CN114143446A - Histogram identification method, system, storage medium and equipment based on edge calculation - Google Patents
Histogram identification method, system, storage medium and equipment based on edge calculation Download PDFInfo
- Publication number
- CN114143446A CN114143446A CN202111218490.9A CN202111218490A CN114143446A CN 114143446 A CN114143446 A CN 114143446A CN 202111218490 A CN202111218490 A CN 202111218490A CN 114143446 A CN114143446 A CN 114143446A
- Authority
- CN
- China
- Prior art keywords
- histogram
- straight lines
- filtering
- image
- identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004364 calculation method Methods 0.000 title claims abstract description 36
- 238000001914 filtration Methods 0.000 claims abstract description 35
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000001514 detection method Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 abstract description 3
- 238000013215 result calculation Methods 0.000 abstract description 3
- 238000004519 manufacturing process Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000009545 invasion Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 241000830535 Ligustrum lucidum Species 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- G06T5/70—
-
- G06T5/73—
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/04—Processing captured monitoring data, e.g. for logfile generation
- H04L43/045—Processing captured monitoring data, e.g. for logfile generation for graphical visualisation of monitoring data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N25/00—Circuitry of solid-state image sensors [SSIS]; Control thereof
- H04N25/60—Noise processing, e.g. detecting, correcting, reducing or removing noise
- H04N25/617—Noise processing, e.g. detecting, correcting, reducing or removing noise for reducing electromagnetic interference, e.g. clocking noise
Abstract
The invention discloses a histogram identification method, a system, a storage medium and equipment based on edge calculation, wherein the method comprises the steps of adjusting the position of a camera to obtain a histogram video; decoding the histogram video to obtain a histogram stream, analyzing the histogram stream frame by frame, including: drawing an identification area and marking lines on the histogram; preprocessing the columnar picture; taking the position of the marked line as the bottom of the histogram, detecting all straight lines in the histogram through a Hough straight line detection function of machine vision, filtering according to the lengths of the detected straight lines, selecting the three longest straight lines, arranging according to the vertical coordinate distance after filtering, namely arranging the straight line which is farthest from the top of the histogram and has the largest numerical value in the first straight line, and calculating the three straight lines according to the pixel difference from the top of the histogram to the straight lines to obtain the numerical value of the histogram; and filtering and storing the histogram numerical value. The invention can complete the service of integrating video acquisition, preprocessing, histogram identification, result calculation, filtering and data remote transmission.
Description
Technical Field
The invention relates to the field of big data processing, in particular to a histogram identification method, a system, a storage medium and equipment based on edge calculation.
Background
Industrial equipment such as PLC generally employs a display and control EA system for SA programming, converts data into a histogram through DDE communication, and displays the histogram through a screen of the industrial equipment. Due to the characteristics of industrial equipment, the data is often used for monitoring, and if the data needs to be recorded, the data needs to be recorded manually one by one; of course, the DDE protocol may also be programmed, and data transmitted back by the DDE protocol is decoded by RSLinux and stored in the file of the system, but the use of the DDE protocol requires the industrial equipment manufacturer to perform the process and is not expensive. The existing histogram identification method mainly comprises the following steps: DDE programming, wherein the principle is that the current monitoring value is obtained through industrial equipment supporting a DDE protocol, and then programming is carried out through a connected system; the PLC special decoding module has the principle that monitoring information output by the industrial equipment is automatically decoded and output through the corresponding decoding module and then is obtained through a data line of the module; the internet of things identification module is transformed into a metering module, is installed at the data output end of industrial equipment, calculates the usage amount, converts numerical values into binary data through a chip, and remotely communicates with a public network gateway to complete data acquisition. The disadvantages of the above method are:
1) the cost of reconstruction is high, and the cost of secondary development of a data interface provided by a manufacturer is high;
2) the maintenance cost is too high, the special metering module or the decoding module is damaged to a certain extent in the using process, and the cost for replacing the equipment is too high;
3) the replaceability is poor, industrial equipment used by part of units is long in the year, no decoding equipment exists or programming protocols are not supported, and the improvement cannot be carried out;
4) the invasion is strong, all the modular installations need to disassemble, modify and combine the original equipment, and the equipment has certain invasion to the original working equipment;
5) the implementation cost is high, part of industrial equipment is the core of production, and if the shutdown operation is possibly carried out in the process of modification, certain production cost is increased.
Disclosure of Invention
Aiming at the problems, the invention provides a method for identifying a histogram under the conditions of no change, no invasion and no influence on the work of the existing industrial equipment. The identification process is not changed, is non-invasive, does not influence the existing industrial equipment, and is suitable for scenes needing low-cost histogram data acquisition, such as smart cities, smart communities, intelligent manufacturing, traditional industries and the like.
In a first aspect of the present invention, a histogram identification method based on edge calculation is provided, which includes the following steps:
adjusting the position of a camera to obtain a histogram video;
decoding the histogram video to obtain a histogram stream, analyzing the histogram stream frame by frame, including:
drawing an identification area and marking lines on the histogram;
performing columnar picture preprocessing, including fuzzy processing, noise reduction processing and feature extraction;
recognizing the preprocessed columnar picture, taking the position of a marked line as the bottom of the columnar picture, detecting all straight lines in the columnar picture through a Hough straight line detection function of machine vision, filtering according to the lengths of the detected straight lines, selecting the three longest straight lines, arranging according to the vertical coordinate distance after filtering, namely arranging the straight line which is farthest from the top of the picture and has the largest numerical value in the first straight line, and calculating the numerical value of the columnar picture according to the pixel difference from the top of the picture to the straight line by taking the three selected straight lines;
and filtering and storing the histogram numerical value.
Further, the method includes determining legend information for the histogram based on the histogram video, the legend information including parametric maximum values and units for the histogram.
Further, the specific formula of the value of the histogram is obtained by calculating the selected three straight lines according to the pixel difference from the top of the image to the straight lines:
In a second aspect of the present invention, there is provided a histogram identification system based on edge calculation, the system comprising:
the camera shooting unit is used for adjusting the position of the camera and acquiring a histogram video;
the parsing unit is configured to decode the histogram video to obtain a histogram stream, and parse the histogram stream frame by frame, including:
the identification module is used for drawing an identification area and marking lines on the columnar picture; the preprocessing module is used for preprocessing the columnar picture, and comprises fuzzy processing, noise reduction processing and feature extraction; the recognition module is used for detecting all straight lines in the columnar image by taking the position of the marked line as the bottom of the columnar image through the Hough straight line detection function of machine vision, filtering according to the lengths of the detected straight lines, selecting the three longest straight lines, arranging according to the vertical coordinate distance after filtering, namely arranging the straight line which is farthest from the top of the image and has the largest numerical value in the first straight line, and calculating the three selected straight lines according to the pixel difference from the top of the image to the straight lines to obtain the numerical value of the columnar image;
and the filtering unit is used for filtering and storing the histogram numerical values obtained by the analysis unit.
Furthermore, the system also comprises a communication unit used for transmitting the histogram values stored by the filtering unit.
In a third aspect of the present invention, a storage medium storing a computer program, executable by one or more processors, is provided for implementing the histogram identification method based on edge calculation as described above.
In a fourth aspect of the invention, an electronic device is provided, comprising a memory and a processor, the memory having stored thereon a computer program, the memory and the processor being communicatively connected to each other, the computer program, when executed by the processor, performing the histogram identification method based on edge calculation as described above.
The invention provides a histogram identification method, a system, a storage medium and equipment based on edge calculation, which use the edge calculation technology to identify and detect the histogram; and edge calculation is used for completing integrated services of video acquisition, preprocessing, histogram identification, result calculation, result filtering, data remote transmission and the like. The beneficial effects that finally reach: the construction difficulty is small, and the production is not influenced; the edge calculation technology is used for identifying the histogram grids, the original industrial equipment does not need to be additionally provided with or replaced with a metering module, the construction and maintenance difficulty is small, and operations such as production halt, industry halt and the like are not needed; the device is free from damage and intrusion, and when important industrial equipment is butted, the important industrial equipment does not need to be damaged or paralleled, and the equipment is accessed into the industrial equipment without perception; the cost is low, DDE protocol programming is not needed, an identification server is not needed to be deployed, industrial equipment support is not needed, and any human-eye readable histogram can be identified.
Drawings
FIG. 1 is a flow chart of a histogram identification method based on edge calculation according to an embodiment of the present invention;
FIG. 2 is a flow chart of a histogram analysis method based on edge calculation according to an embodiment of the present invention;
FIG. 3 is a drawing and representation diagram of the identification region of the histogram identification method based on edge calculation according to the embodiment of the present invention;
FIG. 4 is a schematic calculation diagram of a histogram identification method based on edge calculation according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a histogram identification system based on edge calculation according to an embodiment of the present invention;
FIG. 6 is an architecture of a computer device in an embodiment of the invention.
Detailed Description
In order to further describe the technical scheme of the present invention in detail, the present embodiment is implemented on the premise of the technical scheme of the present invention, and detailed implementation modes and specific steps are given.
The invention relates to a method for identifying a histogram under the condition of not influencing the work of the existing industrial equipment, which collects the screen of the industrial equipment through edge calculation, identifies the histogram in the screen by utilizing the edge calculation technology and calculates the final value, and the calculation result can be stored in a local or return application/database server. The identification process is not changed, is non-invasive, does not influence the existing industrial equipment, and is suitable for scenes needing low-cost histogram data acquisition, such as smart cities, smart communities, intelligent manufacturing, traditional industries and the like. The invention provides a histogram identification method based on edge calculation, which comprises the following steps as shown in figure 1:
s1, adjusting the position of the camera to obtain a histogram video;
s2, decoding the histogram video to obtain a histogram stream, and analyzing the histogram stream frame by frame, as shown in fig. 2, including:
s21, drawing an identification area on the histogram and marking a line;
s22, preprocessing the columnar picture, including fuzzy processing, noise reduction processing and feature extraction;
s23, recognizing the preprocessed columnar picture, taking the position of a marked line as the bottom of the columnar picture, detecting all straight lines in the columnar picture through the Hough straight line detection function of machine vision, filtering according to the lengths of the detected straight lines, selecting the three longest straight lines, arranging according to the longitudinal coordinate distance after filtering, namely arranging the straight line which is farthest from the top of the picture and has the largest numerical value in the first straight line, and calculating according to the pixel difference from the top of the picture to the straight lines to obtain the numerical value of the columnar picture by taking the three selected straight lines;
and S3, filtering and storing the values of the histogram.
In some embodiments, after the histogram video is obtained, legend information for the histogram is determined from the histogram video, the legend information including parametric maximum values and units for the histogram.
Further, the specific formula of the value of the histogram is obtained by calculating the selected three straight lines according to the pixel difference from the top of the image to the straight lines:
In one embodiment, the specific steps are as follows:
step 1, adjusting the position of a camera (supporting RTSP streaming or USB direct connection), ensuring the collection quality, writing histogram legend information such as the maximum numerical value and digital unit of a histogram into a configuration file, and facilitating the number conversion after reading the histogram;
step 2, decoding the acquired video stream to obtain a picture, and drawing an identification area and a marking line on the decoded picture through OpenCV, wherein the result is shown in FIG. 3;
step 3, analyzing the decoded video stream by a glossy privet, completing color conversion by calling an OpenCV.cvtColor function, avoiding interference, calling an OpenCV.GaussianBlur function to perform fuzzy (reduce recognition sensitivity) and noise reduction (remove electromagnetic interference brought by networks, other equipment and the like), and calling an OpenCV.adaptivethreshold function to complete image preprocessing operations such as binaryzation (feature extraction) and the like;
step 4, taking the position of the marked line as the bottom of the histogram, detecting all straight lines in the graph phase through the Hough straight line detection function of machine vision, filtering according to the lengths of the detected straight lines, selecting the three longest straight lines, filtering, then performing reverse arrangement according to the vertical coordinate distance (the upper left corner is 0), namely arranging the straight lines farthest from the top, taking the first three lines to calculate, and finally obtaining the numerical value of the histogram, wherein the calculation formula is
The schematic diagram is shown in FIG. 4;
step 5, filtering operation is carried out on the values of the histogram by using a numerical filtering algorithm, the numerical filtering algorithm classifies and counts a large number of values, and the classification with the largest number is selected to remove unreasonable values, including but not limited to unreasonable values, unidentified values or values which do not accord with equipment running mean value fluctuation and the like caused by the fact that the result output in the step 4 is influenced by illumination, human shadow and the like;
in a specific embodiment, when the video monitoring is tested for 10 minutes, 80% of the recognition results are 7811 times, 79% of the recognition results are 393 times, 83% of the recognition results are 1785 times, 81% of the recognition results are 10 times, and 82% of the recognition results are 1 time, and after the filtering processing, 80% of the recognition results are considered to be accurate recognition results, because the occurrence times are the highest.
Step 6, storing the histogram data obtained in the step 5 in a memory in a file stream mode, and utilizing a communication module to remotely transmit the data;
in the following, a system corresponding to the method shown in fig. 1 according to an embodiment of the present disclosure is described with reference to fig. 3, the system 100 being a histogram identification system 100 based on edge calculation, the system 100 comprising: the camera unit 101 is used for adjusting the position of a camera to acquire a histogram video; the parsing unit 102 is configured to decode the histogram video to obtain a histogram stream, and parse the histogram stream frame by frame, and includes: the identification module 1021 is used for drawing an identification area and marking lines on the columnar picture; the preprocessing module 1022 is configured to perform preprocessing on the columnar picture, including blur processing, noise reduction processing, and feature extraction; the recognition module 1023 is used for detecting all straight lines in the columnar image by taking the marking line position as the bottom of the columnar image through the Hough straight line detection function of machine vision, filtering according to the lengths of the detected straight lines, selecting the three longest straight lines, arranging according to the vertical coordinate distance after filtering, namely arranging the straight line which is farthest from the top of the image and has the largest numerical value in the first straight line, and calculating the numerical value of the columnar image by taking the three selected straight lines according to the pixel difference from the top of the image to the straight lines; and the filtering unit 103 is configured to filter and store the histogram values obtained by the analyzing unit 102. In addition to the above units and modules, the system 100 may also include other components, and the system 100 further includes a communication unit 104 for transmitting the histogram values stored by the filtering unit.
The specific working process of the histogram identification system 100 based on edge calculation refers to the description of the histogram identification method based on edge calculation, and is not repeated here.
In addition, the system of the embodiment of the present invention can also be implemented by means of the architecture of the electronic device shown in fig. 4. Fig. 4 shows the architecture of the electronic device. As shown in fig. 4, includes a communication component 201, an input/output component 202, a bus 203, a processor 204, a memory 205, and the like. The processor 204 performs a histogram identification method based on edge calculations as described above, and the memory 205 may store various data or files used by the electronic device for processing and/or communication and program instructions executed by the processor. The received histogram values may further be stored in the memory 205 or transmitted via the communication component 201. The architecture shown in fig. 4 is merely exemplary, and one or more of the components in fig. 4 may be adjusted as needed when implementing different electronic devices.
Embodiments of the invention may also be implemented as a computer-readable storage medium. A computer-readable storage medium according to an embodiment has computer-readable instructions stored thereon. The computer readable instructions, when executed by a processor, may perform a histogram identification method based on edge calculation according to an embodiment of the present invention described with reference to the above drawings.
The invention provides a histogram identification method, a system, a storage medium and equipment based on edge calculation, which use the edge calculation technology to identify and detect the histogram; and edge calculation is used for completing integrated services of video acquisition, preprocessing, histogram identification, result calculation, result filtering, data remote transmission and the like. The beneficial effects that finally reach: the construction difficulty is small, and the production is not influenced; the edge calculation technology is used for identifying the histogram grids, the original industrial equipment does not need to be additionally provided with or replaced with a metering module, the construction and maintenance difficulty is small, and operations such as production halt, industry halt and the like are not needed; the device is free from damage and intrusion, and when important industrial equipment is butted, the important industrial equipment does not need to be damaged or paralleled, and the equipment is accessed into the industrial equipment without perception; the cost is low, DDE protocol programming is not needed, an identification server is not needed to be deployed, industrial equipment support is not needed, and any human-eye readable histogram can be identified.
In this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process or method.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (7)
1. A histogram identification method based on edge calculation is characterized by comprising the following steps:
adjusting the position of a camera to obtain a histogram video;
decoding the histogram video to obtain a histogram stream, analyzing the histogram stream frame by frame, including:
drawing an identification area and marking lines on the histogram;
performing columnar picture preprocessing, including fuzzy processing, noise reduction processing and feature extraction;
taking the position of the marked line as the bottom of the histogram, detecting all straight lines in the histogram through a Hough straight line detection function of machine vision, filtering according to the lengths of the detected straight lines, selecting the three longest straight lines, arranging according to the longitudinal coordinate distance after filtering, namely arranging the straight line farthest from the top of the histogram in the first position, and calculating the three selected straight lines according to the pixel difference from the top of the histogram to the straight lines to obtain the numerical value of the histogram;
and filtering and storing the histogram numerical value.
2. The method of claim 1, further comprising determining legend information for the histogram from the histogram video, the legend information including parametric maximum values and units for the histogram.
3. The histogram identification method based on edge calculation according to claim 1, wherein the specific formula of the histogram value obtained by calculating the pixel difference from the top of the image to the straight line is:
4. An edge-computation-based histogram identification system, the system comprising:
the camera shooting unit is used for adjusting the position of the camera and acquiring a histogram video;
the parsing unit is configured to decode the histogram video to obtain a histogram stream, and parse the histogram stream frame by frame, including:
the identification module is used for drawing an identification area and marking lines on the columnar picture; the preprocessing module is used for preprocessing the columnar picture, and comprises fuzzy processing, noise reduction processing and feature extraction; the recognition module is used for detecting all straight lines in the columnar image by taking the position of the marked line as the bottom of the columnar image through the Hough straight line detection function of machine vision, filtering according to the lengths of the detected straight lines, selecting the three longest straight lines, arranging according to the vertical coordinate distance after filtering, namely arranging the straight line farthest from the top of the image in the first position, and calculating the three selected straight lines according to the pixel difference from the top of the image to the straight line to obtain the numerical value of the columnar image;
and the filtering unit is used for filtering and storing the histogram numerical values obtained by the analysis unit.
5. The edge-computation-based histogram identification system of claim 4, further comprising a communication unit for transmitting the histogram values stored by the filtering unit.
6. A storage medium storing a computer program executable by one or more processors to perform the method of histogram identification based on edge calculation according to any one of claims 1 to 3.
7. An electronic device comprising a memory and a processor, the memory having a computer program stored thereon, the memory and the processor being communicatively coupled to each other, the computer program when executed by the processor performing the histogram identification method based on edge calculation according to any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111218490.9A CN114143446A (en) | 2021-10-20 | 2021-10-20 | Histogram identification method, system, storage medium and equipment based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111218490.9A CN114143446A (en) | 2021-10-20 | 2021-10-20 | Histogram identification method, system, storage medium and equipment based on edge calculation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114143446A true CN114143446A (en) | 2022-03-04 |
Family
ID=80394464
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111218490.9A Pending CN114143446A (en) | 2021-10-20 | 2021-10-20 | Histogram identification method, system, storage medium and equipment based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114143446A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104284065A (en) * | 2014-09-30 | 2015-01-14 | 华中科技大学 | Industrial intelligent camera based on FPGA |
| CN108416377A (en) * | 2018-02-26 | 2018-08-17 | 阿博茨德（北京）科技有限公司 | Information extracting method in block diagram and device |
| US20180336405A1 (en) * | 2017-05-17 | 2018-11-22 | Tab2Ex, Llc | Method of digitizing and extracting meaning from graphic objects |
| CN109840278A (en) * | 2019-01-28 | 2019-06-04 | 平安科技（深圳）有限公司 | Histogram data switching control method, device, computer equipment and storage medium |
| CN109934221A (en) * | 2019-02-22 | 2019-06-25 | 山东大学 | Power equipment based on attention mechanism automatically analyzes identification monitoring method and system |
| CN110363092A (en) * | 2019-06-17 | 2019-10-22 | 平安科技（深圳）有限公司 | Histogram recognition methods, device, equipment and computer readable storage medium |
| CN110851280A (en) * | 2019-11-13 | 2020-02-28 | 深圳航天智慧城市系统技术研究院有限公司 | Automatic data acquisition method based on distributed intelligent edge computing technology |
| CN112101237A (en) * | 2020-09-17 | 2020-12-18 | 新华智云科技有限公司 | Histogram data extraction and conversion method |
-
2021
- 2021-10-20 CN CN202111218490.9A patent/CN114143446A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104284065A (en) * | 2014-09-30 | 2015-01-14 | 华中科技大学 | Industrial intelligent camera based on FPGA |
| US20180336405A1 (en) * | 2017-05-17 | 2018-11-22 | Tab2Ex, Llc | Method of digitizing and extracting meaning from graphic objects |
| CN108416377A (en) * | 2018-02-26 | 2018-08-17 | 阿博茨德（北京）科技有限公司 | Information extracting method in block diagram and device |
| CN109840278A (en) * | 2019-01-28 | 2019-06-04 | 平安科技（深圳）有限公司 | Histogram data switching control method, device, computer equipment and storage medium |
| CN109934221A (en) * | 2019-02-22 | 2019-06-25 | 山东大学 | Power equipment based on attention mechanism automatically analyzes identification monitoring method and system |
| CN110363092A (en) * | 2019-06-17 | 2019-10-22 | 平安科技（深圳）有限公司 | Histogram recognition methods, device, equipment and computer readable storage medium |
| CN110851280A (en) * | 2019-11-13 | 2020-02-28 | 深圳航天智慧城市系统技术研究院有限公司 | Automatic data acquisition method based on distributed intelligent edge computing technology |
| CN112101237A (en) * | 2020-09-17 | 2020-12-18 | 新华智云科技有限公司 | Histogram data extraction and conversion method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109299703B (en) | Method and device for carrying out statistics on mouse conditions and image acquisition equipment | |
| US20130070099A1 (en) | Image based dial gauge reading | |
| CN105701476A (en) | Machine vision-based automatic identification system and method for production line products | |
| CN102915432A (en) | Method and device for extracting vehicle-bone microcomputer image video data | |
| CN113419298B (en) | Multi-parameter hydrological meteorological data acquisition device | |
| KR20150108118A (en) | Remote automatic metering system based image recognition | |
| CN107392202A (en) | A kind of pointer type Recognition of Reading method and system | |
| CN103824257A (en) | Two-dimensional code image preprocessing method | |
| CN115861210A (en) | Transformer substation equipment abnormity detection method and system based on twin network | |
| CN202815869U (en) | Vehicle microcomputer image and video data extraction apparatus | |
| CN114143446A (en) | Histogram identification method, system, storage medium and equipment based on edge calculation | |
| JP2017521011A (en) | Symbol optical detection method | |
| CN112148555A (en) | Intelligent reading and identifying method and system for fault warning information | |
| CN111818286A (en) | Video monitoring equipment fault detection system | |
| CN113837312B (en) | Method and device for evaluating running state of zinc oxide arrester | |
| CN110617670A (en) | Unmanned refrigerator based on image recognition and recognition method thereof | |
| CN110942058A (en) | Instrument data reading method based on CCD machine vision recognition | |
| CN115479891A (en) | Automatic detection system and method for circuit board mounted components based on image recognition | |
| CN115147752A (en) | Video analysis method and device and computer equipment | |
| CN111669575B (en) | Method, system, electronic device, medium and terminal for testing image processing effect | |
| CN114612897A (en) | Intelligent fruit and vegetable weighing and ticketing method and device, electronic equipment and storage medium | |
| CN112861817A (en) | Instrument noise image processing method | |
| CN209881981U (en) | Remote meter reading system of bus electronic stop board | |
| CN114039279A (en) | Control cabinet monitoring method and system in rail transit station | |
| CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence |
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 |