CN116016851A - Intelligent meter reading system and method - Google Patents
Intelligent meter reading system and method Download PDFInfo
- Publication number
- CN116016851A CN116016851A CN202211598122.6A CN202211598122A CN116016851A CN 116016851 A CN116016851 A CN 116016851A CN 202211598122 A CN202211598122 A CN 202211598122A CN 116016851 A CN116016851 A CN 116016851A
- Authority
- CN
- China
- Prior art keywords
- data
- image data
- text
- module
- model
- 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
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000005611 electricity Effects 0.000 claims abstract description 32
- 238000007781 pre-processing Methods 0.000 claims abstract description 22
- 238000004891 communication Methods 0.000 claims abstract description 19
- 238000012806 monitoring device Methods 0.000 claims abstract description 12
- 238000012544 monitoring process Methods 0.000 claims abstract description 11
- 238000001514 detection method Methods 0.000 claims description 18
- 238000012360 testing method Methods 0.000 claims description 15
- 238000012937 correction Methods 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004377 microelectronic Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
The invention discloses an intelligent meter reading system and method, wherein the system comprises a node monitoring device arranged on each power consumption node and a server arranged on a cloud, and the node monitoring device comprises an image acquisition module, a communication module, a power module and a main control module; the main control module is connected to the server through the communication module in a communication way and is used for receiving data from the server and controlling the image acquisition module to acquire the data; the image acquisition module is used for acquiring image data of an ammeter of the electricity consumption node and transmitting the data to the communication module; the server is used for receiving the image data from the node monitoring device, preprocessing the image data, recognizing characters, outputting the preprocessed image data into character data, and converting the character data into electricity consumption data. The invention realizes meter reading of each monitoring node independently by utilizing the image recognition technology and internet calculation.
Description
Technical Field
The invention belongs to the technical field of power systems, and particularly relates to an intelligent meter reading system and method.
Background
The remote meter reading system is a result of deep integration of a modern computer, a microelectronic technology and a network communication technology, can automatically measure, automatically control and automatically store related physical quantities as a conventional meter, displays measurement results and control states, and has the application characteristics of a network: the remote meter reading system can be subjected to functional operation through the Internet, measurement results are obtained, parameter setting, real-time monitoring and fault judgment are carried out on the meter reading system, and dynamic information can be issued on the Internet.
In the prior art, the centralized meter reading is usually carried out on the electric quantity in the area through the concentrator and then the data are summarized, but the concentrator is usually installed in the area in a plug-in box mode, so that the cost is high and the maintenance procedure is complex.
Disclosure of Invention
The invention aims to solve the technical problem of providing an intelligent meter reading system and method for reducing meter reading cost and improving meter reading accuracy.
In order to solve the above technical problems, the present invention provides an intelligent meter reading system, including: the system comprises node monitoring devices arranged on all power utilization nodes and a server arranged on a cloud end, wherein each node monitoring device comprises an image acquisition module, a communication module, a power supply module and a main control module;
the main control module is connected to the server through the communication module in a communication way and is used for receiving data from the server and controlling the image acquisition module to acquire the data;
the image acquisition module is used for acquiring image data of an ammeter of the electricity consumption node and transmitting the data to the communication module;
the server is used for receiving the image data from the node monitoring device, preprocessing the image data, recognizing characters, outputting the preprocessed image data into character data, and converting the character data into electricity consumption data.
Further, the server is provided with an image preprocessing module and a text recognition module, after receiving the image data, the server preprocesses the image data through the image preprocessing module, and the image preprocessing specifically comprises binarization and denoising; the text recognition module is used for carrying out character segmentation on the preprocessed image data to obtain single characters, carrying out one-to-one matching recognition on the single characters and numbers, characters and letters in the database, and outputting recognized character data.
Further, the intelligent meter reading system further comprises a local storage module and a display module, wherein the local storage module is used for storing the image data collected each time, and the display module is used for calling and displaying the image data stored by the local storage module.
Further, the intelligent meter reading system further comprises an electric meter concentrator and an electric quantity metering unit, wherein a plurality of the electric quantity metering units are correspondingly connected to each electricity utilization node, the electric meter concentrator is connected to an electric meter of each electricity utilization node, and the electric quantity metering unit is connected with the local storage module.
The invention also provides an intelligent meter reading method, which comprises the following steps:
step S1, acquiring image data of a certain monitoring node;
s2, preprocessing the acquired image data, segmenting characters in the image data, and identifying through a plurality of text identification models;
step S3, if the recognition results of the text recognition models are the same, outputting text data;
step S4, if the identification result of any text identification model in the plurality of text identification models is different from other text identification models, performing first self-detection on the text identification model, and outputting text data after the first self-detection;
and S5, adding a data identifier to the text data and outputting the text data as electricity utilization data.
Further, the step S2 specifically includes: preprocessing the image data, including binarization and denoising, and then extracting features of the image data; after feature extraction is completed, character-by-character segmentation is performed on the data characters in the fixed area, and then text recognition is performed.
Further, the specific steps of the first self-detection include:
extracting first image data with the same recognition result of each text recognition model from the historical acquisition data and assigning values;
assigning values to the second image data with different recognition results;
calculating a sample average value of the assigned first image data and second image data;
if the average value of the samples is in a preset confidence interval, outputting text data; otherwise, executing the second self-detection until the text data is output after the text data passes through.
Further, the specific steps of the second self-detection include:
acquiring third image data of the current monitoring node, marking the third image data as questioning data, and transmitting the questioning data to a server;
receiving the challenge response data from the server, and collecting fourth image data at the same time; the electric meter metering unit collects first electric quantity data and second electric quantity data simultaneously while collecting third image data and fourth image data;
the plurality of text recognition models after the challenge models are removed recognize the third image data and the fourth image data, and the recognition results are compared with the first electric quantity data and the second electric quantity data;
if the recognition results of a certain text recognition model are consistent in comparison, marking the text recognition model as a confidence model, and outputting text data; otherwise, marking as a questioning model;
and acquiring the identification results of all the questioning models, comparing the identification results with the first electric quantity data and the second electric quantity data, and executing model error correction.
Further, the specific step of correcting the suspicious model includes:
sequentially comparing each questioning model by taking the questioning time of the text recognition model as a sequence;
if the recognition result in the questioning model is a font error, when the total number and the total type of the font errors are in a preset range, adjusting the font recognized in the questioning model into a correct font, outputting the correct font, and deleting the questioning mark of the questioning model; otherwise, the text recognition model is deleted.
Further, the first self-detection and the second self-detection are performed at a predetermined cycle.
The implementation of the invention has the following beneficial effects: collecting a data image through a camera and preprocessing the data image by utilizing image recognition and internet calculation, recognizing the preprocessed image into a text by adopting various models, and judging the effectiveness of the text by comparing the consistency of recognition results of various character models; when the identification results are inconsistent, the invention realizes error correction in the meter reading process by utilizing the first self-detection mechanism and the second self-detection mechanism, and ensures the accuracy of image identification by utilizing the Internet.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of an intelligent meter reading system according to an embodiment of the invention.
Fig. 2 is a schematic flow chart of an intelligent meter reading method according to the second embodiment of the invention.
Fig. 3 is a schematic flow chart of an intelligent meter reading method according to the second embodiment of the invention.
Detailed Description
The following description of embodiments refers to the accompanying drawings, which illustrate specific embodiments in which the invention may be practiced.
Referring to fig. 1, a first embodiment of the present invention provides an intelligent meter reading system, including: the system comprises node monitoring devices arranged on all power utilization nodes and a server arranged on a cloud end, wherein each node monitoring device comprises an image acquisition module, a communication module, a power supply module and a main control module;
the main control module is connected to the server through the communication module in a communication way and is used for receiving data from the server and controlling the image acquisition module to acquire the data;
the image acquisition module is used for acquiring image data of an ammeter of the electricity consumption node and transmitting the data to the communication module;
the server is used for receiving the image data from the node monitoring device, preprocessing the image data, recognizing characters, outputting the preprocessed image data into character data, and converting the character data into electricity consumption data.
As a preferred mode of this embodiment, the image acquisition module of this embodiment may be a camera with a photographing function, where the camera acquires an indication of a mechanical ammeter or a digital ammeter, and the acquired image data is transmitted by the communication module and then sent to the server, and is processed by the server.
The server is provided with an image preprocessing module and a text recognition module, and after receiving the image data, the server firstly preprocesses the image data through the image preprocessing module, and the content of the image preprocessing comprises binarization and denoising. The image data is preprocessed to highlight the data content in the image, so that the background is weakened and the noise is removed. The text recognition module firstly carries out character segmentation on the preprocessed image, namely, carries out one-by-one decomposition on the data in the recognition area to obtain single characters, then carries out one-to-one matching recognition and application on the single characters and numbers, characters and letters in the database, and outputs the recognized character data. The communication module is responsible for receiving control instructions from the server and transmitting the monitoring data displayed in text form to the server. In this embodiment, the text recognition module adopts a text recognition technology that is common in the prior art, and will not be described herein.
As a preferred mode of this embodiment, the intelligent meter reading system further includes a local storage module and a display module, where the local storage module is used to store the image data collected each time, and the display module is used to call and display the image data stored in the local storage module. In addition, the intelligent meter reading system further comprises an ammeter concentrator and an electricity metering unit, wherein a plurality of the electricity metering units are correspondingly connected to each electricity utilization node, the ammeter concentrator is connected to the ammeter of each electricity utilization node, and the electricity metering unit is connected with the local storage module. The ammeter concentrator and the electricity metering unit are devices for collecting electricity data commonly used in the prior art, in this embodiment, the ammeter concentrator and the electricity metering unit are used as error correction means, and error correction is performed through the electricity metering unit instead of a main meter reading means when the electricity collected by the data collecting unit is wrong.
Corresponding to the intelligent meter reading system described in the first embodiment of the present invention, a second embodiment of the present invention further provides an intelligent meter reading method, as shown in fig. 2, comprising the following steps:
step S1, acquiring image data of a certain monitoring node;
s2, preprocessing the acquired image data, segmenting characters in the image data, and identifying through a plurality of text identification models;
step S3, if the recognition results of the text recognition models are the same, outputting text data;
step S4, if the identification result of any text identification model in the plurality of text identification models is different from other text identification models, performing first self-detection on the text identification model, and outputting text data after the first self-detection;
and S5, adding a data identifier to the text data and outputting the text data as electricity utilization data.
Specifically, referring to fig. 3, after the image data of the electric meter of the monitoring node is collected in step S1, the image data is transmitted to the server. Step S2, preprocessing the image data, including binarization and denoising, and then extracting features of the image data. Character attribute features in the images, which are beneficial to text recognition, are extracted through feature extraction, and the character attribute features comprise geometric shape information of characters, so that subsequent text recognition can be conveniently carried out. After feature extraction is completed, character-by-character segmentation is performed on the data characters in the fixed area, and then text recognition is performed.
Since the single model does not always recognize the correct result, in order to ensure the reliability of the recognition result, step S4 needs to apply the first self-test, and the specific steps of performing the first self-test are as follows:
extracting first image data with the same recognition result of each text recognition model from the historical acquisition data and assigning values;
assigning values to the second image data with different recognition results;
calculating a sample average value of the assigned first image data and second image data;
if the average value of the samples is in a preset confidence interval, outputting text data; otherwise, executing the second self-detection until the text data is output after the text data passes through.
In the present embodiment, three text recognition models are taken as an example.
First, the model a and the model B are used for identification at the same time, the identification results a and B are compared, and if a=b, the result is output.
If a is not equal to b, re-identifying by using a model C, comparing the identification result C with a and b, and outputting a result C when c=a or c=b.
When a, b and c are all different, i.e. the identification result is wrong, marking the image as p i ，p i The value is 0. When at least two of a, b and c are equal, i.e. the identification result is correct, the first self-detection is correct, the image is marked as q j 。
Marked p i ，q j Together, the set R is composed of:
R＝(p i ,q j ),i＝1,2,…,m,j＝1,2,…,n
then, the value of the recognition accuracy I of the number of samples in the set R is calculated:
wherein I is identification accuracy; m+n is the total number of samples, where m is p i N is q j Is the number of (3); p is p i ，q j Values are marked for the image.
The confidence interval of the sample is determined and set according to the actual meter reading accuracy requirement, the confidence interval of the identification accuracy is [ e, f ], when I is more than or equal to e, the accuracy of the identification result is determined to be in a normal range, the acquisition and the identification process are not failed, and the next round of acquisition is directly carried out; when I < f, then a second self-test is performed.
The specific steps for performing the second self-test are as follows:
acquiring third image data of the current monitoring node, marking the third image data as questioning data, and transmitting the questioning data to a server;
receiving the challenge response data from the server, and collecting fourth image data at the same time; the electric meter metering unit collects first electric quantity data and second electric quantity data simultaneously while collecting third image data and fourth image data;
the plurality of text recognition models after the challenge models are removed recognize the third image data and the fourth image data, and the recognition results are compared with the first electric quantity data and the second electric quantity data;
if the recognition results of a certain text recognition model are consistent in comparison, marking the text recognition model as a confidence model, and outputting text data; otherwise, marking as a questioning model;
and acquiring the identification results of all the questioning models, comparing the identification results with the first electric quantity data and the second electric quantity data, and executing model error correction.
The specific steps of correcting the challenge model are as follows:
sequentially comparing each questioning model by taking the questioning time of the text recognition model as a sequence; if the recognition result in the question model is a font error, when the total number and the total type of the font error are within the preset range, the font with the wrong recognition is adjusted to be a correct font and then output; otherwise, the text recognition model is deleted.
The font error refers to misjudgment errors between two fonts which want to be close, such as a number 1 and a number 7, the fonts are easy to misjudge on a liquid crystal digital display screen, when the total number and the total type of the font errors are within a permissible preset range, the text recognition model is considered to be a training error, after the questioning mark of the questioning model is deleted, the text recognition model can be continuously used after the wrong fonts are modified to be correct, otherwise, the text recognition model cannot be continuously used and should be deleted in a server.
As a preferred mode of the embodiment, the server periodically adds new text recognition models, so that the problem that the server cannot be used due to excessive deleted quantity after long-time use is avoided, and meanwhile, the more text recognition models are, the more accurate the text recognition result is.
As a preferred mode of this embodiment, when the second self-test is performed, if the correct proportion of the text recognition model is recognized in the history data and the proportion of the text recognition model which is not questioned at this time is higher than the proportion of the questioning model in all the text models, the correct text recognition model recognition data in the recognition result is directly compared, rather than the data of the electricity metering unit.
And finally, outputting the identification result and the electricity consumption data, storing the identification result and the electricity consumption data into an electricity consumption text in a unified format, and displaying the electricity consumption data in a text form, wherein the text comprises the collection time of the electricity consumption data, the number of an ammeter, the number of a monitoring node, the number of an electricity consumption measurement unit, the number of a concentrator, the number of an image collection module and the electricity consumption data, and storing the corresponding image data when storing the electricity consumption text.
As a preferable mode of the present embodiment, when any of the first self-test and the second self-test does not occur, the present embodiment also executes the first self-test and the second self-test at a predetermined period, and periodically performs the first self-test and the second self-test to prevent the meter reading result from being erroneous.
As can be seen from the above description, compared with the prior art, the invention has the following beneficial effects: collecting a data image through a camera and preprocessing the data image by utilizing image recognition and internet calculation, recognizing the preprocessed image into a text by adopting various models, and judging the effectiveness of the text by comparing the consistency of recognition results of various character models; when the identification results are inconsistent, the invention realizes error correction in the meter reading process by utilizing the first self-detection mechanism and the second self-detection mechanism, and ensures the accuracy of image identification by utilizing the Internet.
The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.
Claims (10)
1. An intelligent meter reading system, comprising: the system comprises node monitoring devices arranged on all power utilization nodes and a server arranged on a cloud end, wherein each node monitoring device comprises an image acquisition module, a communication module, a power supply module and a main control module;
the main control module is connected to the server through the communication module in a communication way and is used for receiving data from the server and controlling the image acquisition module to acquire the data;
the image acquisition module is used for acquiring image data of an ammeter of the electricity consumption node and transmitting the data to the communication module;
the server is used for receiving the image data from the node monitoring device, preprocessing the image data, recognizing characters, outputting the preprocessed image data into character data, and converting the character data into electricity consumption data.
2. The intelligent meter reading system according to claim 1, wherein the server is provided with an image preprocessing module and a text recognition module, and after receiving the image data, the server performs preprocessing on the image data through the image preprocessing module, wherein the image preprocessing specifically comprises binarization and denoising; the text recognition module is used for carrying out character segmentation on the preprocessed image data to obtain single characters, carrying out one-to-one matching recognition on the single characters and numbers, characters and letters in the database, and outputting recognized character data.
3. The intelligent meter reading system of claim 1, further comprising a local storage module and a display module, wherein the local storage module is used for storing the image data collected each time, and the display module is used for calling the image data stored by the local storage module and displaying the image data.
4. The intelligent meter reading system of claim 3, further comprising a meter concentrator and a power metering unit, wherein a plurality of the power metering units are correspondingly connected to each power utilization node, the meter concentrator is connected to the meter of each power utilization node, and the power metering unit is connected to the local storage module.
5. An intelligent meter reading method is characterized by comprising the following steps:
step S1, acquiring image data of a certain monitoring node;
s2, preprocessing the acquired image data, segmenting characters in the image data, and identifying through a plurality of text identification models;
step S3, if the recognition results of the text recognition models are the same, outputting text data;
step S4, if the identification result of any text identification model in the plurality of text identification models is different from other text identification models, performing first self-detection on the text identification model, and outputting text data after the first self-detection;
and S5, adding a data identifier to the text data and outputting the text data as electricity utilization data.
6. The intelligent meter reading method according to claim 5, wherein the step S2 specifically includes: preprocessing the image data, including binarization and denoising, and then extracting features of the image data; after feature extraction is completed, character-by-character segmentation is performed on the data characters in the fixed area, and then text recognition is performed.
7. The intelligent meter reading method according to claim 5, wherein the specific step of the first self-test comprises:
extracting first image data with the same recognition result of each text recognition model from the historical acquisition data and assigning values;
assigning values to the second image data with different recognition results;
calculating a sample average value of the assigned first image data and second image data;
if the average value of the samples is in a preset confidence interval, outputting text data; otherwise, executing the second self-detection until the text data is output after the text data passes through.
8. The intelligent meter reading method according to claim 7, wherein the specific step of the second self-test comprises:
acquiring third image data of the current monitoring node, marking the third image data as questioning data, and transmitting the questioning data to a server;
receiving the challenge response data from the server, and collecting fourth image data at the same time; the electric meter metering unit collects first electric quantity data and second electric quantity data simultaneously while collecting third image data and fourth image data;
the plurality of text recognition models after the challenge models are removed recognize the third image data and the fourth image data, and the recognition results are compared with the first electric quantity data and the second electric quantity data;
if the recognition results of a certain text recognition model are consistent in comparison, marking the text recognition model as a confidence model, and outputting text data; otherwise, marking as a questioning model;
and acquiring the identification results of all the questioning models, comparing the identification results with the first electric quantity data and the second electric quantity data, and executing model error correction.
9. The intelligent meter reading method according to claim 8, wherein the specific step of correcting the suspected model includes:
sequentially comparing each questioning model by taking the questioning time of the text recognition model as a sequence;
if the recognition result in the questioning model is a font error, when the total number and the total type of the font errors are in a preset range, adjusting the font recognized in the questioning model into a correct font, outputting the correct font, and deleting the questioning mark of the questioning model; otherwise, the text recognition model is deleted.
10. The smart meter reading method of claim 9, wherein the first self-test and the second self-test are performed at a predetermined period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211598122.6A CN116016851A (en) | 2022-12-14 | 2022-12-14 | Intelligent meter reading system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211598122.6A CN116016851A (en) | 2022-12-14 | 2022-12-14 | Intelligent meter reading system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116016851A true CN116016851A (en) | 2023-04-25 |
Family
ID=86020095
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211598122.6A Pending CN116016851A (en) | 2022-12-14 | 2022-12-14 | Intelligent meter reading system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116016851A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116824602A (en) * | 2023-07-17 | 2023-09-29 | 国网浙江省电力有限公司 | Electric charge data analysis processing method, device and storage medium |
-
2022
- 2022-12-14 CN CN202211598122.6A patent/CN116016851A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116824602A (en) * | 2023-07-17 | 2023-09-29 | 国网浙江省电力有限公司 | Electric charge data analysis processing method, device and storage medium |
| CN116824602B (en) * | 2023-07-17 | 2023-12-01 | 国网浙江省电力有限公司 | Electric charge data analysis processing method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214280B (en) | Shop identification method and device based on street view, electronic equipment and storage medium | |
| CN111950396B (en) | Meter reading neural network identification method | |
| CN114119518A (en) | Method and system for detecting temperature abnormal point in infrared image of current transformer | |
| CN116016851A (en) | Intelligent meter reading system and method | |
| CN114511718B (en) | Intelligent management method and system for materials for building construction | |
| CN115047322B (en) | Method and system for identifying fault chip of intelligent medical equipment | |
| CN112804336A (en) | Fault detection method, device, system and computer readable storage medium | |
| CN113469178B (en) | Power meter identification method based on deep learning | |
| CN106895791A (en) | A kind of board deformation monitoring early warning system | |
| CN111353502B (en) | Digital table identification method and device and electronic equipment | |
| CN114358242A (en) | Heterojunction battery production monitoring system and method | |
| CN111626046A (en) | Correlation verification method for positions of telemetering text primitives and equipment primitives of transformer substation | |
| CN112906602B (en) | Automatic identification device and identification method for electric quantity meter of power distribution cabinet based on image processing | |
| CN112113638B (en) | Water meter function self-checking device and method | |
| CN113076730A (en) | Test report intelligent management method, device, system and storage medium | |
| CN111291691B (en) | Deep learning-based substation secondary equipment instrument panel reading detection method | |
| CN112818993A (en) | Character wheel reading meter end identification method and equipment for camera direct-reading meter reader | |
| CN112153320A (en) | Method and device for measuring size of article, electronic equipment and storage medium | |
| CN117173223A (en) | Standard template generation method, device, equipment and medium for ammeter code-breaking screen | |
| CN111047731A (en) | AR technology-based telecommunication room inspection method and system | |
| CN116230253A (en) | Pharmacy medicine checking method and device based on image recognition and storage medium | |
| CN113920497B (en) | Nameplate recognition model training method, nameplate recognition method and related devices | |
| CN115588196A (en) | Pointer type instrument reading method and device based on machine vision | |
| CN115439864A (en) | Water meter reading identification method and system, computer equipment and storage medium | |
| CN114821625A (en) | Automatic identification method, device, equipment and storage medium for secondary screen cabinet wiring |
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 |