CN108197634A - Automatic meter reading method, system, computer equipment and readable storage medium storing program for executing - Google Patents
Automatic meter reading method, system, computer equipment and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN108197634A CN108197634A CN201711209340.5A CN201711209340A CN108197634A CN 108197634 A CN108197634 A CN 108197634A CN 201711209340 A CN201711209340 A CN 201711209340A CN 108197634 A CN108197634 A CN 108197634A
- Authority
- CN
- China
- Prior art keywords
- gauge table
- amr message
- measured
- meter reading
- dial plate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- 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
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
The present invention relates to a kind of automatic meter reading method, system, computer equipment and readable storage medium storing program for executing.The automatic meter reading method includes：Obtain the dial plate image of gauge table to be measured, feature extraction is carried out to the dial plate image of gauge table to be measured, obtain the characteristic of the dial plate image of gauge table to be measured, characteristic is inputted into amr message detection model, the amr message of gauge table to be measured is obtained, amr message includes gauge table ID, and the gauge table ID that detection obtains is compared with the gauge table ID databases to prestore, when gauge table ID databases include the gauge table ID that detection obtains, obtain amr message and export.Above-mentioned automatic meter reading method, the related data for obtaining gauge table otherwise is known using image, compared to traditional manual meter reading method, improve meter reading efficiency, avoid because by hand make a copy of existing for misdescription, error of omission the problems such as, and the true and false of gauge table is verified by gauge table ID, further ensures the reliability that meter data is made a copy of.
Description
Technical field
The present invention relates to field of power detection, more particularly to a kind of automatic meter reading method, system, computer equipment and can
Read storage medium.
Background technology
Human society enter the era of knowledge-driven economy, rapid development of information technology background under, gauge table and its measure control
Technology processed obtains increasingly extensive application, by the way that metering and correlative charges statistics can be achieved to making a copy of for meter data.
In the prior art, meter reading process still relies on the artificial of staff and reads and record, this to take artificial reading
It takes and the operating type of manual typing continuous data, heavy workload, and there are the problems such as misdescription, error of omission, so as to cause meter reading
Efficiency is low, error rate is high, it is impossible to truly reflect the physical record data of gauge table.
Invention content
Based on this, it is necessary to for the problem of meter reading efficiency is low, error rate is high, provide a kind of automatic meter reading method, system,
Computer equipment and readable storage medium storing program for executing.
A kind of automatic meter reading method, including：
Obtain the dial plate image of gauge table to be measured；
Feature extraction is carried out to the dial plate image of the gauge table to be measured, obtains the dial plate image of the gauge table to be measured
Characteristic；
The characteristic is inputted into amr message detection model, obtains the amr message of the gauge table to be measured, it is described
Amr message includes gauge table ID；
The gauge table ID that detection obtains is compared with the gauge table ID databases to prestore；
When the gauge table ID databases include it is described detect and obtain gauge table ID when, obtain the amr message and defeated
Go out.
It is described when the gauge table ID databases include the gauge table ID for detecting and obtaining in one of the embodiments,
When, it obtains the amr message and includes the step of output：
When the gauge table ID databases include the gauge table ID that the detection obtains, the gauge table to be measured is obtained
Location information；
The location information of the gauge table to be measured is compared with location information prestoring, corresponding with the gauge table ID
It is right；
Location information and the location information phase prestoring, corresponding with the gauge table ID when the gauge table to be measured
Meanwhile it obtains the amr message and exports.
It is described in one of the embodiments, that the characteristic is inputted into amr message detection model, obtain described treat
Before the step of surveying the amr message of gauge table, further include：
The dial plate image of a variety of different amr messages is obtained, creates amr message sample image；
Extract the characteristic of all amr message sample images；
Pattern-recognition training is carried out to the characteristic of all amr message sample images, obtains amr message detection
Model.
The amr message further includes User ID and continuous data in one of the embodiments, described to work as the meter
Scale ID databases include it is described detect and obtain gauge table ID when, after the step of obtaining the amr message and exporting, also
Including：
By the User ID, gauge table ID and continuous data associated storage.
It further includes in one of the embodiments,：
According to the continuous data, metering data is obtained；
According to the continuous data and the metering data, metrical information is generated；
The metrical information is sent to the terminal device of the corresponding User ID of the continuous data.
A kind of Automatic meter reading system, including：
Image collection module, for obtaining the dial plate image of gauge table to be measured；
Characteristic extracting module for carrying out feature extraction to the dial plate image of the gauge table to be measured, obtains described to be measured
The characteristic of the dial plate image of gauge table；
Picture recognition module for the characteristic to be inputted amr message detection model, obtains the metering to be measured
The amr message of table, the amr message include gauge table ID；
Comparing module is compared for will detect the obtained gauge table ID with the gauge table ID databases to prestore；
Output module, for when the gauge table ID databases include the gauge table ID that the detection obtains, obtaining institute
It states amr message and exports.
It further includes in one of the embodiments,：Position acquisition module includes institute for working as the gauge table ID databases
When stating the gauge table ID that detection obtains, the location information of the gauge table to be measured is obtained；
Comparing module, be additionally operable to by the location information of the gauge table to be measured with it is prestoring, corresponding with the gauge table ID
Location information be compared；
Output module is additionally operable to the location information when the gauge table to be measured and the prestore and gauge table ID
When corresponding location information is identical, obtains the amr message and export.
It further includes in one of the embodiments,：
Sample creation module for obtaining the dial plate image of a variety of different amr messages, creates amr message sample image；
The characteristic extracting module is additionally operable to extract the characteristic of all amr message sample images；
Detection model creation module, for carrying out pattern-recognition to the characteristic of all amr message sample images
Training, obtains amr message detection model.
A kind of computer equipment can be run on a memory and on a processor including memory, processor and storage
Computer program, processor perform program when realize any one of embodiment automatic meter reading method.
A kind of computer readable storage medium, is stored thereon with computer program, which realizes when being executed by processor
The automatic meter reading method of any one embodiment.
Above-mentioned automatic meter reading method, system, computer equipment and readable storage medium storing program for executing, by the table for acquiring gauge table to be measured
Disk image, and extract the characteristic of the dial plate image of gauge table to be measured, by characteristic input amr message detection model into
Row detection and identification, so as to automatically identify the amr message of gauge table to be measured, and pass through the gauge table ID in amr message and test
Demonstrate,prove the true and false of the gauge table, when verification result by it is true when just obtain and export the amr message identified.It is above-mentioned to be known based on image
Otherwise obtain gauge table related data, compared to traditional manual meter reading method, improve meter reading efficiency, avoid because
The problems such as making a copy of existing misdescription, error of omission by hand, and by the authenticity verification to gauge table, further ensure gauge table number
According to the reliability made a copy of.
Description of the drawings
Fig. 1 is the flow diagram of automatic meter reading method in an embodiment；
Fig. 2 is the flow diagram of automatic meter reading method in another embodiment；
Fig. 3 is the flow diagram of amr message detection model creation method in an embodiment；
Fig. 4 is the flow diagram of metrical information generation and sending method in an embodiment；
Fig. 5 is the structure diagram of Automatic meter reading system in an embodiment；
Fig. 6 is the structure diagram of Automatic meter reading system in another embodiment；
Fig. 7 is the structure diagram of Automatic meter reading system in another embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the object, technical solution and advantage for making the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, and
It is not used in restriction the application.
As shown in Figure 1, providing a kind of automatic meter reading method in the present embodiment, this method comprises the following steps, and S110 is extremely walked
Rapid S150：
S110 obtains the dial plate image of gauge table to be measured.
Gauge table is commonly used in being recorded in the total amount that substance flows through in sometime interval, and common gauge table includes electricity
Table, water meter, gas meter etc..By taking ammeter as an example, ammeter is the gauge table for measuring electric energy, available for counting electricity consumption data,
Calculating and region power consumption management of electricity cost etc. can be realized based on electricity consumption data.
In this embodiment, the dial plate image of gauge table to be measured is obtained, dial plate image includes the amr message of gauge table, leads to
It crosses the acquired dial plate image of identification and obtains corresponding amr message.
Specifically, the dial plate image of gauge table to be measured using hand-held photographic device or can be copied by staff or user
Meter terminal is acquired, and also can be acquired and be uploaded by being installed on the camera of fixed position, wherein, fixed position is position
Fixed position above gauge table to be measured.The dial plate image of gauge table to be measured is obtained by obtaining acquired image.
S120 carries out feature extraction to the dial plate image of gauge table to be measured, obtains the spy of the dial plate image of gauge table to be measured
Levy data.
After the dial plate image for obtaining gauge table to be measured, the dial plate figure of gauge table to be measured is extracted using image characteristics extraction algorithm
The characteristic of picture is then detected the characteristic extracted.
Characteristic is inputted amr message detection model, obtains the amr message of gauge table to be measured, amr message by S130
Including gauge table ID.
After the characteristic of dial plate image for extracting gauge table to be measured, by the spy of the dial plate image of the gauge table to be measured of extraction
Sign data are matched with amr message detection model pre-establishing, corresponding with characteristic, by being based on and characteristic
The amr message in gauge table to be measured is identified according to corresponding amr message detection model., amr message include gauge table ID, each
Gauge table is corresponded to there are one gauge table ID, and the ID of each gauge table is uniquely determined, and can effectively be distinguished based on gauge table ID
The true and false of gauge table.
Further, amr message for can Efficient Characterization gauge table information related data.By taking ammeter as an example, amr message
It may include User ID, ammeter number and continuous data etc..
The gauge table ID that detection obtains is compared S140 with the gauge table ID databases to prestore.
S150 when gauge table ID databases include the gauge table ID that detection obtains, obtains amr message and exports.
When installing gauge table, the gauge table ID of the gauge table of installation is recorded, and gauge table ID is stored in gauge table
ID databases.When carrying out meter reading, it will identify that obtained gauge table ID is compared with the gauge table ID in database, due to every
The ID of a gauge table is uniquely determined, and when there is the gauge table ID that identification obtains in database, it is logical to illustrate the gauge table
Regular channel installation is crossed, the amr message identified is effective amr message.
Further, the amr message for obtaining and exporting can be stored or be shown.
Above-mentioned automatic meter reading method by acquiring the dial plate image of gauge table to be measured, and extracts the dial plate of gauge table to be measured
The characteristic of image matches the amr message detection model that characteristic input pre-establishes, so as to automatic identification
Go out the amr message of gauge table to be measured, and pass through the true and false that the gauge table ID in amr message verifies the gauge table, when verification is tied
Fruit by it is true when just obtain and export the amr message identified.The above-mentioned phase that automatic identification gauge table otherwise is known based on image
Close data, without by hand made a copy of, improve meter reading efficiency and information system management degree, can reduce the input of manpower with
And the working strength of staff, it avoids because existing for making a copy of by hand the problems such as misdescription, error of omission, and by gauge table
Authenticity verification further ensures the reliability that meter data is made a copy of.
In another embodiment, it as shown in Fig. 2, when gauge table ID databases include the gauge table ID that detection obtains, obtains
The step of taking amr message and exporting, including step S210 to step S230：
S210 when gauge table ID databases include the gauge table ID that detection obtains, obtains the position letter of gauge table to be measured
Breath；
The location information of gauge table to be measured is compared S220 with location information prestoring, corresponding with gauge table ID；
S230, when gauge table to be measured location information with it is prestoring, corresponding with gauge table ID location information is identical when, obtain
It takes amr message and exports.
In the present embodiment, the step of being verified to the position of gauge table is further included.In practical applications, gauge table
Installation steps are complicated, can only be installed by professional staff, and position immobilizes, therefore by gauge table after installation
Position verified, can further identify the true and false of gauge table, it is ensured that acquired amr message is efficiently and accurately copies
Table information.
Specifically, the location information of gauge table can be by gauge table GPS positioning function in itself or based on gauge table
Corresponding IP address determines, can also by the GPS positioning function of hand-hold meter reading terminal or based on the corresponding IP of gauge table
Address determines.
Further, staff obtains the location information of gauge table installation when installing gauge table, and the position is believed
Breath and gauge table ID associated storages, to distinguish the true of gauge table automatically according to location information and gauge table ID in automatic data logging
Puppet.In another embodiment, feature extraction is carried out to the dial plate image of gauge table to be measured, obtains the dial plate figure of gauge table to be measured
Before the step of characteristic of picture, further include：Image preprocessing is carried out to the dial plate image of gauge table to be measured.
In one embodiment, image preprocessing include image smoothing, image transformation, image enhancement, image recovery and
Image filtering etc. or any of which item or multinomial combination.Figure can be eliminated by carrying out image preprocessing to sample image
Unrelated information, restores useful real information as in, enhances detectability for information about and simplifies data to the maximum extent,
So as to improve feature extraction, image segmentation, matching and the reliability of identification.
In another embodiment, image preprocessing further includes, and amr message sample image is normalized.For example,
After the dial plate image of gauge table to be measured is got, by the dial plate image normalization of gauge table to be measured into 240x240 sizes, then
The operation of the characteristic of extraction amr message sample image is performed again.Facilitated in this way by the size of unified amr message follow-up
Amr message is realized and is detected.
As shown in figure 3, in another embodiment, characteristic is inputted into amr message detection model, obtains metering to be measured
Before the step of amr message of table, step S310 is further included to step S330：
S310 obtains the dial plate image of a variety of different amr messages, creates amr message sample image.
One gauge table includes a variety of different amr messages, such as User ID, metering table number and continuous data etc., and
In different types of gauge table, there is also different representations for same class amr message.In the present embodiment, it obtains first more
The dial plate image of the different amr messages of kind, creates amr message sample image, by one species, the dial plate figure of same representation
As being divided into one kind, amr message detection model may finally be established to every one kind, subsequently to can be achieved to copy a variety of differences
The identification of table information improves the accuracy of amr message identification.
S320 extracts the characteristic of all amr message sample images.
Further, it before the step of extracting the characteristic of all amr message sample images, further includes：It is copied to all
Table message sample image carries out image preprocessing.
In one embodiment, image preprocessing include image smoothing, image transformation, image enhancement, image recovery and
Image filtering etc. or any of which item or multinomial combination.Figure can be eliminated by carrying out image preprocessing to sample image
Unrelated information, restores useful real information as in, enhances detectability for information about and simplifies data to the maximum extent,
So as to improve feature extraction, image segmentation, matching and the reliability of identification.
In another embodiment, image preprocessing further includes, and amr message sample image is normalized.For example,
The dial plate image of a variety of different amr messages is collected, after creating amr message sample image, by all establishment amr message samples
This image is all normalized into 240x240 sizes, then extracts the characteristic of amr message sample image.In this way by uniformly copying
The size of table message sample image is convenient subsequently to be established detection model and realizes detection to amr message.
S330 carries out pattern-recognition training to the characteristic of all amr message sample images, obtains amr message inspection
Survey model.
Specifically, amr message detection model may be based on the detection model of grader structure, by believing all meter readings
The characteristic for ceasing sample image carries out pattern-recognition training, and the dial plate image of variety classes, different representations is divided
Class, based on every a kind of establishment amr message detection model.
Wherein, grader can be k nearest neighbor grader, decision tree classifier and support vector machine ensembles learning method etc., no
With grader is divided to have different pattern-recognition training algorithms, user can be based on recognition accuracy, recognition efficiency selects difference
Grader structure amr message detection model.
By obtaining the dial plate image of a variety of different amr messages, sufficient amr message sample image is ensure that, into one
Step extracts the characteristic of all amr message sample images, and pattern is carried out to the characteristic of all amr message sample images
Recognition training and classification, so as to obtain a variety of inhomogeneous amr message detection models, to meet the knowledge to different amr messages
Other demand can further improve the accuracy rate of amr message identification.
In another specific embodiment, amr message further includes User ID and continuous data, when gauge table ID databases
During including detecting obtained gauge table ID, obtain amr message and the step of export after, further include：By User ID, gauge table
ID and continuous data associated storage.Wherein, each gauge table has unique corresponding gauge table ID.
By by User ID, gauge table ID and continuous data associated storage, fully integrating the related data of each gauge table,
To realize that meter data is shared and provides strong data supporting, convenient for the continuous data of each gauge table is carried out statistics and
Management, and corresponding continuous data is inquired by User ID or gauge table ID fast and easys, it is obtained and the use convenient for user
The relevant continuous data in family.
Further, as shown in figure 4, automatic meter reading method further includes step S410 to step S430：
S410 according to continuous data, obtains metering data.
Specifically, according to acquired continuous data, corresponding expense can be calculated using charging algorithmic tool, convenient for root
It is deducted fees or is paid the fees according to the expense of gained.
S420 according to continuous data and metering data, generates metrical information.
Specifically, continuous data and its corresponding metering data are generated into a metrical information.In other embodiments, it counts
Amount information may also include User ID, gauge table ID or other and the relevant data of the gauge table.
Metrical information is sent to the terminal device of the corresponding User ID of continuous data by S430.
By the way that the metrical information of generation to be sent to the terminal device of corresponding User ID, so that user learns current meter
Amount situation and expense situation, carry out the operation such as pay the fees in time.
It further, can also be in advance by User ID and/or gauge table ID and corresponding Terminal Equipment Identifier associated storage, root
Corresponding Terminal Equipment Identifier can be inquired, and metrical information is sent to terminal device according to User ID and/or gauge table ID.Its
In, Terminal Equipment Identifier can be the ID that telephone number, mailbox number etc. can be used for information exchange.
Above-mentioned automatic meter reading method is by obtaining the dial plate image of gauge table to be measured, and based on the amr message being pre-created
Detection model identifies the data information in acquired dial plate image, for example, User ID, gauge table ID and continuous data or
Other and the relevant data of the gauge table realize quickly and accurately meter reading, avoid because of misdescription, error of omission existing for making a copy of by hand
The problems such as, and by carrying out authenticity verification to gauge table, further ensure the reliability that meter data is made a copy of.And by institute
The data correlation storage of acquisition, further improves information system management degree, management and statistics convenient for data.In addition, according to
Acquired data automatically generate relevant metrical information, and metrical information is sent to corresponding user terminal, user is facilitated to obtain
Current metering situation and expense situation are known, to carry out the operation such as pay the fees in time.
Below by taking ammeter as an example, above-mentioned automatic meter reading method is specifically described：
First, User ID, ammeter number dial plate image corresponding with electricity consumption data in a variety of different ammeters are obtained in advance, are created
Sample image, and the characteristic for extracting all sample images carries out pattern-recognition training, by the User ID pair of same ammeter
The dial plate image answered as a kind of, same ammeter the corresponding dial plate image of ammeter number as one kind, the use of same ammeter
The corresponding dial plate image of electric data obtains every a kind of amr message detection model as a kind of.
During meter reading is performed, the dial plate image of ammeter is acquired by photographic device, then obtains acquired electricity
The dial plate image of table, and image identification is carried out to dial plate image based on the amr message detection model being previously obtained, it will identify
To ammeter number be compared with the ammeter number that database has been deposited, when database in the presence of identification obtain ammeter when, further
The location information of ammeter is obtained, and with identifying that the location information of the corresponding storage of obtained ammeter number is compared, works as location information
When comparison is true, User ID, ammeter number and electricity consumption data associated storage that identification is obtained, and be calculated according to electricity consumption data
Electricity consumption data and electricity cost are integrated into power information and are sent to user mobile phone, with the use for reminding user current by electricity cost
Power information, and pay the fees in time.When user needs active obtaining electricity consumption, by inputting User ID and/or ammeter number i.e.
Electricity consumption can be inquired.
By the method achieve to ammeter carry out quickly and accurately meter reading, avoid because by hand make a copy of existing for misdescription,
The problems such as error of omission, and by the authenticity verification to ammeter, further ensure the reliability of ammeter data.It and will be acquired
Data correlation stores, and further improves information system management degree, and staff can adjust electricity consumption according to current electricity consumption situation
Distribute or carry out other power consumption managements.In addition, power information is automatically generated according to electricity consumption data and electricity cost, by power information
Corresponding user terminal is sent to, user is facilitated to learn current electricity consumption situation and expense situation, to pay the fees in time
Deng operation.
In another embodiment, as shown in figure 5, also providing a kind of Automatic meter reading system, which includes image acquisition mould
Block 110, characteristic extracting module 120, picture recognition module 130, comparing module 140 and output module 150.
Image collection module 110, for obtaining the dial plate image of gauge table to be measured.
In this embodiment, image collection module 110 obtains the dial plate image of gauge table to be measured, and dial plate image includes metering
The amr message of table obtains corresponding amr message by the dial plate image for identifying acquired.
Specifically, the dial plate image of gauge table to be measured using hand-held photographic device or can be copied by staff or user
Meter terminal is acquired, and also can be acquired and be uploaded by being installed on the camera of fixed position, wherein, fixed position is position
Fixed position above gauge table to be measured.The dial plate image of gauge table to be measured is obtained by obtaining acquired image.
Characteristic extracting module 120 for carrying out feature extraction to the dial plate image of gauge table to be measured, obtains gauge table to be measured
Dial plate image characteristic.
After image collection module 110 obtains the dial plate image of gauge table to be measured, dial plate image is sent to feature extraction mould
Block 120, characteristic extracting module 120 extract the characteristic of the dial plate image of gauge table to be measured using image characteristics extraction algorithm,
To be detected to the characteristic extracted.
Picture recognition module 130 for characteristic to be inputted amr message detection model, obtains copying for gauge table to be measured
Table information, amr message include gauge table ID.
After characteristic extracting module 120 extracts the characteristic of dial plate image of gauge table to be measured, by the metering to be measured of extraction
The characteristic of the dial plate image of table is sent to picture recognition module 130, and picture recognition module 130 is by the gauge table to be measured of acquisition
The characteristic of dial plate image matched with amr message detection model pre-establishing, corresponding with characteristic, lead to
Cross the amr message identified based on amr message detection model corresponding with characteristic in gauge table to be measured.Amr message includes
Gauge table ID, each gauge table are corresponded to there are one gauge table ID, and the ID of each gauge table is uniquely determined, based on gauge table
ID can effectively distinguish the true and false of gauge table.
Further, amr message for can Efficient Characterization gauge table information related data.By taking ammeter as an example, amr message
It may include User ID, ammeter number and continuous data etc..
Comparing module 140 is compared for will detect obtained gauge table ID with the gauge table ID databases to prestore.
Output module 150, for when gauge table ID databases include the gauge table ID that detection obtains, obtaining amr message
And it exports.
When installing gauge table, the gauge table ID of the gauge table of installation is recorded, and gauge table ID is stored in gauge table
ID databases.When carrying out meter reading, it will identify that obtained gauge table ID is compared with the gauge table ID in database, due to every
The ID of a gauge table is uniquely determined, and when there is the gauge table ID that identification obtains in database, it is logical to illustrate the gauge table
Regular channel installation is crossed, the amr message identified is effective amr message.
Further, the amr message for obtaining and exporting can be stored or be shown.
Above-mentioned Automatic meter reading system by acquiring the dial plate image of gauge table to be measured, and extracts the dial plate of gauge table to be measured
The characteristic of image matches the amr message detection model that characteristic input pre-establishes, so as to automatic identification
Go out the amr message of gauge table to be measured, and pass through the true and false that the gauge table ID in amr message verifies the gauge table, when verification is tied
Fruit by it is true when just obtain and export the amr message identified.The above-mentioned phase that automatic identification gauge table otherwise is known based on image
Close data, without by hand made a copy of, improve meter reading efficiency and information system management degree, can reduce the input of manpower with
And the working strength of staff, it avoids because existing for making a copy of by hand the problems such as misdescription, error of omission, and by gauge table
Authenticity verification further ensures the reliability that meter data is made a copy of.
In another embodiment, as shown in fig. 6, further including position acquisition module 160, for working as gauge table ID database packets
When including the gauge table ID that detection obtains, the location information of gauge table to be measured is obtained.
Comparing module 140 is additionally operable to the location information of gauge table to be measured and position prestoring, corresponding with gauge table ID
Information is compared.
Output module 150 is additionally operable to the location information when gauge table to be measured and position prestoring, corresponding with gauge table ID
When information is identical, obtains amr message and export.
In practical applications, the installation steps of gauge table are complicated, can only be installed by professional staff, and after installation
Position immobilizes, therefore is verified by the position to gauge table, can further identify the true and false of gauge table, it is ensured that obtained
The amr message taken is efficiently and accurately amr message.
Specifically, the location information of gauge table can be by gauge table GPS positioning function in itself or based on gauge table
Corresponding IP address determines, can also by the GPS positioning function of hand-hold meter reading terminal or based on the corresponding IP of gauge table
Address determines.
Further, staff obtains the location information of gauge table installation when installing gauge table, and the position is believed
Breath and gauge table ID associated storages, to distinguish the true of gauge table automatically according to location information and gauge table ID in automatic data logging
Puppet.
In another embodiment, Automatic meter reading system further includes image pre-processing module, for the table to gauge table to be measured
Disk image carries out image preprocessing, and the dial plate image of pretreated gauge table to be measured is sent to characteristic extracting module 120.
In one embodiment, image preprocessing include image smoothing, image transformation, image enhancement, image recovery and
Image filtering etc. or any of which item or multinomial combination.Figure can be eliminated by carrying out image preprocessing to sample image
Unrelated information, restores useful real information as in, enhances detectability for information about and simplifies data to the maximum extent,
So as to improve feature extraction, image segmentation, matching and the reliability of identification.
In another embodiment, image preprocessing further includes, and amr message sample image is normalized.For example,
After the dial plate image of gauge table to be measured is got, by the dial plate image normalization of gauge table to be measured into 240x240 sizes, then
The operation of the characteristic of extraction amr message sample image is performed again.Facilitated in this way by the size of unified amr message follow-up
Amr message is realized and is detected.
In another embodiment, as shown in fig. 7, further including sample creation module 210 and detection model creation module 220.
Sample creation module 210 for obtaining the dial plate image of a variety of different amr messages, creates amr message sample graph
Picture.
One gauge table includes a variety of different amr messages, such as User ID, metering table number and continuous data etc., and
In different types of gauge table, there is also different representations for same class amr message.In the present embodiment, it obtains first more
The dial plate image of the different amr messages of kind, creates amr message sample image, by one species, the dial plate figure of same representation
As being divided into one kind, amr message detection model may finally be established to every one kind, subsequently to can be achieved to copy a variety of differences
The identification of table information improves the accuracy of amr message identification.
Characteristic extracting module 120 is additionally operable to extract the characteristic of all amr message sample images.
Further, image pre-processing module further includes locates in advance for carrying out image to all amr message sample images
Reason, and pretreated all amr message sample images are sent to characteristic extracting module 120.
In one embodiment, image preprocessing include image smoothing, image transformation, image enhancement, image recovery and
Image filtering etc. or any of which item or multinomial combination.Figure can be eliminated by carrying out image preprocessing to sample image
Unrelated information, restores useful real information as in, enhances detectability for information about and simplifies data to the maximum extent,
So as to improve feature extraction, image segmentation, matching and the reliability of identification.
In another embodiment, image preprocessing further includes, and amr message sample image is normalized.For example,
The dial plate image of a variety of different amr messages is collected, after creating amr message sample image, by all establishment amr message samples
This image is all normalized into 240x240 sizes, then extracts the characteristic of amr message sample image.In this way by uniformly copying
The size of table message sample image is convenient subsequently to be established detection model and realizes detection to amr message.
Detection model creation module 220, for carrying out pattern-recognition to the characteristic of all amr message sample images
Training, obtains amr message detection model.
Specifically, amr message detection model may be based on the detection model of grader structure, by believing all meter readings
The characteristic for ceasing sample image carries out pattern-recognition training, and the dial plate image of variety classes, different representations is divided
Class, based on every a kind of establishment amr message detection model.
Wherein, grader can be k nearest neighbor grader, decision tree classifier and support vector machine ensembles learning method etc., no
With grader is divided to have different pattern-recognition training algorithms, user can be based on recognition accuracy, recognition efficiency selects difference
Grader structure amr message detection model.
By obtaining the dial plate image of a variety of different amr messages, sufficient amr message sample image is ensure that, into one
Step extracts the characteristic of all amr message sample images, and pattern is carried out to the characteristic of all amr message sample images
Recognition training and classification, so as to obtain a variety of inhomogeneous amr message detection models, to meet the knowledge to different amr messages
Other demand can further improve the accuracy rate of amr message identification.
In another specific embodiment, amr message further includes User ID and continuous data, and Automatic meter reading system also wraps
Memory module is included, memory module is used for User ID, gauge table ID and continuous data associated storage.
By by User ID, gauge table ID and continuous data associated storage, fully integrating the related data of each gauge table,
To realize that meter data is shared and provides strong data supporting, convenient for the continuous data of each gauge table is carried out statistics and
Management, and corresponding continuous data is inquired by User ID or gauge table ID fast and easys, it is obtained and the use convenient for user
The relevant continuous data in family.
Further, Automatic meter reading system further includes charging module and sending module.
Charging module is used to, according to continuous data, obtain metering data, according to continuous data and metering data, generation metering
Information.
Specifically, according to acquired continuous data, corresponding expense can be calculated using charging algorithmic tool, will be measured
Data and its corresponding metering data generate a metrical information, convenient for being deducted fees or being paid the fees according to the expense of gained.
In other embodiment, metrical information may also include User ID, gauge table ID or other and the relevant data of the gauge table.
Sending module, for metrical information to be sent to the terminal device of the corresponding User ID of continuous data.
By the way that the metrical information of generation to be sent to the terminal device of corresponding User ID, so that user learns current meter
Amount situation and expense situation, carry out the operation such as pay the fees in time.
It further, can also be in advance by User ID and/or gauge table ID and corresponding Terminal Equipment Identifier associated storage, root
Corresponding Terminal Equipment Identifier can be inquired, and metrical information is sent to terminal device according to User ID and/or gauge table ID.Its
In, Terminal Equipment Identifier can be the ID that telephone number, mailbox number etc. can be used for information exchange.
Above-mentioned Automatic meter reading system is by obtaining the dial plate image of gauge table to be measured, and based on the amr message being pre-created
Detection model identifies the data information in acquired dial plate image, for example, User ID, gauge table ID and continuous data or
Other and the relevant data of the gauge table realize quickly and accurately meter reading, avoid because of misdescription, error of omission existing for making a copy of by hand
The problems such as, and by carrying out authenticity verification to gauge table, further ensure the reliability that meter data is made a copy of.And by institute
The data correlation storage of acquisition, further improves information system management degree, management and statistics convenient for data.In addition, according to
Acquired data automatically generate relevant metrical information, and metrical information is sent to corresponding user terminal, user is facilitated to obtain
Current metering situation and expense situation are known, to carry out the operation such as pay the fees in time.
In another embodiment, a kind of computer equipment is also provided, including memory, processor and is stored in memory
Computer program that is upper and can running on a processor, processor realize the automatic data logging side of any one embodiment when performing program
Method.
In another embodiment, a kind of computer readable storage medium is also provided, is stored thereon with computer program, the journey
The automatic meter reading method of any one embodiment is realized when sequence is executed by processor.
Each technical characteristic of embodiment described above can be combined arbitrarily, to make description succinct, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, it is all considered to be the range of this specification record.
Embodiment described above only expresses the several embodiments of the present invention, and description is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that those of ordinary skill in the art are come
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the protection of the present invention
Range.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. a kind of automatic meter reading method, which is characterized in that including：
Obtain the dial plate image of gauge table to be measured；
Feature extraction is carried out to the dial plate image of the gauge table to be measured, obtains the feature of the dial plate image of the gauge table to be measured
Data；
The characteristic is inputted into amr message detection model, obtains the amr message of the gauge table to be measured, the meter reading
Information includes gauge table ID；
The gauge table ID that detection obtains is compared with the gauge table ID databases to prestore；
When the gauge table ID databases include the gauge table ID that the detection obtains, obtain the amr message and export.
2. automatic meter reading method according to claim 1, which is characterized in that described when the gauge table ID databases include
During the gauge table ID that the detection obtains, obtain the amr message and include the step of output：
When the gauge table ID databases include the gauge table ID that the detection obtains, the position of the gauge table to be measured is obtained
Information；
The location information of the gauge table to be measured is compared with location information prestoring, corresponding with the gauge table ID；
When the gauge table to be measured location information with it is described it is prestoring, location information corresponding with the gauge table ID is identical
When, it obtains the amr message and exports.
3. automatic meter reading method according to claim 1, which is characterized in that described by characteristic input meter reading letter
Before the step of ceasing detection model, obtaining the amr message of the gauge table to be measured, further include：
The dial plate image of a variety of different amr messages is obtained, creates amr message sample image；
Extract the characteristic of all amr message sample images；
Pattern-recognition training is carried out to the characteristic of all amr message sample images, obtains amr message detection mould
Type.
4. automatic meter reading method according to claim 1, which is characterized in that the amr message further include User ID and
Continuous data, it is described when the gauge table ID databases include it is described detect and obtain gauge table ID when, obtain meter reading letter
After the step of ceasing and exporting, further include：
By the User ID, gauge table ID and continuous data associated storage.
5. automatic meter reading method according to claim 4, which is characterized in that further include：
According to the continuous data, metering data is obtained；
According to the continuous data and the metering data, metrical information is generated；
The metrical information is sent to the terminal device of the corresponding User ID of the continuous data.
6. a kind of Automatic meter reading system, which is characterized in that including：
Image collection module, for obtaining the dial plate image of gauge table to be measured；
Characteristic extracting module for carrying out feature extraction to the dial plate image of the gauge table to be measured, obtains the metering to be measured
The characteristic of the dial plate image of table；
Picture recognition module for the characteristic to be inputted amr message detection model, obtains the gauge table to be measured
Amr message, the amr message include gauge table ID；
Comparing module is compared for will detect the obtained gauge table ID with the gauge table ID databases to prestore；
Output module, for when the gauge table ID databases include the gauge table ID that the detection obtains, being copied described in acquisition
Table information simultaneously exports.
7. Automatic meter reading system according to claim 6, which is characterized in that position acquisition module is further included, for working as
When stating the gauge table ID that gauge table ID databases are obtained including the detection, the location information of the gauge table to be measured is obtained；
Comparing module is additionally operable to the location information of the gauge table to be measured and position prestoring, corresponding with the gauge table ID
Confidence breath is compared；
Output module, be additionally operable to location information when the gauge table to be measured with it is described prestoring, corresponding with the gauge table ID
Location information it is identical when, obtain the amr message and export.
8. Automatic meter reading system according to claim 6, which is characterized in that further include：
Sample creation module for obtaining the dial plate image of a variety of different amr messages, creates amr message sample image；
The characteristic extracting module is additionally operable to extract the characteristic of all amr message sample images；
Detection model creation module, for carrying out pattern-recognition instruction to the characteristic of all amr message sample images
Practice, obtain amr message detection model.
9. a kind of computer equipment, can run on a memory and on a processor including memory, processor and storage
Computer program, which is characterized in that processor realizes claim 1-5 any one of them automatic data logging side when performing program
Method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
Claim 1-5 any one of them automatic meter reading methods are realized during execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711209340.5A CN108197634A (en) | 2017-11-27 | 2017-11-27 | Automatic meter reading method, system, computer equipment and readable storage medium storing program for executing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711209340.5A CN108197634A (en) | 2017-11-27 | 2017-11-27 | Automatic meter reading method, system, computer equipment and readable storage medium storing program for executing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108197634A true CN108197634A (en) | 2018-06-22 |
Family
ID=62573227
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711209340.5A Pending CN108197634A (en) | 2017-11-27 | 2017-11-27 | Automatic meter reading method, system, computer equipment and readable storage medium storing program for executing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108197634A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109272000A (en) * | 2018-09-10 | 2019-01-25 | 广东电网有限责任公司 | A kind of alignment of robot instrument and focus adjustment method and device |
| CN109271987A (en) * | 2018-08-28 | 2019-01-25 | 上海鸢安智能科技有限公司 | A kind of digital electric meter number reading method, device, system, computer equipment and storage medium |
| CN109413514A (en) * | 2018-10-12 | 2019-03-01 | 广州物道水务科技有限公司 | A kind of data transmission method, device and electronic equipment |
| CN109948756A (en) * | 2019-03-14 | 2019-06-28 | 重庆中陆承大科技有限公司 | Meter register method and kilowatt meter reading-out system |
| CN110220639A (en) * | 2019-06-04 | 2019-09-10 | 国家电网有限公司 | Pressure gauge meter register method, device and terminal device in substation |
| CN110351610A (en) * | 2019-07-17 | 2019-10-18 | 广州物道水务科技有限公司 | A kind of data processing method, device and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955694A (en) * | 2014-04-09 | 2014-07-30 | 广州邦讯信息系统有限公司 | Image recognition meter reading system and method |
| CN104504490A (en) * | 2014-11-25 | 2015-04-08 | 新天科技股份有限公司 | High-intelligent photographing and meter reading system and method |
| CN106570436A (en) * | 2016-11-14 | 2017-04-19 | 三峡大学 | Substation equipment meter reading system and meter reading method based on two-dimensional code |
-
2017
- 2017-11-27 CN CN201711209340.5A patent/CN108197634A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955694A (en) * | 2014-04-09 | 2014-07-30 | 广州邦讯信息系统有限公司 | Image recognition meter reading system and method |
| CN104504490A (en) * | 2014-11-25 | 2015-04-08 | 新天科技股份有限公司 | High-intelligent photographing and meter reading system and method |
| CN106570436A (en) * | 2016-11-14 | 2017-04-19 | 三峡大学 | Substation equipment meter reading system and meter reading method based on two-dimensional code |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271987A (en) * | 2018-08-28 | 2019-01-25 | 上海鸢安智能科技有限公司 | A kind of digital electric meter number reading method, device, system, computer equipment and storage medium |
| CN109272000A (en) * | 2018-09-10 | 2019-01-25 | 广东电网有限责任公司 | A kind of alignment of robot instrument and focus adjustment method and device |
| CN109413514A (en) * | 2018-10-12 | 2019-03-01 | 广州物道水务科技有限公司 | A kind of data transmission method, device and electronic equipment |
| CN109948756A (en) * | 2019-03-14 | 2019-06-28 | 重庆中陆承大科技有限公司 | Meter register method and kilowatt meter reading-out system |
| CN110220639A (en) * | 2019-06-04 | 2019-09-10 | 国家电网有限公司 | Pressure gauge meter register method, device and terminal device in substation |
| CN110220639B (en) * | 2019-06-04 | 2021-09-07 | 国家电网有限公司 | Method and device for reading meter by pressure gauge in transformer substation and terminal equipment |
| CN110351610A (en) * | 2019-07-17 | 2019-10-18 | 广州物道水务科技有限公司 | A kind of data processing method, device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108197634A (en) | Automatic meter reading method, system, computer equipment and readable storage medium storing program for executing | |
| CN104424466B (en) | Method for checking object, body detection device and image pick up equipment | |
| CN109977191B (en) | Problem map detection method, device, electronic equipment and medium | |
| CN109949286A (en) | Method and apparatus for output information | |
| CN109344905A (en) | A kind of transmission facility automatic fault recognition methods based on integrated study | |
| TW201832138A (en) | Image recognition method and apparatus | |
| CN109936582A (en) | Construct the method and device based on the PU malicious traffic stream detection model learnt | |
| CN113344886A (en) | Wafer surface defect detection method and equipment | |
| US20200019820A1 (en) | Learning device, learning method, and learning program | |
| CN109033772A (en) | A kind of input method and device of verification information | |
| CN112052813B (en) | Method and device for identifying translocation between chromosomes, electronic equipment and readable storage medium | |
| CN103383732A (en) | Image processing method and device | |
| TW202009681A (en) | Sample labeling method and device, and damage category identification method and device | |
| CN109360188A (en) | A kind of detection method of high iron catenary equipotential line defective mode | |
| CN109145973A (en) | Method and apparatus for detecting monocrystaline silicon solar cell defect | |
| CN113255590A (en) | Defect detection model training method, defect detection method, device and system | |
| CN112419268A (en) | Method, device, equipment and medium for detecting image defects of power transmission line | |
| JP2020101948A (en) | Action recognition system and action recognition method | |
| CN112327104A (en) | Fault detection and positioning method for power distribution network with distributed power supply | |
| CN109145752A (en) | For assessing the method, apparatus, equipment and medium of object detection and track algorithm | |
| CN107316131A (en) | A kind of electric power meter mounting process quality detecting system based on image recognition | |
| CN110222724A (en) | A kind of picture example detection method, apparatus, computer equipment and storage medium | |
| CN111144429A (en) | Object classification method and system, computer system and computer readable medium | |
| Ke et al. | An automatic instrument recognition approach based on deep convolutional neural network | |
| CN110532186A (en) | Method, apparatus, electronic equipment and the storage medium tested using identifying code |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180622 |