CN105868795A - Method for detecting energy meter model based on visual identification - Google Patents
Method for detecting energy meter model based on visual identification Download PDFInfo
- Publication number
- CN105868795A CN105868795A CN201610263875.XA CN201610263875A CN105868795A CN 105868795 A CN105868795 A CN 105868795A CN 201610263875 A CN201610263875 A CN 201610263875A CN 105868795 A CN105868795 A CN 105868795A
- Authority
- CN
- China
- Prior art keywords
- energy meter
- electric energy
- value
- pixel
- outline drawing
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/755—Deformable models or variational models, e.g. snakes or active contours
- G06V10/7553—Deformable models or variational models, e.g. snakes or active contours based on shape, e.g. active shape models [ASM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
Abstract
The invention relates to a method for detecting an energy meter model based on visual identification. The method comprises a step (1) of utilizing an image collecting device to shoot an energy meter so as to obtain energy meter appearance images; a step (2) of utilizing an image preprocessing device to preprocess the energy meter appearance images so as to output preprocessed appearance images; a step (3) of utilizing a Freescale IMX6 processing device to perform matching one by one based on various standard energy meter patterns prestored in a static storage device, and outputting a type of a reference energy meter pattern matched successfully to serve as a target energy meter type. Through the method, accurate reference data can be provided for a power supply department, and an important basis is provided for supervision on an energy meter by the power supply department.
Description
The present invention is Application No. 201510153367.1, filing date April 1 in 2015 day,
The divisional application of the patent of bright entitled " the electric energy meter model detection method of view-based access control model identification ".
Technical field
The present invention relates to electric energy meter field, particularly relate to the electric energy meter model inspection of a kind of view-based access control model identification
Survey method.
Background technology
Electric energy meter can be carried out as follows classification: by purposes: active electric energy meter, reactive energy-meter, maximum need
Scale, standard electric energy meter, multi tariff time-sharing electric energy meter, prepayment meter (point coin-feed, magnetic card
Formula, electric card type), loss electric energy meter, by operation principle: vicarious (mechanical type), state type (electricity
Minor), electromechanical (hybrid);By accessing power supply natures: alternating-current meter, direct current table;By knot
Structure: monoblock type, split type;By accessing phase line: single-phase, phase three-wire three, three-phase and four-line electric energy meter;
By class of accuracy: common installing type electric energy meter (0.2S, 0.5S, 0.2.0.5.1.0,2.0 grades) and portable type
Accurate electric energy meter (0.01,0.05,0.2 grade);By installing the mode of connection: direct access, indirectly
Access type.
Due to electric energy meter numerous types and widely distributed, the supervision to power supply department brings puzzlement, power supply
When department carries out remote meter reading or periodic maintenance to electric energy meter, the key message first having to obtain is each
The type of the electric energy meter of individual position, just can carry out after determining electric energy meter type corresponding reading collection and
Customization maintenance service.Prior art is by arrangement personnel to each installation site to dissimilar electricity
Can carry out type confirmation by table, this means excessively rely on manually, take time and effort, and there is also some electronics
Means of identification, but existing electronic recognition means cannot ensure type identification precision in inclement weather.
Accordingly, it would be desirable to a kind of new electric energy meter model detection method, substituting loaded down with trivial details artificial cognition behaviour
While work, it is also possible to overcome vile weather especially haze weather that electric energy meter type identification is brought
Interference, thus provide important referential data for power supply department efficiently and in real time, facilitate power supply department
The management of power use and plant maintenance.
Summary of the invention
In order to solve the problems referred to above, according to an aspect of the present invention, the invention provides a kind of based on
The electric energy meter model detection method of visual identity, comprising:
(1) image capture device is utilized to shoot electric energy meter to obtain electric energy meter outline drawing picture;
(2) image-preprocessing device is utilized described electric energy meter outline drawing picture to carry out pretreatment with output
Pretreatment outline drawing picture;
(3) based on all kinds of benchmark electric energy meter patterns prestored in static storage device, utilization flies
Thinking karr IMX6 processing equipment to mate described pretreatment outline drawing picture one by one, output matching becomes
The type of the benchmark electric energy meter pattern of merit exports as target electric energy meter type;
All kinds of benchmark electric energy meter patterns prestored in wherein said static storage device are to each
Plant benchmark electric energy meter profile and shoot obtained image in advance;
Wherein said image-preprocessing device is connected with described image capture device, described Freescale
IMX6 processing equipment is connected respectively with described image-preprocessing device and described static storage device.
According to another aspect of the present invention, the invention provides the electric energy meter of a kind of view-based access control model identification
Model detection method, comprising:
(1) image capture device is utilized to shoot electric energy meter to obtain electric energy meter outline drawing picture;
(2) image-preprocessing device is utilized described electric energy meter outline drawing picture to carry out pretreatment with output
Pretreatment outline drawing picture;
(3) utilize mist elimination processing equipment receive described pretreatment outline drawing picture, to described pretreatment outside
Shape image carries out mist elimination and processes to obtain mist elimination outline drawing picture;
(4) based on all kinds of benchmark electric energy meter patterns prestored in static storage device, utilization flies
Think karr IMX6 processing equipment described mist elimination outline drawing picture is mated one by one, output matching success
Benchmark electric energy meter pattern type as target electric energy meter type export;
All kinds of benchmark electric energy meter patterns prestored in wherein said static storage device are to each
Plant benchmark electric energy meter profile and shoot obtained image in advance;
Wherein said image-preprocessing device is connected with described image capture device, and described mist elimination processes and sets
Standby between described image-preprocessing device and described Freescale IMX6 processing equipment, described in fly
Think karr IMX6 processing equipment to connect respectively with described mist elimination processing equipment and described static storage device
Connect.
Specifically, the step described electric energy meter outline drawing picture being carried out pretreatment includes described electric energy meter
Outline drawing picture carries out contrast enhancement processing, it is thus achieved that strengthen electric energy meter outline drawing picture, and based on Haar
Wavelet filter carries out wavelet filtering process to described enhancing electric energy meter outline drawing picture, described pre-to obtain
Process outline drawing picture.
Further, the electric energy meter model detection method of described view-based access control model identification also includes: it is fixed to utilize
Position equipment carries out real-time positioning, and to described Freescale IMX6 processing equipment output current location number
According to;Wireless Telecom Equipment is utilized to carry out described target electric energy meter type and described current location data beating
Bag, the packet obtained by wireless communication link output packing;Utilize SD card real-time storage institute
State target electric energy meter type and described current location data;LCDs is utilized to show described mesh in real time
Mark electric energy meter type and described current location data.Wherein said location equipment, described radio communication set
SD card standby, described and described LCDs connect respectively with described Freescale IMX6 processing equipment
Connect.
Further, the electric energy meter model detection method of described view-based access control model identification also includes that utilization is described
Freescale IMX6 processing equipment carries out OCR identification, to obtain to described mist elimination outline drawing picture
State the current reading of electric energy meter.
The electric energy meter model detection method of described view-based access control model identification utilizes detecting system to detect.Cause
This, according to an aspect of the present invention, present invention also offers the electric energy phenotype of a kind of view-based access control model identification
Number detecting system, described detecting system includes image capture device, image-preprocessing device, flies to think card
That IMX6 processing equipment and static storage device.Described image capture device is for shooting electric energy meter
To obtain electric energy meter outline drawing picture;Described static storage device has prestored all kinds of benchmark electric energy meter figure
Case;Described image-preprocessing device is connected with described image capture device, to described electric energy meter outline drawing
As carrying out pretreatment to export pretreatment outline drawing picture;Described Freescale IMX6 processing equipment and institute
State image-preprocessing device and described static storage device connects respectively, based on all kinds of benchmark electric energy meter figures
Electric energy meter type corresponding to pretreatment outline drawing picture described in case identification is using defeated as target electric energy meter type
Go out.
More specifically, the electric energy meter model detecting system of described view-based access control model identification also includes:
Location equipment, is connected with described Freescale IMX6 processing equipment, for described detection system
System carries out real-time positioning, and exports current location data to described Freescale IMX6 processing equipment;
Wireless Telecom Equipment, is connected with described Freescale IMX6 processing equipment, for by described mesh
Mark electric energy meter type and described current location data are packed, by wireless communication link output packing
The packet obtained;
SD card, is connected, for mesh described in real-time storage with described Freescale IMX6 processing equipment
Mark electric energy meter type and described current location data;
Power supply, including solar powered device, accumulator, switching switch and electric pressure converter,
Described switching switch is connected, according to accumulator respectively with described solar powered device and described accumulator
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;
LCDs, is connected with described Freescale IMX6 processing equipment, shows institute in real time
State target electric energy meter type and described current location data;
Mist elimination processing equipment, is positioned at described image-preprocessing device and described Freescale IMX6 process
Between equipment, it is used for receiving described pretreatment outline drawing picture, described pretreatment outline drawing picture is gone
Mist processes to obtain mist elimination outline drawing picture, and described mist elimination outline drawing picture is inputted described Freescale
IMX6 processing equipment is to carry out electric energy meter type identification to obtain target electric energy meter type.
More specifically, described mist elimination processing equipment includes:
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;
Overall air light value obtains subset, is connected to obtain described pre-with described image-preprocessing device
Process outline drawing picture, calculate the gray value of each pixel in described pretreatment outline drawing picture, by gray value
The gray value of maximum pixel is as overall air light value;
Atmospheric scattering light value obtains subset, examines with described image-preprocessing device and described haze concentration
Survey subset to connect respectively, each pixel to described pretreatment outline drawing picture, extract its R, G,
In B tri-Color Channel pixel value, minima is as target pixel value, uses the Gaussian smoothing keeping edge
Described target pixel value is filtered by wave filter EPGF (edge-preserving gaussian filter)
Process to obtain filtered target pixel value, target pixel value is deducted filtered target pixel value to obtain mesh
Mark pixel value difference, uses EPGF to be filtered object pixel difference processing to obtain filtered target picture
Element difference, deducts filtered target pixel value filtered target pixel value difference to obtain haze and removes benchmark
Value, haze is removed intensity be multiplied by haze remove reference value with obtain haze remove threshold value, take haze and go
Except the minima in threshold value and target pixel value is as comparison reference, take in comparison reference and 0
Maximum is as the atmospheric scattering light value of 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, with described image-preprocessing device, described overall air light value
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, the pixel value of each pixel in described pretreatment outline drawing picture is deducted described product value with
Obtain the second difference, described second difference is each to obtain divided by the medium transmission rate of each pixel
The sharpening pixel value of individual pixel, in described pretreatment outline drawing picture, the pixel value of each pixel includes
The R of each pixel in described pretreatment outline drawing picture, G, B tri-Color Channel pixel value, accordingly
Ground, it is thus achieved that the sharpening pixel value of each pixel include the R of each pixel, G, B tri-face
Chrominance channel sharpening pixel value, the sharpening pixel value composition mist elimination outline drawing picture of all pixels;
Described Freescale IMX6 processing equipment sets with described mist elimination processing equipment and described static storage
Back-up does not connect, and described mist elimination outline drawing picture and described all kinds of benchmark electric energy meter patterns is carried out one by one
Joining, the type of output matching successful benchmark electric energy meter pattern exports as target electric energy meter type.
More specifically, wherein said static storage device each of prestores benchmark electric energy meter pattern
By each benchmark electric energy meter profile is shot obtained image in advance;Described Image semantic classification
Equipment also includes contrast enhancement processing subset and wavelet filtering subset, at described contrast enhancing
Reason subset is connected with described image capture device, for contrasting described electric energy meter outline drawing picture
Degree enhancement process, it is thus achieved that strengthen electric energy meter outline drawing picture, described wavelet filtering subset and described contrast
Degree enhancement process subset connects, based on Haar wavelet filter to described enhancing electric energy meter outline drawing picture
Carry out wavelet filtering process, to obtain described pretreatment outline drawing picture.
More specifically, in the electric energy meter model detecting system of described view-based access control model identification, described in fly to think
Karr IMX6 processing equipment also carries out OCR identification to described mist elimination outline drawing picture, described to obtain
The current reading of electric energy meter.
More specifically, in the electric energy meter model detecting system of described view-based access control model identification, described image
Collecting device includes front cover glass, camera lens, filter and image-forming electron unit.
More specifically, in the electric energy meter model detecting system of described view-based access control model identification, described haze
Concentration Testing subset, described overall air light value obtain subset, the acquisition of described atmospheric scattering light value
Subset, described medium transmission rate obtain subset and described sharpening Image Acquisition subset is integrated in
On one piece of surface-mounted integrated circuit, and it is respectively adopted different fpga chips and realizes.
More specifically, in the electric energy meter model detecting system of described view-based access control model identification, described haze
Concentration Testing subset, described overall air light value obtain subset, the acquisition of described atmospheric scattering light value
Subset, described medium transmission rate obtain subset and described sharpening Image Acquisition subset is used
The type selecting of fpga chip be all the Artix-7 series of Xilinx company.
The detection method of the electric energy meter model of the view-based access control model identification of the present invention and detecting system, introduce height
The acquisition technology of precision, image recognition technology realize accurately identifying electric energy meter profile, introduce
Wireless communication technology realizes electric energy meter type and the high efficiency of transmission of position, on this basis, according to greatly
Gas attenuation model determines the haze influence factor to image, to the electric energy meter profile gathered under haze weather
Image carries out mist elimination process, it is thus achieved that electric energy meter outline drawing picture clearly, thus reduce under vile weather right
The unfavorable interference of electric energy meter type identification.
Accompanying drawing explanation
Below with reference to accompanying drawing, embodiment of the present invention are described, wherein:
Fig. 1 is the detection of the electric energy meter model detection method implementing the view-based access control model identification according to the present invention
One embodiment of system.
Fig. 2 is the detection of the electric energy meter model detection method implementing the view-based access control model identification according to the present invention
The further embodiment of system.
Detailed description of the invention
Electric energy meter model detection side to the view-based access control model identification implementing the present invention below with reference to accompanying drawings
The embodiment of the detecting system of method is described in detail.
Electric energy meter is used to measure the instrument of electric energy, also known as kilowatt-hour meter, energy meter, kilowatt-hour table, refers to
Measure the instrument of various electrical quantities, be the instrument being specifically used to measure certain time period electric energy aggregate-value.
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 aluminum dish, induces eddy current in aluminum dish;Eddy current is subject to again in magnetic field
To the effect of power, so that aluminum 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 aluminum dish is the biggest, makes aluminum 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 aluminum dish rotates the fastest.When aluminum 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 aluminum dish
Rapid-result direct ratio, aluminum dish rotates the fastest, and braking moment is the biggest.When active moment reaches with braking moment
During to temporary equilibrium, aluminum dish is by uniform rotation.The electric energy that load is consumed is directly proportional to the revolution of aluminum dish.
When aluminum dish rotates, drive enumerator, the electric energy consumed is indicated.Here it is electric energy meter work
Simple procedure.
Due to electric energy meter numerous types and widely distributed, distributing position is complicated, the most existing artificial class
Type detection mode and simple detection of electrons mode cannot meet efficiently and high-precision dual simultaneously
Requirement.To this end, the present invention has built the electric energy meter model detecting system of a kind of view-based access control model identification, logical
Cross image acquisition and image recognition technology meets efficient requirement, overcome severe sky by going hazeization to process
Under gas to electric energy meter reading read negative effect thus meet high-precision requirement.
Fig. 1 is the detection of the electric energy meter model detection method implementing the view-based access control model identification according to the present invention
One embodiment of system, wherein, described detecting system includes that image capture device 1, image are pre-
Processing equipment 2, Freescale IMX6 processing equipment 3, static storage device 4 and power supply 5,
Described image capture device 1 is for shooting electric energy meter to obtain electric energy meter outline drawing picture, described static state
Storage device 4 has prestored all kinds of benchmark electric energy meter pattern, described image-preprocessing device 2 and institute
State image capture device 1 to connect, described electric energy meter outline drawing picture is carried out pretreatment to export pretreatment
Outline drawing picture, described Freescale IMX6 processing equipment 3 and described image-preprocessing device 2 and institute
State static storage device 4 to connect respectively, based on pretreatment described in all kinds of benchmark electric energy meter pattern identification outside
Electric energy meter type corresponding to shape image is to export as target electric energy meter type.
Then, with reference to Fig. 2, the electric energy meter model detection side to the view-based access control model identification implementing the present invention
The further embodiment of the detecting system of method illustrates.Unlike Fig. 1, the enforcement of Fig. 2
In mode, add and be positioned at described image-preprocessing device 2 and described Freescale IMX6 process sets
Mist elimination processing equipment 6 between standby 3.Continue that the system of Fig. 2 is carried out structure to be described as follows.
Described detecting system also includes: location equipment, with described Freescale IMX6 processing equipment 3
Connect, for described detecting system being carried out real-time positioning, and to described Freescale IMX6 process
Equipment 3 exports current location data;
Described detecting system also includes: Wireless Telecom Equipment, sets with described Freescale IMX6 process
Standby 3 connect, for described target electric energy meter type and described current location data being packed, logical
Cross the packet that wireless communication link output packing is obtained;
Described detecting system also includes: SD card, with described Freescale IMX6 processing equipment 3 even
Connect, for target electric energy meter type described in real-time storage and described current location data;
Described power supply 5, turns including solar powered device, accumulator, switching switch and voltage
Parallel operation, described switching switch is connected respectively with described solar powered device and described accumulator, according to
Accumulator dump energy decides whether to be switched to described solar powered device to be supplied by described solar energy
Electrical part is powered, and described electric pressure converter is connected with described switching switch, switching defeated by switching
The 5V voltage entered is converted to 3.3V voltage;
Described detecting system also includes: LCDs, with described Freescale IMX6 processing equipment
3 connect, and show described target electric energy meter type and described current location data in real time;
Described mist elimination processing equipment 6, is positioned at described image-preprocessing device 2 and described Freescale
Between IMX6 processing equipment 3, be used for receiving described pretreatment outline drawing picture, to described pretreatment outside
Shape image carries out mist elimination and processes to obtain mist elimination outline drawing picture, by described for the input of described mist elimination outline drawing picture
Freescale IMX6 processing equipment 3 is to carry out electric energy meter type identification to obtain target electric energy meter type;
Described mist elimination processing equipment 6 farther includes:
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;
Overall air light value obtains subset, is connected to obtain described with described image-preprocessing device 2
Pretreatment outline drawing picture, calculates the gray value of each pixel in described pretreatment outline drawing picture, by gray scale
The gray value of the pixel that value is maximum is as overall air light value;
Atmospheric scattering light value obtains subset, with described image-preprocessing device 2 and described haze concentration
Detection subset connects respectively, and each pixel to described pretreatment outline drawing picture extracts its R,
G, B tri-in Color Channel pixel value minima as target pixel value, use the Gauss keeping edge
Described target pixel value is carried out by smoothing filter EPGF (edge-preserving gaussian filter)
Target pixel value, to obtain filtered target pixel value, is deducted filtered target pixel value to obtain by Filtering Processing
Obtain object pixel difference, use EPGF to be filtered object pixel difference processing to obtain filtering mesh
Mark pixel value difference, deducts filtered target pixel value filtered target pixel value difference to obtain haze and removes base
Quasi-value, removes haze intensity and is multiplied by haze and removes reference value and remove threshold value to obtain haze, take haze
Minima in removal threshold value and target pixel value, as comparison reference, takes in comparison reference and 0
Maximum as the atmospheric scattering light value of 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, with described image-preprocessing device 2, described overall atmosphere light
Value obtains subset and described medium transmission rate obtains subset and connects respectively, deducts each picture by 1
Described first difference, to obtain the first difference, is multiplied by overall air light value to obtain by the medium transmission rate of element
Obtain product value, the pixel value of each pixel in described pretreatment outline drawing picture is deducted described product value
To obtain the second difference, described second difference is every to obtain divided by the medium transmission rate of each pixel
The sharpening pixel value of one pixel, the pixel value bag of each pixel in described pretreatment outline drawing picture
Include the R of each pixel in described pretreatment outline drawing picture, G, B tri-Color Channel pixel value, phase
Ying Di, it is thus achieved that the sharpening pixel value of each pixel include the R, G, B tri-of each pixel
Color Channel sharpening pixel value, the sharpening pixel value composition mist elimination outline drawing picture of all pixels;
Described Freescale IMX6 processing equipment 3 is deposited with described mist elimination processing equipment 6 and described static state
Storage equipment 4 connects respectively, is carried out with described all kinds of benchmark electric energy meter patterns by described mist elimination outline drawing picture
Mating one by one, the type of output matching successful benchmark electric energy meter pattern is defeated as target electric energy meter type
Go out;
Wherein, described static storage device 4 each of prestores benchmark electric energy meter pattern for often
A kind of benchmark electric energy meter profile shoots obtained image in advance;Described image-preprocessing device 2
Also include contrast enhancement processing subset and wavelet filtering subset, described contrast enhancement processing
Equipment is connected with described image capture device 1, for described electric energy meter outline drawing picture is carried out contrast
Enhancement process, it is thus achieved that strengthen electric energy meter outline drawing picture, described wavelet filtering subset and described contrast
Enhancement process subset connects, and enters described enhancing electric energy meter outline drawing picture based on Haar wavelet filter
Row wavelet filtering processes, to obtain described pretreatment outline drawing picture.
Wherein, alternatively, described Freescale IMX6 processing equipment 3 is also to described mist elimination outline drawing
As carrying out OCR identification, to obtain the current reading of described electric energy meter, described image capture device 1
Including front cover glass, camera lens, filter and image-forming electron unit, described haze Concentration Testing subset,
Described overall air light value obtains subset, described atmospheric scattering light value obtains subset, described medium
Transfer rate obtains subset and described sharpening Image Acquisition subset is integrated in one piece of surface-mounted integrated circuit
On, and be respectively adopted different fpga chips and realize, described haze Concentration Testing subset, institute
State overall air light value and obtain subset, described atmospheric scattering light value acquisition subset, described medium biography
The type selecting of the fpga chip that defeated rate acquisition subset and described sharpening Image Acquisition subset are used
It is all the Artix-7 series of Xilinx company.
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.
It addition, FPGA (Field-Programmable Gate Array), i.e. field-programmable gate array
Row, he is the product of development further on the basis of the programming devices such as PAL, GAL, CPLD.
He is to occur as a kind of semi-custom circuit in special IC (ASIC) field, both solves
Determine the deficiency of custom circuit, overcome again the shortcoming that original programming device gate circuit number is limited.
The circuit design completed with hardware description language (Verilog or VHDL), can be through letter
Single comprehensive and layout, is quickly burned onto on FPGA and tests, and is modern IC designs checking
Technology main flow.These can be edited element and can be used to realize some basic logic gates (ratio
Such as AND, OR, XOR, NOT) or more more complicated combination function such as decoder or number
Learn equation.
Inside most FPGA, also comprise memory cell in these editable elements the most tactile
Send out device (Flip-flop) or other more complete block of memory.System designer can be as required
By editable connection, the logical block within FPGA is coupled together, just look like a circuit testing
Plate has been placed in a chip.One dispatch from the factory after the logical block of finished product FPGA and connect can be by
Change according to designer, so FPGA can complete required logic function.
Use the electric energy meter model detection method of the view-based access control model identification of the present invention, for existing electric energy meter
Identification system or excessively to rely on manual or automaticization degree the highest and be disturbed under foggy days
Technical problem, realized electric energy meter by multiple image acquisition targetedly or image processing section
The automatical and efficient identification of type, meanwhile, the use of high-precision mist elimination equipment overcomes under foggy days
The interference that electric energy meter type identification is brought.
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.
Claims (2)
1. an electric energy meter model detection method for view-based access control model identification, the method includes:
(1) image capture device is utilized to shoot electric energy meter to obtain electric energy meter outline drawing picture;
(2) image-preprocessing device is utilized described electric energy meter outline drawing picture to carry out pretreatment to export pretreatment outline drawing picture;
(3) based on all kinds of benchmark electric energy meter patterns prestored in static storage device, utilizing Freescale IMX6 processing equipment to mate described pretreatment outline drawing picture one by one, the type of output matching successful benchmark electric energy meter pattern exports as target electric energy meter type;
All kinds of benchmark electric energy meter patterns prestored in wherein said static storage device are that each benchmark electric energy meter profile is shot obtained image in advance;
Wherein said image-preprocessing device is connected with described image capture device, and described Freescale IMX6 processing equipment is connected respectively with described image-preprocessing device and described static storage device.
2. detection method as claimed in claim 1, the step wherein described electric energy meter outline drawing picture being carried out pretreatment includes described electric energy meter outline drawing picture is carried out contrast enhancement processing, obtain and strengthen electric energy meter outline drawing picture, and based on Haar wavelet filter, described enhancing electric energy meter outline drawing picture is carried out wavelet filtering process, to obtain described pretreatment outline drawing picture;
Farther include: utilize location equipment to carry out real-time positioning, and export current location data to described Freescale IMX6 processing equipment;Wireless Telecom Equipment is utilized described target electric energy meter type and described current location data to be packed, the packet obtained by wireless communication link output packing;Utilize target electric energy meter type and described current location data described in SD card real-time storage;LCDs is utilized to show described target electric energy meter type and described current location data in real time;
Wherein said location equipment, described Wireless Telecom Equipment, described SD card and described LCDs are connected respectively with described Freescale IMX6 processing equipment;
Farther include to utilize described Freescale IMX6 processing equipment that described mist elimination outline drawing picture is carried out OCR identification, to obtain the current reading of described electric energy meter;
The method is to utilize to include that the detecting system of image capture device, image-preprocessing device, Freescale IMX6 processing equipment and static storage device detects;
Wherein said mist elimination processing equipment includes:
Haze Concentration Testing subset, is positioned in air, for the haze concentration of detection electric energy meter position in real time, and determines that intensity removed by haze according to haze concentration, and described haze removes intensity value between 0 to 1;
Overall air light value obtains subset, is connected with described image-preprocessing device to obtain described pretreatment outline drawing picture, calculates the gray value of each pixel in described pretreatment outline drawing picture, using the gray value of pixel maximum for gray value as overall air light value;
nullAtmospheric scattering light value obtains subset,It is connected respectively with described image-preprocessing device and described haze Concentration Testing subset,Each pixel to described pretreatment outline drawing picture,Extract its R,G,In B tri-Color Channel pixel value, minima is as target pixel value,Use and keep the Gaussian filter EPGF at edge to be filtered described target pixel value processing to obtain filtered target pixel value,Target pixel value is deducted filtered target pixel value to obtain object pixel difference,EPGF is used to be filtered object pixel difference processing to obtain filtered target pixel value difference,Filtered target pixel value is deducted filtered target pixel value difference and removes reference value to obtain haze,Haze is removed intensity and is multiplied by haze removal reference value to obtain haze removal threshold value,Take haze and remove the minima in threshold value and target pixel value as comparison reference,Take the atmospheric scattering light value as each pixel of the maximum in comparison reference and 0;
Medium transmission rate obtains subset, obtain subset with described overall air light value and described atmospheric scattering light value obtains subset and is connected respectively, by the atmospheric scattering light value of each pixel divided by overall air light value to obtain except value, deduct described except value is to obtain the medium transmission rate of each pixel by 1;
nullSharpening Image Acquisition subset,With described image-preprocessing device、Described overall air light value obtains subset and described medium transmission rate obtains subset and connects respectively,The medium transmission rate of each pixel is deducted to obtain the first difference by 1,Described first difference is multiplied by overall air light value to obtain product value,The pixel value of each pixel in described pretreatment outline drawing picture is deducted described product value to obtain the second difference,By described second difference divided by the medium transmission rate of each pixel to obtain the sharpening pixel value of each pixel,The R of each pixel during the pixel value of each pixel includes described pretreatment outline drawing picture in described pretreatment outline drawing picture,G,B tri-Color Channel pixel value,Correspondingly,The sharpening pixel value of each pixel obtained includes the R of each pixel,G,B tri-Color Channel sharpening pixel value,The sharpening pixel value composition mist elimination outline drawing picture of all pixels;
Wherein said image-preprocessing device also includes contrast enhancement processing subset and wavelet filtering subset, described contrast enhancement processing subset is connected with described image capture device, for described electric energy meter outline drawing picture is carried out contrast enhancement processing, obtain and strengthen electric energy meter outline drawing picture, described wavelet filtering subset is connected with described contrast enhancement processing subset, based on Haar wavelet filter, described enhancing electric energy meter outline drawing picture is carried out wavelet filtering process, to obtain described pretreatment outline drawing picture;
Wherein said haze Concentration Testing 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 on one piece of surface-mounted integrated circuit, and are respectively adopted different fpga chips and realize.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610263875.XA CN105868795A (en) | 2015-04-01 | 2015-04-01 | Method for detecting energy meter model based on visual identification |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610263875.XA CN105868795A (en) | 2015-04-01 | 2015-04-01 | Method for detecting energy meter model based on visual identification |
CN201510153367.1A CN104700101B (en) | 2015-04-01 | 2015-04-01 | Electric energy meter model detection method based on visual recognition |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510153367.1A Division CN104700101B (en) | 2015-04-01 | 2015-04-01 | Electric energy meter model detection method based on visual recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105868795A true CN105868795A (en) | 2016-08-17 |
Family
ID=53347200
Family Applications (7)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610263875.XA Withdrawn CN105868795A (en) | 2015-04-01 | 2015-04-01 | Method for detecting energy meter model based on visual identification |
CN201610261644.5A Withdrawn CN105894049A (en) | 2015-04-01 | 2015-04-01 | Power meter model detection method based on visual identity |
CN201510153367.1A Active CN104700101B (en) | 2015-04-01 | 2015-04-01 | Electric energy meter model detection method based on visual recognition |
CN201510570542.7A Pending CN105243642A (en) | 2015-04-01 | 2015-04-01 | Visual recognition-based power meter type detection method |
CN201510570788.4A Pending CN105243643A (en) | 2015-04-01 | 2015-04-01 | Visual recognition-based power meter type detection method |
CN201610261645.XA Withdrawn CN105975904A (en) | 2015-04-01 | 2015-04-01 | Watt-hour meter model detection method based on visual identification |
CN201610263381.1A Withdrawn CN105894040A (en) | 2015-04-01 | 2015-04-01 | Power meter model detection method based on visual identity |
Family Applications After (6)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610261644.5A Withdrawn CN105894049A (en) | 2015-04-01 | 2015-04-01 | Power meter model detection method based on visual identity |
CN201510153367.1A Active CN104700101B (en) | 2015-04-01 | 2015-04-01 | Electric energy meter model detection method based on visual recognition |
CN201510570542.7A Pending CN105243642A (en) | 2015-04-01 | 2015-04-01 | Visual recognition-based power meter type detection method |
CN201510570788.4A Pending CN105243643A (en) | 2015-04-01 | 2015-04-01 | Visual recognition-based power meter type detection method |
CN201610261645.XA Withdrawn CN105975904A (en) | 2015-04-01 | 2015-04-01 | Watt-hour meter model detection method based on visual identification |
CN201610263381.1A Withdrawn CN105894040A (en) | 2015-04-01 | 2015-04-01 | Power meter model detection method based on visual identity |
Country Status (1)
Country | Link |
---|---|
CN (7) | CN105868795A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109085773A (en) * | 2017-06-13 | 2018-12-25 | 欧姆龙株式会社 | electric energy management system and computer readable storage medium |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105173036A (en) * | 2015-07-24 | 2015-12-23 | 任元华 | Underwater human body detector based on neural network identification |
CN105129052A (en) * | 2015-07-24 | 2015-12-09 | 王翠平 | Underwater human body searching method |
CN105083505A (en) * | 2015-07-25 | 2015-11-25 | 刘纪君 | System for detecting water area under ship based on image processing |
CN105466940A (en) * | 2015-11-16 | 2016-04-06 | 赵飞腾 | Inflatable current transformer defect monitoring device |
CN107292154B (en) * | 2017-06-09 | 2020-12-11 | 奇安信科技集团股份有限公司 | Terminal feature identification method and system |
CN107389687B (en) * | 2017-06-27 | 2020-10-09 | 北京航空航天大学 | Electronic component appearance image acquisition device and acquisition method thereof |
CN107730478A (en) * | 2017-10-17 | 2018-02-23 | 云南电网有限责任公司电力科学研究院 | A kind of method for detecting shape and device of electric energy metering automation terminal |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8520979B2 (en) * | 2008-08-19 | 2013-08-27 | Digimarc Corporation | Methods and systems for content processing |
CN102236788B (en) * | 2010-04-20 | 2015-09-02 | 荣科科技股份有限公司 | Power meter automatic distinguishing method for image |
CN103049888A (en) * | 2012-12-07 | 2013-04-17 | 西安电子科技大学 | Image/video demisting method based on combination of dark primary color of atmospheric scattered light |
CN104281846A (en) * | 2013-07-12 | 2015-01-14 | 苏州新天远节能环保科技有限公司 | Instrument data collecting method based on visual identity |
CN103913150B (en) * | 2014-04-24 | 2016-03-16 | 国家电网公司 | Intelligent electric energy meter electronic devices and components consistency detecting method |
-
2015
- 2015-04-01 CN CN201610263875.XA patent/CN105868795A/en not_active Withdrawn
- 2015-04-01 CN CN201610261644.5A patent/CN105894049A/en not_active Withdrawn
- 2015-04-01 CN CN201510153367.1A patent/CN104700101B/en active Active
- 2015-04-01 CN CN201510570542.7A patent/CN105243642A/en active Pending
- 2015-04-01 CN CN201510570788.4A patent/CN105243643A/en active Pending
- 2015-04-01 CN CN201610261645.XA patent/CN105975904A/en not_active Withdrawn
- 2015-04-01 CN CN201610263381.1A patent/CN105894040A/en not_active Withdrawn
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109085773A (en) * | 2017-06-13 | 2018-12-25 | 欧姆龙株式会社 | electric energy management system and computer readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN104700101B (en) | 2017-04-19 |
CN105243642A (en) | 2016-01-13 |
CN105894040A (en) | 2016-08-24 |
CN104700101A (en) | 2015-06-10 |
CN105975904A (en) | 2016-09-28 |
CN105243643A (en) | 2016-01-13 |
CN105894049A (en) | 2016-08-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105868795A (en) | Method for detecting energy meter model based on visual identification | |
CN105929236A (en) | Functional electric meter in building elevator room | |
CN105118064A (en) | Method for detecting damage degree of outdoor electric energy meter | |
CN106384117B (en) | A kind of vehicle color identification method and device | |
CN105242232B (en) | Outdoor electrical energy meter fault self-verifying method | |
CN105093167B (en) | Outdoor electrical energy meter fault automatic gauging terminal | |
CN108334815A (en) | Method for inspecting, on off state recognition methods and the system of second power equipment | |
CN105118264B (en) | Electric energy meter wireless kilowatt meter reading-out system | |
CN104702920B (en) | Based on cmos image collection, electric energy meter is carried out to the method for automatic data logging | |
CN103336972A (en) | Foundation cloud picture classification method based on completion local three value model | |
CN104700107A (en) | Electric energy meter reading recognition apparatus based on image processing | |
CN104700425B (en) | Outdoor electric energy meter damaged degree detection platform | |
CN104715267A (en) | Electric energy meter model detection system based on visual identification | |
CN105791755A (en) | Method for automatically reading power meter by using automatic meter reading platform based on image collection | |
CN109345511A (en) | A kind of highway unmanned plane self-checking system | |
CN105657230A (en) | Method for automatically reading electric energy meter through automatic meter reading platform | |
CN211181059U (en) | Accurate recognition equipment of ETC portal license plate | |
Li et al. | Recognition of windmills in remote sensing image by SVM and morphological attribute filters | |
CN105828042A (en) | CMOS image collection-based electric energy meter automatic meter reading platform | |
CN105791757A (en) | Power meter automatic reading platform and automatic meter reading method thereof | |
CN105791756A (en) | Power meter automatic reading platform based on image collection and automatic meter reading method | |
CN105791758A (en) | Method for automatically reading power meter | |
CN105791759A (en) | Method for automatically reading power meter based on image collection | |
CN104735420A (en) | Electric energy meter automatic data logging platform based on CMOS image collecting | |
Pan et al. | Paint Code Identification Using Mobile Color Detector |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20160817 |