CN104714068B - Robot to outdoor electric energy meter meter reading - Google Patents
Robot to outdoor electric energy meter meter reading Download PDFInfo
- Publication number
- CN104714068B CN104714068B CN201510153366.7A CN201510153366A CN104714068B CN 104714068 B CN104714068 B CN 104714068B CN 201510153366 A CN201510153366 A CN 201510153366A CN 104714068 B CN104714068 B CN 104714068B
- Authority
- CN
- China
- Prior art keywords
- electric energy
- energy meter
- value
- image
- pixel
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R11/00—Electromechanical arrangements for measuring time integral of electric power or current, e.g. of consumption
-
- 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
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of robot to outdoor electric energy meter meter reading, including the Big Dipper omniselector, portable hard drive, CMOS vision sensor, Recognition of Reading device and master controller, portable hard drive is used for prestoring all kinds of electric energy meter template, and for prestoring the maximum scale of each class electric energy meter template, minimum scale and pointer model, CMOS vision sensor is used for shooting electric energy meter image, Recognition of Reading device is connected with CMOS vision sensor electric energy meter image is performed image procossing, master controller is connected with the Big Dipper omniselector to control the advanced positions of robot, also it is connected respectively with portable hard drive and Recognition of Reading device, for controlling the automatic meter reading of robot.The present invention also enhances sharpening processor, for performing to go haze to process to electric energy meter image.By the present invention, even if under haze weather, it is also possible to control robot and accurately arrive target meter reading position, and realize the high accuracy meter reading to various outdoor electric energy meters.
Description
Technical field
The present invention relates to electric energy meter monitoring field, particularly relate to a kind of machine to outdoor electric energy meter meter reading
People.
Background technology
Being widely used of electric energy meter, is power supply department charge and the important references number of allotment electric power resource
According to, each is required for installing oneself a electric energy meter with electric unit or individual and monitors the use of oneself
Power consumption.
It is positioned at and there is the meter reading with the electric energy meter of electric unit of high-tension line is always a difficult problem, due to
These electric energy meters are near high-tension line, it is impossible to arrangement personnel use the meter reading of manual patrol, hand-kept
Pattern, and these electric energy meters are usually located at outdoor, if using electronics meter reading pattern to carry out at a distance
Meter reading, it is necessary to there are some image processing equipments, it is possible to overcome the haze weather impact on meter reading image,
Otherwise, the meter reading data precision obtained is the lowest.
After the meter reading scheme of the electric energy meter of high voltage electric unit of the prior art or employing power-off
Manual read's table schema, this mode disturbs and works with the normal of electric unit, or uses based on image
The remote electronic pattern processed, this mode depends on the readability of electric energy meter image, sternly
Under weight haze weather, electric energy meter image is clear not, correspondingly, and the electric energy meter reading accuracy of reading
Poor, affect the regular fee work of power supply department.
Accordingly, it would be desirable to a kind of new technical scheme to outdoor electric energy meter meter reading, it is possible to alternative cost is high
Artificial meter reading mode, and transform existing remote electronics meter reading mode to high voltage electric list
Position outdoor electric energy meter meter reading operation highly efficient and real-time, it is thus achieved that meter reading data not by weather
Impact.
Summary of the invention
In order to solve the problems referred to above, the invention provides a kind of robot to outdoor electric energy meter meter reading,
Introduce far-end remote control commands and the robot traveling control model of near-end speech control instruction combination,
First pass through robot described in the remote control commands coarse adjustment of Remote feeding management platform and advance to target reading
Epi-position is put, then by the phonetic control command of near-end site administrator for machine People's Bank of China described in fine tuning
Enter target meter reading position, improve the automaticity of meter reading, prestore all kinds of electric energy meter mould simultaneously
Plate and maximum scale, minimum scale and the pointer model of each class electric energy meter template, to improve meter reading
Accuracy, finally, the introducing of sharpening processor overcomes the haze weather unfavorable shadow to meter reading data
Ring.
According to an aspect of the present invention, it is provided that a kind of robot to outdoor electric energy meter meter reading, described
Robot include the Big Dipper omniselector, portable hard drive, CMOS vision sensor, Recognition of Reading device and
Master controller, described portable hard drive is used for prestoring all kinds of electric energy meter template, and for depositing in advance
Store up maximum scale, minimum scale and the pointer model of each class electric energy meter template, described CMOS vision
Sensor is used for shooting electric energy meter image, and described Recognition of Reading device is with described CMOS vision sensor even
Connect described electric energy meter image performs image procossing, described master controller and described the Big Dipper omniselector
Connect to control the advanced positions of described robot, also with described portable hard drive and described Recognition of Reading device
Connect respectively, for controlling the automatic meter reading of described robot.
More specifically, in the described robot to outdoor electric energy meter meter reading, also include: power supply,
Including solar powered device, accumulator, switching switch and electric pressure converter, described switching switch with
Described solar powered device and described accumulator connect respectively, according to the decision of accumulator dump energy are
No being switched to described solar powered device to be powered by described solar powered device, described voltage turns
Parallel operation is connected with described switching switch, will be converted to 3.3V by the 5V voltage of switching switch input
Voltage；Speech recognition device, for being converted to the signal of telecommunication, and based on institute by the voice of site administrator
State the signal of telecommunication and generate phonetic control command；Wireless communication interface, wireless with the power supply management platform of far-end
Connecting, with wireless receiving remote control commands, described remote control commands includes the Big Dipper control instruction；
Robot driving mechanism, is connected with described master controller, is used under the control of described master controller,
The behavior act of described robot, described behavior act is driven to include advancing, retreat, turn to and crossing over；
Sharpening processor, between described CMOS vision sensor and described Recognition of Reading device, is used for
Receive described electric energy meter image, described electric energy meter image goes haze process and removes haze electricity to obtain
Energy table image, goes haze electric energy meter image to input described Recognition of Reading device to replace described electric energy by described
Table image is by image procossing；Described sharpening processor also includes: storage subset, for depositing in advance
Storage sky upper limit gray threshold 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, is additionally operable to prestore default picture
Element value threshold value, described presetted pixel value threshold value value is between 0 to 255；Haze Concentration Testing sets
Standby, it is positioned in air, for the haze concentration of detection electric energy meter position in real time, and according to haze
Concentration determines that intensity removed by haze, and described haze removes intensity value between 0 to 1；Region divides
Subset, connects described CMOS vision sensor to receive described electric energy meter image, to described electric energy
Table image carries out gray processing and processes to obtain gray processing electric energy meter image, is also connected with storage subset,
By gray value in described gray processing electric energy meter image at described sky upper limit gray threshold and described sky
Pixel identification between lower limit gray threshold also forms gray processing sky sub pattern, from described gray processing electricity
Described gray processing sky sub pattern can be partitioned into obtain gray processing non-sky subimage by table image, based on
Described gray processing non-sky subimage position in described electric energy meter image obtains and described gray processing
The colour non-sky subimage that non-sky subimage is corresponding；Black channel obtains subset, with described district
Territory divides subset and connects to obtain described colour non-sky subimage, for described colour non-sky gap
Each pixel in image, calculates its R, G, B tri-Color Channel pixel value, non-at described colour
The R of all pixels in sky subimage, G, B tri-extract a numerical value in Color Channel pixel value
The Color Channel at little Color Channel pixel value place is as black channel；Overall air light value obtains son
Equipment, is connected to obtain described presetted pixel value threshold value with storage subset, also divides with described region
Subset and described black channel obtain subset and connect respectively to obtain described electric energy meter image and institute
State black channel, by black channel pixel value in described electric energy meter image more than or equal to presetted pixel value threshold
Multiple pixels of value form set of pixels to be tested, will have maximum gradation value in described set of pixels to be tested
The gray value of pixel as overall air light value；Atmospheric scattering light value obtains subset, with described district
Territory divides subset and described haze Concentration Testing subset connects, respectively to described electric energy meter image
Each pixel, extracts its R, G, B tri-in Color Channel pixel value minima as object pixel
Value, uses the Gaussian filter EPGF (edge-preserving gaussian filter) keeping edge
It is filtered described target pixel value processing to obtain filtered target pixel value, target pixel value is subtracted
Go filtered target pixel value to obtain object pixel difference, use EPGF that object pixel difference is carried out
Filtered target pixel value, to obtain filtered target pixel value difference, is deducted filtered target pixel by Filtering Processing
Difference removes reference value to obtain haze, haze is removed intensity and is multiplied by haze removal reference value to obtain
Threshold value removed by haze, takes haze and removes the minima in threshold value and target pixel value as comparison reference
Value, takes the atmospheric scattering light value as each pixel of the maximum in comparison reference and 0；Medium
Transfer rate obtains subset, obtains subset and described atmospheric scattering light value with described overall air light value
Obtain subset to connect respectively, by the atmospheric scattering light value of each pixel divided by overall air light value with
Obtain except value, deduct 1 described except value is to obtain the medium transmission rate of each pixel；Sharpening figure
As obtaining subset, divide subset with described region, described overall air light value obtains subset and
Described medium transmission rate obtains subset and connects respectively, deducts the medium transmission rate of each pixel by 1
To obtain the first difference, described first difference is multiplied by overall air light value to obtain product value, by institute
State the pixel value of each pixel in electric energy meter image and deduct described product value to obtain the second difference, will
Described second difference divided by the medium transmission rate of each pixel to obtain the sharpening of each pixel
Pixel value, every during in described electric energy meter image, the pixel value of each pixel includes described electric energy meter image
The R of one pixel, G, B tri-Color Channel pixel value, correspondingly, it is thus achieved that each pixel
Sharpening pixel value includes the R of each pixel, G, B tri-Color Channel sharpening pixel value, institute
Haze electric energy meter image is formed by the sharpening pixel value of pixel；Described the Big Dipper omniselector is used for connecing
Receipts the Big Dipper aeronautical satellite is provided, current the Big Dipper data of described robot；Described portable hard drive
It is additionally operable to store electric energy meter upper limit gray threshold and electric energy meter lower limit gray threshold, the described electric energy meter upper limit
Gray threshold and described electric energy meter lower limit gray threshold are for by the electric energy meter dial plate in image and background
Separate；Described Recognition of Reading device also include median filter unit, pretreatment unit, object-recognition unit,
Template matching unit and pointer position determine that unit, described median filter unit process with described sharpening
Equipment 6 connects, for described go haze electric energy meter image filtering to export filtering image, described pre-
Processing unit is connected with described median filter unit, for described filtering image is carried out gray processing process
With output gray level image, described object-recognition unit and described pretreatment unit and described portable hard drive
Connect respectively, by gray value in described gray level image at described electric energy meter upper limit gray threshold and described
Pixel identification between electric energy meter lower limit gray threshold also forms electric energy meter plate image, described template
Matching unit is connected respectively with described object-recognition unit and described portable hard drive, based on described electric energy meter
The target electricity of dial plate subimage match query in all kinds of electric energy meter templates that described portable hard drive stores
Energy table template, provides maximum scale, minimum scale and the pointer model of described target electric energy meter template,
Described pointer position determines that unit connects respectively with described object-recognition unit and described template matching unit
Connect, based in electric energy meter plate image described in described electric energy meter plate image recognition with described pointer
The gauge pointer of Model Matching, calculates the pointer angle of gauge pointer and the horizontal direction recognized, point
Do not calculate described maximum scale and described minimum scale and the maximum scale angle of horizontal direction and minimum
Scale angle, according to pointer angle value bit between maximum scale angle and minimum scale angle
Put, determine outdoor electric energy meter reading；Described master controller and institute's speech recognizer, described channel radio
Communication interface, described robot driving mechanism, described the Big Dipper omniselector, described portable hard drive and described
Recognition of Reading device connects respectively, controls institute according to described phonetic control command or described remote control commands
Stating robot driving mechanism, described master controller receives the outdoor electric energy meter that described Recognition of Reading device sends
Reading, and described outdoor electric energy meter reading is forwarded to described for fulgurite by described wireless communication interface
Platform, the data storage of portable hard drive described in described main controller controls, described remote control commands
Advancing to target meter reading position for robot described in coarse adjustment, described phonetic control command is used for fine tuning institute
State robot and advance to target meter reading position；Wherein, for fulgurite described in described master controller wireless receiving
The Big Dipper control instruction in the remote control commands that platform sends, described the Big Dipper control instruction bag
Including target the Big Dipper data, robot driving mechanism described in described main controller controls advances to described north
The position of target the Big Dipper data described in current the Big Dipper Data Matching that bucket star omniselector sends.
More specifically, in the described robot to outdoor electric energy meter meter reading, described master controller is connecing
The described power supply management platform receiving the forwarding of described wireless communication interface has successfully received outdoor electric energy meter reading
During the return instruction counted, control the relay indicating light of described robot by predetermined time of preset frequency flicker
Number, to point out site administrator.
More specifically, in the described robot to outdoor electric energy meter meter reading, institute's speech recognizer bag
Including sound sensor unit and voice recognition chip, described sound sensor unit is for by site administrator
Voice is converted to the signal of telecommunication, and described voice recognition chip connects described sound sensor unit, for based on
The described signal of telecommunication generates phonetic control command.
More specifically, in the described robot to outdoor electric energy meter meter reading, described voice recognition chip
Use the LD3320 chip of ICRoute company.
More specifically, in the described robot to outdoor electric energy meter meter reading, described median filter unit,
Described pretreatment unit, described object-recognition unit, described template matching unit and described pointer position
Determine that unit is respectively adopted different fpga chips and realizes.
Accompanying drawing explanation
Below with reference to accompanying drawing, embodiment of the present invention are described, wherein:
Fig. 1 is the present invention block diagram to an embodiment of the robot of outdoor electric energy meter meter reading.
Fig. 2 is the present invention structure square frame to the another embodiment of the robot of outdoor electric energy meter meter reading
Figure.
Detailed description of the invention
Embodiment to the robot to outdoor electric energy meter meter reading of the present invention below with reference to accompanying drawings
It is described in detail.
Along with the development of robotics Yu artificial intelligence technology, outdoor movable robot is used to replace
Manually carry out equipment operation to be possibly realized.
Robot belongs to electric power specialized robot research category, and he collects electromechanical integration, multisensor melts
Conjunction, navigator fix, path planning, machine vision, Based Intelligent Control, and be wirelessly transferred, electromagnetism hold concurrently
The technology such as appearance are in one.
Robot carries the sensors such as visible camera, thermal infrared imager, pick up, ultrasound wave,
Employing magnetic tracks is navigated, and by optimum path planning, outdoor high pressure equipment can carry out autonomous or remote control and patrol
Depending on.By methods such as machine vision, infrared measurement of temperature, sound detection, robot can collect equipment
The information such as infrared chart, image and audio frequency, and the thermal defect of automatic identification equipment, abnormal appearance, open
Close or the position of disconnecting link, meter reading, oil level indicator position etc., generate unified standard alarm item and
Patrol and examine report, send warning information to operations staff, and provide basic data for equipment state overhauling.
Robot system also can be accessed by the fixed video monitoring point in electricity consumption place, and covering robot cannot arrive
The observation dead angle reached, it is achieved the whole audience video surveillance.In unmanned, few man on duty electricity consumption place
Or intelligent power place, especially under the geographical conditions such as plateau, cold or severe weather conditions, machine
People can replace or indirect labor completes the monitoring operation of electricity consumption Premises Equipment.After completing monitor task,
Robot is returned to accumulator plant's automatic charging.
The robot to outdoor electric energy meter meter reading of the present invention, uses robot electronics meter reading mode to replace
The artificial meter reading mode of meter reading difficulty, by using the far-end coarse adjustment of robot meter reading position and near-end fine tuning
In conjunction with mode, it is possible to accurately control robot and arrive target meter reading position, use more intelligent simultaneously
Automatic meter reading mode, and according to atmospheric attenuation model determine haze to the influence factor of image to realize
High-precision remove haze image procossing, various outdoor electric energy meter readings in having ensured high voltage electric place
Correct reading.
Fig. 1 is the present invention block diagram to an embodiment of the robot of outdoor electric energy meter meter reading,
Described robot includes the Big Dipper omniselector 1, portable hard drive 2, CMOS vision sensor 3, reading
Evaluator 4 and master controller 5, described portable hard drive 2 is used for prestoring all kinds of electric energy meter template,
And for prestoring maximum scale, minimum scale and the pointer model of each class electric energy meter template,
Described CMOS vision sensor 3 is used for shooting electric energy meter image, and described Recognition of Reading device 4 is with described
CMOS vision sensor 3 connects described electric energy meter image is performed image procossing, described main control
Device 5 is connected the advanced positions controlling described robot with described the Big Dipper omniselector 1, also with described
Portable hard drive 2 and described Recognition of Reading device 4 connect respectively, for controlling the automatic reading of described robot
Table.
Fig. 2 is the present invention structure square frame to the another embodiment of the robot of outdoor electric energy meter meter reading
Figure, it can be seen that unlike Fig. 1, add sharpening processor 6, position in this embodiment
Between CMOS vision sensor 3 and Recognition of Reading device 4.
Then, continue the concrete structure of the robot of the outdoor electric energy meter meter reading of Fig. 2 is carried out further
Explanation.
Described robot also includes: power supply, including solar powered device, accumulator, switching
Switch and electric pressure converter, described switching switch divides with described solar powered device and described accumulator
Do not connect, decide whether to be switched to described solar powered device with by institute according to accumulator dump energy
Stating solar powered device to power, described electric pressure converter is connected with described switching switch, passing through
The 5V voltage of switching switch input is converted to 3.3V voltage.
Described robot also includes: speech recognition device, for being converted to by the voice of site administrator
The signal of telecommunication, and generate phonetic control command based on the described signal of telecommunication.
Described robot also includes: wireless communication interface, and the power supply management platform wireless connections of far-end,
With wireless receiving remote control commands, described remote control commands includes the Big Dipper control instruction.
Described robot also includes: robot driving mechanism, is connected with described master controller 5, is used for
Under the control of described master controller 5, drive the behavior act of described robot, described behavior act
Including advancing, retreat, turn to and crossing over.
Described robot also includes: sharpening processor 6, is positioned at described CMOS vision sensor 3
And between described Recognition of Reading device 4, be used for receiving described electric energy meter image, to described electric energy meter image
Carry out haze process and remove haze electric energy meter image to obtain, go haze electric energy meter image to input by described
Described Recognition of Reading device 4 is to replace described electric energy meter image by image procossing.
Described sharpening processor 6 also 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 CMOS vision sensor 3 to receive described electric energy meter figure
Picture, described electric energy meter image is carried out gray processing process to obtain gray processing electric energy meter image, also with deposit
Storage subset connects, by gray value in described gray processing electric energy meter image at described sky upper limit gray scale threshold
Pixel identification between value and described sky lower limit gray threshold also forms gray processing sky sub pattern, from
Described gray processing electric energy meter image is partitioned into described gray processing sky sub pattern to obtain the non-sky of gray processing
Null subgraph picture, obtains based on described gray processing non-sky subimage position in described electric energy meter image
The colour non-sky subimage that sky subimage non-with described gray processing is corresponding；
Black channel obtains subset, divides subset with described region and is connected to obtain described colour non-
Sky subimage, for each pixel in described colour non-sky subimage, calculates its R, G, B
Three Color Channel pixel values, the R, G, B tri-of all pixels in described colour non-sky subimage
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, minima 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 reference value,
Haze is removed intensity be multiplied by haze remove reference value with obtain haze remove threshold value, take haze remove threshold
Minima 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 of all pixels removes haze electric energy meter image.
Described the Big Dipper omniselector 1 for receiving the Big Dipper aeronautical satellite and provided, described robot
Current the Big Dipper data.
Described portable hard drive 2 is additionally operable to store electric energy meter upper limit gray threshold and electric energy meter lower limit gray scale threshold
Value, described electric energy meter upper limit gray threshold and described electric energy meter lower limit gray threshold are for by image
Electric energy meter dial plate and background separation.
Described Recognition of Reading device 4 also include median filter unit, pretreatment unit, object-recognition unit,
Template matching unit and pointer position determine unit；
Described median filter unit is connected with described sharpening processing equipment 6, for removing haze to described
Electric energy meter image filtering is to export filtering image；
Described pretreatment unit is connected with described median filter unit, for carrying out described filtering image
Gray processing processes with output gray level image；
Described object-recognition unit is connected respectively with described pretreatment unit and described portable hard drive, by institute
State gray value in gray level image grey at described electric energy meter upper limit gray threshold and described electric energy meter lower limit
Spend the pixel identification between threshold value and form electric energy meter plate image；
Described template matching unit is connected respectively with described object-recognition unit and described portable hard drive, base
Inquire about in all kinds of electric energy meter templates that described portable hard drive stores in described electric energy meter plate image
The target electric energy meter template of coupling, provides the maximum scale of described target electric energy meter template, minimum scale
With pointer model；
Described pointer position determines that unit divides with described object-recognition unit and described template matching unit
Do not connect, based in electric energy meter plate image described in described electric energy meter plate image recognition with described
The gauge pointer of pointer Model Matching, calculates the pointer angle of gauge pointer and the horizontal direction recognized
Degree, calculate respectively described maximum scale and described minimum scale and horizontal direction maximum scale angle and
Minimum scale angle, according to pointer angle numerical value between maximum scale angle and minimum scale angle
Position, determines outdoor electric energy meter reading.
Described master controller 5 and institute's speech recognizer, described wireless communication interface, described robot
Drive mechanism, described the Big Dipper omniselector 1, described portable hard drive 2 and described Recognition of Reading device 4 points
Do not connect, control described robotically-driven according to described phonetic control command or described remote control commands
Mechanism.
Described master controller 5 receives the outdoor electric energy meter reading that described Recognition of Reading device 4 sends, and will
Described outdoor electric energy meter reading is forwarded to described power supply management platform, institute by described wireless communication interface
Stating master controller 5 and control the data storage of described portable hard drive 2, described remote control commands is for thick
Adjusting described robot to advance to target meter reading position, described phonetic control command is for machine described in fine tuning
People advances to target meter reading position.
Wherein, what power supply management platform described in described master controller 5 wireless receiving sent remotely controls to refer to
The Big Dipper control instruction in order, described the Big Dipper control instruction includes target the Big Dipper data, described
Master controller 5 controls described robot driving mechanism and advances to working as of described the Big Dipper omniselector 1 transmission
The position of target the Big Dipper data described in front the Big Dipper Data Matching.
Wherein, in the described robot to outdoor electric energy meter meter reading, described master controller 5 is receiving
The described power supply management platform forwarded to described wireless communication interface has successfully received outdoor electric energy meter reading
Return instruction time, the relay indicating light controlling described robot flashes pre-determined number by preset frequency,
To point out site administrator；Alternatively, institute's speech recognizer includes sound sensor unit and voice
Identification chip, described sound sensor unit is used for site administrator's voice is converted to the signal of telecommunication, institute
State voice recognition chip and connect described sound sensor unit, for generating voice control based on the described signal of telecommunication
System instruction, described voice recognition chip can use the LD3320 chip of ICRoute company, Yi Jisuo
State median filter unit, described pretreatment unit, described object-recognition unit, described template matching list
First and described pointer position determines that unit can be respectively adopted different fpga chips and realize.
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 robot to outdoor electric energy meter meter reading of the present invention, for room, existing high voltage electric place
Outer electric energy meter reading is inconvenient or reads the technical problem that data precision is the highest, utilizes network technology and voice
Identification technology, controls remote location and short range position control combines, and ensures that robot can be accurate to
Reach predetermined meter reading position, transform existing automatic meter reading technology, use more intelligent image processing method
Formula realizes high accuracy, the automatic meter reading of highly compatible, improves the work efficiency of transformer substation robot,
More it is essential that by the analysis to atmospheric attenuation model, introduce sharpening processor to remove haze
Impact on electric energy meter image, so that it is guaranteed that outdoor electric energy meter also can be normally carried out far under haze weather
Distance electronic type automatic meter reading.
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 (1)
1. the robot to outdoor electric energy meter meter reading, it is characterized in that, described robot includes the Big Dipper omniselector, portable hard drive, CMOS vision sensor, Recognition of Reading device and master controller, described portable hard drive is used for prestoring all kinds of electric energy meter template, and for prestoring the maximum scale of each class electric energy meter template, minimum scale and pointer model, described CMOS vision sensor is used for shooting electric energy meter image, described Recognition of Reading device is connected with described CMOS vision sensor described electric energy meter image is performed image procossing, described master controller is connected with described the Big Dipper omniselector to control the advanced positions of described robot, also it is connected respectively with described portable hard drive and described Recognition of Reading device, for controlling the automatic meter reading of described robot；
Described robot also includes:
Power supply, including solar powered device, accumulator, switching switch and electric pressure converter, described switching switch is connected respectively with described solar powered device and described accumulator, decide whether to be switched to described solar powered device to be powered by described solar powered device according to accumulator dump energy, described electric pressure converter is connected with described switching switch, will be converted to 3.3V voltage by the 5V voltage of switching switch input；
Speech recognition device, for the voice of site administrator is converted to the signal of telecommunication, and generates phonetic control command based on the described signal of telecommunication；
Wireless communication interface, with the power supply management platform wireless connections of far-end, with wireless receiving remote control commands, described remote control commands includes the Big Dipper control instruction；
Robot driving mechanism, is connected with described master controller, under the control of described master controller, drives the behavior act of described robot, described behavior act to include advancing, retreat, turn to and crossing over；
Sharpening processor, between described CMOS vision sensor and described Recognition of Reading device, for receiving described electric energy meter image, described electric energy meter image goes haze process and removes haze electric energy meter image to obtain, go haze electric energy meter image to input described Recognition of Reading device to replace described electric energy meter image by image procossing by described；
Described sharpening processor also includes:
Storage subset, 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 areas in image, being additionally operable to prestore presetted pixel value threshold value, described presetted 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 determines that intensity removed by haze according to haze concentration, and described haze removes intensity value between 0 to 1；
Region divides subset, connect described CMOS vision sensor to receive described electric energy meter image, described electric energy meter image carries out gray processing process to obtain gray processing electric energy meter image, also it is connected with storage subset, by the pixel identification between described sky upper limit gray threshold and described sky lower limit gray threshold of the gray value in described gray processing electric energy meter image and form gray processing sky sub pattern, it is partitioned into described gray processing sky sub pattern to obtain gray processing non-sky subimage from described gray processing electric energy meter image, the colour non-sky subimage that sky subimage non-with described gray processing is corresponding is obtained based on described gray processing non-sky subimage position in described electric energy meter image；
Black channel obtains subset, divide subset with described region to be connected to obtain described colour non-sky subimage, for each pixel in described colour non-sky subimage, calculate its R, G, B tri-Color Channel pixel value, the R of all pixels in described colour non-sky subimage, G, B tri-extracts the Color Channel at the minimum Color Channel pixel value place of a numerical value in Color Channel pixel value as black channel；
Overall air light value obtains subset, it is connected to obtain described presetted pixel value threshold value with storage subset, also divide subset with described region and described black channel obtains subset and is connected respectively to obtain described electric energy meter image and described black channel, black channel pixel value in described electric energy meter image is formed set of pixels to be tested more than or equal to multiple pixels of presetted pixel value threshold value, using the gray value of the pixel in described set of pixels to be tested with maximum gradation value as overall air light value；
nullAtmospheric scattering light value obtains subset，Divide subset with described region and described haze Concentration Testing subset is connected respectively，Each pixel to described electric energy meter image，Extract its R，G，In B tri-Color Channel pixel value, minima is as target pixel value，Use and keep the Gaussian filter EPGF (edge-preserving gaussian filter) 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，Subset is divided with described region、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 electric energy meter image 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 electric energy meter image in described electric energy meter image，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 of all pixels removes haze electric energy meter image；
Described the Big Dipper omniselector for receive the Big Dipper aeronautical satellite provided, current the Big Dipper data of described robot；
Described portable hard drive is additionally operable to store electric energy meter upper limit gray threshold and electric energy meter lower limit gray threshold, described electric energy meter upper limit gray threshold and described electric energy meter lower limit gray threshold for by the electric energy meter dial plate in image and background separation；
nullDescribed Recognition of Reading device also includes median filter unit、Pretreatment unit、Object-recognition unit、Template matching unit and pointer position determine unit，Described median filter unit is connected with described sharpening processing equipment，For going haze electric energy meter image filtering to export filtering image to described，Described pretreatment unit is connected with described median filter unit，Process for described filtering image being carried out gray processing with output gray level image，Described object-recognition unit is connected respectively with described pretreatment unit and described portable hard drive，By the pixel identification between described electric energy meter upper limit gray threshold and described electric energy meter lower limit gray threshold of the gray value in described gray level image and form electric energy meter plate image，Described template matching unit is connected respectively with described object-recognition unit and described portable hard drive，Based on described electric energy meter plate image target electric energy meter template of match query in all kinds of electric energy meter templates that described portable hard drive stores，Provide the maximum scale of described target electric energy meter template、Minimum scale and pointer model，Described pointer position determines that unit is connected respectively with described object-recognition unit and described template matching unit，Based on gauge pointer with described pointer Model Matching in electric energy meter plate image described in described electric energy meter plate image recognition，Calculate the pointer angle of gauge pointer and the horizontal direction recognized，Calculate described maximum scale and described minimum scale and the maximum scale angle of horizontal direction and minimum scale angle respectively，According to pointer angle numerical value position between maximum scale angle and minimum scale angle，Determine outdoor electric energy meter reading；
Described master controller and institute's speech recognizer, described wireless communication interface, described robot driving mechanism, described the Big Dipper omniselector, described portable hard drive and described Recognition of Reading device connect respectively, described robot driving mechanism is controlled according to described phonetic control command or described remote control commands, described master controller receives the outdoor electric energy meter reading that described Recognition of Reading device sends, and described outdoor electric energy meter reading is forwarded to described power supply management platform by described wireless communication interface, the data storage of portable hard drive described in described main controller controls, described remote control commands advances to target meter reading position for robot described in coarse adjustment, described phonetic control command advances to target meter reading position for robot described in fine tuning；
Wherein, the Big Dipper control instruction in the remote control commands that power supply management platform described in described master controller wireless receiving sends, described the Big Dipper control instruction includes target the Big Dipper data, and robot driving mechanism described in described main controller controls advances to the position of target the Big Dipper data described in current the Big Dipper Data Matching that described the Big Dipper omniselector sends.
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510153366.7A CN104714068B (en) | 2015-04-01 | 2015-04-01 | Robot to outdoor electric energy meter meter reading |
| CN201610272916.1A CN105974169A (en) | 2015-04-01 | 2015-04-01 | Robot capable of reading outdoor electric energy meter |
| CN201610272829.6A CN105785088B (en) | 2015-04-01 | 2015-04-01 | Robot to outdoor electric energy meter meter reading |
| CN201610272830.9A CN105974168A (en) | 2015-04-01 | 2015-04-01 | Robot capable of reading outdoor electric energy meter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510153366.7A CN104714068B (en) | 2015-04-01 | 2015-04-01 | Robot to outdoor electric energy meter meter reading |
Related Child Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610272829.6A Division CN105785088B (en) | 2015-04-01 | 2015-04-01 | Robot to outdoor electric energy meter meter reading |
| CN201610272916.1A Division CN105974169A (en) | 2015-04-01 | 2015-04-01 | Robot capable of reading outdoor electric energy meter |
| CN201610272830.9A Division CN105974168A (en) | 2015-04-01 | 2015-04-01 | Robot capable of reading outdoor electric energy meter |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104714068A CN104714068A (en) | 2015-06-17 |
| CN104714068B true CN104714068B (en) | 2016-10-26 |
Family
ID=53413567
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510153366.7A Active CN104714068B (en) | 2015-04-01 | 2015-04-01 | Robot to outdoor electric energy meter meter reading |
| CN201610272830.9A Pending CN105974168A (en) | 2015-04-01 | 2015-04-01 | Robot capable of reading outdoor electric energy meter |
| CN201610272916.1A Pending CN105974169A (en) | 2015-04-01 | 2015-04-01 | Robot capable of reading outdoor electric energy meter |
Family Applications After (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610272830.9A Pending CN105974168A (en) | 2015-04-01 | 2015-04-01 | Robot capable of reading outdoor electric energy meter |
| CN201610272916.1A Pending CN105974169A (en) | 2015-04-01 | 2015-04-01 | Robot capable of reading outdoor electric energy meter |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN104714068B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108596023A (en) * | 2018-03-13 | 2018-09-28 | 安徽瑞鑫自动化仪表有限公司 | A kind of pointer pressure pressure data extracting method |
| CN109299758A (en) * | 2018-07-27 | 2019-02-01 | 深圳市中兴系统集成技术有限公司 | A kind of intelligent polling method, electronic equipment, intelligent inspection system and storage medium |
| CN110837825A (en) * | 2019-10-17 | 2020-02-25 | 天津大学 | Meter identification and reading system based on embedded type |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104777836A (en) * | 2015-04-01 | 2015-07-15 | 无锡桑尼安科技有限公司 | Outdoor electric energy meter reading method |
Family Cites Families (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB9805556D0 (en) * | 1998-03-17 | 1998-05-13 | Crimewatch Scotland Limited | Alarm systems |
| CN1320987C (en) * | 2004-06-04 | 2007-06-13 | 山东鲁能智能技术有限公司 | Intelligent autonomous power plant equipment round inspecting robot |
| CN201054183Y (en) * | 2006-08-31 | 2008-04-30 | 合肥新思源智能电子有限公司 | Video direct automatic meter reading device |
| CN101079094A (en) * | 2007-04-30 | 2007-11-28 | 中国科学院合肥物质科学研究院 | Meter reading identification device for remote automatic meter reading system |
| CN101320053A (en) * | 2008-07-17 | 2008-12-10 | 菏泽供电公司 | Wireless data and image double-acquisition anti-electricity theft monitoring system and method thereof |
| CN201638053U (en) * | 2009-12-31 | 2010-11-17 | 重庆工商职业学院 | Polling robot |
| CN102114635A (en) * | 2009-12-31 | 2011-07-06 | 武汉大学 | Intelligent controller of inspection robot |
| CN101806601A (en) * | 2010-03-31 | 2010-08-18 | 昆明利普机器视觉工程有限公司 | Hand-hold meter reading terminal of meter and meter reading method based on image recognition technology |
| CN101872541A (en) * | 2010-04-29 | 2010-10-27 | 上海赞润微电子科技有限公司 | Remote meter reading method and remote meter reading system using same |
| CN102082466A (en) * | 2010-10-15 | 2011-06-01 | 重庆市电力公司超高压局 | Intelligent inspection robot system for transformer substation equipment |
| CN102013155B (en) * | 2010-10-26 | 2012-08-08 | 京信通信系统（中国）有限公司 | Remote meter reading system utilizing time division (TD) network and implementation method thereof |
| CN102170574B (en) * | 2011-05-23 | 2012-12-26 | 北京工业大学 | Real-time video defogging system |
| CN102547245A (en) * | 2012-01-17 | 2012-07-04 | 上海雷波信息技术有限公司 | Digital reading equipment of mechanical electricity meter and information reading system |
| CN102857737A (en) * | 2012-07-30 | 2013-01-02 | 浙江新能量科技有限公司 | Remote electric energy information collection system and method based on image recognition |
| CN104270566B (en) * | 2014-09-01 | 2018-09-07 | 深圳市思谋科技有限公司 | Camera direct-reading meter device, system, the method and apparatus for improving Recognition of Reading rate |
| CN204229230U (en) * | 2014-11-27 | 2015-03-25 | 无锡北斗星通信息科技有限公司 | For the Intelligent Mobile Robot of automatic meter reading |
-
2015
- 2015-04-01 CN CN201510153366.7A patent/CN104714068B/en active Active
- 2015-04-01 CN CN201610272830.9A patent/CN105974168A/en active Pending
- 2015-04-01 CN CN201610272916.1A patent/CN105974169A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104777836A (en) * | 2015-04-01 | 2015-07-15 | 无锡桑尼安科技有限公司 | Outdoor electric energy meter reading method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105974168A (en) | 2016-09-28 |
| CN105974169A (en) | 2016-09-28 |
| CN104714068A (en) | 2015-06-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104597903B (en) | Transformer substation routing inspection robot for automatic meter reading | |
| CN103941746B (en) | Image processing system and method is patrolled and examined without man-machine | |
| CN109885097B (en) | Method for planning inspection route of outer edge surface of bridge | |
| CN204229230U (en) | For the Intelligent Mobile Robot of automatic meter reading | |
| CN103984355B (en) | Routing inspection flying robot and overhead power line distance prediction and maintaining method | |
| CN203038112U (en) | Unmanned aerial vehicle (UAV) automatic control system | |
| CN107392247A (en) | Atural object safe distance real-time detection method below a kind of power line | |
| CN210090988U (en) | Unmanned aerial vehicle system of patrolling and examining | |
| CN104410829B (en) | A kind of method of automatic meter reading | |
| CN105300358B (en) | Foreign bodies on transmission lines species detection platform | |
| CN210005927U (en) | bridge inspection unmanned aerial vehicle system | |
| CN109901623B (en) | Method for planning inspection route of pier body of bridge | |
| CN104714068B (en) | Robot to outdoor electric energy meter meter reading | |
| CN109187564A (en) | A kind of sleeve configuration structures real-time deformation monitoring system | |
| CN108681337A (en) | A kind of culvert or the special inspection unmanned plane of bridge and unmanned plane visiting method | |
| CN110570520A (en) | substation maintenance safety distance monitoring method based on SLAM | |
| CN110608716A (en) | Substation maintenance safety distance monitoring method based on SLAM | |
| CN114371725A (en) | System suitable for automatic inspection of wind turbine generator | |
| CN109341542A (en) | Method and its monitoring device based on digital signal sequences length identification fracture width | |
| CN101122540A (en) | Laser imaging SF6 leakage positioning device | |
| CN105785088B (en) | Robot to outdoor electric energy meter meter reading | |
| CN206962973U (en) | A kind of centralized control system for substation inspection | |
| CN104777836B (en) | Outdoor electric energy meter meter reading method | |
| CN108737775B (en) | Big data acquisition platform | |
| Qian et al. | Real-time power line safety distance detection system based on LOAM SLAM |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| CB03 | Change of inventor or designer information |
Inventor after: Li Ke Inventor before: The inventor has waived the right to be mentioned |
|
| COR | Change of bibliographic data | ||
| GR01 | Patent grant | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20160929 Address after: 150000 room 368, No. 1512, Changjiang Road, Nangang District, Heilongjiang District, Harbin City, China Applicant after: HARBIN HUIXIN INSTRUMENT CO., LTD. Address before: 214000 Jiangsu city of Wuxi Province East Pavilion Street Xishan District Yingbin Road No. 1 Applicant before: Wuxi Sani pacifies Science and Technology Ltd. |