CN104102912A - Sub-item metering energy consumption data collection device based on video image identification and method thereof - Google Patents

Sub-item metering energy consumption data collection device based on video image identification and method thereof Download PDF

Info

Publication number
CN104102912A
CN104102912A CN201310113484.6A CN201310113484A CN104102912A CN 104102912 A CN104102912 A CN 104102912A CN 201310113484 A CN201310113484 A CN 201310113484A CN 104102912 A CN104102912 A CN 104102912A
Authority
CN
China
Prior art keywords
image
character
energy consumption
video
control module
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
Application number
CN201310113484.6A
Other languages
Chinese (zh)
Inventor
秦海勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN201310113484.6A priority Critical patent/CN104102912A/en
Publication of CN104102912A publication Critical patent/CN104102912A/en
Pending legal-status Critical Current

Links

Landscapes

  • Image Processing (AREA)

Abstract

The invention relates to a sub-item metering energy consumption data collection device based on video image identification. The method comprises the following steps: one camera is installed at a front end and responsible for taking in numbers of an energy consumption metering instrument or simulating images of pointer type display screens; analog video signals are encoded and converted into digital video signals via a video collector, and then the digital video signals are transmitted to an image preprocessing unit; a series of image processing and analysis are performed by the image preprocessing unit, a character segmentation unit and a character identification unit, and characters in the images are extracted; and character information is stored in a local storage unit according to the prescribed data format so as to be collected and counted by data collection gateway equipment and finally transmitted to an upper-level data center. Compared with a mode that energy consumption data automatic collection is realized by using a digital metering instrument with a data communication interface via replacement, the method is low in construction cost, low in construction difficulty and short in construction period, and has almost no influence on daily use of users so that the method is relatively suitable for occasions that the digital metering instrument cannot be replaced.

Description

A kind of metering separate energy consumption data acquisition device and method based on video image identification
[technical field]
The invention belongs to the metering separate data collecting field of building energy consumption monitoring system, specifically a kind of metering separate energy consumption data acquisition device and method based on video image identification.
[background technology]
Along with propelling, the expanding economy of Urbanization Process In China, the building energy consumption of China accounts for social total energy consumption ratio and is about 30%, and energy-saving potential is huge, and public building stands in the breach, and therefore building energy conservation is imperative.At present, the classification energy consumption of public building mainly comprises water, electric power, combustion gas etc., and gathering energy consumption data by the communication interface of digital metering instrument is the most desirable, the most efficient mode.
But in actual items is implemented, find that the energy consumption measure instrument of most of building does not possess the function of data communication.Conventional method is that existing measuring instrument is changed, and so not only increased construction cost and difficulty of construction, and construction period is longer, can have influence on the normal use of building.Especially in the time that needs are changed water and gas meter, also need to obtain the agreement of relevant unit, in practice of construction, also can run into various restrictions.Technological innovation aspect, traditional video identification technology can only be tackled digital instrument LCDs and be identified, and just cannot identify simulated pointer display screen.In order to overcome the above problems, the present invention proposes the method for video image identification, character and figure in identification video image, reach the object that gathers energy consumption data.
[summary of the invention]
Technical matters to be solved by this invention is: by the on-the-spot energy consumption measure instrument display screen of video monitoring, demonstration data are carried out to image acquisition; By image analysis module, image is carried out to pre-service, Character segmentation, character recognition, finally extract energy consumption numerical value; Numerical value is stored or is sent to on-the-spot comprehensive energy consumption data acquisition gateway.
For achieving the above object, design a kind of metering separate energy consumption data acquisition device based on video image identification, comprise camera, video collector, image pretreatment unit, Character segmentation unit, character recognition unit, storage unit and main control module, it is characterized in that camera is arranged on the display screen top of monitored instrument, be connected to video collector by video line, carry out image acquisition by master control module controls video collector, carry out image pre-service by main control module notice image pretreatment unit; Carrying out image character by main control module notice Character segmentation unit cuts apart, carry out character recognition by main control module notice character recognition unit, the data layout that is finally organized into regulation is saved in storage unit, sends to data acquisition gateway by the data of main control module calls storage unit.
Described monitored instrument comprises digital water meter, electronic metering table, digital gas meter, flow meter; Described camera is responsible for absorbing the image of energy-consumption meter display screen, and exports analog video signal; Described video collector is encoded analog video signal, exports to image pretreatment unit; Described image pretreatment unit embedded industrial control computer, the integrated major functions such as image pre-service, Character segmentation, character recognition processing.This element functions of modules also can directly be integrated with on-site data gathering gateway.
A kind of metering separate energy consumption data acquisition method based on video image identification of another design, is characterized in that the method comprises the steps:
A, the instrument display screen that needs image data is carried out to video monitoring, capture instrumented data image by master control module controls timing and be sent to image analysis module;
B, by master control module controls image analysis module, picture is carried out to pre-service;
C, by master control module controls, pretreated picture is carried out to Character segmentation processing;
D, by master control module controls, the picture after Character segmentation is carried out to character recognition processing;
E, by master control module controls by the energy consumption data of identification in accordance with regulations data layout be saved in local storage unit;
F, by master control module controls, energy consumption data is sent to data acquisition gateway.
In described steps A, discernible instrument is shown and comprises that digital lcd shows, analog pointer shows.
In described step B, successively carry out gray processing processing to gathering image, strengthen processing, binaryzation conversion, sharpening processing, slant correction, normalized.
In described step C, pretreated image is carried out respectively to sciagraphy separating character, upper and lower edge projection method separating character, connected domain method separating character.
Described step D comprises following technology: statistical nature character recognition technologies, structure character recognition technologies and the recognition technology based on neural network.Because application scenario of the present invention is that energy consumption measure instrument is shown to the video analysis of data, its character is mainly the unit symbol of arabic numeral and parameter, the character of analyzing normally occurs repeatedly, has repeatability.So only need early stage by the Template Information about character prototype knowledge and formation identification character, be stored in recognition system.
Described step B also comprises the steps:
B1, first by image gray processing, coloured image is converted to gray level image, with speed up processing, also saved storage space.The advantage of gray level image is to only have strength information and the image that there is no colouring information, and storage gray level image only needs a data matrix, the gray-scale value of the each element representation correspondence position of matrix pixel;
B2, carry out image enhancement processing, adjust the contrast of image, the material particular in outstanding image, in the image after enhancing, character is clear, region is clearly demarcated, has expanded the tonal range of image, is convenient to binaryzation and Character segmentation processing;
B3, carry out image binaryzation conversion, determine suitable threshold value, make character and the background can be separated.The image of binaryzation possesses good conformality, does not lose useful shape information, does not produce extra vacancy;
B4, carry out image sharpening processing, after the differential method and high-pass filtering method sharpening, make fuzzy image become clear, strengthen the outstanding or clear-cut in the edge of image;
B5, carry out image inclination correction, make character in same level position, be convenient to like this cutting apart and improving the accuracy rate of character recognition of character;
B6, be normalized, height and the width dimensions of unified character, make the accuracy of character recognition higher.
Described step C also comprises the steps:
C1, sciagraphy separating character, after character picture binaryzation, scan by column image taking pixel as unit, the pixel that cumulative this train value is 1, and the result of accumulation is the vertical projection of these row.To obtaining the vertical projection of entire image after all column scans of image.The pixel that is 1 due to the boundary gray scale of character in vertical projection histogram is little, therefore this place shows as very low trough after projection, and the boundary using null statistical value row as Character segmentation;
C2, as existed cavity or picture quality not high in character time, while there is after binaryzation Characters Stuck, apply upper and lower edge projection method, solve the defect of traditional vertical projection method.Upper and lower edge projection refers to the distance between character coboundary and lower limb, wherein " character coboundary " refers to taking pixel as unit along the search from top to bottom of image row until run into first point of character zone, " character lower limb " refers to be listed as search from bottom to top until run into first point of character zone taking pixel as unit along image, and upper and lower edge projection is the poor of character coboundary and character lower limb;
C3, connected domain method separating character, can avoid the bad impact bringing of pretreating effect, fundamentally solves the problem of inclination Character segmentation.Its algorithm is first from left to right, scans entire image from top to bottom, finds first unlabelled pixel, and then initialization pixel queue is empty, this pixel mark, adds queue.Secondly search queue head portrait vegetarian refreshments around field pixel mark, add queue and delete team's element and repeat until queue empty with this.Use the quick and precisely all connected domains in positioning image of this algorithm, the error that may occur during due to noise and binaryzation, we must remove, and in region, some can not be obviously the connected domains of character zone, for example, in the excessive or connected domain of the width too small region of number of pixel.After the connected domain of finding out in image, then make the boundary rectangle of each connected domain.
Beneficial effect of the present invention is: the method for utilizing video analysis view data that the present invention proposes, and save on the one hand the cost of instrument replacing and reduced difficulty of construction, also reduce on the other hand construction infection scope.Use of the present invention also, by a kind of new approach is provided for energy consumption data acquisition mode, is used in conjunction with each other the effect that must reach satisfied with traditional acquisition mode.
[brief description of the drawings]
Fig. 1 is system frame structure figure of the present invention
In figure:
1. camera: be mainly used to absorb energy-consumption meter display screen, conventionally export analog video signal;
2. video collector: main being responsible for analog video signal coding, output digit signals;
3. image pretreatment unit: digital picture is carried out a series of processing by main being responsible for, and is convenient to Character segmentation processing;
4. Character segmentation unit: be mainly responsible for, to a succession of character, being divided into single character, be convenient to character recognition processing;
5. character recognition unit: main being responsible for identified single character one by one, forms data and preserves;
6. storage unit: be mainly responsible for the data that storage has been identified, and be ready for sending to data acquisition gateway;
7. main control module: be mainly responsible for to the transmit operation instruction of individual unit, and receive the feedback information of each unit;
8. vision signal;
9. digital signal;
10. control signal;
11. character outputs.
[embodiment]
Now in conjunction with the drawings and the specific embodiments a whole set of technical scheme of the present invention is further elaborated, this manufacturing technology is very clearly for a person skilled in the art.
Embodiment
As shown in Figure 1, the present invention includes that camera image picked-up, video collector Signal coding, image pre-service, image character are cut apart, image character is identified, character data is preserved, it is characterized in that camera is arranged on the display screen top of monitored instrument, is connected to video collector by video line; Carry out image acquisition by master control module controls video collector, after the coding of going forward side by side, pass through netting twine output digital video signal; Carry out image pre-service by main control module notice image pretreatment unit; Carrying out image character by main control module notice Character segmentation unit cuts apart; Carry out character recognition by main control module notice character recognition unit, the data layout that is finally organized into regulation is saved in storage unit.Send to data acquisition gateway by the data of main control module calls storage unit as required.
The present invention has disclosed a kind of metering separate energy consumption data acquisition method based on video image identification, inconvenient or do not allow to change the occasion of measuring instrument, energy consumption data is gathered automatically; For energy consumption data acquisition provides again a kind of simple and feasible method.
For the ease of description afterwards, first term is carried out to description below:
Energy consumption measure instrument: building energy consumption gauge table mainly comprises digital water meter, electronic metering table, digital gas meter, flow meter etc., according to actual conditions, the instrument that does not normally possess communication function of installing in building of a specified duration for some year.
Video frequency pick-up head: be responsible for the image of picked-up energy-consumption meter display screen, and export analog video signal;
Video image acquisition device: analog video signal is encoded, export to image analyzing unit;
Image analyzing unit: embedded industrial control computer, the integrated major functions such as image pre-service, Character segmentation, character recognition processing.This element functions of modules also can directly be integrated with on-site data gathering gateway.
Data acquisition gateway: be applied to the special embedded Communication Gateway of fan-free of data acquisition in building energy consumption monitoring system.Built-in embedded OS, support to be configured and planning database by Web mode, compatible various common device communications protocol, can realize communication and data acquisition between various device, Data Transport Protocol meets " government offices' office building and large public building energy-consumption monitoring system subitem energy consumption data acquisition technology directive/guide " standard.
System work process narration:
Refer to Fig. 1, the metering separate energy consumption data acquisition method that the present invention is based on video image identification comprises the steps:
A, the instrument display screen that needs image data is carried out to video monitoring, capture instrumented data image by master control module controls timing and be sent to image analysis module;
B, by master control module controls image analysis module, picture is carried out to pre-service;
C, by master control module controls, pretreated picture is carried out to Character segmentation processing;
D, by master control module controls, the picture after Character segmentation is carried out to character recognition processing;
E, by master control module controls by the energy consumption data of identification in accordance with regulations data layout be saved in local storage unit;
F, by master control module controls, energy consumption data is sent to data acquisition gateway.
In sum, the metering separate energy consumption data acquisition method based on video image identification that the present invention proposes, the display screen of energy consumption measure instrument is carried out to video monitoring, to after monitored picture coding, send to image analyzing unit, extract the energy consumption character in image through character recognition scheduling algorithm, data layout is in accordance with regulations preserved, then sends to energy consumption data gateway to add up and forward.The present invention is the occasion of being inconvenient to change digital energy-consumption meter, and a kind of efficient, feasible solution is provided, thereby has intactly realized the data acquisition of building energy consumption metering separate.

Claims (9)

1. the metering separate energy consumption data acquisition device based on video image identification, comprise camera, video collector, image pretreatment unit, Character segmentation unit, character recognition unit, storage unit and main control module, it is characterized in that camera is arranged on the display screen top of monitored instrument, be connected to video collector by video line, carry out image acquisition by master control module controls video collector, carry out image pre-service by main control module notice image pretreatment unit; Carrying out image character by main control module notice Character segmentation unit cuts apart, carry out character recognition by main control module notice character recognition unit, the data layout that is finally organized into regulation is saved in storage unit, sends to data acquisition gateway by the data of main control module calls storage unit.
2. a kind of metering separate energy consumption data acquisition device based on video image identification as claimed in claim 1, is characterized in that described monitored instrument comprises digital water meter, electronic metering table, digital gas meter, flow meter; Described camera is responsible for absorbing the image of energy-consumption meter display screen, and exports analog video signal; Described video collector is encoded analog video signal, exports to image pretreatment unit; Described image pretreatment unit embedded industrial control computer, the integrated major functions such as image pre-service, Character segmentation, character recognition processing.This element functions of modules also can directly be integrated with on-site data gathering gateway.
3. the metering separate energy consumption data acquisition method based on video image identification, is characterized in that the method comprises the steps:
A, the instrument display screen that needs image data is carried out to video monitoring, capture instrumented data image by master control module controls timing and be sent to image analysis module;
B, by master control module controls image analysis module, picture is carried out to pre-service;
C, by master control module controls, pretreated picture is carried out to Character segmentation processing;
D, by master control module controls, the picture after Character segmentation is carried out to character recognition processing;
E, by master control module controls by the energy consumption data of identification in accordance with regulations data layout be saved in local storage unit;
F, by master control module controls, energy consumption data is sent to data acquisition gateway.
4. a kind of metering separate energy consumption data acquisition method based on video image identification as claimed in claim 3, is characterized in that in described steps A, discernible instrument being shown and comprising that digital lcd shows, analog pointer shows.
5. a kind of metering separate energy consumption data acquisition method based on video image identification as claimed in claim 3, it is characterized in that in described step B, successively carry out gray processing processing to gathering image, strengthen processing, binaryzation conversion, sharpening processing, slant correction, normalized.
6. a kind of metering separate energy consumption data acquisition method based on video image identification as claimed in claim 3, is characterized in that described step B also comprises the steps:
B1, first by image gray processing, coloured image is converted to gray level image, with speed up processing, also saved storage space.The advantage of gray level image is to only have strength information and the image that there is no colouring information, and storage gray level image only needs a data matrix, the gray-scale value of the each element representation correspondence position of matrix pixel;
B2, carry out image enhancement processing, adjust the contrast of image, the material particular in outstanding image, in the image after enhancing, character is clear, region is clearly demarcated, has expanded the tonal range of image, is convenient to binaryzation and Character segmentation processing;
B3, carry out image binaryzation conversion, determine suitable threshold value, make character and the background can be separated.The image of binaryzation possesses good conformality, does not lose useful shape information, does not produce extra vacancy;
B4, carry out image sharpening processing, after the differential method and high-pass filtering method sharpening, make fuzzy image become clear, strengthen the outstanding or clear-cut in the edge of image;
B5, carry out image inclination correction, make character in same level position, be convenient to like this cutting apart and improving the accuracy rate of character recognition of character;
B6, be normalized, height and the width dimensions of unified character, make the accuracy of character recognition higher.
7. a kind of metering separate energy consumption data acquisition method based on video image identification as claimed in claim 3, it is characterized in that in described step C, pretreated image is carried out respectively to sciagraphy separating character, upper and lower edge projection method separating character, connected domain method separating character.
8. a kind of metering separate energy consumption data acquisition method based on video image identification as claimed in claim 3, is characterized in that described step C also comprises the steps:
C1, sciagraphy separating character, after character picture binaryzation, scan by column image taking pixel as unit, the pixel that cumulative this train value is 1, and the result of accumulation is the vertical projection of these row.To obtaining the vertical projection of entire image after all column scans of image.The pixel that is 1 due to the boundary gray scale of character in vertical projection histogram is little, therefore this place shows as very low trough after projection, and the boundary using null statistical value row as Character segmentation;
C2, as existed cavity or picture quality not high in character time, while there is after binaryzation Characters Stuck, apply upper and lower edge projection method, solve the defect of traditional vertical projection method.Upper and lower edge projection refers to the distance between character coboundary and lower limb, wherein " character coboundary " refers to taking pixel as unit along the search from top to bottom of image row until run into first point of character zone, " character lower limb " refers to be listed as search from bottom to top until run into first point of character zone taking pixel as unit along image, and upper and lower edge projection is the poor of character coboundary and character lower limb;
C3, connected domain method separating character, can avoid the bad impact bringing of pretreating effect, fundamentally solves the problem of inclination Character segmentation.Its algorithm is first from left to right, scans entire image from top to bottom, finds first unlabelled pixel, and then initialization pixel queue is empty, this pixel mark, adds queue.Secondly search queue head portrait vegetarian refreshments around field pixel mark, add queue and delete team's element and repeat until queue empty with this.Use the quick and precisely all connected domains in positioning image of this algorithm, the error that may occur during due to noise and binaryzation, we must remove, and in region, some can not be obviously the connected domains of character zone, for example, in the excessive or connected domain of the width too small region of number of pixel.After the connected domain of finding out in image, then make the boundary rectangle of each connected domain.
9. a kind of metering separate energy consumption data acquisition method based on video image identification as claimed in claim 3, it is characterized in that in described step D, the image that Character segmentation was processed, carries out respectively statistical nature character recognition, structure character recognition and the identification based on neural network.
CN201310113484.6A 2013-04-02 2013-04-02 Sub-item metering energy consumption data collection device based on video image identification and method thereof Pending CN104102912A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310113484.6A CN104102912A (en) 2013-04-02 2013-04-02 Sub-item metering energy consumption data collection device based on video image identification and method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310113484.6A CN104102912A (en) 2013-04-02 2013-04-02 Sub-item metering energy consumption data collection device based on video image identification and method thereof

Publications (1)

Publication Number Publication Date
CN104102912A true CN104102912A (en) 2014-10-15

Family

ID=51671052

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310113484.6A Pending CN104102912A (en) 2013-04-02 2013-04-02 Sub-item metering energy consumption data collection device based on video image identification and method thereof

Country Status (1)

Country Link
CN (1) CN104102912A (en)

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105163196A (en) * 2015-06-19 2015-12-16 美国掌赢信息科技有限公司 Real-time video coding method and electronic equipment
CN105163195A (en) * 2015-06-19 2015-12-16 美国掌赢信息科技有限公司 Real-time video coding method and electronic equipment
CN105335760A (en) * 2015-11-16 2016-02-17 南京邮电大学 Image number character recognition method
CN105930842A (en) * 2016-04-15 2016-09-07 深圳市永兴元科技有限公司 Character recognition method and device
CN106874910A (en) * 2017-01-19 2017-06-20 广州优库电子有限公司 The self-service meter reading terminal of low-power consumption instrument long-distance and method based on OCR identifications
CN106878685A (en) * 2017-03-21 2017-06-20 陈艳婕 A kind of energy consumption data acquisition device and method based on image recognition
CN108053872A (en) * 2017-12-27 2018-05-18 苏州麦迪斯顿医疗科技股份有限公司 A kind of harvester and its acquisition method of data of dialysing
CN108337323A (en) * 2018-03-19 2018-07-27 深圳增强现实技术有限公司 A kind of metering instrument data AR Compare Systems and method based on full terminal
CN109063614A (en) * 2018-07-19 2018-12-21 江苏省计量科学研究院 A kind of liquid crystal display digit recognition method
CN109066986A (en) * 2018-09-03 2018-12-21 南京永为科技有限公司 Intelligent power distribution control system
CN109360396A (en) * 2018-09-27 2019-02-19 长江大学 Remote meter reading method and system based on image recognition technology and NB-IoT technology
CN110032348A (en) * 2019-03-21 2019-07-19 北京空间飞行器总体设计部 A kind of character display method, device, medium
TWI667557B (en) * 2017-01-19 2019-08-01 由田新技股份有限公司 Instrumentation image analyzing device, system, method, and computer readable medium
CN110689017A (en) * 2018-07-06 2020-01-14 康姆德润达(无锡)测量技术有限公司 Filter membrane ID image recognition system
CN111260572A (en) * 2020-01-13 2020-06-09 湖南城市学院 Recorder for computer graphic image processing and image processing method
CN111401381A (en) * 2020-03-27 2020-07-10 白志青 Digital monitoring system and monitoring method for slow door imaging recognition instrument
CN111414218A (en) * 2020-03-18 2020-07-14 合肥讯飞读写科技有限公司 Method, device and equipment for adjusting character contrast in display page
CN111639646A (en) * 2020-05-18 2020-09-08 山东大学 Test paper handwritten English character recognition method and system based on deep learning
CN114170753A (en) * 2021-12-03 2022-03-11 辰安天泽智联技术有限公司 Information acquisition and processing system and method for building fire fighting system

Cited By (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105163195A (en) * 2015-06-19 2015-12-16 美国掌赢信息科技有限公司 Real-time video coding method and electronic equipment
CN105163196A (en) * 2015-06-19 2015-12-16 美国掌赢信息科技有限公司 Real-time video coding method and electronic equipment
CN105335760A (en) * 2015-11-16 2016-02-17 南京邮电大学 Image number character recognition method
CN105930842A (en) * 2016-04-15 2016-09-07 深圳市永兴元科技有限公司 Character recognition method and device
TWI667557B (en) * 2017-01-19 2019-08-01 由田新技股份有限公司 Instrumentation image analyzing device, system, method, and computer readable medium
CN106874910A (en) * 2017-01-19 2017-06-20 广州优库电子有限公司 The self-service meter reading terminal of low-power consumption instrument long-distance and method based on OCR identifications
CN106878685A (en) * 2017-03-21 2017-06-20 陈艳婕 A kind of energy consumption data acquisition device and method based on image recognition
CN108053872A (en) * 2017-12-27 2018-05-18 苏州麦迪斯顿医疗科技股份有限公司 A kind of harvester and its acquisition method of data of dialysing
CN108337323B (en) * 2018-03-19 2021-11-23 深圳增强现实技术有限公司 Instrument metering data AR comparison system and method based on full terminal
CN108337323A (en) * 2018-03-19 2018-07-27 深圳增强现实技术有限公司 A kind of metering instrument data AR Compare Systems and method based on full terminal
CN110689017A (en) * 2018-07-06 2020-01-14 康姆德润达(无锡)测量技术有限公司 Filter membrane ID image recognition system
CN109063614A (en) * 2018-07-19 2018-12-21 江苏省计量科学研究院 A kind of liquid crystal display digit recognition method
CN109066986A (en) * 2018-09-03 2018-12-21 南京永为科技有限公司 Intelligent power distribution control system
CN109360396B (en) * 2018-09-27 2021-07-30 长江大学 Remote meter reading method and system based on image recognition technology and NB-IoT technology
CN109360396A (en) * 2018-09-27 2019-02-19 长江大学 Remote meter reading method and system based on image recognition technology and NB-IoT technology
CN110032348A (en) * 2019-03-21 2019-07-19 北京空间飞行器总体设计部 A kind of character display method, device, medium
CN110032348B (en) * 2019-03-21 2022-05-24 北京空间飞行器总体设计部 Character display method, device and medium
CN111260572A (en) * 2020-01-13 2020-06-09 湖南城市学院 Recorder for computer graphic image processing and image processing method
CN111414218A (en) * 2020-03-18 2020-07-14 合肥讯飞读写科技有限公司 Method, device and equipment for adjusting character contrast in display page
CN111401381A (en) * 2020-03-27 2020-07-10 白志青 Digital monitoring system and monitoring method for slow door imaging recognition instrument
CN111639646B (en) * 2020-05-18 2021-04-13 山东大学 Test paper handwritten English character recognition method and system based on deep learning
CN111639646A (en) * 2020-05-18 2020-09-08 山东大学 Test paper handwritten English character recognition method and system based on deep learning
CN114170753A (en) * 2021-12-03 2022-03-11 辰安天泽智联技术有限公司 Information acquisition and processing system and method for building fire fighting system
CN114170753B (en) * 2021-12-03 2024-04-19 天泽智联科技股份公司 Information acquisition processing system and method for building fire protection system

Similar Documents

Publication Publication Date Title
CN104102912A (en) Sub-item metering energy consumption data collection device based on video image identification and method thereof
CN108765404B (en) A kind of road damage testing method and device based on deep learning image classification
CN107527067B (en) Railway roadbed disease intelligent identification method based on ground penetrating radar
CN107463931A (en) A kind of real-time pointer instrument reading method and device based on ARM platforms
CN101706875B (en) Hand-held laser code-jetting character recognizer under complex background
CN109636772A (en) The defect inspection method on the irregular shape intermetallic composite coating surface based on deep learning
CN104809188B (en) A kind of data mining analysis method of talent drain in corporations and device
CN110070530A (en) A kind of powerline ice-covering detection method based on deep neural network
CN108711148B (en) Tire defect intelligent detection method based on deep learning
CN102915432A (en) Method and device for extracting vehicle-bone microcomputer image video data
CN110503070A (en) Traffic automation monitoring method based on Aerial Images object detection process technology
CN109993154A (en) The lithium sulfur type instrument intelligent identification Method of substation's simple pointer formula
WO2021258636A1 (en) Deep hierarchical fuzzy algorithm-based environmental protection equipment recognition method and system
CN110287967B (en) Image-based digit and mechanical watch digit identification method
CN110427943A (en) A kind of intelligent electric meter technique for partitioning based on R-CNN
CN107264570A (en) steel rail light band distribution detecting device and method
CN201355495Y (en) Mall passenger flow analysis system
CN201654804U (en) Character recognizer
CN104048966A (en) Big-law-based cloth cover defect detection and classification method
CN202815869U (en) Vehicle microcomputer image and video data extraction apparatus
CN115272843A (en) Road disease detection method and system based on bridging characteristic fusion
CN111339927A (en) Intelligent work state identification system for personnel in electric power business hall
CN110428398A (en) A kind of high iron catenary bracing wire defect inspection method based on deep learning
CN103941672A (en) Airfield runway snow removing work quality evaluating system
CN109933583A (en) A kind of passenger flow statistics and objective group's portrait analysis method and system

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C02 Deemed withdrawal of patent application after publication (patent law 2001)
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20141015