CN114998887B - Intelligent identification method for electric energy meter - Google Patents
Intelligent identification method for electric energy meter Download PDFInfo
- Publication number
- CN114998887B CN114998887B CN202210941114.0A CN202210941114A CN114998887B CN 114998887 B CN114998887 B CN 114998887B CN 202210941114 A CN202210941114 A CN 202210941114A CN 114998887 B CN114998887 B CN 114998887B
- Authority
- CN
- China
- Prior art keywords
- gray
- display area
- liquid crystal
- crystal display
- pixel point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/1444—Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/146—Aligning or centring of the image pick-up or image-field
- G06V30/147—Determination of region of interest
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
- Y04S20/30—Smart metering, e.g. specially adapted for remote reading
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Control Of Indicators Other Than Cathode Ray Tubes (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to an electric energy meter intelligent identification method, which comprises the following steps: the method comprises the steps of obtaining a plurality of continuous liquid crystal display area images and initial gray level distribution models of pixel points in the liquid crystal display area images, obtaining a first frame of electrified images and a liquid crystal display area after an electric energy meter is electrified, dividing pixel points in the liquid crystal display area into a first pixel point and a second pixel point, calculating a target gray level mean value of the first pixel point, updating the gray level mean value of the initial gray level distribution model to obtain the first gray level distribution model, obtaining target pixel points which do not meet the first gray level distribution model, carrying out connected domain analysis, determining the size of a single digital display area in the liquid crystal display area and each digital display area, obtaining the numerical value of the digital display area of each frame of electrified images, and obtaining the electric quantity display quantity of the electric energy meter in each frame of electrified images.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an intelligent identification method for an electric energy meter.
Background
As technology advances, conventional mechanical electricity meters are gradually being replaced with smart digital display meters that automatically recognize their own numbers and transmit them to a control system.
However, limited by regional factors and technical factors, some electric meters cannot realize automatic data acquisition, only manual meter reading by workers can be arranged, the efficiency of manual meter reading is low, and meter reading errors easily occur, so that with the development of artificial intelligence, workers only need to acquire images of the electric energy meters, and can realize digital extraction and identification of the electric energy meters through an image processing technology, thereby reducing the requirement of data acquisition.
Therefore, in the prior art, when an electric energy meter is processed by using an image processing technology, the identification of the number of electric meters is mainly realized by using a threshold segmentation technology, for example, as disclosed in patent No. CN110084241A, a longitudinal projection method is mainly used in the process of acquiring the cut-off position of each number, and the cut-off position of each number is selected by setting a fixed pixel number threshold, so as to determine a number area.
Therefore, the present invention needs to provide an intelligent identification method for an electric energy meter to solve the above problems.
Disclosure of Invention
The invention provides an intelligent identification method for an electric energy meter, which aims to solve the problem of low identification precision of the conventional electric quantity readings.
The intelligent identification method for the electric energy meter adopts the following technical scheme:
acquiring a plurality of continuous non-electrified liquid crystal display area images of the electric energy meter, and acquiring an initial gray level distribution model of each pixel point according to gray levels of the pixel points at the same position in the plurality of non-electrified liquid crystal display area images;
acquiring a first frame of electrified image after the electric energy meter is electrified, acquiring a liquid crystal display area in the first frame of electrified image, and dividing pixel points in the liquid crystal display area into first pixel points which do not meet an initial gray level distribution model and second pixel points which meet the initial gray level distribution model according to the gray level value of each pixel point in the liquid crystal display area;
acquiring Euclidean distances corresponding to each first pixel point and all second pixel points, calculating a target gray level mean value corresponding to the first pixel point according to the Euclidean distance corresponding to each first pixel point, a gray level value, a gray level mean value of an initial gray level distribution model and a gray level variance, and updating the gray level mean value of the initial gray level distribution model corresponding to the first pixel point according to the target gray level mean value corresponding to each first pixel point to obtain a first gray level distribution model;
acquiring pixel points of which the gray values in the liquid crystal display area in each electrified image do not meet the first gray distribution model as target pixel points, analyzing the connected domains of all the target pixel points in the next electrified image of the first electrified image to obtain a plurality of connected domains, determining the size of a single digital display area in the liquid crystal display area according to the coordinates of the target pixel points in the connected domains of the next electrified image, and acquiring all the digital display areas;
acquiring a numerical value corresponding to each digital display area in the next frame of electrified image according to the numerical value corresponding to each digital display area of the first frame of electrified image and the connected domain in each digital display area of the next frame of electrified image, and so on to acquire the numerical value of the digital display area of each frame of electrified image;
and acquiring the electric quantity readings of the electric energy meters in the corresponding frame of power-on images according to the numerical value of the digital display area of each frame of power-on image.
Preferably, the step of obtaining an initial gray distribution model of each pixel point according to the gray values of the pixel points at the same position in the gray images of the plurality of frames of unpowered liquid crystal display area images includes:
carrying out single Gaussian model fitting on gray values of pixel points at the same positions in gray images of a plurality of frames of unpowered liquid crystal display area images by using an EM (effective magnetic field) algorithm to obtain Gaussian models corresponding to the pixel points;
and taking the Gaussian model corresponding to each pixel point as an initial gray distribution model of the corresponding pixel point.
Preferably, the step of acquiring the liquid crystal display region in the first frame power-on image includes:
acquiring a gray mean value and a variance of an initial gray distribution model corresponding to each pixel point;
acquiring a gray distribution range corresponding to the initial gray distribution model according to the gray mean and the variance of the initial gray distribution model;
acquiring pixel points of which the gray values do not belong to a gray distribution range in a first frame of electrified image;
acquiring the maximum circumscribed rectangle of all pixel points of which the gray values do not belong to the gray distribution range in the first frame of electrified image;
and taking the maximum external rectangle as a liquid crystal display area.
Preferably, the step of dividing the pixels in the liquid crystal display area into first pixels which do not satisfy the initial gray distribution model and second pixels which satisfy the initial gray distribution model according to the gray value of each pixel in the liquid crystal display area comprises:
acquiring a gray distribution range of an initial gray distribution model corresponding to each pixel point in a liquid crystal display area;
taking pixel points in the liquid crystal display area, of which the gray values do not belong to the gray distribution range of the corresponding initial gray distribution model, as first pixel points;
and taking the pixel points of which the gray values in the liquid crystal display area belong to the gray distribution range of the initial gray distribution model corresponding to the pixel points as second pixel points.
Preferably, the formula of the target gray level mean value corresponding to each first pixel point is calculated according to the euclidean distance, the gray level value corresponding to each first pixel point, the gray level mean value and the gray level variance of the initial gray level distribution model:
in the formula (I), the compound is shown in the specification,
indicating the first in the liquid crystal display region
A target gray level mean value corresponding to each first pixel point;
Preferably, the step of determining the size of a single digital display area in the liquid crystal display area according to the coordinates of the target pixel point in the connected domain of the next frame of power-on image includes:
acquiring position coordinates of all target pixel points of each connected domain in a next electrified image of the first electrified image;
acquiring a maximum abscissa, a maximum ordinate, a minimum abscissa and a minimum ordinate in position coordinates of target pixel points of all connected domains;
and acquiring the size of a single digital display area in the liquid crystal display area according to the maximum abscissa, the maximum ordinate, the minimum abscissa and the minimum ordinate.
Preferably, the step of obtaining the numerical value corresponding to each digital display area in the next frame of electrified image according to the numerical value corresponding to each digital display area in the first frame of electrified image and the connected domain in each digital display area in the next frame of electrified image comprises;
acquiring a difference value area between a connected area in a next frame of electrified image of the first frame of electrified image and a corresponding area in the first frame of electrified image, wherein the numerical value of a digital display area of the first frame of electrified image is 0;
and determining the numerical value corresponding to each digital display area in the next frame of electrified image according to the difference area.
The beneficial effects of the invention are: the invention relates to an intelligent identification method of an electric energy meter, which comprises the steps of obtaining an unpowered liquid crystal display area image of the electric energy meter and an initial gray distribution model and a first gray distribution model of each pixel point corresponding to an electrified image, determining a digital display area in the liquid crystal display area by utilizing the characteristic that the gray of the liquid crystal display area changes after the electrified image is electrified, and then judging the pixel points with changed gray in the digital display area of each electrified image according to the first gray distribution model, thereby determining the change condition from a previous frame image to the current frame electrified image according to the pixel points with changed gray, further determining a numerical value in each digital display area and further determining the electric quantity indicating number of the electrified image of the current frame.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic structural diagram of an embodiment of an intelligent identification method for an electric energy meter according to the present invention;
FIG. 2 is a diagram illustrating a change in numerical values of a digital display area from a first frame power-on image to a second frame power-on image in an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
An embodiment of an intelligent identification method for an electric energy meter according to the present invention is applicable to a scenario in which real-time detection is performed from when the electric energy meter is installed, and the method is used for detecting display areas of the electric energy meter with different sizes, as shown in fig. 1, and the method includes:
s1, obtaining a plurality of continuous non-electrified liquid crystal display area images of the electric energy meter, and obtaining an initial gray level distribution model of each pixel point according to gray levels of the pixel points at the same position in the plurality of non-electrified liquid crystal display area images.
Specifically, in the embodiment, a camera is arranged at a position right opposite to an electric energy meter to be installed, an image of the installed electric energy meter is collected through the camera, a non-electrified liquid crystal display area image is obtained according to the image of the electric energy meter, a threshold segmentation technology adopted when the non-electrified liquid crystal display area image of the electric energy meter is obtained cuts the non-electrified liquid crystal display area image from the image of the electric energy meter, namely the collected non-electrified liquid crystal display area image of the electric energy meter is the non-electrified liquid crystal display area image of the newly installed electric energy meter, in order to avoid the influence of illumination on gray values of pixel points in the image of the outdoor electric energy meter, the embodiment utilizes an EM algorithm to perform single-gaussian model fitting on gray values of pixel points at the same position in gray images of multi-frame non-electrified liquid crystal display area images to obtain gaussian models corresponding to the pixel points, and uses the gaussian models corresponding to the gray values as initial gray distribution models corresponding to the pixel points, it is required to explain that the single-gaussian model is used to perform fitting on gray value changes of the pixel points, the gray values of the pixel points in a certain range, and therefore, the influence of illumination can be avoided to a certain extent.
S2, acquiring a first frame of electrified image after the electric energy meter is electrified, acquiring a liquid crystal display area in the first frame of electrified image, and dividing pixel points in the liquid crystal display area into first pixel points which do not meet an initial gray distribution model and second pixel points which meet the initial gray distribution model according to the gray value of each pixel point in the liquid crystal display area.
Specifically, it should be noted that, in this embodiment, the detection is started from a new electric energy meter, that is, the numerical value of the digital display area of the first frame of the electrified image after the electric energy meter is electrified is 0, so that the liquid crystal display area is obtained according to the characteristic that the gray scale of the liquid crystal display area after being electrified can be greatly changed, and the bar code area of the electric energy meter and the area of the housing of the electric energy meter do not change before and after being electrified.
The process of acquiring the liquid crystal display area comprises the following steps: acquiring a gray mean value and a variance of an initial gray distribution model corresponding to each pixel point; acquiring a gray distribution range corresponding to the initial gray distribution model according to the gray mean and the variance of the initial gray distribution model, wherein the gray distribution range of the initial gray distribution model is as follows because the initial gray distribution model is already described as a gaussian model in the step S1 and the gaussian model is a normal distribution model:
wherein, in the process,
is shown as
The gray average value of the initial gray distribution model corresponding to each pixel point,
denotes the first
The gray variance of the initial gray distribution model corresponding to each pixel point, so that the gray value in the first frame of electrified image acquired first is notPixel points belonging to a gray scale distribution range; acquiring the maximum external rectangle of all pixel points of which the gray values do not belong to the gray distribution range in the first frame of electrified image; it should be noted that, in this embodiment, a pixel point that a gray value of a first frame of powered image after the power meter is powered on cannot meet a gray distribution range of a corresponding initial gray distribution model is regarded as a pixel point whose gray value changes after the power meter is powered on, and therefore, the pixel point is regarded as a pixel point of a liquid crystal display screen for displaying information content, so as to determine a liquid crystal display area.
Specifically, since not every pixel point in the liquid crystal display region will have a gray level change, the pixel points in the liquid crystal display region need to be divided into two types, one type of pixel point with unchanged gray level and one type of pixel point with changed gray level, so that the gray level distribution range of the initial gray level distribution model corresponding to every pixel point in the liquid crystal display region is obtained first; taking a pixel point in the liquid crystal display area, of which the gray value does not belong to the gray distribution range of the initial gray distribution model corresponding to the pixel point, as a first pixel point, and the first pixel point does not satisfy the gray distribution range of the initial gray distribution model of the first pixel point, so that the embodiment considers that the gray value of the first pixel point changes; and taking the pixel points of which the gray values belong to the gray distribution range of the corresponding initial gray distribution model in the liquid crystal display area as second pixel points, wherein the second pixel points are subjected to gray change, so that the gray values of the second pixel points meet the gray distribution range of the corresponding initial gray distribution model.
S3, obtaining Euclidean distances corresponding to each first pixel point and all second pixel points, calculating a target gray level mean value corresponding to the first pixel point according to the Euclidean distance corresponding to each first pixel point, the gray level value, the gray level mean value of the initial gray level distribution model and the gray level variance, and updating the gray level mean value of the initial gray level distribution model corresponding to the first pixel point according to the target gray level mean value corresponding to each first pixel point to obtain the first gray level distribution model.
Specifically, since the gray value of the pixel point at each position in the electrified image is not changed, but when the electric energy meter is located outdoors, the collected electrified image is affected by natural illumination, so that the gray value of the pixel point at each position can generate gray fluctuation within a certain range, therefore, in step S1, the variance of the initial gray distribution model corresponding to each pixel point is generated by illumination change, but the illumination change condition at each position is not changed, that is, when a pixel point on the liquid crystal display region becomes information displayed in the liquid crystal display region, the gray value of the pixel point changes relative to that when the electric energy meter is not electrified, and the range of the gray fluctuation at the position does not change during the working process of the electric energy meter, that is, the variance of the gray distribution model corresponding to the pixel point does not change, and the gray value of the pixel point of the current display information is the gray value of the display information under the comprehensive influence of illumination, and is not the normal gray value thereof, the gray value of the current pixel point is directly used as the target gray value mean value to update the gray value of the initial gray distribution model, which is likely to cause the gray distribution of the pixel point to shift, and further, and the gray value of the electric energy meter may not change due to the first gray value of the electric energy meter.
Based on this, in order to ensure the accuracy of electric quantity reading identification, when the gray value of the pixel itself has a large gray variation, the gray value of each display information pixel (the first pixel in the present invention) needs to be updated according to the gray value and the relative position of the non-display information pixel (i.e. the second pixel in the present invention) in the liquid crystal display region, specifically, a formula for calculating the target gray average value corresponding to each first pixel according to the euclidean distance, the gray value corresponding to each first pixel, and the gray average value and the gray variance of the initial gray distribution model is provided:
in the formula (I), the compound is shown in the specification,
indicating the first in the liquid crystal display region
A target gray level mean value corresponding to each first pixel point;
in the formula, use is made of
Is shown in the liquid crystal display region
A second pixel point corresponding to the first pixel point
The relative size between the initial gray distribution models of the second pixel points is expressed
The gray distribution in the gray value range of the electric energy meter accounts for the proportion of the gray distribution range of the initial gray distribution model, so that the gray distribution in the gray value range of the electric energy meter is used for representing the gray deviation degree of the pixel point caused by the influence of illumination on the electrified image during collection, in the actual environment, the illumination intensity of each position on the surface of the electric energy meter is possibly not uniform, but the illumination intensity of the pixel points in a local range is relatively consistent, and the gray value of the second pixel point cannot be changed, so the gray value of the second pixel point can only be influenced by illumination, therefore, the deviation degree of the gray value caused by the influence of illumination on each second pixel point of the electric energy meter during the collection of the electrified image relative to the mean value of the initial gray distribution model is combined with the deviation degree of each first pixel pointAnd the distance between the two pixel points and each first pixel point is used for judging the gray value of the first pixel point relative to the actual gray average value when the electrified image is collected, so that the gray average value of the initial gray distribution model at each position in the liquid crystal display area of the electric energy meter is updated according to the formula, and the updated first gray distribution model of each first pixel point is obtained.
And S4, acquiring pixel points of which the gray values in the liquid crystal display area in each frame of electrified image do not meet the first gray distribution model and serving as target pixel points, analyzing connected domains of all the target pixel points in the next frame of electrified image of the first frame of electrified image to obtain a plurality of connected domains, determining the size of a single digital display area in the liquid crystal display area according to the coordinates of the target pixel points in the connected domains of the next frame of electrified image, and acquiring all the digital display areas.
Specifically, the distribution condition of the pixel points in the liquid crystal display area in each electrified image is analyzed by using the first gray scale distribution model obtained in the step S3, when the gray scale value of the pixel point does not satisfy the first gray scale distribution model, it is indicated that the pixel point has large gray scale change, it needs to be noted that, in the actual working process of the electric energy meter, the relevant character part of the liquid crystal display area does not change, and only the indication number corresponding to the electric quantity changes, so that the certain number of the large gray scale change of the liquid crystal display area is the electric quantity indication number, therefore, in this embodiment, the pixel point whose gray scale value does not satisfy the first gray scale distribution model in the liquid crystal display area in each electrified image is firstly selected and used as the target pixel point, the target pixel point is the pixel point whose gray scale changes, so that the connected domain analysis is firstly performed on the target pixel point to obtain a plurality of connected domains, the size of a single digital display area in the liquid crystal display area is determined according to the coordinates of the target pixel point in the connected domain of the next electrified image of the first frame image, wherein the single digital display area in the liquid crystal display area determined according to the coordinates of the connected domain of the connected image of the next electrified frame image of the next electrified image of the first frame includes the step: acquiring position coordinates of all target pixel points of each connected domain in a next electrified image of the first electrified image; acquiring a maximum abscissa, a maximum ordinate, a minimum abscissa and a minimum ordinate in position coordinates of target pixel points of all connected domains; the size of a single digital display area in the liquid crystal display area is obtained according to the maximum abscissa, the maximum ordinate, the minimum abscissa and the minimum ordinate, specifically, the longitudinal length of the single digital display area is the difference value between the maximum ordinate and the minimum ordinate, and the transverse length of the single digital display area is the difference value between the maximum abscissa and the minimum abscissa, so that the size of the single digital display area is determined.
And S5, acquiring a numerical value corresponding to each digital display area in the next frame of electrified image according to the numerical value corresponding to each digital display area of the first frame of electrified image and the connected domain in each digital display area of the next frame of electrified image, and so on to acquire the numerical value of the digital display area of each frame of electrified image.
Specifically, in the embodiment, a new electric energy meter is used for detection, so that a numerical value in each digital display area in a first frame of electrified image is determined to be 0, the electric energy meter is considered to be displayed well, then a connected domain formed by target pixel points of a next frame of electrified image of the first frame of electrified image is obtained, each connected domain is a stroke of a number according to the shape and size of the connected domain, a difference area between the connected domain in the next frame of electrified image of the first frame of electrified image and a corresponding digital display area in the first frame of electrified image is estimated, wherein the numerical value in the digital display area of the first frame of electrified image is 0; determining the numerical value corresponding to each digital display area in the next frame of electrified image according to the shape of the difference area; as shown in fig. 2, this process is a change process from when the value of the digital display area of the first frame of power-on image is 0 to when the value of the corresponding digital display area in the next frame of image of the acquired first frame of power-on image is 1.
And S6, acquiring the electric quantity readings of the electric energy meters in the corresponding frame of power-on images according to the numerical value of the digital display area of each frame of power-on image.
In particular, the reading of the electric energy meter is carried out fromLeft-right reading, therefore, the abscissa of the pixel point of the decimal part in the electricity quantity display of the electric energy meter is larger, the existing electric energy meter is often in a two-decimal form, when the electricity consumption is increased, the acquisition sequence of each digital display area is acquired according to the change sequence of each digital area, namely the first digit
The numerical value of each numerical display area is
，
Is shown as
The number of regions where the gray scale change occurs,
the larger the value of (A), the higher the corresponding digit, so the electricity quantity reading of the electric energy meter in each frame of electrified image is calculated according to the following formula:
in the formula (I), the compound is shown in the specification,
representing the electric quantity readings of the electric energy meter in the current frame electrifying image;
it should be noted that, the electric quantity reading of the electric energy meter relates to 1 digit after the decimal point, so that
A decimal value is indicated.
In summary, according to the intelligent identification method for the electric energy meter, the unpowered liquid crystal display area image of the electric energy meter and the initial gray level distribution model and the first gray level distribution model of each pixel point corresponding to the powered image are obtained, the digital display area in the liquid crystal display area is determined by using the characteristic that the gray level of the liquid crystal display area changes after being powered on, then the pixel point with the gray level change in the digital display area of each powered image is determined according to the first gray level distribution model, so that the change condition from the previous frame image to the current frame powered image is determined according to the pixel point with the gray level change, the numerical value in each digital display area is further determined, and the electric quantity indicator of the current frame powered image is further determined.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (7)
1. An electric energy meter intelligent identification method is characterized by comprising the following steps:
acquiring a plurality of continuous non-electrified liquid crystal display area images of the electric energy meter, and acquiring an initial gray level distribution model of each pixel point according to gray levels of the pixel points at the same position in the plurality of non-electrified liquid crystal display area images;
acquiring a first frame of electrified image after the electric energy meter is electrified, acquiring a liquid crystal display area in the first frame of electrified image, and dividing pixel points in the liquid crystal display area into first pixel points which do not meet an initial gray level distribution model and second pixel points which meet the initial gray level distribution model according to the gray level value of each pixel point in the liquid crystal display area;
acquiring Euclidean distances corresponding to each first pixel point and all second pixel points, calculating a target gray level mean value corresponding to the first pixel point according to the Euclidean distance corresponding to each first pixel point, a gray level value, a gray level mean value of an initial gray level distribution model and a gray level variance, and updating the gray level mean value of the initial gray level distribution model corresponding to the first pixel point according to the target gray level mean value corresponding to each first pixel point to obtain a first gray level distribution model;
acquiring pixel points of which the gray value in the liquid crystal display area in each frame of electrified image does not meet a first gray distribution model and serving as target pixel points, performing connected domain analysis on all the target pixel points in a next frame of electrified image of the first frame of electrified image to obtain a plurality of connected domains, determining the size of a single digital display area in the liquid crystal display area according to the coordinates of the target pixel points in the connected domains of the next frame of electrified image, and acquiring all the digital display areas;
acquiring a numerical value corresponding to each digital display area in the next frame of electrified image according to the numerical value corresponding to each digital display area of the first frame of electrified image and the connected domain in each digital display area of the next frame of electrified image, and so on to acquire the numerical value of the digital display area of each frame of electrified image;
and acquiring the electric quantity reading of the electric energy meter in the corresponding frame of the power-on image according to the numerical value of the digital display area of each frame of the power-on image.
2. The intelligent identification method for the electric energy meter according to claim 1, wherein the step of obtaining the initial gray distribution model of each pixel point according to the gray values of the pixel points at the same positions in the gray images of the liquid crystal display area images without electrification comprises the following steps:
carrying out single Gaussian model fitting on gray values of pixel points at the same position in gray images of a plurality of frames of unpowered liquid crystal display area images by utilizing an EM (effective magnetic field) algorithm to obtain Gaussian models corresponding to the pixel points;
and taking the Gaussian model corresponding to each pixel point as an initial gray distribution model of the corresponding pixel point.
3. The intelligent identification method for the electric energy meter according to claim 1, characterized in that the step of acquiring the liquid crystal display area in the first frame of the electrified image comprises the following steps:
acquiring a gray mean value and a variance of an initial gray distribution model corresponding to each pixel point;
acquiring a gray distribution range corresponding to the initial gray distribution model according to the gray mean and the variance of the initial gray distribution model;
acquiring pixel points of which the gray values do not belong to a gray distribution range in a first frame of electrified image;
acquiring the maximum external rectangle of all pixel points of which the gray values do not belong to the gray distribution range in the first frame of electrified image;
and taking the maximum external rectangle as a liquid crystal display area.
4. The intelligent identification method of the electric energy meter according to claim 1, wherein the step of dividing the pixel points in the liquid crystal display area into first pixel points which do not satisfy the initial gray distribution model and second pixel points which satisfy the initial gray distribution model according to the gray value of each pixel point in the liquid crystal display area comprises:
acquiring a gray distribution range of an initial gray distribution model corresponding to each pixel point in a liquid crystal display area;
taking pixel points in the liquid crystal display area, of which the gray values do not belong to the gray distribution range of the corresponding initial gray distribution model, as first pixel points;
and taking the pixel points of which the gray values in the liquid crystal display area belong to the gray distribution range of the initial gray distribution model corresponding to the pixel points as second pixel points.
5. The intelligent identification method for the electric energy meter according to claim 1, characterized in that a formula for calculating a target gray mean value corresponding to each first pixel point according to the Euclidean distance and the gray value corresponding to each first pixel point, and the gray mean value and the gray variance of the initial gray distribution model is as follows:
in the formula (I), the compound is shown in the specification,
indicating the first in the liquid crystal display region
A target gray average value corresponding to each first pixel point;
6. The intelligent identification method for the electric energy meter according to claim 1, characterized in that the step of determining the size of a single digital display area in the liquid crystal display area according to the coordinates of the target pixel point in the connected domain of the next frame of power-on image comprises the following steps:
acquiring position coordinates of all target pixel points of each connected domain in a next electrified image of the first electrified image;
acquiring a maximum abscissa, a maximum ordinate, a minimum abscissa and a minimum ordinate in position coordinates of target pixel points of all connected domains;
and acquiring the size of a single digital display area in the liquid crystal display area according to the maximum abscissa, the maximum ordinate, the minimum abscissa and the minimum ordinate.
7. The intelligent identification method for the electric energy meter according to claim 1, characterized in that the step of obtaining the numerical value corresponding to each digital display area in the next frame of electrified image according to the numerical value corresponding to each digital display area in the first frame of electrified image and the connected domain in each digital display area in the next frame of electrified image comprises;
acquiring a difference value area between a connected area in a next electrified image of the first electrified image frame and a corresponding area in the first electrified image frame, wherein the numerical value of a digital display area of the first electrified image frame is 0;
and determining the numerical value corresponding to each digital display area in the next frame of electrified image according to the difference area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210941114.0A CN114998887B (en) | 2022-08-08 | 2022-08-08 | Intelligent identification method for electric energy meter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210941114.0A CN114998887B (en) | 2022-08-08 | 2022-08-08 | Intelligent identification method for electric energy meter |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114998887A CN114998887A (en) | 2022-09-02 |
| CN114998887B true CN114998887B (en) | 2022-10-11 |
Family
ID=83022940
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210941114.0A Active CN114998887B (en) | 2022-08-08 | 2022-08-08 | Intelligent identification method for electric energy meter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114998887B (en) |
Citations (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013063820A1 (en) * | 2011-11-01 | 2013-05-10 | 青岛海信网络科技股份有限公司 | Method and device for positioning license plate image |
| CN106228159A (en) * | 2016-07-29 | 2016-12-14 | 深圳友讯达科技股份有限公司 | A kind of gauge table meter copying device based on image recognition and method thereof |
| 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 |
| CN108573261A (en) * | 2018-04-17 | 2018-09-25 | 国家电网公司 | A kind of read out instrument recognition methods suitable for Intelligent Mobile Robot |
| WO2019000653A1 (en) * | 2017-06-30 | 2019-01-03 | 清华大学深圳研究生院 | Image target identification method and apparatus |
| CN109409290A (en) * | 2018-10-26 | 2019-03-01 | 中国人民解放***箭军工程大学 | A kind of thermometer calibrating reading automatic recognition system and method |
| CN109977944A (en) * | 2019-02-21 | 2019-07-05 | 杭州朗阳科技有限公司 | A kind of recognition methods of digital water meter reading |
| CN110084241A (en) * | 2019-05-05 | 2019-08-02 | 山东大学 | A kind of ammeter automatic reading method based on image recognition |
| CN110210477A (en) * | 2019-05-24 | 2019-09-06 | 四川阿泰因机器人智能装备有限公司 | A kind of digital instrument Recognition of Reading method |
| CN110944237A (en) * | 2019-12-12 | 2020-03-31 | 成都极米科技股份有限公司 | Subtitle area positioning method and device and electronic equipment |
| CN112040198A (en) * | 2020-09-16 | 2020-12-04 | 南通天成现代农业科技有限公司 | Intelligent water meter reading identification system and method based on image processing |
| WO2020253119A1 (en) * | 2019-06-18 | 2020-12-24 | 深圳壹账通智能科技有限公司 | Graphic verification code recognizing method and apparatus, readable storage medium, and terminal device |
| CN112307824A (en) * | 2019-07-30 | 2021-02-02 | 深圳怡化电脑股份有限公司 | Method, device, system and readable medium for identifying tampering of bill number area |
| JP2021043836A (en) * | 2019-09-13 | 2021-03-18 | キヤノン株式会社 | Image processor, control method thereof, program |
| CN112686264A (en) * | 2020-12-31 | 2021-04-20 | 中广核研究院有限公司 | Digital instrument reading method and device, computer equipment and storage medium |
| CN113160222A (en) * | 2021-05-14 | 2021-07-23 | 电子科技大学 | Production data identification method for industrial information image |
| CN113191351A (en) * | 2021-02-01 | 2021-07-30 | 青岛理工大学 | Reading identification method and device of digital electric meter and model training method and device |
| CN113409353A (en) * | 2021-06-04 | 2021-09-17 | 杭州联吉技术有限公司 | Motion foreground detection method and device, terminal equipment and storage medium |
| CN114359538A (en) * | 2022-01-04 | 2022-04-15 | 重庆邮电大学 | Water meter reading positioning and identifying method |
| CN114387274A (en) * | 2022-03-24 | 2022-04-22 | 武汉昊月纸箱包装有限公司 | Carton defect detection method based on artificial intelligence |
| WO2022099598A1 (en) * | 2020-11-13 | 2022-05-19 | 浙江大学 | Video dynamic target detection method based on relative statistical features of image pixels |
| CN114549670A (en) * | 2022-02-23 | 2022-05-27 | 京东方数字科技有限公司 | Image processing method and image processing system |
| CN114627463A (en) * | 2022-03-29 | 2022-06-14 | 国网江苏省电力有限公司泰州供电分公司 | Non-contact power distribution data identification method based on machine identification |
| CN114782479A (en) * | 2022-06-17 | 2022-07-22 | 江苏乐尔环境科技股份有限公司 | Industrial equipment state monitoring and management method |
| CN114845180A (en) * | 2022-04-12 | 2022-08-02 | 福州新知智联科技有限公司 | Low-power-consumption digital identification remote meter reading device and identification method thereof |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170091572A1 (en) * | 2015-06-07 | 2017-03-30 | Apple Inc. | System And Method For Text Detection In An Image |
| CN107590498B (en) * | 2017-09-27 | 2020-09-01 | 哈尔滨工业大学 | Self-adaptive automobile instrument detection method based on character segmentation cascade two classifiers |
| US11036995B2 (en) * | 2019-01-25 | 2021-06-15 | Gracenote, Inc. | Methods and systems for scoreboard region detection |
-
2022
- 2022-08-08 CN CN202210941114.0A patent/CN114998887B/en active Active
Patent Citations (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013063820A1 (en) * | 2011-11-01 | 2013-05-10 | 青岛海信网络科技股份有限公司 | Method and device for positioning license plate image |
| CN106228159A (en) * | 2016-07-29 | 2016-12-14 | 深圳友讯达科技股份有限公司 | A kind of gauge table meter copying device based on image recognition and method thereof |
| WO2018018788A1 (en) * | 2016-07-29 | 2018-02-01 | 深圳友讯达科技股份有限公司 | Image recognition-based meter reading apparatus and method thereof |
| WO2019000653A1 (en) * | 2017-06-30 | 2019-01-03 | 清华大学深圳研究生院 | Image target identification method and apparatus |
| 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 |
| CN108573261A (en) * | 2018-04-17 | 2018-09-25 | 国家电网公司 | A kind of read out instrument recognition methods suitable for Intelligent Mobile Robot |
| CN109409290A (en) * | 2018-10-26 | 2019-03-01 | 中国人民解放***箭军工程大学 | A kind of thermometer calibrating reading automatic recognition system and method |
| CN109977944A (en) * | 2019-02-21 | 2019-07-05 | 杭州朗阳科技有限公司 | A kind of recognition methods of digital water meter reading |
| CN110084241A (en) * | 2019-05-05 | 2019-08-02 | 山东大学 | A kind of ammeter automatic reading method based on image recognition |
| CN110210477A (en) * | 2019-05-24 | 2019-09-06 | 四川阿泰因机器人智能装备有限公司 | A kind of digital instrument Recognition of Reading method |
| WO2020253119A1 (en) * | 2019-06-18 | 2020-12-24 | 深圳壹账通智能科技有限公司 | Graphic verification code recognizing method and apparatus, readable storage medium, and terminal device |
| CN112307824A (en) * | 2019-07-30 | 2021-02-02 | 深圳怡化电脑股份有限公司 | Method, device, system and readable medium for identifying tampering of bill number area |
| JP2021043836A (en) * | 2019-09-13 | 2021-03-18 | キヤノン株式会社 | Image processor, control method thereof, program |
| CN110944237A (en) * | 2019-12-12 | 2020-03-31 | 成都极米科技股份有限公司 | Subtitle area positioning method and device and electronic equipment |
| CN112040198A (en) * | 2020-09-16 | 2020-12-04 | 南通天成现代农业科技有限公司 | Intelligent water meter reading identification system and method based on image processing |
| WO2022099598A1 (en) * | 2020-11-13 | 2022-05-19 | 浙江大学 | Video dynamic target detection method based on relative statistical features of image pixels |
| CN112686264A (en) * | 2020-12-31 | 2021-04-20 | 中广核研究院有限公司 | Digital instrument reading method and device, computer equipment and storage medium |
| CN113191351A (en) * | 2021-02-01 | 2021-07-30 | 青岛理工大学 | Reading identification method and device of digital electric meter and model training method and device |
| CN113160222A (en) * | 2021-05-14 | 2021-07-23 | 电子科技大学 | Production data identification method for industrial information image |
| CN113409353A (en) * | 2021-06-04 | 2021-09-17 | 杭州联吉技术有限公司 | Motion foreground detection method and device, terminal equipment and storage medium |
| CN114359538A (en) * | 2022-01-04 | 2022-04-15 | 重庆邮电大学 | Water meter reading positioning and identifying method |
| CN114549670A (en) * | 2022-02-23 | 2022-05-27 | 京东方数字科技有限公司 | Image processing method and image processing system |
| CN114387274A (en) * | 2022-03-24 | 2022-04-22 | 武汉昊月纸箱包装有限公司 | Carton defect detection method based on artificial intelligence |
| CN114627463A (en) * | 2022-03-29 | 2022-06-14 | 国网江苏省电力有限公司泰州供电分公司 | Non-contact power distribution data identification method based on machine identification |
| CN114845180A (en) * | 2022-04-12 | 2022-08-02 | 福州新知智联科技有限公司 | Low-power-consumption digital identification remote meter reading device and identification method thereof |
| CN114782479A (en) * | 2022-06-17 | 2022-07-22 | 江苏乐尔环境科技股份有限公司 | Industrial equipment state monitoring and management method |
Non-Patent Citations (2)
| Title |
|---|
| Research on the Visual Recognition Method of;Lingqi Meng等;《 2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)》;20210405;全文 * |
| 基于图像的智能燃气表自动检测***设计;唐子成等;《电子测量技术》;20180831;第41卷(第16期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114998887A (en) | 2022-09-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113040034B (en) | Water-saving irrigation control system and control method | |
| CN108491959B (en) | Intelligent similar weather forecast method and system and information data processing terminal | |
| CN109800698A (en) | Icon detection method based on depth network | |
| CN111950812B (en) | Method and device for automatically identifying and predicting rainfall | |
| CN105160682B (en) | Method for detecting image edge and device | |
| CN111652089B (en) | Automatic water level identification method and system based on image processing | |
| CN113643276B (en) | Textile texture defect automatic detection method based on statistical analysis | |
| WO2020237540A1 (en) | Power grid user classification method and device, and computer-readable storage medium | |
| CN202548896U (en) | System for measuring steel packaging parameters | |
| CN114758249A (en) | Target object monitoring method, device, equipment and medium based on field night environment | |
| CN114627461A (en) | Method and system for high-precision identification of water gauge data based on artificial intelligence | |
| CN117037132A (en) | Ship water gauge reading detection and identification method based on machine vision | |
| CN114998887B (en) | Intelligent identification method for electric energy meter | |
| CN112699824B (en) | Method and device for detecting constant of electric energy meter and storage medium | |
| Shuo et al. | Digital recognition of electric meter with deep learning | |
| CN112396618A (en) | Grain boundary extraction and grain size measurement method based on image processing | |
| CN114078234B (en) | Detection method, system, storage medium and equipment for power supply area construction process | |
| CN115311443B (en) | Oil leakage identification method for hydraulic pump | |
| CN114742849B (en) | Leveling instrument distance measuring method based on image enhancement | |
| CN108955909A (en) | A kind of oil temperature gauge identification number reading method based on machine vision | |
| CN115713691A (en) | Pixel-level electric power popularity estimation method and device based on noctilucent remote sensing | |
| CN115546799A (en) | Backlight-free water meter liquid crystal display screen display number identification method under poor lighting condition | |
| CN114240924A (en) | Power grid equipment quality evaluation method based on digitization technology | |
| CN114882059A (en) | Dimension measuring method, device and equipment based on image analysis and storage medium | |
| CN114494680A (en) | Accumulated water detection method, device, equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |