CN118247239A - Electric energy meter abnormality detection method based on visual recognition - Google Patents
Electric energy meter abnormality detection method based on visual recognition Download PDFInfo
- Publication number
- CN118247239A CN118247239A CN202410333365.XA CN202410333365A CN118247239A CN 118247239 A CN118247239 A CN 118247239A CN 202410333365 A CN202410333365 A CN 202410333365A CN 118247239 A CN118247239 A CN 118247239A
- Authority
- CN
- China
- Prior art keywords
- electric energy
- energy meter
- software
- visual identification
- template
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000000007 visual effect Effects 0.000 title claims abstract description 42
- 230000005856 abnormality Effects 0.000 title claims abstract description 16
- 238000001514 detection method Methods 0.000 title claims abstract description 16
- RVCKCEDKBVEEHL-UHFFFAOYSA-N 2,3,4,5,6-pentachlorobenzyl alcohol Chemical compound OCC1=C(Cl)C(Cl)=C(Cl)C(Cl)=C1Cl RVCKCEDKBVEEHL-UHFFFAOYSA-N 0.000 claims abstract description 30
- 238000012790 confirmation Methods 0.000 claims description 7
- 238000000034 method Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000005611 electricity Effects 0.000 claims description 6
- 238000012986 modification Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 238000005286 illumination Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30141—Printed circuit board [PCB]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an electric energy meter abnormality detection method based on visual identification, which is characterized in that PCBA on an electric energy meter is compared through visual identification hardware and visual identification software, and places with abnormality on a PCBA board of the electric energy meter can be rapidly identified, wherein the visual identification software design flow is as follows: configuring electric energy meter manufacturer and model information in software; disassembling normal electric energy meters of corresponding manufacturers and models, and installing PCBA boards to vision recognition position software to control cameras to take pictures; taking the photographed picture as a template in software, forming an electric energy meter template library, disassembling an electric energy meter suspected to be modified and disassembled on site, installing the disassembled PCBA board at an identification position, and finding a template corresponding to the manufacturer and the model from the software; the software performs comparison and identification through an algorithm; and on visual recognition software, identifying suspicious points and scoring the suspicious points according to the similarity matching degree.
Description
Technical Field
The invention belongs to the technical field of power systems, and particularly relates to an electric energy meter abnormality detection method based on visual identification.
Background
The electric energy meter is installed on the customer site and used for metering the electric energy consumed by the electric power customer and charging. Some electric power customers can destroy the electric energy meter through various channels to influence the metering, including disassembling the electric energy meter, changing internal components and the like.
The electric power company can check and lock suspected users through the system and the site, can tear the site electric energy meter back to analysis to suspected electric energy meter component steal damaged, disassemble the electric energy meter after tearing back, manually observe which place in the electric energy meter is manually operated, including changing resistance, welding wires and the like, and after the general judgment, the electric energy meter is measured and confirmed by an instrument. The manufacturers and types of electric energy meters are very numerous, and the memory and the delicacy of staff are very tested by naked eyes.
The primary analysis after the electric energy meter is disassembled at present basically depends on the naked eyes, so that the abnormality such as obvious wiring and the like can be identified by naked eyes, and the abnormality such as resistor replacement and the like is not very obvious modification, so that the identification is difficult due to the fact that the electric energy meter manufacturer and the type are relatively more, errors can occur, and further analysis and confirmation are influenced.
The automatic mode needs to be considered for rapid and accurate identification, manufacturers and types of electric energy meters are very many, visual field spaces of PCBA boards of different electric energy meters need to be considered, management of PCBA template libraries of the electric energy meters is needed, and extraction of PCBA feature points of different types is needed.
Disclosure of Invention
In order to solve the defects and shortcomings in the prior art, the invention provides the visual identification-based electric energy meter anomaly detection method which is used for comparing and identifying the detached single-three-phase electric energy meter PCBA through visual identification software and hardware, and greatly improves the identification accuracy and the identification efficiency relative to naked eye inspection.
The invention provides the following technical scheme: the utility model provides an electric energy meter anomaly detection method based on visual identification, compares PCBA on the electric energy meter through visual identification hardware + visual identification software, can discern the place that has the anomaly on the electric energy meter PCBA board fast, wherein visual identification hardware includes supporting subassembly and the light source of making a video recording that uses, and wherein visual identification software design flow is as follows:
The method comprises the steps of R1, configuring manufacturer and model information of the electric energy meter in software;
R2, disassembling the normal electric energy meter corresponding to the manufacturer and the model, and installing the PCBA board to the visual identification position;
S3, controlling a camera to take pictures by software;
R4, taking the photographed picture as a template in software to form an electric energy meter template library;
R5. dismantling the electric energy meter of suspected modification components disassembled on site to steal electricity, and installing the dismantled PCBA board at the identification position;
r6. finding out templates corresponding to the manufacturer and the model from software;
R7. software performs comparison and identification through an algorithm;
r8. on visual recognition software, identify suspicious points and score suspicious points according to similarity match.
Preferably, the camera assembly adopts a matched camera and a lens, the camera is 2000 ten thousand pixels, and the frame rate is not lower than 19 frames; the lens is arranged below the camera, and the working distance of the lens is 450mm; the light source adopts annular white surface light, so that the illumination average property is ensured to the maximum extent; the distance from the lens to the bottom of the light source is 35mm, and the distance from the light source to the surface of the identification object is 415mm.
Preferably, the template storage in the step R4 is not distorted, and is stored in a mode of an image file, and meanwhile, the template storage is managed in a database according to a manufacturer, a model and a storage path.
An electric energy meter abnormality detection method based on visual identification comprises the following specific steps:
s1, a camera acquires an image: acquiring an image through a camera;
s2, finding a template image from a software library: finding the current manufacturer and model in a PCBA template library of the electric energy meter configured by software, and automatically importing a stored electric energy meter template;
s3, preprocessing two images: graying, denoising and edge enhancement are respectively and sequentially carried out on the acquired image and the template image;
S4, extracting features from the template image: extracting the main detected resistance characteristics;
S5, performing feature matching with the acquired image: identifying on the acquired image by the identified features, wherein the deviation value needs to be considered;
S6, identifying a difference point: and comparing the difference points of the two analyzed pictures, and marking on the acquired images.
Preferably, in step S4, the resistor text is used as a main feature point in the feature definition, and the text on the resistor is identified and matched with the text position, and the text position is opposite to the reference zero point of the board, and the reference zero point is the position of the round hole in the upper left corner of each board.
Preferably, the resistance character identifiers of the template image are identified in the software, and if 10 resistance character identifiers are provided, the resistance character identifiers are marked as follows ：Text1->(X1,Y1)、Text2->(X2,Y2)、Text3->(X3,Y3)、Text4->(X4,Y4)、Text5->(X5,Y5)、Text6->(X6,Y6)、Text7->(X7,Y7)、Text8->(X8,Y8)、Text9->(X9,Y9)、Text10->(X10,Y10);
Wherein Text is specific Text content, X is X-axis coordinate relative to a reference, Y is Y-axis coordinate relative to the reference, and the unit is mm; and (3) carrying out weighted calculation through relative coordinates X and Y, calculating Z=X, 10000+Y, establishing a sequence corresponding to the Text through Z values, and sequencing from small to large according to the Z values:
Z1->Text1,Z2->Text2,Z3->Text3,Z4->Text4,Z5->Text5,Z6->Text6,Z7->Te xt7,Z8->Text8,Z9->Text9,Z10->Text10.
Preferably, the acquired image resistance text marks are identified in software, and if 10 are used, the acquired image resistance text marks are marked in sequence ：Text1'->(X1',Y1')、Text2'->(X2',Y2')、Text3'->(X3',Y3')、Text4'->(X4',Y4')、Text5'->(X5',Y5')、Text6'->(X6',Y6')、Text7'->(X7',Y7')、Text8'->(X8',Y8')、Text9'->(X9',Y9')、Text10'->(X10',Y10');
Weighting calculation is carried out through relative coordinates X ', Y', Z '=X' =10000+Y 'is calculated, a sequence corresponding to Text' is established through a Z 'value, and the sequence is ordered from small to large according to the Z' value Z1'->Text1',Z2'->Text2',Z3'->Text3',Z4'->Text4',Z5'->Text5',Z6'->Text6',Z7'->Text7',Z8'->Text8',Z9'->Text9',Z10'->Text10'.
Preferably, firstly, calculating the range of a weighted Z according to the maximum deviation of X and Y by 1mm, performing traversal comparison of relative Z points and Z-point Text, and then performing confirmation comparison according to the difference between the template and the acquired image Z and whether the two Z-point Text are consistent or not, finally positioning out the resistance position with the difference, and marking by adopting a red square frame, thereby facilitating the confirmation by manpower.
The beneficial effects of the invention are as follows:
According to the invention, the sizes and the recognition visual fields of the PCBA plates of the single-phase and three-phase electric energy meters are comprehensively considered, and the detached PCBA plates of the single-phase and three-phase electric energy meters are compared and recognized through visual recognition software and hardware, so that the recognition accuracy and the recognition efficiency are greatly improved relative to naked eye inspection.
Drawings
FIG. 1 is a flow chart of a design of recognition vision software in the present invention;
FIG. 2 is an overall flow chart of the present invention;
FIG. 3 is a diagram of a visual recognition hardware configuration in accordance with the present invention;
FIG. 4 is a PCBA diagram of an electric energy meter to be identified in the invention;
fig. 5-7 are PCBA diagrams of the electric energy meter compared by software in the present invention.
Detailed Description
The invention will be described in further detail with reference to the accompanying drawings, which are not intended to limit the scope of the invention.
The invention discloses an abnormal electricity utilization detection method of an electric energy meter based on visual identification. The PCBA of the electric energy meter to be identified is shown in fig. 4.
Wherein the visual recognition hardware design is as shown in fig. 3: the size and the recognition visual field of the PCBA board of the single-phase and three-phase electric energy meter are comprehensively considered, and the whole hardware is as shown in the above chart. The camera is 2000 ten thousand pixels, and the frame rate is not lower than 19 frames; a lens is arranged under the camera, and the working distance of the lens is 450mm; the light source adopts annular white surface light, so that the illumination average property can be ensured to the maximum extent; the lens-to-face bottom distance was 35mm and the face-to-identification no-surface distance was 415mm.
The visual recognition software design flow is shown in fig. 1, and the steps are as follows:
1. Configuring electric energy meter manufacturer and model information in software;
2. Disassembling normal electric energy meters of corresponding manufacturers and models, and installing PCBA boards at visual identification positions;
3. The software controls the camera to take pictures;
4. Taking a photographed picture as a template in software to form an electric energy meter template library; (template storage is not distorted, and is stored in a mode of image files, and meanwhile, management is carried out in a database according to manufacturer, model and storage path)
5. Disassembling the electric energy meter of which the suspected modified components are disassembled on site and stealing electricity, and installing the disassembled PCBA board at the identification position;
6. Finding out templates corresponding to the manufacturer and the model from software;
7. The software performs comparison and identification through an algorithm;
8. and on visual recognition software, identifying suspicious points and scoring the suspicious points according to the similarity matching degree.
The specific software comparison steps of the invention are shown in fig. 2, and the specific steps are as follows:
1. The camera acquires an image: acquiring an image through a camera;
2. finding a template image from a software library: finding the current manufacturer and model in a PCBA template library of the electric energy meter configured by software, and automatically importing a stored electric energy meter template;
3. preprocessing two images: graying, denoising and edge enhancement are respectively and sequentially carried out on the acquired image and the template image;
4. extracting features from the template image: extracting the main detected resistance characteristics (the resistance replacement on the board is most common in actual electricity stealing sites and is not well recognized by naked eyes);
5. Feature matching is carried out with the acquired image: identifying on the acquired image by the identified features, wherein the deviation value needs to be considered;
6. And (3) identifying a difference point: and comparing the difference points of the two analyzed pictures, and marking on the acquired images.
The main comparison method is as follows:
The on-site electricity stealing in the PCBA of the electric energy meter is common, the replacement of the resistor is difficult to judge manually, and in addition, the resistor on the electric energy meter is relatively more, so that the comparison, identification and positioning of the resistor are very critical. As shown in fig. 5-7, a corner on the PCBA board of the electric energy meter:
When a certain locating point on a conventional PCBA-based board, such as a relay, is used for locating other characteristic points by an MCU chip and performing comparison and analysis, the problem that the identification accuracy is low due to the small deviation of the board batch, the deviation can be transmitted, and different locating points are required to be found by different manufacturer boards, so that software adaptation and the like are caused is found.
Through experiments, the resistor characters are used as a main characteristic point in characteristic definition, characters on the resistor are identified and matched with the positions of the characters, and the positions of the characters are relative to the reference zero point of the board (the reference zero point is the position of a round hole in the upper left corner of each board).
The resistance character identifiers of the template image are identified in the software, for example, 10 characters are marked as follows ：Text1->(X1,Y1)、Text2->(X2,Y2)、Text3->(X3,Y3)、Text4->(X4,Y4)、Text5->(X5,Y5)、Text6->(X6,Y6)、Text7->(X7,Y7)、Text8->(X8,Y8)、Text9->(X9,Y9)、Text10->(X10,Y10)
Wherein Text is specific Text content, X is X-axis coordinate relative to a reference, Y is Y-axis coordinate relative to the reference, and the unit is mm.
Weighting calculation is carried out through relative coordinates X and Y, Z=X, 10000+Y is calculated, a sequence corresponding to Text is established through Z values, and the sequences are ordered from small to large according to the Z values Z1->Text1,Z2->Text2,Z3->Text3,Z4->Text4,Z5->Text5,Z6->Text6,Z7->Text7,Z8->Te xt8,Z9->Text9,Z10->Text10.
The acquired image resistance character identifiers are identified in software, for example, 10 identifiers are marked in sequence ：Text1'->(X1',Y1')、Text2'->(X2',Y2')、Text3'->(X3',Y3')、Text4'->(X4',Y4')、Text5'->(X5',Y5')、Text6'->(X6',Y6')、Text7'->(X7',Y7')、Text8'->(X8',Y8')、Text9'->(X9',Y9')、Text10'->(X10',Y10').
Weighting calculation is carried out through relative coordinates X ', Y', Z '=X' =10000+Y 'is calculated, a sequence corresponding to Text' is established through a Z 'value, and the sequence is ordered from small to large according to the Z' value Z1'->Text1',Z2'->Text2',Z3'->Text3',Z4'->Text4',Z5'->Text5',Z6'->Text6',Z7'->Text7',Z8'->Text8',Z9'->Text9',Z10'->Text10'.
Firstly, calculating the range of a weighted Z according to the maximum deviation of X and Y by 1mm, performing traversal comparison of relative Z points and Z point Text, then performing confirmation comparison according to the difference value between a template and a collected image Z and whether the two Z corresponding Text are consistent, finally positioning out the resistance position with the difference, marking by adopting a red square frame, and facilitating the confirmation by manpower
Although particular embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations may be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. The electric energy meter abnormality detection method based on visual identification is characterized in that PCBA on an electric energy meter is compared through visual identification hardware and visual identification software, an abnormal place on a PCBA board of the electric energy meter can be rapidly identified, the visual identification hardware comprises a camera shooting assembly and a light source which are matched, and the visual identification software design flow is as follows:
The method comprises the steps of R1, configuring manufacturer and model information of the electric energy meter in software;
R2, disassembling the normal electric energy meter corresponding to the manufacturer and the model, and installing the PCBA board to the visual identification position;
S3, controlling a camera to take pictures by software;
R4, taking the photographed picture as a template in software to form an electric energy meter template library;
R5. dismantling the electric energy meter of suspected modification components disassembled on site to steal electricity, and installing the dismantled PCBA board at the identification position;
r6. finding out templates corresponding to the manufacturer and the model from software;
R7. software performs comparison and identification through an algorithm;
r8. on visual recognition software, identify suspicious points and score suspicious points according to similarity match.
2. The visual identification-based electric energy meter abnormality detection method according to claim 1, characterized by comprising the steps of: the camera is 2000 ten thousand pixels, and the frame rate is not lower than 19 frames; the lens is arranged below the camera, and the working distance of the lens is 450mm; the light source adopts annular white surface light, so that the illumination average property is ensured to the maximum extent; the distance from the lens to the bottom of the light source is 35mm, and the distance from the light source to the surface of the identification object is 415mm.
3. The visual identification-based electric energy meter abnormality detection method according to claim 1, characterized by comprising the steps of: and in the step R4, the template storage is not distorted, is stored in a mode of an image file, and is managed in a database according to a manufacturer, a model and a storage path.
4. The visual identification-based electric energy meter abnormality detection method according to claim 1, characterized by comprising the steps of: the method comprises the following specific steps:
s1, a camera acquires an image: acquiring an image through a camera;
s2, finding a template image from a software library: finding the current manufacturer and model in a PCBA template library of the electric energy meter configured by software, and automatically importing a stored electric energy meter template;
s3, preprocessing two images: graying, denoising and edge enhancement are respectively and sequentially carried out on the acquired image and the template image;
S4, extracting features from the template image: extracting the main detected resistance characteristics;
S5, performing feature matching with the acquired image: identifying on the acquired image by the identified features, wherein the deviation value needs to be considered;
S6, identifying a difference point: and comparing the difference points of the two analyzed pictures, and marking on the acquired images.
5. The visual identification-based electric energy meter abnormality detection method according to claim 4, wherein the method comprises the following steps: in the step S4, in terms of feature definition, the resistor characters are used as a main feature point, characters on the resistor are identified and the positions of the characters are matched, the positions of the characters are opposite to the reference zero point of the board, and the reference zero point is the position of the round hole in the upper left corner of each board.
6. The visual identification-based electric energy meter abnormality detection method according to claim 4, wherein the method comprises the following steps: the resistance character marks of the template image are identified in the software, if 10 are provided, the resistance character marks are marked as follows in turn ：Text1->(X1,Y1)、Text2->(X2,Y2)、Text3->(X3,Y3)、Text4->(X4,Y4)、Text5->(X5,Y5)、Text6->(X6,Y6)、Text7->(X7,Y7)、Text8->(X8,Y8)、Text9->(X9,Y9)、Text10->(X10,Y10);
Wherein Text is specific Text content, X is X-axis coordinate relative to a reference, Y is Y-axis coordinate relative to the reference, and the unit is mm; and (3) carrying out weighted calculation through relative coordinates X and Y, calculating Z=X, 10000+Y, establishing a sequence corresponding to the Text through Z values, and sequencing from small to large according to the Z values:
Z1->Text1,Z2->Text2,Z3->Text3,Z4->Text4,Z5->Text5,Z6->Text6,Z7->Te xt7,Z8->Text8,Z9->Text9,Z10->Text10.
7. The visual identification-based electric energy meter abnormality detection method according to claim 6, wherein the method comprises the following steps: the acquired image resistance character identifiers are identified in software, if 10 are available, the acquired image resistance character identifiers are marked as follows in turn ：Text1'->(X1',Y1')、Text2'->(X2',Y2')、Text3'->(X3',Y3')、Text4'->(X4',Y4')、Text5'->(X5',Y5')、Text6'->(X6',Y6')、Text7'->(X7',Y7')、Text8'->(X8',Y8')、Text9'->(X9',Y9')、Text10'->(X10',Y10');
Weighting calculation is carried out through relative coordinates X ', Y', Z '=X' =10000+Y 'is calculated, a sequence corresponding to Text' is established through a Z 'value, and the sequence is ordered from small to large according to the Z' value Z1'->Text1',Z2'->Text2',Z3'->Text3',Z4'->Text4',Z5'->Text5',Z6'->Text6',Z7'->Text7',Z8'->Text8',Z9'->Text9',Z10'->Text10'.
8. The visual identification-based electric energy meter abnormality detection method according to claim 7, characterized by:
firstly, calculating the range of a weighting Z according to the maximum deviation of X and Y by 1mm, performing traversal comparison of relative Z points and Z point Text, then performing confirmation comparison according to the difference value between a template and an acquired image Z and whether the two Z corresponding Text are consistent, finally positioning out the resistance position with the difference, and marking by adopting a red square frame, thereby facilitating the confirmation by manpower.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410333365.XA CN118247239A (en) | 2024-03-22 | 2024-03-22 | Electric energy meter abnormality detection method based on visual recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410333365.XA CN118247239A (en) | 2024-03-22 | 2024-03-22 | Electric energy meter abnormality detection method based on visual recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118247239A true CN118247239A (en) | 2024-06-25 |
Family
ID=91556647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410333365.XA Pending CN118247239A (en) | 2024-03-22 | 2024-03-22 | Electric energy meter abnormality detection method based on visual recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118247239A (en) |
-
2024
- 2024-03-22 CN CN202410333365.XA patent/CN118247239A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI757825B (en) | System and method for pcb inspection based on false defect detection | |
| CN110119680B (en) | Automatic error checking system of regulator cubicle wiring based on image recognition | |
| CN107907775B (en) | Wiring detection method and wiring detection device | |
| CN109638959B (en) | Power equipment remote signaling function debugging method and system based on AR and deep learning | |
| CN110619623B (en) | Automatic identification method for heating of joint of power transformation equipment | |
| CN115908420A (en) | Method, device and equipment for detecting defects of printed circuit board and storage medium | |
| WO2020174625A1 (en) | Production management device | |
| CN111504381A (en) | Terminal row product online detection device and detection method thereof | |
| CN113688817A (en) | Instrument identification method and system for automatic inspection | |
| CN108921209A (en) | Image identification method, device and electronic equipment | |
| US5408537A (en) | Mounted connector pin test using image processing | |
| CN113030123A (en) | AOI detection feedback system based on Internet of things | |
| CN107084989B (en) | Method and system for adding AOI device database | |
| CN108960850A (en) | Method for anti-counterfeit and device, anti-fake traceability system | |
| CN118247239A (en) | Electric energy meter abnormality detection method based on visual recognition | |
| CN110674889B (en) | Image training method for ammeter terminal fault recognition | |
| CN115546140A (en) | Display panel detection method and system and electronic device | |
| CN107729839B (en) | Method and device for identifying on-off state of pull-plug switch of protection pressing plate | |
| CN115636232A (en) | Automatic mechanical arm inserting method based on optical fiber connector end face detector | |
| CN115754873A (en) | Wiring detection method and system for mutual inductor error test | |
| CN114581360A (en) | Photovoltaic module label detection method, device, equipment and computer storage medium | |
| CN111369517A (en) | Automatic quality inspection method and device for solar panel, electronic equipment and storage medium | |
| CN109060831A (en) | A kind of automatic dirty detection method based on bottom plate fitting | |
| CN117095389B (en) | Image data processing method and system based on liquid crystal visual recognition unit | |
| CN117687385B (en) | Automatic test method and system applied to flat PCBA control module |
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 |