Summary of the invention
In order to solve the problems referred to above, the invention provides a kind of outdoor electric energy meter damaged degree detection flat
Platform, uses the mode of electronic meter reading to substitute original manual metering mode, utilizes high-precision image to adopt
Collection technology and image processing techniques have built a set of electric energy meter detection platform, ensure the efficient of data acquisition
Rate, meanwhile, determines the haze influence factor to image according to atmospheric attenuation model, and to foggy days
The electric energy meter image of lower collection carries out hazeization and processes, it is thus achieved that electric energy meter image clearly, thus protects
The accuracy of barrier outdoor electric energy meter damaged degree detection.
According to an aspect of the present invention, it is provided that a kind of outdoor electric energy meter damaged degree detection platform, institute
State platform and include high-definition camera, image processor, static memory and master controller, described high definition
Camera is for shooting to obtain electric energy meter image to electric energy meter, and described image processor is with described
High-definition camera connects, for described electric energy meter image being carried out image procossing, to extract described electric energy
Bezel, cluster image in table image, described static memory has prestored benchmark electric energy meter block diagram case,
Described master controller is connected respectively with described image processor and described static memory, based on described base
Quasi-electric energy meter block diagram case and the matching result of described bezel, cluster image, determine the damaged journey of described electric energy meter
Degree.
More specifically, in described outdoor electric energy meter damaged degree detection platform, also include: GPS is fixed
Position device, for receiving the current GPS location of electric energy meter of gps satellite feedback, and with described master control
Device processed connects so that described current GPS location is sent to described master controller;GPRS communication interface,
It is connected with described master controller, for by the damaged degree of described electric energy meter and described current GPS location
It is packaged as GPRS data bag, and described GPRS data bag is wirelessly sent to the power supply management of far-end
Platform;Power supply, including solar powered device, battery, switching switch and electric pressure converter,
Described switching switch is connected, according to battery respectively with described solar powered device and described battery
Dump energy decides whether to be switched to described solar powered device with by described solar powered device
Power supply, described electric pressure converter is connected with described switching switch, with by the 5V by switching switch input
Voltage is converted to 3.3V voltage;Sharpening processing equipment, is positioned at described high-definition camera and described image
Between processor, it is used for receiving described electric energy meter image, described electric energy meter image is carried out mist elimination process
To obtain mist elimination electric energy meter image, described mist elimination electric energy meter image is inputted described image processor to replace
Change described electric energy meter image by image procossing to extract the bezel, cluster image in described mist elimination electric energy meter image;
Described sharpening processing equipment also includes: storage subset, is used for prestoring sky upper limit gray scale threshold
Value and sky lower limit gray threshold, described sky upper limit gray threshold and described sky lower limit gray threshold
For isolating the sky areas in image, it is additionally operable to prestore presetted pixel value threshold value, described pre-
If pixel value threshold value value is between 0 to 255;Haze Concentration Testing subset, is positioned in air,
For the haze concentration of detection electric energy meter position in real time, and determine that haze is removed according to haze concentration
Intensity, described haze removes intensity value between 0 to 1;Region divides subset, connects described
High-definition camera to receive described electric energy meter image, described electric energy meter image is carried out gray processing process with
Obtain gray processing electric energy meter image, be also connected, by described gray processing electric energy meter image with storage subset
Middle gray value pixel between described sky upper limit gray threshold and described sky lower limit gray threshold
Identify and form gray processing sky sub pattern, being partitioned into described gray scale from described gray processing electric energy meter image
Change sky sub pattern is to obtain gray processing non-sky subgraph, based on described gray processing non-sky subgraph
Position in described electric energy meter image obtains the colour that sky subgraph non-with described gray processing is corresponding
Non-sky subgraph;Black channel obtains subset, divides subset with described region and is connected to obtain
Described colour non-sky subgraph, for each pixel in described colour non-sky subgraph, calculates
Its R, G, B tri-Color Channel pixel value, the R of all pixels in described colour non-sky subgraph,
G, B tri-extracts the face at the minimum Color Channel pixel value place of a numerical value in Color Channel pixel value
Chrominance channel is as black channel;Overall air light value obtains subset, is connected to obtain with storage subset
Obtain described presetted pixel value threshold value, also divide subset with described region and described black channel obtains son
Equipment connects to obtain described electric energy meter image and described black channel respectively, by described electric energy meter image
Middle black channel pixel value forms pixel to be tested more than or equal to multiple pixels of presetted pixel value threshold value
Collection, using the gray value of the pixel in described set of pixels to be tested with maximum gradation value as overall air
Light value;Atmospheric scattering light value obtains subset, divides subset and described haze concentration with described region
Detection subset connects respectively, and each pixel to described electric energy meter image extracts its R, G, B
In three Color Channel pixel values, minimum of a value is as target pixel value, uses the Gaussian smoothing filter keeping edge
Ripple device EPGF (edge-preserving gaussian filter) is filtered place to described target pixel value
Target pixel value, to obtain filtered target pixel value, is deducted filtered target pixel value to obtain target by reason
Pixel value difference, uses EPGF to be filtered object pixel difference processing to obtain filtered target pixel
Difference, deducts filtered target pixel value filtered target pixel value difference to obtain haze and removes a reference value,
Haze is removed intensity be multiplied by haze remove a reference value with obtain haze remove threshold value, take haze remove threshold
Minimum of a value in value and target pixel value, as comparison reference, takes the maximum in comparison reference and 0
It is worth the atmospheric scattering light value as each pixel;Medium transmission rate obtains subset, with described entirety
Air light value obtains subset and described atmospheric scattering light value obtains subset and connects respectively, by each
The atmospheric scattering light value of pixel divided by overall air light value to obtain except value, deduct 1 described except value with
Obtain the medium transmission rate of each pixel;Sharpening Image Acquisition subset, divides with described region
Subset, described overall air light value obtain subset and described medium transmission rate obtains subset respectively
Connect, deduct the medium transmission rate of each pixel by 1 to obtain the first difference, by described first poor
Value is multiplied by overall air light value to obtain product value, by the picture of each pixel in described electric energy meter image
Element value deducts described product value to obtain the second difference, by described second difference divided by each pixel
Medium transmission rate to obtain the sharpening pixel value of each pixel, in described electric energy meter image each
The pixel value of pixel includes the R of each pixel in described electric energy meter image, G, B tri-Color Channel
Pixel value, correspondingly, it is thus achieved that the sharpening pixel value of each pixel include the R of each pixel,
G, B tri-Color Channel sharpening pixel value, the sharpening pixel value composition mist elimination electric energy of all pixels
Table image;Described image processor is after receiving described mist elimination electric energy meter image, by described mist elimination electricity
HSV image can be converted to by table image, extract the H channel value of each pixel in HSV image,
H channel value is obtained in described bezel, cluster H passage threshold range based on bezel, cluster H passage threshold range
Multiple pixels, form the bezel, cluster image in described mist elimination electric energy meter image by the plurality of pixel;Described
Master controller is connected respectively with described image processor and described static memory, based on described benchmark electricity
Energy table bezel, cluster pattern and the matching result of the bezel, cluster image in described mist elimination electric energy meter image, determine described
The damaged degree of electric energy meter, described benchmark electric energy meter block diagram case is electric energy meter intact to quality in advance
Carry out shooting obtained image;Wherein, described image processor also includes built-in memory cell,
For storing described bezel, cluster H passage threshold range, described bezel, cluster H passage threshold range is by bezel, cluster H
Passage upper limit threshold and bezel, cluster H passage lower threshold composition.
More specifically, in described outdoor electric energy meter damaged degree detection platform, described master controller exists
After receiving the bezel, cluster image in described mist elimination electric energy meter image, in described mist elimination electric energy meter image
Bezel, cluster image carries out image sharpening, self adaptation recursive filtering and OCR identifying processing successively, to obtain
Electric energy meter reading.
More specifically, in described outdoor electric energy meter damaged degree detection platform, described high-definition camera
OV7640 sensor for Omnivision company.
More specifically, in described outdoor electric energy meter damaged degree detection platform, described master controller is
AT89C51 system.
More specifically, in described outdoor electric energy meter damaged degree detection platform, described storage is set
Haze Concentration Testing subset standby, described, described region divide subset, described black channel obtains
Subset, described overall air light value obtain subset, described atmospheric scattering light value obtains subset,
Described medium transmission rate obtains subset and described sharpening Image Acquisition subset is integrated in one block of electricity
On the plate of road.
Detailed description of the invention
Embodiment party to the outdoor electric energy meter damaged degree detection platform of the present invention below with reference to accompanying drawings
Case is described in detail.
The operation principle of electric energy meter is as follows: when electric energy meter is accessed circuit-under-test, current coil and electricity
Just having alternating current to flow through in line ball circle, the two alternating current produces in their iron core respectively and hands over
The magnetic flux become;Alternating flux passes aluminium dish, induces eddy current in aluminium dish;Eddy current is subject to again in magnetic field
To the effect of power, so that aluminium dish obtains torque (actively moment) and rotates.The power of load consumption
The biggest, the biggest by the electric current of current coil, the eddy current induced in aluminium dish is the biggest, makes aluminium dish turn
Dynamic moment is the biggest.The i.e. size of torque is directly proportional with the power of load consumption.Power is the biggest, turns
Square is the biggest, and aluminium dish rotates the fastest.When aluminium dish rotates, the braking produced by permanent magnet again
The effect of moment, braking moment is in opposite direction with actively moment;The size of braking moment turns with aluminium dish
Rapid-result direct ratio, aluminium dish rotates the fastest, and braking moment is the biggest.When active moment reaches with braking moment
During to transient equilibrium, aluminium dish is by uniform rotation.The electric energy that load is consumed is directly proportional to the revolution of aluminium dish.
When aluminium dish rotates, drive counter, the electric energy consumed is indicated.Here it is electric energy meter work
Simple procedure.
Due to electric energy meter have large number of, be distributed scattered feature, electric energy meter outward appearance damage testing needs
To meet high efficiency, high-precision requirement simultaneously.But, electric energy meter outward appearance of the prior art is damaged
All there is intrinsic defect in detection scheme: (1) is although artificial detection mode can guarantee that testing result
Precision, however it is necessary that consuming substantial amounts of cost of labor, inefficient, real-time is the strongest;(2)
More existing detection of electrons schemes can only ensure the reading collection under home, due to much electricity
Table is placed in open air, under the weather that visibility is relatively low, such as, under foggy days environment, often causes
The electric energy meter of shooting is image blurring unclear, and correspondingly, testing result error is the biggest.
To this end, the present invention has built a kind of outdoor electric energy meter damaged degree detection platform, by have for
Property image acquisition and processing technology meet efficient requirement, by go hazeization process realize under bad weather
Also can carry out the detection of high-precision electric energy meter damaged degree, thus meet above two requirement simultaneously.
Fig. 1 is the knot according to the outdoor electric energy meter damaged degree detection platform shown in embodiment of the present invention
Structure block diagram, described platform includes high-definition camera 1, image processor 2, static memory 3 and
Master controller 4, described high-definition camera 1 is used for shooting to obtain electric energy meter image to electric energy meter,
Described image processor 2 is connected with described high-definition camera 1, for carrying out described electric energy meter image
Image procossing, to extract the bezel, cluster image in described electric energy meter image, described static memory 3 is in advance
Store benchmark electric energy meter block diagram case, described master controller 4 and described image processor 2 and described
Static memory 3 connects respectively, based on described benchmark electric energy meter block diagram case and described bezel, cluster image
Matching result, determines the damaged degree of described electric energy meter.
Then, continue the concrete structure of the outdoor electric energy meter damaged degree detection platform of the present invention is carried out
Further instruction.
Described platform also includes: GPS locator, for receiving working as of the electric energy meter of gps satellite feedback
Front GPS location, and be connected described current GPS location is sent to institute with described master controller 4
State master controller.
Described platform also includes: GPRS communication interface, is connected with described master controller 4, and being used for will
The damaged degree of described electric energy meter and described current GPS location are packaged as GPRS data bag, and by institute
State GPRS data bag and be wirelessly sent to the power supply management platform of far-end.
Described platform also includes: power supply, opens including solar powered device, battery, switching
Close and electric pressure converter, described switching switch and described solar powered device and described battery difference
Connect, decide whether to be switched to described solar powered device with by described according to battery dump energy
Solar powered device is powered, and described electric pressure converter is connected with described switching switch, with will be by cutting
The 5V voltage changing switch input is converted to 3.3V voltage.
Described platform also includes: sharpening processing equipment, is positioned at described high-definition camera 1 and described figure
As, between processor 2, being used for receiving described electric energy meter image, described electric energy meter image carried out mist elimination
Process to obtain mist elimination electric energy meter image, described mist elimination electric energy meter image is inputted described image processor
2 to replace described electric energy meter image by image procossing to extract the bezel, cluster in described mist elimination electric energy meter image
Image.
Further, described sharpening processing equipment includes with lower component:
Storage subset, is used for prestoring sky upper limit gray threshold and sky lower limit gray threshold,
Described sky upper limit gray threshold and described sky lower limit gray threshold are for isolating the sky in image
Dummy section, is additionally operable to prestore presetted pixel value threshold value, and described presetted pixel value threshold value value is 0
Between 255;
Haze Concentration Testing subset, is positioned in air, for detection electric energy meter position in real time
Haze concentration, and determine that intensity removed by haze according to haze concentration, described haze is removed intensity value and is existed
Between 0 to 1;
Region divides subset, connects described high-definition camera 1 to receive described electric energy meter image, right
Described electric energy meter image carries out gray processing and processes to obtain gray processing electric energy meter image, also sets with storage
Standby connection, by gray value in described gray processing electric energy meter image in described sky upper limit gray threshold and institute
State the pixel identification between sky lower limit gray threshold and form gray processing sky sub pattern, from described ash
Degreeization electric energy meter image is partitioned into described gray processing sky sub pattern to obtain gray processing non-sky null subgraph
Picture, obtains with described based on described gray processing non-sky subgraph position in described electric energy meter image
The colour non-sky subgraph that gray processing non-sky subgraph is corresponding;
Black channel obtains subset, divides subset with described region and is connected to obtain described colour non-
Sky subgraph, for each pixel in described colour non-sky subgraph, calculates its R, G, B
Three Color Channel pixel values, the R, G, B tri-of all pixels in described colour non-sky subgraph
Color Channel pixel value extracts the Color Channel at the minimum Color Channel pixel value place of a numerical value
As black channel;
Overall air light value obtains subset, is connected to obtain described presetted pixel value with storage subset
Threshold value, also divides subset with described region and described black channel obtains subset and is connected respectively to obtain
Obtain described electric energy meter image and described black channel, by black channel pixel value in described electric energy meter image
Set of pixels to be tested is formed, by described picture to be tested more than or equal to multiple pixels of presetted pixel value threshold value
Element concentrates the gray value of the pixel with maximum gradation value as overall air light value;
Atmospheric scattering light value obtains subset, divides subset and the inspection of described haze concentration with described region
Survey subset to connect respectively, each pixel to described electric energy meter image, extract its R, G, B
In three Color Channel pixel values, minimum of a value is as target pixel value, uses the Gaussian smoothing filter keeping edge
Ripple device EPGF (edge-preserving gaussian filter) is filtered place to described target pixel value
Target pixel value, to obtain filtered target pixel value, is deducted filtered target pixel value to obtain target by reason
Pixel value difference, uses EPGF to be filtered object pixel difference processing to obtain filtered target pixel
Difference, deducts filtered target pixel value filtered target pixel value difference to obtain haze and removes a reference value,
Haze is removed intensity be multiplied by haze remove a reference value with obtain haze remove threshold value, take haze remove threshold
Minimum of a value in value and target pixel value, as comparison reference, takes the maximum in comparison reference and 0
It is worth the atmospheric scattering light value as each pixel;
Medium transmission rate obtains subset, obtains subset and described air with described overall air light value
Scattering light value obtains subset and connects respectively, by big divided by entirety for the atmospheric scattering light value of each pixel
Gas light value, to obtain except value, deducts described except value is to obtain the medium transmission rate of each pixel by 1;
Sharpening Image Acquisition subset, divides subset, described overall air light value with described region
Obtain subset and described medium transmission rate obtains subset and connects respectively, deduct each pixel by 1
Medium transmission rate to obtain the first difference, described first difference is multiplied by overall air light value to obtain
Product value, deducts described product value to obtain by the pixel value of each pixel in described electric energy meter image
Second difference, by described second difference divided by the medium transmission rate of each pixel to obtain each picture
The sharpening pixel value of element, in described electric energy meter image, the pixel value of each pixel includes described electric energy
The R of each pixel in table image, G, B tri-Color Channel pixel value, correspondingly, it is thus achieved that every
The sharpening pixel value of one pixel includes the R of each pixel, G, B tri-Color Channel sharpening
Pixel value, the sharpening pixel value composition mist elimination electric energy meter image of all pixels.
Described image processor 2 is after receiving described mist elimination electric energy meter image, by described mist elimination electric energy
Table image is converted to HSV image, the H channel value of each pixel in extraction HSV image, base
In bezel, cluster H passage threshold range obtain H channel value in described bezel, cluster H passage threshold range many
Individual pixel, forms the bezel, cluster image in described mist elimination electric energy meter image by the plurality of pixel.
Described master controller 4 is connected respectively with described image processor 2 and described static memory 3,
Based on the bezel, cluster image in described benchmark electric energy meter block diagram case and described mist elimination electric energy meter image
Joining result, determine the damaged degree of described electric energy meter, described benchmark electric energy meter block diagram case is the most right
The electric energy meter that quality is intact carries out shooting obtained image.
Wherein, described image processor 2 also includes built-in memory cell, is used for storing described bezel, cluster
H passage threshold range, described bezel, cluster H passage threshold range is by bezel, cluster H passage upper limit threshold and bezel, cluster
H passage lower threshold forms.
Wherein, in described platform, alternatively, described master controller 4 is receiving described mist elimination electricity
After bezel, cluster image in energy table image, the bezel, cluster image in described mist elimination electric energy meter image is carried out successively
Image sharpening, self adaptation recursive filtering and OCR identifying processing, to obtain electric energy meter reading, described
High-definition camera 1 is the OV7640 sensor of Omnivision company, and described master controller 4 is single
Sheet machine AT89C51, and can by described storage subset, described haze Concentration Testing subset,
Described region divides subset, described black channel obtains subset, described overall air light value obtains
Subset, described atmospheric scattering light value obtain subset, described medium transmission rate obtains subset and institute
State sharpening Image Acquisition subset to be integrated on one piece of circuit board.
It addition, haze image can remove haze by what a series of images processing equipment realized image,
To obtain the image of sharpening, improve the visibility of image.These image processing equipments perform not respectively
Same image processing function, the principle formed based on haze, reach to remove the effect of haze.Haze figure
The sharpening of picture processes all has great using value, military domain bag for dual-use field
Including military and national defense, remote sensing navigation etc., civil area includes road monitoring, target following and automatic Pilot
Deng.
The process that haze image is formed can be described by atmospheric attenuation process, in haze image and reality
The medium of the available overall air light value of the relation between image i.e. sharpening image and each pixel passes
Defeated rate is stated, i.e. in the case of known haze image, according to overall air light value and each picture
The medium transmission rate of element, can solve sharpening image.
There are some and have in the solving of medium transmission rate for overall air light value and each pixel
Effect and through the means of checking, such as, for the medium transmission rate of each pixel, need to obtain whole
Body atmosphere light value and the atmospheric scattering light value of each pixel, and the atmospheric scattering light value of each pixel
Can be at the Gaussian smoothing that each pixel pixel value in haze image is carried out twice holding edge
Filtering and obtain, therebetween, the intensity that haze is removed is adjustable;And the acquisition pattern of entirety air light value has
Two kinds, a kind of mode is, (i.e. can make in haze image by obtaining the black channel of haze image
The black channel value of some pixels is the lowest, black channel is R, and G, B tri-is in Color Channel
A kind of), in haze image, the multiple pixels bigger than normal by finding black channel pixel value are found
The pixel of gray value maximum obtains, and gray value that will search out, gray value is maximum pixel is made
For overall air light value, participate in the sharpening of each pixel in haze image and process;It addition, it is overall
Air light value also can obtain in the following manner: calculates the gray value of each pixel in haze image, will
The gray value of the pixel that gray value is maximum is as overall air light value.
Relation between concrete haze image and real image i.e. sharpening image, and parameters
Between relation can be found in above content.
By the discussion to haze image formation basic theory, build between haze image and sharpening image
Relation, represent this relation by multiple parameters, subsequently by the multiple parameter values obtained and haze figure
The image that picture the most reducible acquisition definition is higher, owing to some statistical means have been used in the acquisition of parameter
And empirical means, the image that the most described definition is higher can not be fully equivalent to real image, but
Have and considerable degree of gone haze effect, provide effectively for the every field operation under haze weather
Ensure.
Use the outdoor electric energy meter damaged degree detection platform of the present invention, break for existing electric energy meter outward appearance
Damage degree detecting scheme detection efficiency technology that is low and that there may be precision the highest at bad weather to ask
Topic, by using IMAQ and image processing techniques targetedly, substitutes manual detection mode,
Improve detection efficiency, meanwhile, add sharpening processing equipment based on atmospheric attenuation model and realize mist elimination
Hazeization processes, and overcomes the haze weather impact on damaged degree testing result, it is ensured that be supplied to power supply
The accuracy of the reference data of door.
Although it is understood that the present invention discloses as above with preferred embodiment, but above-mentioned enforcement
Example is not limited to the present invention.For any those of ordinary skill in the art, without departing from
Under technical solution of the present invention ambit, all may utilize the technology contents of the disclosure above to the technology of the present invention
Scheme makes many possible variations and modification, or is revised as the Equivalent embodiments of equivalent variations.Therefore,
Every content without departing from technical solution of the present invention, the technical spirit of the foundation present invention is to above example
Any simple modification, equivalent variations and the modification done, all still falls within technical solution of the present invention protection
In the range of.