CN112487866A - Water meter type identification method and system - Google Patents

Water meter type identification method and system Download PDF

Info

Publication number
CN112487866A
CN112487866A CN202011208734.0A CN202011208734A CN112487866A CN 112487866 A CN112487866 A CN 112487866A CN 202011208734 A CN202011208734 A CN 202011208734A CN 112487866 A CN112487866 A CN 112487866A
Authority
CN
China
Prior art keywords
water meter
dial
type
image
water
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
Application number
CN202011208734.0A
Other languages
Chinese (zh)
Inventor
丁武
刘宏宇
陈学志
于洋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Liaoning Changjiang Intelligent Technology Co Ltd
Original Assignee
Liaoning Changjiang Intelligent Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Liaoning Changjiang Intelligent Technology Co Ltd filed Critical Liaoning Changjiang Intelligent Technology Co Ltd
Priority to CN202011208734.0A priority Critical patent/CN112487866A/en
Publication of CN112487866A publication Critical patent/CN112487866A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
    • G01F15/00—Details of, or accessories for, apparatus of groups G01F1/00 - G01F13/00 insofar as such details or appliances are not adapted to particular types of such apparatus
    • G01F15/06—Indicating or recording devices
    • G01F15/061—Indicating or recording devices for remote indication
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/20—Image enhancement or restoration using local operators
    • G06T5/30—Erosion or dilatation, e.g. thinning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/40—Image enhancement or restoration using histogram techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/02—Recognising information on displays, dials, clocks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Fluid Mechanics (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Arrangements For Transmission Of Measured Signals (AREA)

Abstract

The embodiment of the application provides an outer hanging water gauge equipment of checking meter, only needs simple equipment can realize long-range checking meter, need not to reform transform the water gauge on a large scale, the realization cost that reduces long-range checking meter that can be very big. Meanwhile, the technical characteristics of Artificial Intelligence (AI) on computer vision identification processing are utilized to identify the water meter dial, so that the water meter type can be accurately and quickly obtained, and the subsequent water meter reading equipment can call a corresponding meter reading algorithm to perform meter reading operation according to the identified water meter type.

Description

Water meter type identification method and system
Technical Field
The application relates to the technical field of water meter reading, in particular to a water meter type identification method and system.
Background
The current manual visual reading of water meters is a time-consuming, inefficient and expensive data acquisition method; changing or upgrading water meters to achieve automatic data collection and communication is time-consuming and expensive, and due to the fact that brands, models and even data formats of the water meters are different, even if data uploaded by the water meters are obtained, data identification difficulty and pressure exist, and practicability is poor.
With the development of the technology of the internet of things, a remote meter reading service for a traditional non-intelligent water meter becomes a new service field of the internet of things, and when the meter reading service of the traditional non-intelligent water meter is realized, after the non-intelligent water meter is connected with an external monitoring device, the monitoring device is used for collecting and reporting data of the non-intelligent water meter; for example, when a non-intelligent water meter is read, a common method is as follows: and reading dial plate information of the non-intelligent water meter by using the plug-in camera of the non-intelligent water meter.
However, the traditional non-intelligent water meter comprises a pointer type and a digital type, and obviously, a corresponding meter reading algorithm can be called only if the type of the water meter is accurately identified. Therefore, how to effectively identify the type of the water meter becomes a technical problem which needs to be solved urgently at present, and related solutions are not provided in the prior art.
Disclosure of Invention
In order to solve the technical problems existing in the background technology, the application provides a water meter type identification method and system.
A first aspect of the present application provides a water meter type identification method, the method including:
shooting a water meter dial by a camera of the water meter reading equipment to obtain a water meter dial image, and sending the water meter dial image to a processor;
and the processor calls an artificial intelligence algorithm to identify the water meter dial and outputs a water meter type identification result.
Preferably, the processor is arranged in a water meter reading device or a server, and correspondingly, the water meter reading device is further provided with a communication module for respectively sending the water meter type identification result or the water meter dial image to the server.
Preferably, before the processor invokes an artificial intelligence algorithm to identify the water meter dial, the method includes:
and binarizing the water meter dial image by adopting a histogram equalization algorithm, carrying out connected domain analysis on the binarized image by adopting a morphological expansion algorithm, and taking an area defined by the identified regular boundary of the connected domain as an effective area of the dial.
Preferably, the artificial intelligence algorithm is a neural network based algorithm.
Preferably, the artificial intelligence algorithm requires pre-training, including:
the method comprises the steps that a server receives a dial plate image returned by a water meter reading device according to preset frequency, wherein the dial plate image is manually added with an association relation with a water meter type, and the water meter type comprises a pointer type and a digital type; the server also acquires a preset number of images of the non-water meters;
and when the number of each type of image reaches a preset value, the server inputs the three types of sample images into the neural network model for training, so that the trained neural network model is obtained.
Preferably, the trained neural network model comprises a feature database, and the feature database comprises a pointer type water meter feature set, a digital water meter feature set and a non-water meter feature set.
Preferably, the characteristics in the pointer water meter feature set are used for representing the existence of one or more linear narrow connected domains, the digital water meter feature set is used for representing the existence of one or more digital characters, and the non-water meter feature set is a virtual set and is used for representing the absence of the characteristics in the pointer water meter feature set and the digital water meter feature set.
Preferably, the calling the artificial intelligence algorithm to identify the water meter dial comprises:
set of setting labels Li＝(L1，L2，L3) WhereinLabel L1-L3Respectively corresponding to the pointer type water meter characteristic set, the digital type water meter characteristic set and the non-water meter characteristic set to represent the type of the water meter; the trained neural network model carries out foreground identification on the effective area of the binarized dial plate image, analyzes and obtains the characteristics of the foreground image, and carries out similarity calculation on the characteristics and each characteristic set so as to determine the label L to which the characteristics belongi。
Preferably, the loss function of the neural network model is defined as:
Figure BDA0002758040440000021
where i is the index number of anchor, piIs the predicted probability of the ith anchor as the object; if Anchor is positive, true tag
Figure BDA0002758040440000031
Is 1, if anchor is negative, then
Figure BDA0002758040440000032
Is 0;
tiis a vector representing the parameterized coordinates of the predicted bounding box, and
Figure BDA0002758040440000033
is the parameterized coordinate of the true value box associated with the positive anchor; l isclsLogarithmic loss function, L, representing the classification loss of objects versus non-objectsregA regression loss function representing the anchor;
Figure BDA0002758040440000034
indicating that only the positive anchor activates the regression loss function, otherwise the regression loss is disabled; n is a radical ofcls、NregAre respectively Lcls、
Figure BDA0002758040440000035
The normalization parameter of (a) is calculated,
λ is the weight.
A second aspect of the present application provides a water meter type identification system, the system includes a water meter reading device and a server, wherein the water meter reading device includes a camera device and a communication module, and the water meter reading device or the server includes a processor;
the camera device is used for shooting the water meter dial to obtain a water meter dial image and sending the water meter dial image to the processor;
and the processor is used for receiving the water meter dial image, calling an artificial intelligence algorithm to identify the water meter dial and outputting a water meter type identification result.
The invention has the beneficial effects that:
according to the technical scheme, the neural network model is trained by adopting the pointer type water meter dial plate image, the digital water meter dial plate image and the non-water meter image, so that the neural network model establishes characteristic sets capable of accurately representing various types of water meters, namely the pointer type water meter characteristic set, the digital water meter characteristic set and the non-water meter characteristic set, a water meter type identification result can be rapidly and accurately output, and a subsequent water meter reading device can call a corresponding meter reading algorithm to perform meter reading operation according to the identified water meter type. Meanwhile, the technical scheme of the application not only utilizes the accurate and quick technical advantages of the artificial intelligence algorithm in image recognition, but also improves the neural network model, specifically designs and improves the loss function of the neural network model, and further improves the accuracy of the neural network model in classification recognition.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic flow chart of a water meter type identification method disclosed in an embodiment of the present application;
fig. 2 is a schematic diagram illustrating a recognition principle of a neural network model in the water meter type recognition method disclosed in the embodiment of the present application;
fig. 3 is a schematic structural diagram of a water meter type identification system disclosed in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present application, it should be noted that if the terms "upper", "lower", "inside", "outside", etc. are used for indicating the orientation or positional relationship based on the orientation or positional relationship shown in the drawings or the orientation or positional relationship which the present invention product is usually put into use, it is only for convenience of describing the present application and simplifying the description, but it is not intended to indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and be operated, and thus, should not be construed as limiting the present application.
Furthermore, the appearances of the terms "first," "second," and the like, if any, are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
It should be noted that the features of the embodiments of the present application may be combined with each other without conflict.
Example one
Referring to fig. 1, fig. 1 is a schematic flow chart illustrating a water meter type identification method according to an embodiment of the present application. As shown in fig. 1, a water meter type identification method according to an embodiment of the present application includes:
s1, shooting a water meter dial by a camera of the water meter reading equipment to obtain a water meter dial image, and sending the water meter dial image to a processor;
and S2, the processor calls an artificial intelligence algorithm to identify the water meter dial and outputs a water meter type identification result.
In this application embodiment, this application has set up outer hanging water gauge equipment of checking meter, only needs simple equipment can realize long-range checking meter, need not to reform transform the water gauge on a large scale, the realization cost that reduces long-range checking meter that can be very big. In recent years, Artificial Intelligence (AI) has been rapidly developed and widely used, and achieved fruitful results. In view of the technical characteristics that the artificial intelligence technology has accuracy, rapidness, learning evolution and the like in the aspect of computer vision identification processing, the technical scheme of the application identifies the water meter dial by using the artificial intelligence algorithm, so that the water meter type can be accurately and rapidly obtained.
In this optional embodiment, the processor is disposed in the water meter reading device or the server, and correspondingly, the water meter reading device further includes a communication module for respectively sending the water meter type identification result or the water meter dial image to the server.
In this application embodiment, both can set up image identification and classification processing in the water gauge equipment of checking meter of front end, so set up, the server only need receive final classification discernment can, can effectively reduce the processing load of server, improve entire system's operating efficiency. In addition, because the water meter reading equipment is provided with the communication module, the shot images can be selectively transmitted back to the server for unified processing, so that the hardware cost of the water meter reading equipment is reduced, and the rapid popularization of the water meter reading equipment is facilitated.
In this optional implementation, before the processor invokes an artificial intelligence algorithm to identify the water meter dial, the method includes:
and binarizing the water meter dial image by adopting a histogram equalization algorithm, carrying out connected domain analysis on the binarized image by adopting a morphological expansion algorithm, and taking an area defined by the identified regular boundary of the connected domain as an effective area of the dial.
In the embodiment of the application, due to various factors such as irregular installation, movement and irregular dial of the water meter, images shot by the camera cannot completely contain the counting part of the dial, and therefore, the images of the dial need to be preprocessed before being recognized. Namely, the dial image is subjected to binarization processing to obtain a binarization image only containing black pixels and white pixels, so that the calculation amount and the identification difficulty of subsequent processing can be effectively reduced; meanwhile, since the dial is generally regular in shape, such as circular or square, the connected domain having regular boundaries is the effective area of the dial.
In this alternative embodiment, the artificial intelligence algorithm is a neural network based algorithm.
In the embodiment of the application, the neural network algorithm is one of ten artificial intelligence algorithms, and has a self-learning function. For example, when image recognition is implemented, a plurality of different image templates and corresponding recognition results need to be input into the neural network in advance, and the network can slowly learn to recognize similar images through a self-learning function. Based on the characteristics of the neural network, the embodiment selects the neural network algorithm to identify the water meter type.
In this optional embodiment, the artificial intelligence algorithm needs to be pre-trained, including:
the method comprises the steps that a server receives a dial plate image returned by a water meter reading device according to preset frequency, wherein the dial plate image is manually added with an association relation with a water meter type, and the water meter type comprises a pointer type and a digital type; the server also acquires a preset number of images of the non-water meters;
and when the number of each type of image reaches a preset value, the server inputs the three types of sample images into the neural network model for training, so that the trained neural network model is obtained.
In this optional embodiment, the trained neural network model includes a feature database, and the feature database includes a pointer type water meter feature set, a digital type water meter feature set, and a non-water meter feature set.
In this optional embodiment, the characteristics in the pointer water meter feature set are used for representing the existence of one or more linear narrow connected domains, the digital water meter feature set is used for representing the existence of one or more digital characters, and the non-water meter feature set is a virtual set and is used for representing the absence of the characteristics in the pointer water meter feature set and the digital water meter feature set.
In this optional embodiment, the calling the artificial intelligence algorithm to identify the water meter dial includes:
set of setting labels Li＝(L1，L2，L3) Wherein the label L1-L3Respectively corresponding to the pointer type water meter characteristic set, the digital type water meter characteristic set and the non-water meter characteristic set to represent the type of the water meter; the trained neural network model carries out foreground identification on the effective area of the binarized dial plate image, analyzes and obtains the characteristics of the foreground image, and carries out similarity calculation on the characteristics and each characteristic set so as to determine the label L to which the characteristics belongi。
In this alternative embodiment, the loss function of the neural network model is defined as:
Figure BDA0002758040440000061
where i is the index number of anchor, piIs the predicted probability of the ith anchor as the object; if Anchor is positive, true tag
Figure BDA0002758040440000062
Is 1, if anchor is negative, then
Figure BDA0002758040440000063
Is 0;
tiis a vector representing the parameterized coordinates of the predicted bounding box, and
Figure BDA0002758040440000064
is the parameterized coordinate of the true value box associated with the positive anchor; l isclsLogarithmic loss function, L, representing the classification loss of objects versus non-objectsregA regression loss function representing the anchor;
Figure BDA0002758040440000071
indicating that only the positive anchor activates the regression loss function, otherwise the regression loss is disabled; n is a radical ofcls、NregAre respectively Lcls、
Figure BDA0002758040440000072
The normalization parameter of (a) is calculated,
λ is the weight.
In the embodiment of the application, it is ensured that the final classification recognition result is accurate, which is very important key content. The Loss Function (Loss Function) in the neural network algorithm is used for measuring the dissatisfaction degree of the output result, so the Loss Function is designed to ensure the accuracy of the identification result.
Example two
Referring to fig. 3, fig. 3 is a schematic structural diagram of a water meter type identification system disclosed in the embodiment of the present application. As shown in fig. 3, the water meter type identification system according to the embodiment of the present application includes a water meter reading device and a server, where the water meter reading device includes a camera and a communication module, and the water meter reading device or the server includes a processor;
the camera device is used for shooting the water meter dial to obtain a water meter dial image and sending the water meter dial image to the processor;
and the processor is used for receiving the water meter dial image, calling an artificial intelligence algorithm to identify the water meter dial and outputting a water meter type identification result.
In this application embodiment, this application has set up outer hanging water gauge equipment of checking meter, only needs simple equipment can realize long-range checking meter, need not to reform transform the water gauge on a large scale, the realization cost that reduces long-range checking meter that can be very big. In recent years, Artificial Intelligence (AI) has been rapidly developed and widely used, and achieved fruitful results. In view of the technical characteristics that the artificial intelligence technology has accuracy, rapidness, learning evolution and the like in the aspect of computer vision identification processing, the technical scheme of the application identifies the water meter dial by using the artificial intelligence algorithm, so that the water meter type can be accurately and rapidly obtained.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (10)

1. A water meter type identification method, the method comprising:
shooting a water meter dial by a camera of the water meter reading equipment to obtain a water meter dial image, and sending the water meter dial image to a processor;
and the processor calls an artificial intelligence algorithm to identify the water meter dial and outputs a water meter type identification result.
2. The method of claim 1, wherein: the processor is arranged on the water meter reading device or the server, and correspondingly, the water meter reading device is further provided with a communication module used for respectively sending the water meter type identification result or the water meter dial image to the server.
3. The method of claim 1, wherein: before the processor calls an artificial intelligence algorithm to identify the water meter dial, the method comprises the following steps:
and binarizing the water meter dial image by adopting a histogram equalization algorithm, carrying out connected domain analysis on the binarized image by adopting a morphological expansion algorithm, and taking an area defined by the identified regular boundary of the connected domain as an effective area of the dial.
4. A method according to any one of claims 1-3, characterized in that: the artificial intelligence algorithm is an algorithm based on a neural network.
5. The method of claim 1, wherein: the artificial intelligence algorithm requires pre-training, including:
the method comprises the steps that a server receives a dial plate image returned by a water meter reading device according to preset frequency, wherein the dial plate image is manually added with an association relation with a water meter type, and the water meter type comprises a pointer type and a digital type; the server also acquires a preset number of images of the non-water meters;
and when the number of each type of image reaches a preset value, the server inputs the three types of sample images into the neural network model for training, so that the trained neural network model is obtained.
6. The method of claim 5, wherein: the trained neural network model comprises a feature database, wherein the feature database comprises a pointer type water meter feature set, a digital type water meter feature set and a non-water meter feature set.
7. The method of claim 6, wherein: the characteristic in the pointer water gauge feature set is used for the representation to have the narrow connected domain of one or more linear types, digital water gauge feature set is used for the representation to have one or more digital characters, non-water gauge feature set is virtual set, and it is used for the representation not to possess pointer water gauge feature set with the characteristic in the digital water gauge feature set.
8. The method of claim 1, wherein: calling an artificial intelligence algorithm to identify the water meter dial, and comprising the following steps:
set of setting labels Li＝(L1，L2，L3) Wherein the label L1-L3Respectively corresponding to the pointer type water meter characteristic set, the digital type water meter characteristic set and the non-water meter characteristic set to represent the type of the water meter; the trained neural network model carries out foreground identification on the effective area of the binarized dial plate image, analyzes and obtains the characteristics of the foreground image, and carries out similarity calculation on the characteristics and each characteristic set so as to determine the label L to which the characteristics belongi。
9. The method of claim 1, wherein: the loss function of the neural network model is defined as:
Figure FDA0002758040430000021
where i is the index number of anchor, piIs the predicted probability of the ith anchor as the object; if Anchor is positive, true tag
Figure FDA0002758040430000022
Is 1, if anchor is negative, then
Figure FDA0002758040430000023
Is 0; t is tiIs a vector representing the parameterized coordinates of the predicted bounding box, and
Figure FDA0002758040430000024
is the parameterized coordinate of the true value box associated with the positive anchor; l isclsLogarithmic loss function, L, representing the classification loss of objects versus non-objectsregA regression loss function representing the anchor;
Figure FDA0002758040430000025
indicating that only the positive anchor activates the regression loss function, otherwise the regression loss is disabled; n is a radical ofcls、NregAre respectively provided withIs Lcls、
Figure FDA0002758040430000026
λ is a weight.
10. A water meter type identification system is characterized in that: the system comprises water meter reading equipment and a server, wherein the water meter reading equipment comprises a camera device and a communication module, and the water meter reading equipment or the server comprises a processor;
the camera device is used for shooting the water meter dial to obtain a water meter dial image and sending the water meter dial image to the processor;
and the processor is used for receiving the water meter dial image, calling an artificial intelligence algorithm to identify the water meter dial and outputting a water meter type identification result.
CN202011208734.0A 2020-11-03 2020-11-03 Water meter type identification method and system Pending CN112487866A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011208734.0A CN112487866A (en) 2020-11-03 2020-11-03 Water meter type identification method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011208734.0A CN112487866A (en) 2020-11-03 2020-11-03 Water meter type identification method and system

Publications (1)

Publication Number Publication Date
CN112487866A true CN112487866A (en) 2021-03-12

Family

ID=74926328

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011208734.0A Pending CN112487866A (en) 2020-11-03 2020-11-03 Water meter type identification method and system

Country Status (1)

Country Link
CN (1) CN112487866A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108491844A (en) * 2018-02-07 2018-09-04 西安工程大学 Water meter automatic checkout system based on image procossing and its image processing method
CN109029641A (en) * 2018-07-27 2018-12-18 华南理工大学 A kind of water meter automatic testing method based on Faster-rcnn
CN111414934A (en) * 2020-01-21 2020-07-14 国网浙江省电力有限公司湖州供电公司 Pointer type meter reading automatic identification method based on fast R-CNN and U-Net
CN111444781A (en) * 2020-03-09 2020-07-24 武汉理工大学 Water meter reading identification method and equipment and storage medium
CN111553200A (en) * 2020-04-07 2020-08-18 北京农业信息技术研究中心 Image detection and identification method and device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108491844A (en) * 2018-02-07 2018-09-04 西安工程大学 Water meter automatic checkout system based on image procossing and its image processing method
CN109029641A (en) * 2018-07-27 2018-12-18 华南理工大学 A kind of water meter automatic testing method based on Faster-rcnn
CN111414934A (en) * 2020-01-21 2020-07-14 国网浙江省电力有限公司湖州供电公司 Pointer type meter reading automatic identification method based on fast R-CNN and U-Net
CN111444781A (en) * 2020-03-09 2020-07-24 武汉理工大学 Water meter reading identification method and equipment and storage medium
CN111553200A (en) * 2020-04-07 2020-08-18 北京农业信息技术研究中心 Image detection and identification method and device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王长旭: "水表读数识别系统的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 10, 15 October 2018 (2018-10-15), pages 138 - 550 *

Similar Documents

Publication Publication Date Title
CN111860573B (en) Model training method, image category detection method and device and electronic equipment
Laroca et al. Convolutional neural networks for automatic meter reading
Salomon et al. Deep learning for image-based automatic dial meter reading: Dataset and baselines
CN112052186B (en) Target detection method, device, equipment and storage medium
CN108229418B (en) Human body key point detection method and apparatus, electronic device, storage medium, and program
TW202009681A (en) Sample labeling method and device, and damage category identification method and device
CN112862757A (en) Weight evaluation system based on computer vision technology and implementation method
CN115131283A (en) Defect detection and model training method, device, equipment and medium for target object
CN114882213A (en) Animal weight prediction estimation system based on image recognition
CN114463567A (en) Block chain-based intelligent education operation big data plagiarism prevention method and system
CN114360038B (en) Weak supervision RPA element identification method and system based on deep learning
CN115880260A (en) Method, device and equipment for detecting base station construction and computer readable storage medium
CN115082776A (en) Electric energy meter automatic detection system and method based on image recognition
CN116188756A (en) Instrument angle correction and indication recognition method based on deep learning
Triantoro et al. Image based water gauge reading developed with ANN Kohonen
CN111931721B (en) Method and device for detecting color and number of annual inspection label and electronic equipment
CN116205905B (en) Power distribution network construction safety and quality image detection method and system based on mobile terminal
Shuo et al. Digital recognition of electric meter with deep learning
CN109784257B (en) Transformer thermometer detection and identification method
CN112487866A (en) Water meter type identification method and system
Vorozhtsova et al. System approach to development of intellectual information mobile system for electric power metering
CN115909151A (en) Method for identifying serial number of motion container under complex working condition
CN113642582A (en) Ammeter reading identification method and device, electronic equipment and storage medium
CN111242047A (en) Image processing method and apparatus, electronic device, and computer-readable storage medium
Wang et al. The comparison of canny and structured forests edge detection application in precision identification of pointer instrument

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