CN111562540B - Electric energy meter detection monitoring method based on dynamic image recognition and analysis - Google Patents
Electric energy meter detection monitoring method based on dynamic image recognition and analysis Download PDFInfo
- Publication number
- CN111562540B CN111562540B CN202010416450.4A CN202010416450A CN111562540B CN 111562540 B CN111562540 B CN 111562540B CN 202010416450 A CN202010416450 A CN 202010416450A CN 111562540 B CN111562540 B CN 111562540B
- Authority
- CN
- China
- Prior art keywords
- electric energy
- energy meter
- image
- monitoring
- sensor
- 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
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/04—Testing or calibrating of apparatus covered by the other groups of this subclass of instruments for measuring time integral of power or current
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Abstract
The invention discloses an electric energy meter detection monitoring method based on dynamic image recognition and analysis, relates to the technical field of electric energy metering monitoring, solves the technical problem that the monitoring of large-range abnormal phenomena in an electric energy meter verification assembly line workshop is poor at present, and provides a novel solution. The invention organically combines the electronic sensor technology, the image processing technology, the data processing technology, the control technology and the computer technology, is applied to the electric energy meter detection field, realizes the intelligent and automatic monitoring of the detection technology, improves the monitoring strength of the electric energy meter detection site, realizes the extraction of the dynamic state information of the electric energy meter in the assembly line by using an improved difference method, acquires the site motion state information by dividing images, realizes the abnormal analysis of the electric energy meter detection site by adopting an ant colony algorithm, realizes the monitoring of the electric energy meter detection working condition, and simultaneously also realizes the monitoring of suspicious personnel.
Description
Technical Field
The invention relates to the technical field of electric energy metering, in particular to an electric energy meter detection monitoring method based on dynamic image recognition and analysis.
Background
In the technical field of electric energy meter detection, in particular to a large-scale assembly line detection process of an electric energy meter, component main bodies of a verification assembly line, such as a feeding machine, a mechanical transmission conveyor, a blanking machine, an image recognition seal device, a labeling machine, a power source, a standard meter and other components are all important components for verifying the electric energy meter, and an intelligent electric energy meter automatic assembly line verification system can realize the functions of automatic transmission, automatic connection and disconnection, automatic verification, automatic seal, labeling, intelligent sorting and warehousing and the like of the intelligent electric energy meter, realize the automation and the intellectualization of the whole verification process of the intelligent electric energy meter, effectively avoid manual errors, and improve the verification quality and efficiency of the intelligent electric energy meter. However, in the detection process, especially in the place where connection exists, accidents such as clamping, suspending and the like of the electric energy meter in operation are easy to occur due to the arrangement positions and the hardware arrangement conditions in the production line. The manual monitoring working condition not only needs to consume a large amount of manpower and increases the production cost of enterprises, but also is easy to cause errors due to long-term manual labor and fatigue. In the large-scale electric energy meter verification assembly line field, suspicious personnel appear, and the situation of stealing meter appears, so that a monitoring method is needed to specially monitor the production working condition of a large-scale production workshop and to monitor the suspicious personnel.
Disclosure of Invention
Aiming at the defects of the prior art, the invention discloses an electric energy meter detection monitoring method based on dynamic image recognition and analysis, which can realize the monitoring of the field working condition of a large-scale electric energy meter production line, effectively avoid abnormal accidents in the operation process of the electric energy meter, monitor suspicious personnel, realize the remote monitoring and realize the monitoring of the field working condition of the electric energy meter verification line.
In order to solve the technical problems, the invention adopts the following technical scheme:
an electric energy meter detection monitoring system based on dynamic image recognition and analysis is characterized in that: the monitoring system includes:
the device layer is internally provided with at least an electric energy meter calibrating device, an electric energy meter calibrating assembly line, sensor equipment or an electric energy meter calibrating system and is used for detecting electric energy meter data information, wherein the electric energy meter data information at least comprises current, voltage, power, vibration or ripple, and the sensor equipment at least comprises an envelope electric sensor, an infrared sensor, a speed sensor, an acceleration sensor, a GIS sensor, a vibration sensor, a ripple sensor, a temperature and humidity sensor, an angle sensor, a magnetic field sensor, a rotating speed sensor, an RFID tag, a GPS device, a ray radiation sensor, a heat-sensitive sensor, an energy consumption sensor or an M2M terminal;
the detection layer is internally provided with at least an image acquisition unit and is used for acquiring the verification condition of the electric energy meter in the factory building and the entering and exiting information of abnormal personnel in the factory building so as to realize unmanned detection of the electric energy meter detection site; the image acquisition unit at least comprises an industrial camera and an image sensor, and performs data transmission through a wired communication module at least comprising an RS485 communication module, an RS232 communication module, an infrared communication module or a carrier communication module and a wireless communication module at least comprising a TCP/IP communication module, a ZigBee wireless communication module, a GPRS communication module, a CDMA wireless communication module or a Bluetooth communication module;
the image processing layer is provided with at least an image recognition unit, the image recognition unit at least comprises an image analysis module and an image extraction module, wherein the image extraction module is used for extracting acquired image information, dividing the extracted image, and analyzing and calculating the divided image information through the image analysis module;
the monitoring layer is internally provided with at least a monitoring device, the monitoring device is connected with an alarm module and a display module, and unmanned, remote and intelligent monitoring is carried out on the electric energy meter detection site through analyzing and calculating the acquired images; wherein:
the output end of the equipment layer is connected with the input end of the detection layer, the output end of the detection layer is connected with the input end of the image processing layer, and the output end of the image processing layer is connected with the input end of the monitoring layer.
As a further technical scheme of the invention, the image sensor adopts an OV7670 module with an AL422B cache, the industrial camera is a CCD industrial camera, and the industrial camera is provided with a 360 ° rotary camera.
As a further technical scheme of the invention, the control component of the image recognition unit is an STM32 microprocessor, and the STM32 microprocessor adopts an STM32F103VET6 embedded control chip based on a Cortex-M3 kernel.
As a further technical scheme of the invention, the image extraction module and the image analysis module are respectively provided with an I/O interface for receiving digital signals and analog information.
As a further technical scheme of the invention, the alarm module is an audible and visual alarm module, and the display module is an LCD large-screen rolling display screen.
In order to solve the technical problems, the invention adopts the following technical scheme:
the utility model provides a electric energy meter detection monitoring method based on dynamic image recognition and analysis which is characterized in that: the method comprises the following steps:
(S1) data acquisition; acquiring data information of an electric energy meter detection site, wherein the data information comprises electric energy meter working condition information and site abnormal personnel activity information, then cleaning or preprocessing the acquired electric energy meter image information or data information, outputting pure electric energy meter site data detection information, and acquiring original data;
(S2) data transfer; the method comprises the steps of receiving and transmitting the operation conditions of electric energy meters in a factory building at different electric energy meter detection stations and the in-and-out conditions of field abnormal personnel in a wired communication or wireless communication mode;
(S3) data processing; extracting the acquired images by an improved difference method, and adopting an ant colony algorithm to realize the abnormality analysis of the electric energy meter detection site, so as to dynamically monitor the abnormality of the electric energy meter detection site;
(S4) electric energy meter field monitoring; through image analysis and processing, the electric energy meter is remotely and dynamically observed in the monitoring room to detect the site condition, and the monitoring site is displayed in real time.
As a further technical scheme of the invention, the improved difference method in the step (S3) is as follows:
let it be assumed that the monitored image is at coordinatesThe pixel value at +.>Use->Is expressed in->The department indicates->Setting the threshold value as +.>The following steps are:
when (when)When the environment is abnormal, the environment is indicated to have abnormal phenomenon;
when (when)When the environment is unchanged, the environment is indicated; wherein threshold->In the range of 0.1-1000.
As a further technical scheme of the present invention, the improved difference method in the step (S3) is a maximum inter-class variance method, where the maximum inter-class variance method is:
let the gray scale of the image be,/>The pixel at the position is marked as +.>In the decimated image, the total pixels are represented by the following formula: />;
In image segmentation, the gray threshold of the image is expressed asDividing the image into +_ according to the segmentation threshold>、Two kinds of->Gray value range +.>The gray probability value is expressed as: />The method comprises the steps of carrying out a first treatment on the surface of the Then->The gray value range of (2) is +.>The gray probability is +.>The method comprises the steps of carrying out a first treatment on the surface of the The average gray value of these two classes can be formulated as:
as a further technical scheme of the invention, the relation between the average values of the gray values of the two classes is as follows:
as a further technical solution of the present invention, it is assumed that the set threshold value is expressed as:
the result after image segmentation can be expressed as:
has the positive beneficial effects that:
the invention organically combines the electronic sensor technology, the image processing technology, the data processing technology, the control technology and the computer technology, is applied to the electric energy meter detection field, realizes the intelligent and automatic monitoring of the detection technology, improves the monitoring strength of the electric energy meter detection site, realizes the extraction of the dynamic state information of the electric energy meter in the production line by using an improved difference method, acquires the site motion state information by dividing images, realizes the abnormal analysis of the electric energy meter detection site by adopting an ant colony algorithm, realizes the monitoring of the electric energy meter detection working condition, and simultaneously realizes the monitoring of suspicious personnel.
Drawings
FIG. 1 is a schematic diagram of an electric energy meter detection monitoring system based on dynamic image recognition and analysis;
FIG. 2 is a schematic diagram of an image acquisition unit architecture in an electric energy meter detection monitoring system based on dynamic image recognition and analysis;
FIG. 3 is a schematic diagram of an image recognition unit architecture in an electric energy meter detection monitoring system based on dynamic image recognition and analysis according to the present invention;
FIG. 4 is a schematic flow chart of a method for detecting and monitoring an electric energy meter based on dynamic image recognition and analysis;
fig. 5 is a schematic diagram of an algorithm model in an electric energy meter detection monitoring method based on dynamic image recognition and analysis.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1 System
As shown in fig. 1-3, an electric energy meter detection monitoring system based on dynamic image recognition and analysis, the system comprises: an electric energy meter detection monitoring system based on dynamic image recognition and analysis, wherein the monitoring system comprises:
the device layer is internally provided with at least an electric energy meter calibrating device, an electric energy meter calibrating assembly line, sensor equipment or an electric energy meter calibrating system and is used for detecting electric energy meter data information, wherein the electric energy meter data information at least comprises current, voltage, power, vibration or ripple, and the sensor equipment at least comprises an envelope electric sensor, an infrared sensor, a speed sensor, an acceleration sensor, a GIS sensor, a vibration sensor, a ripple sensor, a temperature and humidity sensor, an angle sensor, a magnetic field sensor, a rotating speed sensor, an RFID tag, a GPS device, a ray radiation sensor, a heat-sensitive sensor, an energy consumption sensor or an M2M terminal;
the detection layer is internally provided with at least an image acquisition unit and is used for acquiring the verification condition of the electric energy meter in the factory building and the entering and exiting information of abnormal personnel in the factory building so as to realize unmanned detection of the electric energy meter detection site; the image acquisition unit at least comprises an industrial camera and an image sensor, and performs data transmission through a wired communication module at least comprising an RS485 communication module, an RS232 communication module, an infrared communication module or a carrier communication module and a wireless communication module at least comprising a TCP/IP communication module, a ZigBee wireless communication module, a GPRS communication module, a CDMA wireless communication module or a Bluetooth communication module;
the image processing layer is provided with at least an image recognition unit, the image recognition unit at least comprises an image analysis module and an image extraction module, wherein the image extraction module is used for extracting acquired image information, dividing the extracted image, and analyzing and calculating the divided image information through the image analysis module;
the monitoring layer is internally provided with at least a monitoring device, the monitoring device is connected with an alarm module and a display module, and unmanned, remote and intelligent monitoring is carried out on the electric energy meter detection site through analyzing and calculating the acquired images; wherein:
the output end of the equipment layer is connected with the input end of the detection layer, the output end of the detection layer is connected with the input end of the image processing layer, and the output end of the image processing layer is connected with the input end of the monitoring layer.
By adopting the technical scheme, the electronic sensor technology, the image processing technology, the data processing technology, the control technology and the computer technology are organically combined together and applied to the electric energy meter detection field, the intelligent and automatic monitoring of the detection technology is realized, the monitoring force of the electric energy meter detection site is improved.
In a further embodiment, referring specifically to fig. 2, the image sensor employs an OV7670 module with an AL422B cache, the industrial camera is a CCD industrial camera with a 360 ° rotating camera. In a specific application, the image acquisition unit may be capable of three-dimensional movement in X-axis, Y-axis and Z-axis directions in spatial three-dimensional coordinates, which may be achieved by arranging the image acquisition unit on a slideway with a slide and a guide rail. More specifically, motors connected with the sliding blocks are arranged on the X-axis, Y-axis and Z-axis arms respectively, and the sliding blocks are driven by the motors, so that the image acquisition unit can freely move in the directions of the X-axis, Y-axis and Z-axis, and dead-angle-free image acquisition is realized. In other embodiments, the shooting angle is adjusted through an automatic focusing camera, so that image information acquisition of the detection range of the electric energy meter in the electric energy meter production workshop is realized.
In a further embodiment, referring specifically to fig. 3, the control component of the image recognition unit is an STM32 microprocessor, and the STM32 microprocessor adopts an STM32F103VET6 embedded control chip based on Cortex-M3 kernel. The image extraction module is used for extracting characteristics of each image to be processed in an image set and a background image set in an electric energy meter detection workshop, the training module is used for training by using the characteristics to obtain the classifier for distinguishing objects from the background, the image generation module can also be used for outputting images, and finally generated images are displayed. The image extraction module and the image analysis module are respectively provided with an I/O interface for receiving digital signals and analog information, and the output of image data is realized through the arranged I/O interfaces.
In a further embodiment, the alarm module is an audible and visual alarm module, and the display module is an LCD large screen scrolling display screen.
Example 2 method
The utility model provides a electric energy meter detection monitoring method based on dynamic image recognition and analysis which is characterized in that: the method comprises the following steps:
(S1) data acquisition; acquiring data information of an electric energy meter detection site, wherein the data information comprises electric energy meter working condition information and site abnormal personnel activity information, then cleaning or preprocessing the acquired electric energy meter image information or data information, outputting pure electric energy meter site data detection information, and acquiring original data;
(S2) data transfer; the method comprises the steps of receiving and transmitting the operation conditions of electric energy meters in a factory building at different electric energy meter detection stations and the in-and-out conditions of field abnormal personnel in a wired communication or wireless communication mode;
(S3) data processing; extracting the acquired images by an improved difference method, and adopting an ant colony algorithm to realize the abnormality analysis of the electric energy meter detection site, so as to dynamically monitor the abnormality of the electric energy meter detection site; this technical scheme will be described in detail below.
Scheme one of image recognition
Firstly, dividing an image, as the on-site motion state is multi-target motion, and the electric energy meter in a pipeline dynamically changes position along with the time, when abnormal change information is extracted, after the moving image appears in a detection range, the change between adjacent frames of a monitoring image is obvious, the invention applies a difference method, and when the pixel information of the image extracted immediately before is expressed by a formula, the monitoring image is assumed to be in coordinatesThe pixel value at +.>Use->Is expressed in->The department indicates->Setting the threshold value as +.>The following steps are:
when (when)When +.>When the environment is unchanged, the environment is indicated. In the above calculation process, threshold +.>The method is characterized in that the method is set by a manager according to specific working occasions and daily experience accumulation, evaluation objects are different, and threshold settings are different, for example, the operation conditions of the electric energy meter on a production line are judged, and whether workshop personnel are abnormal or not is judged.
Image recognition scheme II
When the first image recognition scheme is adopted for calculation, the phenomenon of low precision and the like are easy to be caused by setting a threshold value, the method is utilized, the image segmentation is carried out by combining with the maximum inter-class variance method, and the gray scale range of the image is set asFor the convenience of calculation, will +.>The pixel at the position is marked as +.>In the decimated image, the total pixels are represented by the following formula:
the method comprises the steps of carrying out a first treatment on the surface of the The probability of each gray level in the image is assumed to be: />The method comprises the steps of carrying out a first treatment on the surface of the The average gray value may represent
The method comprises the steps of carrying out a first treatment on the surface of the In image division, let the gray threshold of the image be expressed as +.>Dividing the image into +_ according to the segmentation threshold>、/>Two kinds of->Gray value range +.>The gray probability value is expressed as: />The method comprises the steps of carrying out a first treatment on the surface of the Then->The gray value range of (2) is +.>The gray probability is +.>The method comprises the steps of carrying out a first treatment on the surface of the The average gray value of these two classes can be formulated as:
then there is the following relationship:
wherein the set threshold is formulated as: the method comprises the steps of carrying out a first treatment on the surface of the
The result after image segmentation can be expressed as:
and further acquiring the areas where two adjacent frames of suspected targets move in the pictures acquired by the electric energy meter detection sites through the segmented areas. The moving area of the suspicious object can be detected through the texture features, so that the judgment of the moving object is realized.
The image analysis method will be described below
The invention adopts ant colony algorithm to realize the abnormality analysis of the electric energy meter detection site, and assumes the extracted graphThe image information isEach pixel in the image is defined as +.>Wherein->The method comprises the steps of representing an image into a plurality of small pixels by ant elements, representing the gray level, gradient and field of the image by each ant, forming a three-dimensional vector, dividing the image into the plurality of small pixels, calculating the distance between the pixels by using a Euclidean distance formula, and representing the distance between the pixels by using the formula:
in the above-mentioned formula(s),representing arbitrary pixels in the decimated image>And->Distance between them.
The influence degree of different components of each pixel on the distance is determined by the information quantity, wherein the calculation formula of the information quantity can be expressed as follows:
in the above-mentioned formula(s),representing a plurality of small pixels divided, i.e. ant elements, in one implementationIn the example, a->The value of (2) can be 2-5, ">Expressed as a weighting factor>Represented as radius of cluster +.>Expressed as an information amount.
The probability formula for path selection may be:
in the above formula, 0 is the other case, indicating selectionTo->Probability of the path between, wherein ∈>Information represented as the accumulation of the individual pixels during the clustering process, < >>Expressed as an impact factor of the heuristic guidance function on path selection, wherein:
Because of the continuous movement of the field personnel, the information quantity on each pixel changes in real time, and the information quantity needs to be continuously adjusted, and the adjustment formula is as follows:
in the above-mentioned formula(s),indicating the degree of attenuation of the amount of information with the movement of the detection site, < >>Representing the increment of the information quantity in the new circulation path during the new movement, wherein +.>
Wherein the method comprises the steps ofIndicate->Only the amount of information left by the ant element in the new circulation path.
Through the algorithm, an abnormal information area is selected, wherein the abnormal area comprises working condition information, detection field device information and suspicious personnel information in the detection range of the electric energy meter. According to the invention, the dynamic image of a large-range observation area is obtained, and the dynamic image information is obtained through dynamic image analysis and processing, so that the abnormal signal is early warned.
(S4) electric energy meter field monitoring; through image analysis and processing, the electric energy meter is remotely and dynamically observed in the monitoring room to detect the site condition, and the monitoring site is displayed in real time.
In the step, the processed data information can be transmitted to an upper management center, so that real-time and online monitoring of the data can be realized. The electric energy meter detection site identification is facilitated, when the electric energy meter is stuck in a shell in the production line or due to the stagnation of faults of the electric energy meter, suspicious personnel walk, electric energy meter site detection can be effectively realized, and the normal running of the electric energy meter detection running water and the monitoring of the suspicious personnel in the site are facilitated.
While specific embodiments of the present invention have been described above, it will be understood by those skilled in the art that these specific embodiments are by way of example only, and that various omissions, substitutions, and changes in the form and details of the methods and systems described above may be made by those skilled in the art without departing from the spirit and scope of the invention. For example, it is within the scope of the present invention to combine the above-described method steps to perform substantially the same function in substantially the same way to achieve substantially the same result. Accordingly, the scope of the invention is limited only by the following claims.
Claims (2)
1. An electric energy meter detection monitoring system based on dynamic image recognition and analysis is characterized in that: the monitoring system includes:
the device layer is internally provided with at least an electric energy meter calibrating device, an electric energy meter calibrating assembly line, sensor equipment or an electric energy meter calibrating system and is used for detecting electric energy meter data information, wherein the electric energy meter data information at least comprises current, voltage, power, vibration or ripple, and the sensor equipment at least comprises an envelope electric sensor, an infrared sensor, a speed sensor, an acceleration sensor, a GIS sensor, a vibration sensor, a ripple sensor, a temperature and humidity sensor, an angle sensor, a magnetic field sensor, a rotating speed sensor, an RFID tag, a GPS device, a ray radiation sensor, a heat-sensitive sensor, an energy consumption sensor or an M2M terminal;
the detection layer is internally provided with at least an image acquisition unit and is used for acquiring the verification condition of the electric energy meter in the factory building and the entering and exiting information of abnormal personnel in the factory building so as to realize unmanned detection of the electric energy meter detection site; the image acquisition unit at least comprises an industrial camera and an image sensor, and performs data transmission through a wired communication module at least comprising an RS485 communication module, an RS232 communication module, an infrared communication module or a carrier communication module and a wireless communication module at least comprising a TCP/IP communication module, a ZigBee wireless communication module, a GPRS communication module, a CDMA wireless communication module or a Bluetooth communication module;
the image processing layer is provided with at least an image recognition unit, the image recognition unit at least comprises an image analysis module and an image extraction module, wherein the image extraction module is used for extracting acquired image information, dividing the extracted image, and analyzing and calculating the divided image information through the image analysis module;
extracting the acquired images by an improved difference method, and adopting an ant colony algorithm to realize the abnormality analysis of the electric energy meter detection site, so as to dynamically monitor the abnormality of the electric energy meter detection site;
let it be assumed that the monitored image is at coordinatesThe pixel value at +.>Use->Is expressed in->The place representsSetting the threshold value as +.>The following steps are:
when (when)When the environment is abnormal, the environment is indicated to have abnormal phenomenon;
when (when)When the environment is unchanged, the environment is indicated; wherein threshold->In the range of 0.1 to 1000;
the maximum inter-class variance method is as follows:
let the gray scale of the image be,/>The pixel at the position is marked as +.>In the decimated image, the total pixels are represented by the following formula: />;
In image segmentation, let the gray threshold of the image be denoted as i, and divide the image into segments according to the segmentation threshold、/>Two kinds of->Gray value range [ L ] 1, i]The gray probability value is expressed as: />The method comprises the steps of carrying out a first treatment on the surface of the Then->The gray value range of (1) is [ i+1, L 2 ]The gray probability is +.>The method comprises the steps of carrying out a first treatment on the surface of the The average gray value of these two classes can be formulated as: />
The relationship between the gray value averages of the two classes is:
the set threshold is formulated as:
the result after image segmentation can be expressed as:
the monitoring layer is internally provided with at least a monitoring device, the monitoring device is connected with an alarm module and a display module, and unmanned, remote and intelligent monitoring is carried out on the electric energy meter detection site through analyzing and calculating the acquired images; wherein: the output end of the equipment layer is connected with the input end of the detection layer, the output end of the detection layer is connected with the input end of the image processing layer, and the output end of the image processing layer is connected with the input end of the monitoring layer;
the image sensor adopts an OV7670 module with an AL422B cache, the industrial camera is a CCD industrial camera, and the industrial camera is provided with a 360-degree rotary camera, the control component of the image recognition unit is an STM32 microprocessor, the STM32 microprocessor adopts an STM32F103VET6 embedded control chip based on a Cortex-M3 kernel, and the image extraction module and the image analysis module are respectively provided with an I/O interface for receiving digital signals and analog information; the alarm module is an audible and visual alarm module, and the display module is an LCD large-screen rolling display screen;
the image acquisition unit performs three-dimensional movement in the directions of an X axis, a Y axis and a Z axis in the space three-dimensional coordinates, and is arranged on a slideway with a sliding block and a guide rail.
2. A method for monitoring an electric energy meter detection monitoring system based on dynamic image recognition and analysis is characterized in that: the method comprises the following steps:
(S1) data acquisition; acquiring data information of an electric energy meter detection site, wherein the data information comprises electric energy meter working condition information and site abnormal personnel activity information, then cleaning or preprocessing the acquired electric energy meter image information or data information, outputting pure electric energy meter site data detection information, and acquiring original data;
(S2) data transfer; the method comprises the steps of receiving and transmitting the operation conditions of electric energy meters in a factory building at different electric energy meter detection stations and the in-and-out conditions of field abnormal personnel in a wired communication or wireless communication mode;
(S3) data processing; extracting the acquired images by an improved difference method, and adopting an ant colony algorithm to realize the abnormality analysis of the electric energy meter detection site, so as to dynamically monitor the abnormality of the electric energy meter detection site;
(S4) electric energy meter field monitoring; through image analysis and processing, the electric energy meter is remotely and dynamically observed in the monitoring room to detect the site condition, and the monitoring site is displayed in real time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010416450.4A CN111562540B (en) | 2020-05-17 | 2020-05-17 | Electric energy meter detection monitoring method based on dynamic image recognition and analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010416450.4A CN111562540B (en) | 2020-05-17 | 2020-05-17 | Electric energy meter detection monitoring method based on dynamic image recognition and analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111562540A CN111562540A (en) | 2020-08-21 |
CN111562540B true CN111562540B (en) | 2023-04-28 |
Family
ID=72074762
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010416450.4A Active CN111562540B (en) | 2020-05-17 | 2020-05-17 | Electric energy meter detection monitoring method based on dynamic image recognition and analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111562540B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117635905A (en) * | 2023-12-13 | 2024-03-01 | 国网上海市电力公司 | Intelligent monitoring method for electric energy meter attachment quality based on image recognition algorithm |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN206146850U (en) * | 2016-09-21 | 2017-05-03 | 苏州工业园区慧吉彬自动化设备有限公司 | Automatic detection line |
CN206387742U (en) * | 2017-01-16 | 2017-08-08 | 东莞理工学院 | A kind of AOI detection means of use CCD images positioning |
CN108825941A (en) * | 2018-05-03 | 2018-11-16 | 长春工业大学 | A kind of Airborne Camera ground motion test device of multiaxis cooperative motion |
CN209471178U (en) * | 2018-12-26 | 2019-10-08 | 武汉新能源研究院有限公司 | A kind of automation plane impedance measurement device based on motion control and machine vision |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
SG119169A1 (en) * | 2003-01-20 | 2006-02-28 | Nanyang Polytechnic | Path searching system using multiple groups of cooperating agents and method thereof |
CN101286199A (en) * | 2007-09-14 | 2008-10-15 | 西北工业大学 | Method of image segmentation based on area upgrowth and ant colony clustering |
CN101620441B (en) * | 2009-08-05 | 2014-02-12 | 重庆百年通信设备有限公司 | Monitoring system in communication computer room |
CN102323564B (en) * | 2011-07-22 | 2014-06-18 | 浙江省电力公司 | Electric energy meter verification unit and working method thereof |
CN102508192A (en) * | 2011-10-31 | 2012-06-20 | 河南省电力公司计量中心 | System for detecting display of liquid crystal display screens of electric energy meters in batched mode |
CN102930280A (en) * | 2012-10-05 | 2013-02-13 | 中国电子科技集团公司第十研究所 | Method for identifying overhead high-voltage wire automatically from infrared image |
KR101533087B1 (en) * | 2015-02-09 | 2015-07-03 | 성균관대학교산학협력단 | Vehicular ad-hoc network routing method based on ant colony optimization and vehicular ad-hoc network device using the same |
CN105867267A (en) * | 2016-04-05 | 2016-08-17 | 江苏电力信息技术有限公司 | Method for automatically reporting instrument readings of distribution station room through image identification technology |
WO2017204750A1 (en) * | 2016-05-27 | 2017-11-30 | Nanyang Technological University | Method of assessing a performance of an electrochemical cell, and apparatus thereof |
CN107172395B (en) * | 2017-06-01 | 2019-10-11 | 青岛科技大学 | Workshop Internet-based monitors system and method |
CN109975740A (en) * | 2019-05-13 | 2019-07-05 | 广东省计量科学研究院(华南国家计量测试中心) | A kind of calibrating monitoring system of electric energy meter checking device |
-
2020
- 2020-05-17 CN CN202010416450.4A patent/CN111562540B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN206146850U (en) * | 2016-09-21 | 2017-05-03 | 苏州工业园区慧吉彬自动化设备有限公司 | Automatic detection line |
CN206387742U (en) * | 2017-01-16 | 2017-08-08 | 东莞理工学院 | A kind of AOI detection means of use CCD images positioning |
CN108825941A (en) * | 2018-05-03 | 2018-11-16 | 长春工业大学 | A kind of Airborne Camera ground motion test device of multiaxis cooperative motion |
CN209471178U (en) * | 2018-12-26 | 2019-10-08 | 武汉新能源研究院有限公司 | A kind of automation plane impedance measurement device based on motion control and machine vision |
Also Published As
Publication number | Publication date |
---|---|
CN111562540A (en) | 2020-08-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105894529B (en) | Parking space state detection method and apparatus and system | |
CN103454285A (en) | Transmission chain quality detection system based on machine vision | |
CN106092195A (en) | A kind of monitoring water environment system | |
CN110850723A (en) | Fault diagnosis and positioning method based on transformer substation inspection robot system | |
CN107024182A (en) | A kind of shield tunnel deformation wireless monitor system and method | |
CN109683609A (en) | A kind of electric intelligent inspection system and method | |
CN111562540B (en) | Electric energy meter detection monitoring method based on dynamic image recognition and analysis | |
CN110570520A (en) | substation maintenance safety distance monitoring method based on SLAM | |
CN110703760A (en) | Newly-increased suspicious object detection method for security inspection robot | |
CN110608716A (en) | Substation maintenance safety distance monitoring method based on SLAM | |
CN101833117A (en) | Intelligent vehicle safety vision detection device and motion target tracking method | |
CN112906602B (en) | Automatic identification device and identification method for electric quantity meter of power distribution cabinet based on image processing | |
CN107271446B (en) | Visual detection method for rubber wire of timing gear chamber of engine | |
CN104869369A (en) | Multi-angle electric video monitoring system | |
CN112702570A (en) | Security protection management system based on multi-dimensional behavior recognition | |
CN202141155U (en) | Automatic monitoring system air conditioner operation | |
CN113420695A (en) | Rapid flame detection method based on MSRCR and YOLOv4-Tiny algorithm | |
CN203164738U (en) | Machine vision control system based on cloud computing | |
Wang et al. | Offset Detection of Grate Trolley’s Side Plate Based on YOLOv4 | |
CN202004914U (en) | Intelligent video image quality automatic analysis system | |
CN112381053A (en) | Environment-friendly monitoring system with image tracking function | |
CN111780674A (en) | Visual detection system based on image processing and machine learning | |
Huang et al. | Smoke identification of low-light indoor video based on support vector machine | |
JP3295482B2 (en) | Moving object detection method and apparatus | |
CN215643036U (en) | Intelligent monitoring and alarming system for oil leakage of oil field |
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 |