CN111401357B - Pointer type instrument reading method based on text detection - Google Patents
Pointer type instrument reading method based on text detection Download PDFInfo
- Publication number
- CN111401357B CN111401357B CN202010087850.5A CN202010087850A CN111401357B CN 111401357 B CN111401357 B CN 111401357B CN 202010087850 A CN202010087850 A CN 202010087850A CN 111401357 B CN111401357 B CN 111401357B
- Authority
- CN
- China
- Prior art keywords
- scale
- pointer
- image
- center
- instrument
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- 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)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Character Input (AREA)
Abstract
The invention discloses a pointer type instrument reading method based on text detection, which comprises the following steps: s10, collecting images of a pointer instrument; s20, detecting and identifying the position and the indication of the scale text; s30, determining the center of the pointer rotation, namely the circle center of the scale ring; s40, converting the circular scale area into a rectangle; s50, dividing a rectangular scale area from the image; s60, reading of the pointer type instrument is read through a modified distance method. The invention realizes the meter reading method with higher precision and has stronger robustness to the ambient light and the shooting angle.
Description
Technical Field
The invention belongs to the technical field of instruments and meters, and relates to a pointer instrument reading method based on text detection.
Background
The pointer instrument is widely applied to industries such as petrochemical industry, electric power and the like due to the advantages of simple structure, convenient use, low cost and the like. With the development of scientific technology, the original manual reading of the pointer instrument is difficult to meet the industrial real-time and intelligent monitoring requirements, so that a method capable of accurately identifying the pointer instrument is urgently needed.
At present, the method with higher reading accuracy is a reading method based on polar coordinate transformation, and the main idea is to conduct polar coordinate transformation on an image of the instrument, so that scales which are originally distributed in an arc shape are changed into linear distribution. The method is not only suitable for uniform scale pointer tables, but also suitable for pointer tables with non-uniform scale marks, and has a wide application range. According to the method, firstly, the rotation center of the pointer needs to be extracted, and in the existing research center, the rotation center of the pointer is mostly fitted with a circle center by using scale coordinates as fitting points. And because the feature points of the scale coordinates are fewer, when illumination changes, the extraction of the scale coordinates may fail, and the reading result is greatly affected.
Disclosure of Invention
In order to solve the problems, the invention provides a pointer type meter reading method based on text detection aiming at the defects of the existing pointer type meter reading method so as to improve the accuracy of meter reading and the robustness of an algorithm. .
In order to achieve the above purpose, the technical scheme of the invention is a pointer instrument reading method based on text detection, which comprises the following steps:
s10, collecting images of a pointer instrument;
s20, detecting and identifying the position and the indication of the scale text;
s30, determining the center of the pointer rotation, namely the circle center of the scale ring;
s40, converting the circular scale area into a rectangle;
s50, dividing a rectangular scale area from the image;
s60, reading of the pointer type instrument is read through a modified distance method.
Preferably, in the detecting and identifying coordinates and readings of the scale text in S20, the RCNN network is used to detect and identify positions and readings of scale values, where the positions of the scale values are used for determining the circle center of the scale ring in S30, and the readings of the scale text are used for reading of the pointer instrument in S60.
Preferably, the RCNN network detects and identifies that training of the network needs to be completed in advance, including the following steps:
shooting and collecting pointer instrument images with different readings;
labeling the images according to network input requirements to prepare a data set;
training an RCNN network;
the trained network can be used for detecting and identifying scale values in images.
Preferably, in the step S30, the center coordinates of the scale value text area obtained in the step S20 are determined in the center of the circle of the scale ring, and after the center coordinates of the scale value text area are determined in the step S30, the points can be known to be distributed circularly according to the scale distribution rule of the pointer instrument, so that the circle is fitted by a least square method, and the coordinates of the circle center of the scale are obtained.
Preferably, the S40 circular scale area is converted into a rectangle, so that the scale lines arranged around the circular arc become arranged along the horizontal direction, the pointer rotating around the center of the circle becomes slid along the horizontal direction, the transformation of the circular moment is essentially a process of transforming the image from the cartesian coordinate system to the polar coordinate system with a certain point in the image as the center, and the coordinate transformation formula is as follows:
wherein ρ and θ are the polar diameter and the polar angle in the polar coordinate system, and x and y are the horizontal and vertical coordinates of the pixel point in the Cartesian coordinate system.
Preferably, the step S50 of segmenting the scale area from the image includes the steps of:
s51, converting the image into a gray scale, wherein the formula is as follows,
Gray=R*0.299+G*0.587+B*0.114;
wherein R, G, B represents the color values of the three red, green and blue channels in the RGB color space, and Gray represents the converted Gray value;
s52, converting the image into a binary image, adaptively selecting a threshold value for different areas in the image, and when the pixel value of the pixel in the area is larger than the threshold value, representing the pixel value by 255, otherwise, representing the pixel value by 0;
and S53, dividing the scale area from the image, and detecting the scale area in the polar coordinate image of the instrument by adopting a horizontal projection method.
Preferably, the S60 reads the reading of the pointer meter by distance method, and the formula 4 can calculate the reading:
wherein n is the number of graduation marks between the graduation mark represented by the A graduation value and the graduation mark closest to the pointer at the left end of the pointer; n is [ A, B ]]The dividing value of each scale in the numerical value interval; X-X l For pointer x and left nearest tick mark x l Is a distance of (2); x is x r -x l Is the nearest scale mark x at the right end of the pointer r And the nearest scale mark x at the left end of the pointer l Is a distance of (3).
The invention has at least the following beneficial effects:
1. the circle center is fitted by detecting the text coordinates of the scale values, so that the adaptability to different illumination is enhanced, the requirement on shooting angles is reduced, and the method can be widely applied to meters in various scenes;
2. the improved distance method reading is adopted, the text recognition network is used for recognizing the scale value text to obtain a large numerical value interval where the pointer is located, and then the current reading is obtained through the distance ratio of the pointer to the scale marks on the two sides, so that the distance method has smaller error compared with the distance method from zero scale to full scale marks.
Drawings
FIG. 1 is a flow chart of the steps of a method for text detection-based pointer meter reading according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a scale area and a pointer separated after polar coordinate transformation according to a text detection-based pointer meter reading method according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
On the contrary, the invention is intended to cover any alternatives, modifications, equivalents, and variations as may be included within the spirit and scope of the invention as defined by the appended claims. Further, in the following detailed description of the present invention, certain specific details are set forth in order to provide a better understanding of the present invention. The present invention will be fully understood by those skilled in the art without the details described herein.
Method example 1
Referring to fig. 1, the technical solution of the present invention is a step flowchart of a pointer meter reading method based on text detection, which includes the following steps:
s10, collecting images of a pointer instrument;
s20, detecting and identifying the position and the indication of the scale text;
s30, determining the center of the pointer rotation, namely the circle center of the scale ring;
s40, converting the circular scale area into a rectangle;
s50, dividing a rectangular scale area from the image;
s60, reading of the pointer type instrument is read through a modified distance method.
In the specific embodiment
And S20, detecting and identifying the positions and the readings of the scale values by using an RCNN network in the process of detecting and identifying the coordinates and the readings of the scale text. The position of the scale value is used for determining the circle center of the scale ring S30, and the reading of the scale text is used for the reading of the pointer instrument in the step S60. The RCNN network detects and identifies that training of the network needs to be completed in advance, and comprises the following steps: shooting and collecting pointer instrument images with different readings; labeling the images according to network input requirements to prepare a data set; the RCNN network is trained. The trained network can be used for detecting and identifying scale values in images.
S30, determining the rotation center of the pointer, namely the center of the circle of the scale ring, and after the center coordinates of the scale value text area obtained in S20, knowing that the points are distributed circularly according to the scale distribution rule of the pointer instrument, so that the circle is fitted by a least square method, and the coordinates of the center of the circle of the scale are obtained.
The S40 circular scale area is converted into a rectangle, the purpose of the circular scale area is that scale lines arranged around an arc are changed to be arranged along the horizontal direction, a pointer rotating around a circle center is changed to slide along the horizontal direction, and the circular moment conversion is essentially a process of converting an image from a Cartesian coordinate system to a polar coordinate system by taking a certain point in the image as a center. The coordinate transformation formula is as follows:
wherein ρ and θ are the polar diameter and the polar angle in the polar coordinate system, and x and y are the horizontal and vertical coordinates of the pixel point in the Cartesian coordinate system.
S50 separates the rectangular scale area from the image, before which the image needs to be converted into a binary image. The image is first converted into a gray scale, the formula is as follows,
Gray=R*0.299+G*0.587+B*0.114;
wherein R, G, B represents the color values of the three red, green and blue channels in the RGB color space, and Gray represents the converted Gray value;
then, different local thresholds are selected at different positions of the image, the pixel value in the partial image is assigned a value of 255 greater than the threshold, and the pixel value in the partial image is assigned a value of 0 less than the threshold.
And then, separating the scale areas in the polar coordinate image of the instrument by adopting a projection method, wherein the distances between scale lines in the scale areas are equal, and the variance of the distances is a small value which is approximately close to 0, so that the variances of the scale distances of each row in the image are projected in the horizontal direction, and the threshold value of the variances is set for screening the scale areas. The variance is calculated as:
wherein n is the total number of scales, dis i (i=0, 1,2.. Sub.n-1) is the spacing between the scales, dis (dis) aver Is the average value of the inter-scale spacing.
S60, reading out the pointer type instrument by using a general improved distance method, wherein fig. 2 is an image for separating a scale area and a pointer, the scale area in the image is distributed in a rectangular shape, in fig. 2, 1 is the separated pointer, 2 is a scale mark of which the left end is nearest to the pointer, 3 is a scale mark of which the right end is nearest to the pointer, and the numerical interval of the pointer is [ A, B ]. The reading of the pointer meter can be calculated as follows:
wherein n is the number of graduation marks between the graduation mark represented by the A graduation value and the graduation mark closest to the pointer at the left end of the pointer, and in fig. 2, n is 3; n is [ A, B ]]The dividing value of each scale in the numerical value interval; X-X l For pointer x and its left nearest tick mark x l Is a distance of (2); x is x r -x l Is the nearest scale mark x at the right end of the pointer r And the nearest scale mark x at the left end of the pointer l Is a distance of (3).
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (3)
1. The pointer type instrument reading method based on text detection is characterized by comprising the following steps of:
s10, collecting images of a pointer instrument;
s20, detecting and identifying the position and the indication of the scale text;
s30, determining the center of the pointer rotation, namely the circle center of the scale ring;
s40, converting the circular scale area into a rectangle;
s50, dividing a rectangular scale area from the image;
s60, reading out the reading of the pointer instrument through an improved distance method;
s20, detecting and identifying the coordinates and the readings of the scale text, wherein an RCNN network is used for detecting and identifying the positions and the readings of scale values, the positions of the scale values are used for determining the circle centers of the scale rings in S30, and the readings of the scale text are used for reading of the pointer type instrument in S60;
the RCNN network detects and identifies that training of the network needs to be completed in advance, and comprises the following steps:
shooting and collecting pointer instrument images with different readings;
labeling the images according to network input requirements to prepare a data set;
training an RCNN network;
the trained network can be used for detecting and identifying scale values in images;
s30, determining the center of rotation of the pointer, namely the center of a circle of the scale ring, and after the center coordinates of the scale value text area obtained in S20, knowing that the points are distributed circularly according to the scale distribution rule of the pointer instrument, so that the circle is fitted by a least square method, and the coordinates of the center of the circle of the scale are obtained;
the S40 circular scale area is converted into a rectangle, so that scale lines arranged around an arc are arranged along the horizontal direction, a pointer rotating around a circle center is slid along the horizontal direction, the circular moment conversion is essentially a process of converting an image from a Cartesian coordinate system to a polar coordinate system by taking a certain point in the image as the center, and the coordinate conversion formula is as follows:
wherein ρ and θ are the polar diameter and the polar angle in the polar coordinate system, and x and y are the horizontal and vertical coordinates of the pixel point in the Cartesian coordinate system.
2. The method according to claim 1, wherein S50 segments the scale area from the image, comprising the steps of:
s51, converting the image into a gray scale, wherein the formula is as follows,
Gray=R*0.299+G*0.587+B*0.114;
wherein R, G, B represents the color values of the three red, green and blue channels in the RGB color space, and Gray represents the converted Gray value;
s52, converting the image into a binary image, adaptively selecting a threshold value for different areas in the image, and when the pixel value of the pixel in the area is larger than the threshold value, representing the pixel value by 255, otherwise, representing the pixel value by 0;
and S53, dividing the scale area from the image, and detecting the scale area in the polar coordinate image of the instrument by adopting a horizontal projection method.
3. The method of claim 1, wherein S60 reads the readings of the pointer meter by distance method, and the readings are calculated:
wherein n is the number of graduation marks between the graduation mark represented by the A graduation value and the graduation mark closest to the pointer at the left end of the pointer; n is [ A, B ]]The dividing value of each scale in the numerical value interval; X-X l For pointer x and left nearest tick mark x l Is the distance between (2)Separating; x is x r -x l Is the nearest scale mark x at the right end of the pointer r And the nearest scale mark x at the left end of the pointer l Is a distance of (3).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010087850.5A CN111401357B (en) | 2020-02-12 | 2020-02-12 | Pointer type instrument reading method based on text detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010087850.5A CN111401357B (en) | 2020-02-12 | 2020-02-12 | Pointer type instrument reading method based on text detection |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111401357A CN111401357A (en) | 2020-07-10 |
CN111401357B true CN111401357B (en) | 2023-09-15 |
Family
ID=71434214
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010087850.5A Active CN111401357B (en) | 2020-02-12 | 2020-02-12 | Pointer type instrument reading method based on text detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111401357B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112329770B (en) * | 2020-10-30 | 2024-02-23 | 江苏理工学院 | Instrument scale identification method and device |
CN112464986B (en) * | 2020-10-30 | 2023-01-24 | 山东浪潮科学研究院有限公司 | Reading method and device for pointer type disc instrument |
CN113269193A (en) * | 2021-06-08 | 2021-08-17 | 上海高德威智能交通系统有限公司 | Pointer type meter reading method, device and storage medium |
CN113566863B (en) * | 2021-06-11 | 2023-12-26 | 北京眸视科技有限公司 | Pointer table reading method and device |
CN113989514A (en) * | 2021-10-11 | 2022-01-28 | 佳源科技股份有限公司 | Pointer positioning method based on template filtering |
CN115601743A (en) * | 2022-12-13 | 2023-01-13 | 南京瀚元科技有限公司(Cn) | Power distribution room pointer type instrument registration automatic reading identification method |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004133560A (en) * | 2002-10-08 | 2004-04-30 | Central Res Inst Of Electric Power Ind | Automatic reading method and automatic reader for analog meter |
CN101620682A (en) * | 2008-06-30 | 2010-01-06 | 汉王科技股份有限公司 | Method and system for automatically identifying readings of pointer type meters |
CN105260709A (en) * | 2015-09-28 | 2016-01-20 | 北京石油化工学院 | Water meter detecting method, apparatus, and system based on image processing |
WO2016101643A1 (en) * | 2014-12-26 | 2016-06-30 | 国网重庆市电力公司电力科学研究院 | Meter data read method and system |
CN106599897A (en) * | 2016-12-09 | 2017-04-26 | 广州供电局有限公司 | Machine vision-based pointer type meter reading recognition method and device |
CN107490398A (en) * | 2017-08-04 | 2017-12-19 | 湖北工业大学 | A kind of gauge pointer automatic identifying method |
CN107590498A (en) * | 2017-09-27 | 2018-01-16 | 哈尔滨工业大学 | A kind of self-adapted car instrument detecting method based on Character segmentation level di- grader |
CN107729896A (en) * | 2017-10-24 | 2018-02-23 | 武汉科技大学 | A kind of automatic identifying method suitable for the wide tuning drive gear formula instrument of transformer station |
EP3410063A1 (en) * | 2017-05-31 | 2018-12-05 | Leica Geosystems AG | Geodetic surveying with correction for instrument tilt |
JP2019192168A (en) * | 2018-04-27 | 2019-10-31 | 株式会社東芝 | Reading system, reading method, program, and recording medium |
CN110543878A (en) * | 2019-08-07 | 2019-12-06 | 华南理工大学 | pointer instrument reading identification method based on neural network |
CN110598690A (en) * | 2019-08-01 | 2019-12-20 | 达而观信息科技(上海)有限公司 | End-to-end optical character detection and identification method and system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1122521A1 (en) * | 2000-02-01 | 2001-08-08 | Setrix AG | Method and apparatus for monitoring an analog meter |
-
2020
- 2020-02-12 CN CN202010087850.5A patent/CN111401357B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004133560A (en) * | 2002-10-08 | 2004-04-30 | Central Res Inst Of Electric Power Ind | Automatic reading method and automatic reader for analog meter |
CN101620682A (en) * | 2008-06-30 | 2010-01-06 | 汉王科技股份有限公司 | Method and system for automatically identifying readings of pointer type meters |
WO2016101643A1 (en) * | 2014-12-26 | 2016-06-30 | 国网重庆市电力公司电力科学研究院 | Meter data read method and system |
CN105260709A (en) * | 2015-09-28 | 2016-01-20 | 北京石油化工学院 | Water meter detecting method, apparatus, and system based on image processing |
CN106599897A (en) * | 2016-12-09 | 2017-04-26 | 广州供电局有限公司 | Machine vision-based pointer type meter reading recognition method and device |
EP3410063A1 (en) * | 2017-05-31 | 2018-12-05 | Leica Geosystems AG | Geodetic surveying with correction for instrument tilt |
CN107490398A (en) * | 2017-08-04 | 2017-12-19 | 湖北工业大学 | A kind of gauge pointer automatic identifying method |
CN107590498A (en) * | 2017-09-27 | 2018-01-16 | 哈尔滨工业大学 | A kind of self-adapted car instrument detecting method based on Character segmentation level di- grader |
CN107729896A (en) * | 2017-10-24 | 2018-02-23 | 武汉科技大学 | A kind of automatic identifying method suitable for the wide tuning drive gear formula instrument of transformer station |
JP2019192168A (en) * | 2018-04-27 | 2019-10-31 | 株式会社東芝 | Reading system, reading method, program, and recording medium |
CN110598690A (en) * | 2019-08-01 | 2019-12-20 | 达而观信息科技(上海)有限公司 | End-to-end optical character detection and identification method and system |
CN110543878A (en) * | 2019-08-07 | 2019-12-06 | 华南理工大学 | pointer instrument reading identification method based on neural network |
Non-Patent Citations (2)
Title |
---|
Xinxin Zheng等.Pointer Instrument Recognition Algorithm Based on Haar-Like Feature and Polar Expansion.《2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC)》.2018,全文. * |
盛庆华等.基于双重霍夫空间投票的指针表自动读数方法.《仪器仪表学报》.2019,第1-10页. * |
Also Published As
Publication number | Publication date |
---|---|
CN111401357A (en) | 2020-07-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111401357B (en) | Pointer type instrument reading method based on text detection | |
CN111950330B (en) | Pointer instrument indication detection method based on target detection | |
CN112257676B (en) | Pointer type instrument reading method and system and inspection robot | |
CN108460327B (en) | Automatic identification method for reading of pointer instrument based on image processing | |
CN112906694B (en) | Reading correction system and method for transformer substation inclined pointer instrument image | |
CN102176228B (en) | Machine vision method for identifying dial plate information of multi-pointer instrument | |
CN110580480A (en) | Meter reading identification method based on image processing | |
CN111368906B (en) | Pointer type oil level meter reading identification method based on deep learning | |
CN104657711B (en) | A kind of readings of pointer type meters automatic identifying method of robust | |
CN112818988A (en) | Automatic reading identification method and system for pointer instrument | |
CN105913095A (en) | Instrument recognition method for transformer substation patrol inspection robot | |
CN112149667A (en) | Method for automatically reading pointer type instrument based on deep learning | |
CN111814919A (en) | Instrument positioning and identifying system based on deep learning | |
CN110909738A (en) | Automatic reading method of pointer instrument based on key point detection | |
CN105426809A (en) | Method for automatically identifying instrument pointer | |
CN113269193A (en) | Pointer type meter reading method, device and storage medium | |
CN114399677A (en) | Pointer instrument identification method based on text region reading | |
CN111091121B (en) | Ellipse dial plate detection and correction method based on image processing | |
CN112036391B (en) | Electronic inspection method and system based on shale gas field production station | |
CN109784257B (en) | Transformer thermometer detection and identification method | |
CN111126371A (en) | Coarse pointer dial reading method based on image processing | |
CN114240984B (en) | Circular mark point edge extraction method and application thereof | |
CN116245948A (en) | Monocular vision cooperative target and pose measuring and calculating method | |
CN116403085A (en) | Multi-pointer instrument identification method and device for transformer substation based on multitasking | |
CN113591875B (en) | High-precision pointer type instrument identification method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |