CN111783785A - Water meter identification system and method - Google Patents
Water meter identification system and method Download PDFInfo
- Publication number
- CN111783785A CN111783785A CN202010633627.6A CN202010633627A CN111783785A CN 111783785 A CN111783785 A CN 111783785A CN 202010633627 A CN202010633627 A CN 202010633627A CN 111783785 A CN111783785 A CN 111783785A
- Authority
- CN
- China
- Prior art keywords
- water
- module
- water meter
- quantity value
- picture
- 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.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 227
- 238000000034 method Methods 0.000 title claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 17
- 230000002787 reinforcement Effects 0.000 claims abstract description 17
- 230000005540 biological transmission Effects 0.000 claims abstract description 8
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 230000000306 recurrent effect Effects 0.000 claims description 2
- 238000013135 deep learning Methods 0.000 abstract description 3
- 238000012545 processing Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 102100032202 Cornulin Human genes 0.000 description 1
- 101000920981 Homo sapiens Cornulin Proteins 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
-
- 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
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/02—Recognising information on displays, dials, clocks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Molecular Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Physics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a water meter identification system and an identification method, wherein the water meter identification system comprises a plurality of image acquisition modules, a network transmission module, a server and a client, wherein the server further comprises a positioning module, a preprocessing module, an identification module, a prediction module and a reinforcement learning module. The water meter identification system and the identification method provided by the invention are used for carrying out water meter picture numerical value positioning and numerical value text identification based on deep learning and reinforcement learning, so that the water meter water data is intelligently copied, the problems of complexity, time consumption and the like of manual meter reading are avoided, and the working efficiency is improved; the water consumption data of the water meter is analyzed through statistical data to predict the water consumption before the next week of the water meter, and powerful data support is provided for improving water management work.
Description
Technical Field
The invention belongs to the technical field of deep learning, reinforcement learning and image processing, and particularly relates to a water meter identification system and an identification method.
Background
Water meters for enterprises, public institutions and residential dwellings are generally arranged in pipelines, kitchen water valves and other places. Because the mounted position of some water meters is unreasonable, make the staff can't easily obtain the water gauge count, the water gauge appears the phenomenon such as drop of water, fog even for some water gauges, leads to the water gauge to count the inaccuracy, brings huge puzzlement for staff's work of checking meter.
With the development of AI technology, people begin to apply artificial intelligence to traditional industries, save manpower, and implement intelligent operations. However, the water supply of the water plant still adopts manual meter reading, the time and the labor are consumed, and the situations of wrong reading, missed reading and the like also exist.
Disclosure of Invention
The invention provides a water meter identification system and an identification method, which can avoid the problems of tedious manual meter reading, inaccuracy and the like, improve the water consumption statistical efficiency and improve the working quality in the aspect of water affairs.
The water meter identification system provided by the invention comprises a plurality of image acquisition modules, a server and a client;
the image acquisition module is arranged at each water meter, the water meter pictures containing water quantity values are acquired through the image acquisition module, the acquired water meter picture information is sent to the server, the server identifies and stores the water quantity value information in the water meter pictures, and a worker inquires the water consumption information of each water meter stored in the server through the client.
Preferably, the image acquisition module transmits the acquired water meter picture information to the server through the network transmission module.
Preferably, the server further comprises a positioning module, a preprocessing module, an identification module, and a prediction module;
the positioning module detects the value and positions the water quantity value in the water meter picture through the positioning model, and sends the water meter picture information of the positioned water quantity value position to the preprocessing module;
the preprocessing module is used for positioning and cutting a part of the water quantity value picture according to the positioned water quantity value position, correcting and/or enhancing information and reducing noise of the cut water quantity value picture, and sending the processed water quantity value picture information to the identification module;
the identification module identifies the value in the water quantity value picture through the identification model and transmits the identified water quantity value information to the prediction module;
the prediction module calculates and stores the water consumption of each water meter through the prediction model, and predicts the water quantity value of the next period of each water meter according to the stored water consumption information.
Preferably, the positioning model is a text positioning network, and the text positioning network is trained and checked through a water meter picture data set marked with a water quantity numerical value position.
Preferably, the preprocessing module performs hough mapping correction processing on the oblique picture, and performs information enhancement and noise reduction processing on the blurred picture.
Preferably, the convolution cyclic neural network is trained and checked by adopting a water yield value image data set with a marked value, so as to obtain the identification model.
Preferably, the prediction module takes a time-cycle neural network as a prediction model.
Preferably, the server further comprises a reinforcement learning module, the recognition module sends the water quantity value picture which cannot be recognized to the reinforcement learning module, the reinforcement learning module detects and reads the received water quantity value picture information through the Monte Carlo algorithm unit, and the recognition module is trained and updated by the water quantity value picture data with the read value.
The invention also discloses an identification method based on the water meter identification system, which comprises the following steps:
step 1, collecting water meter pictures at each water meter by adopting an image collection module, and transmitting picture data to a server through a network transmission module;
step 3, the preprocessing module positions and cuts a part of water quantity value pictures in the water meter pictures according to the positioned water quantity value positions, corrects and/or enhances information and reduces noise of the water quantity value pictures, and the processed pictures are sent to the identification module;
step 4, the identification module identifies the water quantity value in the water quantity value picture through the identification model and sends the water quantity value to the prediction module;
step 5, when the identification model can not identify the water quantity value in the water quantity value picture, the identification module sends the water quantity value picture data to the reinforcement learning module, the reinforcement learning module detects and reads the received water quantity value picture information through the Monte Carlo algorithm unit, and the identification module is trained and updated by the identified water quantity value picture data;
and 6, calculating and storing the water consumption of each water meter by the prediction module through the prediction module, and predicting the water quantity value of the next period of each water meter according to the stored water consumption information by the prediction module.
The water meter identification system and the identification method provided by the invention read the water consumption of each water meter by performing text positioning and identification on the collected water meter picture, realize artificial intelligent meter reading and greatly improve the water consumption statistical efficiency; meanwhile, the water quantity value of the next period of each water meter is predicted through the stored water consumption of each water meter, and powerful data support is provided for improving water management work.
Drawings
Fig. 1 is a schematic structural diagram of a water meter identification system provided by the invention.
Detailed Description
The present invention will now be described in detail by describing in detail preferred embodiments thereof with reference to the attached drawings.
The water meter identification system provided by the invention comprises a plurality of image acquisition modules, a network transmission module 2, a server 3 and a client 4.
The water meters are generally dispersedly arranged in all units and residences, an image acquisition module is arranged at each water meter for counting the water consumption of the water meters, and water meter pictures containing water quantity values are acquired. In the embodiment of the invention, each image acquisition module adopts a micro camera to shoot a water meter picture and then transmits the water meter picture to the server 3 through the network transmission module 2. The server 3 positions the numerical text in the water meter picture, identifies the water quantity numerical value in the water meter picture and stores the water quantity numerical value, and meanwhile, the server 3 can predict the water consumption of each water meter in the next period. The client 4 is in communication connection with the server 3, and water service staff can inquire water consumption information of water meters of all units and residents by logging in the client, such as historical water consumption, current water consumption of the water meters, predicted water consumption of the next period and the like, and perform relevant statistical analysis.
The server 3 further comprises a positioning module 31, a pre-processing module 32, an identification module 33 and a prediction module 34, as shown in fig. 1.
In the server 3, the positioning module 31 receives the water meter picture information data transmitted by the network transmission module 2. In the water gauge picture of image acquisition module collection, contain the water yield numerical value with water gauge and water gauge surrounding environment as the background, orientation module 31 is through the accurate positioning water yield numerical value position of orientation model. In the embodiment of the invention, a CTPN model is used as a positioning model, and a Text positioning network CTPN (connectionist Text forward network) is adopted to perform algorithm detection on characters transversely distributed in a water meter picture, so that a water quantity value in the picture is positioned.
Before the positioning model is used for positioning the water meter picture numerical value, a large amount of training data needs to be collected to carry out model training on the positioning model. Specifically, gather a large amount of water gauge pictures, use labelme mark water gauge picture water yield numerical value positional information, divide into training set and test set with the water gauge picture data of mark, train the location model through the training set, carry out the inspection through the test set to the training effect and rectify, verify that qualified back location model can be used for fixing a position water gauge picture numerical value. Labelme is a labeling software of a data set neural network learning method.
The positioning module 31 sends the water meter picture information data of the positioning water quantity numerical value position to the preprocessing module 32. The preprocessing module 32 further positions and cuts the picture of the water amount value part according to the positioned water amount value position, such as connected domain segmentation and dripping segmentation, to obtain a water amount value picture, performs hough mapping correction processing on the inclined picture, and performs information enhancement and noise reduction processing on the blurred picture, so as to improve the picture quality, and facilitate the subsequent recognition module 33 to perform convolution extraction on features and recognize a value text. Specifically, all points in the image are mapped into a feature space, all points on the same straight line are mapped onto the same point in the feature space, the straight line is judged by judging the number of the points, and meanwhile, the oblique image is corrected according to the calculated angle; the information of the blurred picture is enhanced, and the bleached (camera overexposed) picture or the over-dark (underexposed) picture is corrected through gamaa conversion.
The preprocessing module 32 sends the processed water amount value picture information data to the recognition module 33. The identification model in the identification module 33 is a CNN + RNN + CTC model, specifically, features of a picture are extracted through a convolutional Neural network CNN (volumetric Neural networks), and then converted into a feature sequence, which is input as a sequence of a recurrent Neural network RNN (volumetric Neural networks), the RNN network is used for predicting a sequence, and the sequence generated by the RNN is corrected through CTC (connective Temporal classification) and a label, so as to identify a numerical text.
Before the identification model is used for identifying the preprocessed water yield value picture, a large amount of training data needs to be collected for model training. Specifically, water yield value pictures of a large number of marked values are collected and divided into a training set and a testing set, a convolution cycle neural network (CRNN) is trained through the training set, and a training effect is checked and corrected through the testing set, so that a recognition model is obtained.
The identification module 33 transmits the information of the identified water amount value to the prediction module 34. The prediction module 34 calculates and stores the water consumption of each water meter by using the time cycle neural network LSTM as a prediction model, and predicts the water quantity value of each water meter in the next period according to the stored water consumption information. Specifically, the water consumption of each water meter in each period is counted, for example, the water consumption in each quarter, the water consumption in a working day and a non-working day and the like, collected water consumption data are normalized and input into a time-cycle neural network (LSTM) to carry out a large amount of data analysis to obtain a statistical rule, and therefore the water consumption in a future period is predicted.
The client 4 is in communication connection with the prediction module 34, and water service staff can inquire water consumption information of the water meter by logging in the client to perform relevant statistical analysis.
The server 3 also includes a reinforcement learning module 35. When the recognition module 33 cannot recognize the value text in the water amount value picture, the water amount value picture information data is sent to the reinforcement learning module 35. The reinforcement learning module 35 detects and reads the received water amount value image information through the monte carlo algorithm unit, identifies the water amount value image value text, and then sends the image related data to the identification module 33 to train and update the identification module 33.
The water meter identification system and the identification method provided by the invention are used for carrying out water meter picture numerical value positioning and numerical value text identification based on deep learning and reinforcement learning, so that the water meter water data is intelligently copied, the problems of complexity, time consumption and the like of manual meter reading are avoided, and the working efficiency is improved; the water consumption data of the water meter is analyzed through statistical data to predict the water consumption before the next week of the water meter, and powerful data support is provided for improving water management work.
While the present invention has been described in detail with reference to the preferred embodiments, it should be understood that the above description should not be taken as limiting the invention. Various modifications and alterations to this invention will become apparent to those skilled in the art upon reading the foregoing description. Accordingly, the scope of the invention should be determined from the following claims.
Claims (9)
1. A water meter identification system is characterized by comprising a plurality of image acquisition modules, a server and a client;
the image acquisition module is arranged at each water meter, the water meter pictures containing water quantity values are acquired through the image acquisition module, the acquired water meter picture information is sent to the server, the server identifies and stores the water quantity value information in the water meter pictures, and a worker inquires the water consumption information of each water meter stored in the server through the client.
2. The water meter identification system of claim 1, wherein the image capture module transmits the captured water meter picture information to the server via the network transmission module.
3. The water meter identification system of claim 1, wherein the server further comprises a positioning module, a preprocessing module, an identification module, and a prediction module;
the positioning module detects the value and positions the water quantity value in the water meter picture through the positioning model, and sends the water meter picture information of the positioned water quantity value position to the preprocessing module;
the preprocessing module is used for positioning and cutting a part of the water quantity value picture according to the positioned water quantity value position, correcting and/or enhancing information and reducing noise of the cut water quantity value picture, and sending the processed water quantity value picture information to the identification module;
the identification module identifies the value in the water quantity value picture through the identification model and transmits the identified water quantity value information to the prediction module;
the prediction module calculates and stores the water consumption of each water meter through the prediction model, and predicts the water quantity value of the next period of each water meter according to the stored water consumption information.
4. The water meter identification system of claim 3, wherein the location model is a text location network, the text location network being trained and verified via the water meter picture data set labeled with water volume value locations.
5. The water meter identification system of claim 3, wherein the preprocessing module performs Hough map correction on the oblique picture and performs information enhancement and noise reduction on the blurred picture.
6. The water meter identification system of claim 3, wherein the identification model is obtained by training and testing a convolutional recurrent neural network using a water volume value image data set of labeled values.
7. The water meter identification system of claim 3, wherein the prediction module uses a time-cycled neural network as the prediction model.
8. The water meter identification system of claim 7, wherein the server further comprises a reinforcement learning module;
the recognition module sends the water quantity value picture which cannot be recognized to the reinforcement learning module, the reinforcement learning module detects and reads the received water quantity value picture information through the Monte Carlo algorithm unit, and the recognition module is trained and updated by the water quantity value picture data of the read value.
9. An identification method based on the water meter identification system of any one of claims 1 to 8, characterized in that the identification method comprises the following processes:
step 1, collecting water meter pictures at each water meter by adopting an image collection module, and transmitting picture data to a server through a network transmission module;
step 2, in the server, a positioning module detects the position of the water quantity value in the positioning water meter picture through a positioning model and sends the water meter picture information of the position of the water quantity value to a preprocessing module;
step 3, the preprocessing module positions and cuts a part of water quantity value pictures in the water meter pictures according to the positioned water quantity value positions, corrects and/or enhances information and reduces noise of the water quantity value pictures, and the processed pictures are sent to the identification module;
step 4, the identification module identifies the water quantity value in the water quantity value picture through the identification model and sends the water quantity value to the prediction module;
step 5, when the identification model can not identify the water quantity value in the water quantity value picture, the identification module sends the water quantity value picture data to the reinforcement learning module, the reinforcement learning module detects and reads the received water quantity value picture information through the Monte Carlo algorithm unit, and the identification module is trained and updated by the identified water quantity value picture data;
and 6, calculating and storing the water consumption of each water meter by the prediction module through the prediction module, and predicting the water quantity value of the next period of each water meter according to the stored water consumption information by the prediction module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010633627.6A CN111783785B (en) | 2020-07-02 | 2020-07-02 | Water meter identification system and identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010633627.6A CN111783785B (en) | 2020-07-02 | 2020-07-02 | Water meter identification system and identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111783785A true CN111783785A (en) | 2020-10-16 |
| CN111783785B CN111783785B (en) | 2024-04-09 |
Family
ID=72758432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010633627.6A Active CN111783785B (en) | 2020-07-02 | 2020-07-02 | Water meter identification system and identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111783785B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159172A (en) * | 2021-04-20 | 2021-07-23 | 上海济辰水数字科技有限公司 | Intelligent water meter image positioning training method, intelligent water meter identification system and method |
| CN113159170A (en) * | 2021-04-20 | 2021-07-23 | 上海济辰水数字科技有限公司 | Intelligent water meter identification system and method based on deep learning |
| CN113177656A (en) * | 2021-04-16 | 2021-07-27 | 水利部珠江水利委员会技术咨询(广州)有限公司 | Multi-level water-saving analysis method and system based on intelligent water affairs |
| CN113221959A (en) * | 2021-04-20 | 2021-08-06 | 上海济辰水数字科技有限公司 | Intelligent water meter image recognition training method, intelligent water meter recognition system and intelligent water meter recognition method |
| CN115994837A (en) * | 2023-03-23 | 2023-04-21 | 河北雄安睿天科技有限公司 | Management system and method for water affair data |
| CN116883986A (en) * | 2023-08-07 | 2023-10-13 | 上海威派格智慧水务股份有限公司 | Water meter data identification method, device, equipment and computer readable medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107911654A (en) * | 2017-11-16 | 2018-04-13 | 四川长虹电器股份有限公司 | Water-flowmeter auto-recording and method based on image processing techniques |
| CN108830271A (en) * | 2018-06-13 | 2018-11-16 | 深圳市云识科技有限公司 | A kind of digital displaying meter Recognition of Reading method based on convolutional neural networks |
| CN109064731A (en) * | 2018-10-08 | 2018-12-21 | 深圳蜜獾智抄科技有限公司 | Image identification system, the collection with image identification system copy data system and a kind of remote concentrated ammeter reading method |
| WO2019174130A1 (en) * | 2018-03-14 | 2019-09-19 | 平安科技（深圳）有限公司 | Bill recognition method, server, and computer readable storage medium |
-
2020
- 2020-07-02 CN CN202010633627.6A patent/CN111783785B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107911654A (en) * | 2017-11-16 | 2018-04-13 | 四川长虹电器股份有限公司 | Water-flowmeter auto-recording and method based on image processing techniques |
| WO2019174130A1 (en) * | 2018-03-14 | 2019-09-19 | 平安科技（深圳）有限公司 | Bill recognition method, server, and computer readable storage medium |
| CN108830271A (en) * | 2018-06-13 | 2018-11-16 | 深圳市云识科技有限公司 | A kind of digital displaying meter Recognition of Reading method based on convolutional neural networks |
| CN109064731A (en) * | 2018-10-08 | 2018-12-21 | 深圳蜜獾智抄科技有限公司 | Image identification system, the collection with image identification system copy data system and a kind of remote concentrated ammeter reading method |
Non-Patent Citations (2)
| Title |
|---|
| 康鑫;孙晓刚;万磊;: "复杂场景下的水表示数检测与识别", 计算机应用, no. 2 * |
| 蒋良卫;黄玉柱;邓芙蓉;: "基于深度学习技术的图片文字提取技术的研究", 信息***工程, no. 03 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113177656A (en) * | 2021-04-16 | 2021-07-27 | 水利部珠江水利委员会技术咨询(广州)有限公司 | Multi-level water-saving analysis method and system based on intelligent water affairs |
| CN113159172A (en) * | 2021-04-20 | 2021-07-23 | 上海济辰水数字科技有限公司 | Intelligent water meter image positioning training method, intelligent water meter identification system and method |
| CN113159170A (en) * | 2021-04-20 | 2021-07-23 | 上海济辰水数字科技有限公司 | Intelligent water meter identification system and method based on deep learning |
| CN113221959A (en) * | 2021-04-20 | 2021-08-06 | 上海济辰水数字科技有限公司 | Intelligent water meter image recognition training method, intelligent water meter recognition system and intelligent water meter recognition method |
| CN115994837A (en) * | 2023-03-23 | 2023-04-21 | 河北雄安睿天科技有限公司 | Management system and method for water affair data |
| CN116883986A (en) * | 2023-08-07 | 2023-10-13 | 上海威派格智慧水务股份有限公司 | Water meter data identification method, device, equipment and computer readable medium |
| CN116883986B (en) * | 2023-08-07 | 2024-04-26 | 上海威派格智慧水务股份有限公司 | Water meter data identification method, device, equipment and computer readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111783785B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111783785A (en) | Water meter identification system and method | |
| CN111950396B (en) | Meter reading neural network identification method | |
| CN109543992A (en) | Intelligent polling method, device, intelligent terminal and server | |
| CN111914767B (en) | Scattered sewage enterprise detection method and system based on multi-source remote sensing data | |
| CN104484909A (en) | Method and device for routing inspection point determination, interaction method and interaction device | |
| CN107194823A (en) | A kind of mobile terminal agricultural monitoring method for early warning and system | |
| CN114518143A (en) | Intelligent environment sensing system | |
| CN115993366B (en) | Workpiece surface detection method and system based on sensing equipment | |
| CN117370919B (en) | Remote monitoring system for sewage treatment equipment | |
| CN113343998A (en) | Reading monitoring system and method for electric power mechanical meter, computer equipment and application | |
| CN117314313A (en) | Intelligent warehouse management system driven by artificial intelligence and Internet of things | |
| CN112541569A (en) | Sensor online training system and method based on machine learning | |
| CN112906602B (en) | Automatic identification device and identification method for electric quantity meter of power distribution cabinet based on image processing | |
| CN106780435A (en) | A kind of object count method and device | |
| CN114417981A (en) | Intelligent river length patrol system | |
| CN113393342A (en) | Building decoration project overall process management method and system | |
| CN113076730A (en) | Test report intelligent management method, device, system and storage medium | |
| CN116863122A (en) | Ammeter meter reading processing method, device, cloud end, system and medium | |
| CN115938009B (en) | Intelligent electronic inspection positioning method and system | |
| CN112132519A (en) | Bottled gas cross network system based on thing networking big data | |
| CN209881981U (en) | Remote meter reading system of bus electronic stop board | |
| CN108875738B (en) | Cloud identification error correction system and method of intelligent camera watch | |
| CN111271608A (en) | Leakage management system and method for compressed air system | |
| CN116754025B (en) | Image recognition technology-based auxiliary water balance test water quantity monitoring method | |
| CN116151521B (en) | Big data information acquisition method and system |
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 |