window of (2B+1) × (2B+1)
The set of composition；
(2) relative difference of other pixel brightness values in obtained pixel p and its neighborhood is subjected to descending arrangement, and
The accumulated value for the K forward relative mistake that sort is calculated,
And
In formula, RLKIt (p) is the accumulated value for the K forward relative difference that sort, RkIt (p) is k-th of value after sequence,
In, the value of K can according to actual needs can be with self-setting；
(3) RL that will be obtainedK(p) it is compared with preset noise threshold T, if more than T, then pixel p is noise spot,
And add it to setConversely, then adding it to set { Ψ }N；
(4) all pixels point is traversed, the noise point set of second video image can be obtainedAnd non-noise point
Gather { Ψ }N。
The utility model has the advantages that this not only adds figures if directly carrying out noise reduction process to the second video image all pixels point
As the burden of denoising unit 341, while the denoising efficiency of image denoising unit 341 is also reduced, applicant is innovatively first right
Second video image carries out noise spot detection, and the pixel in the second video image is divided, the second video image is obtained
Noise point setWith non-noise point set { Ψ }N, so that need to only be carried out to noise spot in subsequent progress noise reduction
Noise reduction process improves the denoising efficiency of the image denoising unit 341, alleviates the burden of the image denoising unit 341, thus
Extend the service life of the image denoising unit 341.Wherein, when being divided to the pixel in the second video image,
Obtained relative difference is carried out descending by the relative difference for first calculating other pixel brightness values in pixel and its neighborhood, and
The accumulated value of K forward relative difference of calculated permutations, and accumulated value is compared with preset noise threshold, and then judges
The noise spot is non-noise point or noise spot.The value of K is arranged according to actual needs, and when the value of K is bigger, it is cumulative to represent it
Value is bigger, then the probability for the pixel being divided into noise spot is also bigger, although being needed to a certain extent to more pixels
Noise reduction process is carried out, but also improves noise reduction effect, preferably improves the picture quality of the image, it is more conducively subsequent to the figure
As being handled, each power equipment is analyzed with the presence or absence of defect and its defect type.
In an optional embodiment, second video image to after denoising carries out edge detection and divides
It cuts, obtains video image only comprising power equipment, specifically；
(1) with pixel s (xs, ys) centered on, it selects a size for the sliding window of (2t+1) × (2t+1), utilizes
Following formula calculate separately the transverse edge characteristic value of pixel s, longitudinal edge characteristic value, left clinodiagonal edge feature value and
Right clinodiagonal edge feature value；
In formula,Respectively indicate the transverse edge characteristic value of pixel, longitudinal edge characteristic value,
Left clinodiagonal edge feature value and right clinodiagonal edge feature value；G () is the gray value of pixel, and σ is preset height
This weighting coefficient；
(3) it is based on the calculated result of step (2), the integrated value for being used for reflecting edge feature is calculated using following formula
IfThen pixel s is marginal point, conversely, the pixel is non-edge point；
(4) all pixels point in the second video image after traversal denoising, and according to obtained edge detection results to going
The second video image after making an uproar is split, and obtains video image only comprising power equipment.
The utility model has the advantages that the purpose of the embodiment of the present invention is to analyze power equipment with the presence or absence of defect, therefore only need pair
Power equipment image is analyzed, in the above-described embodiment, by carrying out edge to the second video image after denoising
It detects and divides, obtain only comprising the video image including power equipment, so that only needing to be directed to when subsequent characteristics are extracted to divide
Video image after cutting is handled, and this aspect alleviates the negative of subsequent image enhancement unit 343 and feature extraction unit 344
Load, also improves the treatment effeciency of subsequent image enhancement unit 343 and feature extraction unit 344, on the other hand so as to right
Each defects of power equipment situation is identified that easy access personnel quickly carry out the power equipment of existing defects faster
Maintenance.When carrying out edge detection, it is special that applicant innovatively introduces the transverse edge characteristic value of each pixel, longitudinal edge
Value indicative, left clinodiagonal edge feature value and right clinodiagonal edge feature value, first pass through the transverse direction for calculating separately each pixel
Edge feature value, longitudinal edge characteristic value, left clinodiagonal edge feature value and right clinodiagonal edge feature value, later basis
Obtained transverse edge characteristic value, longitudinal edge characteristic value, left clinodiagonal edge feature value and right clinodiagonal edge feature
Value obtains the integrated value for being able to reflect the pixel edge feature, to accurately be examined to whether each pixel belongs to marginal point
It surveys.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as understanding, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (7)
1. a kind of safety supervision visualization system based on Streaming Media and AI technology characterized by comprising successively carry out data communication
Video data acquiring platform, data transmitting server and the visualized management terminal computer of connection；
The video data acquiring platform is set in electric operating scene, for acquiring the video image at electric operating scene, and
By the video image real-time Transmission of acquisition to the data transmitting server；The video image includes: existing about electric operating
First video image of scene and the second video image about each power equipment in electric operating scene；
The data transmitting server, for being cached the video image received；
The visualized management terminal computer for obtaining the first video image from the data transmitting server, and passes through
Video window is presented；It is also used to obtain the second video image from the data transmitting server, later to second view
Frequency image is handled, and judges that each power equipment whether there is defect and corresponding defect type, and pass through the video window
Each defects of power equipment situation is presented in mouth.
2. safety supervision visualization system according to claim 1, which is characterized in that the video data acquiring platform includes:
It is deployed in the monitoring camera of designated position and the image sensing being deployed near each power equipment in the electric operating scene
Device.
3. safety supervision visualization system according to claim 1, which is characterized in that further include: it is whole with the visualized management
Hold the terminal control equipment of computer communication connection, the terminal control equipment, for calculating to the visualized management terminal
Machine issues instruction, so that the visualized management terminal computer executes corresponding operation.
4. safety supervision visualization system according to claim 1, which is characterized in that the visualized management terminal computer is also
For obtaining weather information from meteorological publishing center, and presented by the video window.
5. safety supervision visualization system according to claim 1, which is characterized in that the visualized management terminal computer packet
Include: the first video image obtains module, the second video image obtains module, weather information obtains module, at the second video image
Manage module, power equipments defect monitoring modular and video window；
First video image obtains module and is used to obtain the first video image from the data transmitting server, and passes through institute
Video window is stated to be presented；
Second video image obtains module and is used to obtain the second video image from the data transmitting server, and is transmitted to
The second video image processing module；
The weather information obtains module and is used to obtain weather information from meteorological publishing center, and is carried out by the video window
It presents；
The second video image processing module obtains the spy of each power equipment for handling second video image
Levy data；
The power equipments defect monitoring modular, for according to the characteristic of each power equipment and being set about each electric power for prestoring
The characteristic of standby defect type, judge each power equipment whether there is defect and corresponding defect type, and will judgement
As a result it is presented by the video window.
6. safety supervision visualization system according to claim 5, which is characterized in that the second video image processing module packet
Include image denoising unit, edge detection unit, image enhancing unit and feature extraction unit；
Described image denoising unit is for denoising second video image；
The edge detection unit is used to carry out edge detection to the second video image after denoising and divide, and obtains only comprising electricity
The video image of power equipment；
Described image enhancement unit is used to carry out enhancing processing to the video image that segmentation obtains；
The feature extraction unit is used for from the feature for extracting power equipment in description video image in enhanced video image
Data.
7. safety supervision visualization system according to claim 6, which is characterized in that it is described to second video image into
Row denoising, specifically:
(1) noise measuring is carried out to the pixel in second video image, obtains the noise spot of second video image
SetWith non-noise point set { Ψ }N；
(2) gray processing processing is carried out to second video image, and the gray value of each noise spot is estimated, respectively made an uproar
The estimated value of sound point gray value；Wherein, the estimated value of the gray value of noise spot A is acquired using following formula:
In formula,For the estimated value of the gray value of noise spot A, G (A) is the gray value of noise spot A, and Γ, which is with noise spot A, is
The sliding window of the heart, ZΓ、WΓNon-noise points and noise points, G in respectively sliding window Γz、GwRespectively sliding window Γ
The gray value of the sum of the grayscale values noise spot w of interior non-noise point z,For after gray processing in the second video image it is all non-noise
Point gray value mean value, γ1、γ2For preset weight coefficient；
(3) set that the estimated value of each noise spot gray value and non-noise point gray value are constituted is the second video figure after denoising
As data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910798218.9A CN110493574B (en) | 2019-08-27 | 2019-08-27 | Security monitoring visualization system based on streaming media and AI technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910798218.9A CN110493574B (en) | 2019-08-27 | 2019-08-27 | Security monitoring visualization system based on streaming media and AI technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110493574A true CN110493574A (en) | 2019-11-22 |
| CN110493574B CN110493574B (en) | 2021-06-11 |
Family
ID=68553600
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910798218.9A Active CN110493574B (en) | 2019-08-27 | 2019-08-27 | Security monitoring visualization system based on streaming media and AI technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110493574B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476537A (en) * | 2020-03-31 | 2020-07-31 | 广州高新工程顾问有限公司 | BIM-based engineering cost dynamic control system and method |
| CN112415922A (en) * | 2020-10-21 | 2021-02-26 | 深圳供电局有限公司 | Transformer substation monitoring system based on streaming media |
| CN112491968A (en) * | 2020-11-05 | 2021-03-12 | 深圳供电局有限公司 | Edge-end operation method of AI camera in power grid |
| CN113299025A (en) * | 2021-04-28 | 2021-08-24 | 金卯新能源集团有限公司 | Personnel climbing warning method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1761285A (en) * | 2005-09-14 | 2006-04-19 | 上海广电（集团）有限公司中央研究院 | Method for removing isolated noise point in video |
| US20080154387A1 (en) * | 2006-12-25 | 2008-06-26 | Kyojiro Nambu | Management system for managing a use status of a device |
| CN106790538A (en) * | 2016-12-22 | 2017-05-31 | 逯帅 | Power system is set up and fault solution method for pushing with O＆M fault database |
| CN108174165A (en) * | 2018-01-17 | 2018-06-15 | 重庆览辉信息技术有限公司 | Electric power safety operation and O＆M intelligent monitoring system and method |
| CN109117855A (en) * | 2018-08-06 | 2019-01-01 | 深圳众厉电力科技有限公司 | Abnormal power equipment image identification system |
| CN109145789A (en) * | 2018-08-09 | 2019-01-04 | 炜呈智能电力科技（杭州）有限公司 | Power supply system safety work support method and system |
-
2019
- 2019-08-27 CN CN201910798218.9A patent/CN110493574B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1761285A (en) * | 2005-09-14 | 2006-04-19 | 上海广电（集团）有限公司中央研究院 | Method for removing isolated noise point in video |
| US20080154387A1 (en) * | 2006-12-25 | 2008-06-26 | Kyojiro Nambu | Management system for managing a use status of a device |
| CN106790538A (en) * | 2016-12-22 | 2017-05-31 | 逯帅 | Power system is set up and fault solution method for pushing with O＆M fault database |
| CN108174165A (en) * | 2018-01-17 | 2018-06-15 | 重庆览辉信息技术有限公司 | Electric power safety operation and O＆M intelligent monitoring system and method |
| CN109117855A (en) * | 2018-08-06 | 2019-01-01 | 深圳众厉电力科技有限公司 | Abnormal power equipment image identification system |
| CN109145789A (en) * | 2018-08-09 | 2019-01-04 | 炜呈智能电力科技（杭州）有限公司 | Power supply system safety work support method and system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476537A (en) * | 2020-03-31 | 2020-07-31 | 广州高新工程顾问有限公司 | BIM-based engineering cost dynamic control system and method |
| CN112415922A (en) * | 2020-10-21 | 2021-02-26 | 深圳供电局有限公司 | Transformer substation monitoring system based on streaming media |
| CN112491968A (en) * | 2020-11-05 | 2021-03-12 | 深圳供电局有限公司 | Edge-end operation method of AI camera in power grid |
| CN113299025A (en) * | 2021-04-28 | 2021-08-24 | 金卯新能源集团有限公司 | Personnel climbing warning method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110493574B (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110493574A (en) | Safety supervision visualization system based on Streaming Media and AI technology | |
| CN112434880B (en) | Patrol route planning and patrol personnel management system based on deep learning | |
| CN109801282A (en) | Pavement behavior detection method, processing method, apparatus and system | |
| US9214016B2 (en) | Pantograph monitoring system and method | |
| CN108680833B (en) | Composite insulator defect detection system based on unmanned aerial vehicle | |
| CN106841381B (en) | Steel wire rope online flaw detection monitoring system and method and mining multi-rope friction lifting system | |
| CN104601956A (en) | Power transmission line online monitoring system and method based on fixed-wing unmanned aerial vehicle | |
| CN112258491A (en) | Three-dimensional simulation method for defects of power equipment | |
| CN102490764A (en) | Automatic detection method of track turnout notch | |
| CN109297978B (en) | Binocular imaging-based power line unmanned aerial vehicle inspection and defect intelligent diagnosis system | |
| WO2020232710A1 (en) | Haze image quality evaluation method and system, storage medium, and electronic device | |
| CN111896549A (en) | Building crack monitoring system and method based on machine learning | |
| CN115494193B (en) | Machine vision-based flame transverse propagation detection method and system for single body combustion test | |
| CN114187511A (en) | Intelligent monitoring method for power transmission panoramic big data | |
| CN115936672A (en) | Smart power grid online safety operation and maintenance management method and system | |
| CN116612048B (en) | Method and system for deblurring optical satellite remote sensing image | |
| CN112947585A (en) | Power grid unmanned aerial vehicle inspection method, device and system based on 5G cloud edge-end cooperation | |
| CN107300360A (en) | A kind of shaft size fast algorithm of detecting of rain fed crops seed three | |
| KR102355997B1 (en) | method for monitoring the soundness of concrete structure based on smart glass | |
| CN110798680B (en) | Single-frame no-reference self-adaptive video snowflake noise detection method | |
| CN112232307B (en) | Method for detecting wearing of safety helmet in night vision environment | |
| CN114154032A (en) | Three-dimensional visual three-dimensional inspection method, system and device for transformer substation and storage medium | |
| CN111192253A (en) | Definition checking method and system based on contrast sensitivity and contrast | |
| CN110136104A (en) | Image processing method, system and medium based on unmanned aerial vehicle station | |
| CN117274884B (en) | Construction dust pollution event detection method and system based on image recognition |
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 | ||
| CB02 | Change of applicant information |
Address after: Luohu District Shenzhen Shennan Road 518000 No. 4020 Guangdong provincial power dispatching center building Applicant after: SHENZHEN POWER SUPPLY BUREAU Co.,Ltd. Applicant after: China Southern Power Grid Shenzhen Digital Power Grid Research Institute Co.,Ltd. Address before: Luohu District Shenzhen Shennan Road 518000 No. 4020 Guangdong provincial power dispatching center building Applicant before: SHENZHEN POWER SUPPLY BUREAU Co.,Ltd. Applicant before: SHENZHEN COMTOP INFORMATION TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 518000 electric power dispatching and communication building, 4020 Shennan East Road, Luohu District, Shenzhen, Guangdong Patentee after: SHENZHEN POWER SUPPLY BUREAU Co.,Ltd. Country or region after: Zhong Guo Patentee after: China Southern Power Grid Digital Platform Technology (Guangdong) Co.,Ltd. Address before: 518000 electric power dispatching and communication building, 4020 Shennan East Road, Luohu District, Shenzhen, Guangdong Patentee before: SHENZHEN POWER SUPPLY BUREAU Co.,Ltd. Country or region before: Zhong Guo Patentee before: China Southern Power Grid Shenzhen Digital Power Grid Research Institute Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240321 Address after: 518000 electric power dispatching and communication building, 4020 Shennan East Road, Luohu District, Shenzhen, Guangdong Patentee after: SHENZHEN POWER SUPPLY BUREAU Co.,Ltd. Country or region after: Zhong Guo Address before: 518000 electric power dispatching and communication building, 4020 Shennan East Road, Luohu District, Shenzhen, Guangdong Patentee before: SHENZHEN POWER SUPPLY BUREAU Co.,Ltd. Country or region before: Zhong Guo Patentee before: China Southern Power Grid Digital Platform Technology (Guangdong) Co.,Ltd. |