CN107392202A - A kind of pointer type Recognition of Reading method and system - Google Patents

A kind of pointer type Recognition of Reading method and system Download PDF

Info

Publication number
CN107392202A
CN107392202A CN201710522680.7A CN201710522680A CN107392202A CN 107392202 A CN107392202 A CN 107392202A CN 201710522680 A CN201710522680 A CN 201710522680A CN 107392202 A CN107392202 A CN 107392202A
Authority
CN
China
Prior art keywords
image
pointer type
interest
area
reading
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
CN201710522680.7A
Other languages
Chinese (zh)
Inventor
聂为清
吴绍根
黄跃珍
裴佳敏
谭俊
马婷
梁永晔
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.)
Guangzhou Radio And Television Property Management Co Ltd
Original Assignee
Guangzhou Radio And Television Property Management Co Ltd
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 Guangzhou Radio And Television Property Management Co Ltd filed Critical Guangzhou Radio And Television Property Management Co Ltd
Priority to CN201710522680.7A priority Critical patent/CN107392202A/en
Publication of CN107392202A publication Critical patent/CN107392202A/en
Pending legal-status Critical Current

Links

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
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/48—Extraction of image or video features by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation
    • 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)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a kind of pointer type Recognition of Reading method, the image of pointer type equipment is gathered first, then the image of area-of-interest is intercepted out, then straight line is obtained from the image of the area-of-interest, build the position masterplate of pointer type equipment, the reading that the pointer type equipment is currently shown is identified from the position masterplate, the reading is finally sent to Surveillance center；Invention additionally discloses a kind of pointer type Recognition of Reading system, including image acquisition units, area-of-interest image acquisition unit, masterplate construction unit, Recognition of Reading unit and communication unit.In the case that the present invention transforms inside not carried out to non intelligent indicator instrument, realize and the intelligent reading and intelligent data of non intelligent indicator instrument are collected.

Description

A kind of pointer type Recognition of Reading method and system
Technical field
The present invention relates to instrument field, more particularly to a kind of pointer type Recognition of Reading method and system.
Background technology
In our daily life, it is necessary to using various types of living resources, including：Water, electricity, coal gas etc., these Living resources are that various resource suppliers are transported to end user by certain mode, and user must be to used resource Paid by using stock number, therefore, to end user using the metering of resource be implement payment basis and premise, and To using the metering of resource be by various resources " meter " complete.
Current many residential quarters, industrial park, office block using do not possess teledata send automatically/read work( The so-called non intelligent meter of energy, in order to periodically obtain the reading in this type meters, it is necessary to be carried out by certain cycle It is artificial to read, therefore, workload is big, reading not in time, error rate it is high.In order to be incorporated into the automatic system of centralized management Unite and expand, it is necessary to carry out " non-intrusion type " to this kind of meter within framework, i.e., expanded by outside, make them also can be by default Cycle or require to upload meter reading to center service system.
The content of the invention
The purpose of the embodiment of the present invention is to provide a kind of pointer type Recognition of Reading method and system, can be effectively to non intelligent The function of indicator instrument is expanded, and realizes and the intelligent reading and intelligent data of non intelligent indicator instrument are collected.
To achieve the above object, the embodiments of the invention provide a kind of pointer type Recognition of Reading method, it is characterised in that bag Include step：
S1, the original image for gathering pointer type equipment；
S2, ROI processing is carried out to the original image, to intercept the image of area-of-interest；
S3, straight line is obtained from the image of the area-of-interest, build the position masterplate of pointer type equipment；
S4, position identification is carried out to the position masterplate, to obtain the reading information of the pointer type equipment；
S5, the reading information is sent to Surveillance center.
Compared with prior art, a kind of pointer type Recognition of Reading method disclosed in the one of embodiment of the present invention, first The image of pointer type equipment is gathered, the image of area-of-interest is then intercepted out, then from the image of the area-of-interest Straight line is obtained, the position masterplate of pointer type equipment is built, identifies that the pointer type equipment currently shows from the position masterplate The reading shown, the reading is finally sent to Surveillance center, the feelings transformed inside not carried out to non intelligent indicator instrument Under condition, realize and the intelligent reading and intelligent data of non intelligent indicator instrument are collected.
As the improvement of such scheme, the original image is RGB image.
As the improvement of such scheme, the step S3 is specifically included：
S31, the image of the area-of-interest is converted into gray level image from RGB image, obtains the ash of area-of-interest Spend image；
S32, the gray level image to the area-of-interest carry out binary conversion treatment, obtain the binary picture of area-of-interest Picture.
Improvement as such scheme, it is characterised in that carry out the binary conversion treatment and use gray scale draw value value method.
Improvement as such scheme, it is characterised in that the step S3 also includes：
Straight line is obtained from the binary image of the area-of-interest, builds the position masterplate.
As the improvement of such scheme, the step S3 also includes：
S33, the binary image micronization processes to the area-of-interest, from the binary image of the area-of-interest In obtain tuning drive gear skeleton；
S34, straight line is obtained from the tuning drive gear skeleton, build the position masterplate of pointer type equipment.
Compared with prior art, a kind of pointer type Recognition of Reading method disclosed in the one of embodiment of the present invention, passes through Micronization processes are carried out to the binary image of the area-of-interest, the degree of accuracy for obtaining straight line are improved, so as to improve Rheme puts the confidence level of masterplate, improves the accuracy of the reading information finally given.
As the improvement of such scheme, iteration is used to the micronization processes of the binary image of the area-of-interest Algorithm.
As the improvement of such scheme, straight line is obtained using Hough or Radon conversion.
In order to solve the above-mentioned technical problem, the embodiment of the present invention additionally provides a kind of pointer type Recognition of Reading system, and it is special Sign is, including：
Image acquisition units, for gathering the original image of pointer type equipment；
Area-of-interest image acquisition unit, ROI processing is carried out to the original image, to intercept the figure of area-of-interest Picture；
Masterplate construction unit, for obtaining straight line from the image of the area-of-interest, build the position of pointer type equipment Put masterplate；
Recognition of Reading unit, position identification is carried out for the position masterplate, to obtain the reading of the pointer type equipment Information；
Communication unit, for the reading information to be sent into Surveillance center.
Compared with prior art, a kind of pointer type Recognition of Reading system disclosed by the invention, image acquisition units collection refer to The original image of needle-like equipment, area-of-interest image acquisition unit intercept out the figure of area-of-interest from the original image Picture, masterplate construction unit obtain straight line from the image of the area-of-interest, build the position masterplate of pointer type equipment, reading Recognition unit identifies the reading that the pointer type equipment is currently shown from the position masterplate, finally by communication unit by institute State reading and be sent to Surveillance center, in the case of being transformed inside not carried out to non intelligent indicator instrument, realize to non-intelligence The intelligent reading and intelligent data of energy indicator instrument collect.
Brief description of the drawings
Fig. 1 is a kind of main flow schematic diagram of pointer type Recognition of Reading method in the embodiment of the present invention；
Fig. 2 is the specific schematic flow sheets of a kind of pointer type Recognition of Reading method and step S3 in the embodiment of the present invention；
Fig. 3 is a kind of primary structure schematic diagram of pointer type Recognition of Reading system in the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.It is based on Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of creative work is not made Embodiment, belong to the scope of protection of the invention.
Referring to Fig. 1 and Fig. 2, Fig. 1 is a kind of main flow of pointer type Recognition of Reading method provided in an embodiment of the present invention Schematic diagram, Fig. 2 are the specific schematic flow sheets of step S3, and the embodiment of the present invention includes step：
S1, the original image for gathering pointer type equipment；The original image of collecting device automatic data collection pointer type equipment, use Acquisition method can include the picture of camera shooting pointer type equipment or video by recording pointer type equipment etc., herein Do not repeat；Preferably, the colour model that the original image collected in the present embodiment uses is RGB, in other embodiments, Color can also HSV or HSI, do not influence the beneficial effect that obtains of the present invention.
S2, ROI processing is carried out to the original image, preset the area-of-interest number of the corresponding pointer type equipment According to, after the original image is collected, by ROI algorithms to the original image carry out area-of-interest extraction, obtain To the image of the area-of-interest, while filter out the image information in other regions.
S3, straight line is obtained from the image of the area-of-interest, build the position masterplate of pointer type equipment；Specifically, Include step referring to Fig. 2, step S3：
S31, the image of the area-of-interest is converted into gray level image from RGB image, specific transfer algorithm is using meter Calculate formula：
Gray=R*0.299+G*0.587+B*0.114
Wherein, Gray is gray value, and R is the R values in RGB image, and G is the G values in RGB image, and B is the B in RGB image Value, is calculated the gray value of the current location by the rgb value of current pixel location point and is changed, obtain the sense The gray level image in interest region.
S32, according to actual grey image information set binary-state threshold, to the gray level image of the area-of-interest Binarization operation is carried out, the tuning drive gear and background for making the gray level image of the area-of-interest are presented black and white, obtained respectively The binary image of area-of-interest.Specifically, the gray level image of the area-of-interest is entered using gray scale draw value value method Row binary conversion treatment.In the present embodiment, black is presented in scale and pointer, and white is presented in background, but in other embodiments, Can be scale and pointer presentation white, black is presented in background, does not influence the beneficial effect that the present invention obtains.
S33, the binary image to the area-of-interest carry out micronization processes, obtain tuning drive gear skeleton.Specifically, Using iterative algorithm, the pixel edge of the scale graph and pointer figure is gradually deleted, until the scale graph and described Pointer figure is left the tuning drive gear skeleton in figure center；In other embodiments, noniterative algorithm can also be used, is such as based on Algorithm of range conversion etc., the beneficial effect that the present invention obtains is not influenceed.
S44, straight line is obtained from the tuning drive gear skeleton, build the position masterplate of pointer type equipment.Specifically, using Hough transform obtains the scale of the pointer type equipment and the line pattern of pointer from the tuning drive gear skeleton, according to obtaining The scale got and the position of the line pattern of the pointer, construct the position masterplate of the pointer type equipment.
In other embodiments, micronization processes directly can be carried out to the gray level image of the area-of-interest, obtains institute Tuning drive gear skeleton is stated, does not influence the beneficial effect that the present invention obtains.
S4, position identification is carried out to the position masterplate, to obtain the reading information of the pointer type equipment.Specifically, By the position masterplate compared with default built-in template, the more specific location information of pointer in the position masterplate is obtained, from institute State the reading information that the pointer type equipment is read in the more specific location information of pointer.
S5, the reading information extracted is sent to Surveillance center, approach can be wirelessly transferred or wired biography Defeated, therefore not to repeat here.
Surveillance center is implemented function such as by gathering data based on the reading information：(1) basic data acquisition Function, this is most basic business function, gathers periodically or on demand basic data；(2) anomaly data detection function, to collection To basic data in abnormal data detected, for example, the use to water resource, if this reading occur being more than or Less than some empirical value of historical data, then it is considered as abnormal data, it is necessary to again read off or artificial detection.(3) at data analysis Function is managed, according to the needs of business, completes the analysis to basic data and statistical function, and show result by default requirement To manager.
When it is implemented, gathering the image of pointer type equipment first, the image of area-of-interest, conversion sense are then intercepted out The Color scheme of the image in interest region, straight line is then obtained from the image of the area-of-interest, build pointer type equipment Position masterplate, the reading that the pointer type equipment is currently shown is analyzed from the position masterplate, finally by the reading Surveillance center is sent to, in the case of being transformed inside not carried out to non intelligent indicator instrument, is realized to non intelligent pointer The intelligent reading and intelligent data of meter collect.
The present embodiment effectively can carry out the expansion of " non-intrusion type " to the function of non intelligent indicator instrument, realize to non- The intelligent reading and intelligent data of intelligent pointer meter collect.
Referring to Fig. 3, the embodiment of the present invention additionally provides a kind of pointer type Recognition of Reading system, the pointer type Recognition of Reading System 10 includes image acquisition units 1, area-of-interest image acquisition unit 2, masterplate construction unit 3, the and of Recognition of Reading unit 4 Communication unit 5.
Image acquisition units 1 are used to gather pointer type equipment drawing picture, carry out IMAQ to pointer type equipment drawing picture, obtain The original image information of the pointer type equipment, and the original image information is sent to area-of-interest image acquisition unit 2.Preferably, the colour model that the original image collected in the present embodiment uses is RGB, in other embodiments, color The beneficial effect that the present invention obtains can not be influenceed with HSV or HSI.
Area-of-interest image acquisition unit 2 receives the original image information of the transmission of image acquisition units 1, to institute State original image information to be analyzed, using suitable default area-of-interest image zooming-out parameter, based on ROI algorithms to described Original image information carries out area-of-interest image zooming-out, obtains region of interest area image, and by the region of interest area image It is sent to masterplate construction unit 3.
Masterplate construction unit 3, for carrying out micronization processes to the region of interest area image, to obtain tuning drive gear bone Frame.Masterplate construction unit 3 first to the region of interest area image carry out gradation conversion, by the region of interest area image from RGB image is converted to gray level image, and specific transfer algorithm uses calculation formula：
Gray=R*0.299+G*0.587+B*0.114
Wherein, Gray is gray value, and R is the R values in RGB image, and G is the G values in RGB image, and B is the B in RGB image Value, is calculated the gray value of the current location by the rgb value of current pixel location point and is changed, obtain the sense The gray level image in interest region.
Binary-state threshold is set according to actual grey image information, masterplate construction unit 3 is to the area-of-interest Gray level image carry out binarization operation, make the tuning drive gear of the gray level image of the area-of-interest and background present respectively it is black White, obtain the binary image of area-of-interest.Specifically, using gray scale draw value value method to the ash of the area-of-interest Spend image and carry out binary conversion treatment.In the present embodiment, black is presented in scale and pointer, and white is presented in background, but in other realities Apply in example or white is presented in scale and pointer, black is presented in background, does not influence the beneficial effect that the present invention obtains.
Masterplate construction unit 3 carries out micronization processes to the binary image of the area-of-interest, obtains tuning drive gear bone Frame.Specifically, using iterative algorithm, the pixel edge of the scale graph and pointer figure is gradually deleted, until the scale Figure and the pointer figure are left the skeleton part in figure center, tuning drive gear skeleton；In other embodiments, can also adopt With noniterative algorithm, such as algorithm based on range conversion, the beneficial effect that the present invention obtains is not influenceed.
Subsequent masterplate construction unit 3 obtains straight line from the tuning drive gear skeleton, builds the position mould of pointer type equipment Version.Specifically, obtained using Hough transform from the tuning drive gear skeleton pointer type equipment scale and pointer it is straight Line graph, according to the scale got and the position of the line pattern of the pointer, construct the pointer type equipment Position masterplate.
In other embodiments, micronization processes directly can be carried out to the gray level image of the area-of-interest, obtains institute Tuning drive gear skeleton is stated, does not influence the beneficial effect that the present invention obtains.
Recognition of Reading unit 4, for carrying out position identification to the position masterplate, to obtain the reading of the pointer type equipment Number information；Specifically, Recognition of Reading unit 4 by the position masterplate compared with default built-in template, obtain the position mould The more specific location information of pointer in version, the reading letter of the pointer type equipment is read from the more specific location information of the pointer Breath.
Communication unit 5 is used to the reading information being sent to Surveillance center, and approach can be wirelessly transferred or wired Transmission, therefore not to repeat here.
When it is implemented, the original image of pointer type equipment, area-of-interest figure are gathered by image acquisition units first As acquiring unit intercepts out the image of area-of-interest from the original image, masterplate construction unit is from the area-of-interest Image in obtain straight line, build the position masterplate of pointer type equipment, Recognition of Reading unit identifies from the position masterplate The reading that the pointer type equipment is currently shown, the reading is finally sent to Surveillance center by communication unit, not to non- In the case that intelligent pointer meter carries out internal transformation, the intelligent reading to non intelligent indicator instrument and intelligent number are realized According to collecting.
Described above is the preferred embodiment of the present invention, it is noted that for those skilled in the art For, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications are also considered as Protection scope of the present invention.

Claims (9)

  1. A kind of 1. pointer type Recognition of Reading method, it is characterised in that including step：
    S1, the original image for gathering pointer type equipment；
    S2, ROI processing is carried out to the original image, to intercept the image of area-of-interest；
    S3, straight line is obtained from the image of the area-of-interest, build the position masterplate of pointer type equipment；
    S4, position identification is carried out to the position masterplate, to obtain the reading information of the pointer type equipment；
    S5, the reading information is sent to Surveillance center.
  2. 2. a kind of pointer type Recognition of Reading method as claimed in claim 1, it is characterised in that the original image is schemed for RGB Picture.
  3. 3. a kind of pointer type Recognition of Reading method as claimed in claim 2, it is characterised in that the step S3 includes：
    S31, the image of the area-of-interest is converted into gray level image from RGB image, obtains the gray-scale map of area-of-interest Picture；
    S32, the gray level image to the area-of-interest carry out binary conversion treatment, obtain the binary image of area-of-interest.
  4. 4. a kind of pointer type Recognition of Reading method as claimed in claim 3, it is characterised in that carry out the binary conversion treatment and adopt With gray scale draw value value method.
  5. 5. a kind of pointer type Recognition of Reading method as claimed in claim 4, it is characterised in that the step S3 also includes：
    Straight line is obtained from the binary image of the area-of-interest, builds the position masterplate.
  6. 6. a kind of pointer type Recognition of Reading method as claimed in claim 4, it is characterised in that the step S3 also includes：
    S33, the binary image micronization processes to the area-of-interest, from the binary image of the area-of-interest To tuning drive gear skeleton；
    S34, straight line is obtained from the tuning drive gear skeleton, build the position masterplate of pointer type equipment.
  7. 7. a kind of pointer type Recognition of Reading method as claimed in claim 6, it is characterised in that to the two of the area-of-interest The micronization processes of value image use iterative algorithm.
  8. 8. a kind of pointer type Recognition of Reading method as claimed in claim 1, it is characterised in that converted using Hough or Radon Obtain straight line.
  9. A kind of 9. pointer type Recognition of Reading system, it is characterised in that including：
    Image acquisition units, for gathering the original image of pointer type equipment；
    Area-of-interest image acquisition unit, ROI processing is carried out to the original image, to intercept the image of area-of-interest；
    Masterplate construction unit, for obtaining straight line from the image of the area-of-interest, build the position mould of pointer type equipment Version；
    Recognition of Reading unit, position identification is carried out for the position masterplate, to obtain the reading information of the pointer type equipment；
    Communication unit, for the reading information to be sent into Surveillance center.
CN201710522680.7A 2017-06-30 2017-06-30 A kind of pointer type Recognition of Reading method and system Pending CN107392202A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710522680.7A CN107392202A (en) 2017-06-30 2017-06-30 A kind of pointer type Recognition of Reading method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710522680.7A CN107392202A (en) 2017-06-30 2017-06-30 A kind of pointer type Recognition of Reading method and system

Publications (1)

Publication Number Publication Date
CN107392202A true CN107392202A (en) 2017-11-24

Family

ID=60334567

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710522680.7A Pending CN107392202A (en) 2017-06-30 2017-06-30 A kind of pointer type Recognition of Reading method and system

Country Status (1)

Country Link
CN (1) CN107392202A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109858560A (en) * 2019-02-18 2019-06-07 广东中粤电力科技有限公司 A kind of image of gauge with pointer identification reading and safe early warning method
CN110097062A (en) * 2019-04-26 2019-08-06 亿嘉和科技股份有限公司 A kind of pointer recognition methods using pointer central point
CN112733842A (en) * 2020-12-30 2021-04-30 三川智慧科技股份有限公司 5G network system of water meter
CN112749699A (en) * 2020-12-30 2021-05-04 三川智慧科技股份有限公司 5G network communication method and system for water meter
CN112749698A (en) * 2020-12-30 2021-05-04 三川智慧科技股份有限公司 5G network system

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
何智杰 等: "高精度指针仪表自动读数识别方法", 《计算机辅助工程》 *
张鼎: "摩巧车仪表图像自动检测方法研究", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》 *
戴亚文等: "基于灰度信息的多特征模板匹配法", 《电测与仪表》 *
李静: "基于图像处理的指针式水表检定系统的研究与设计", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109858560A (en) * 2019-02-18 2019-06-07 广东中粤电力科技有限公司 A kind of image of gauge with pointer identification reading and safe early warning method
CN110097062A (en) * 2019-04-26 2019-08-06 亿嘉和科技股份有限公司 A kind of pointer recognition methods using pointer central point
CN112733842A (en) * 2020-12-30 2021-04-30 三川智慧科技股份有限公司 5G network system of water meter
CN112749699A (en) * 2020-12-30 2021-05-04 三川智慧科技股份有限公司 5G network communication method and system for water meter
CN112749698A (en) * 2020-12-30 2021-05-04 三川智慧科技股份有限公司 5G network system

Similar Documents

Publication Publication Date Title
CN107392202A (en) A kind of pointer type Recognition of Reading method and system
CN107403180A (en) A kind of numeric type equipment detection recognition method and system
CN109360396A (en) Remote meter reading method and system based on image recognition technology and NB-IoT technology
CN108573261A (en) A kind of read out instrument recognition methods suitable for Intelligent Mobile Robot
CN103914678B (en) Abandoned land remote sensing recognition method based on texture and vegetation indexes
CN104881865A (en) Forest disease and pest monitoring and early warning method and system based on unmanned plane image analysis
CN103927507A (en) Improved multi-instrument reading identification method of transformer station inspection robot
CN102915432A (en) Method and device for extracting vehicle-bone microcomputer image video data
CN107122787A (en) A kind of image scaling quality evaluating method of feature based fusion
CN102855485B (en) The automatic testing method of one grow wheat heading
CN107065037A (en) A kind of Data of Automatic Weather acquisition control system
CN114518143A (en) Intelligent environment sensing system
CN105869164A (en) Method and system for detecting on/off state of switch
CN110659637A (en) Electric energy meter number and label automatic identification method combining deep neural network and SIFT features
Jin et al. A Smart Water Metering System Based on Image Recognition and Narrowband Internet of Things.
CN202815869U (en) Vehicle microcomputer image and video data extraction apparatus
CN105893938A (en) Oil temperature gauge reading method and system
CN105427279A (en) Grassland drought status monitoring system based on and machine vision and Internet of things, grassland drought status monitoring method
CN108305347A (en) A kind of controller switching equipment inspection operational method
CN111027565A (en) Power transmission and transformation equipment report content generation method based on optical vision semantic extraction
CN109815784A (en) A kind of intelligent method for classifying based on thermal infrared imager, system and storage medium
CN106909881A (en) The method and system of corn breeding base ridge number are extracted based on unmanned aerial vehicle remote sensing images
CN111767826A (en) Timing fixed-point scene abnormity detection method
CN107895365B (en) Image matching method and monitoring system for power transmission channel external damage protection
CN109979588A (en) Image scanning pathological section 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
RJ01 Rejection of invention patent application after publication

Application publication date: 20171124

RJ01 Rejection of invention patent application after publication