CN116958983A - Pointer type pressure gauge automatic calibrator indication reading method based on machine vision - Google Patents
Pointer type pressure gauge automatic calibrator indication reading method based on machine vision Download PDFInfo
- Publication number
- CN116958983A CN116958983A CN202310934785.9A CN202310934785A CN116958983A CN 116958983 A CN116958983 A CN 116958983A CN 202310934785 A CN202310934785 A CN 202310934785A CN 116958983 A CN116958983 A CN 116958983A
- Authority
- CN
- China
- Prior art keywords
- pointer
- instrument
- image
- dial
- machine vision
- 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 47
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000003708 edge detection Methods 0.000 claims abstract description 13
- 230000009466 transformation Effects 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 238000012216 screening Methods 0.000 claims abstract description 5
- 238000004891 communication Methods 0.000 claims abstract description 4
- 238000012937 correction Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 17
- 238000010586 diagram Methods 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 230000002146 bilateral effect Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000007670 refining Methods 0.000 claims description 6
- 230000007547 defect Effects 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 5
- 238000011426 transformation method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 2
- 239000011159 matrix material Substances 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005489 elastic deformation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L25/00—Testing or calibrating of apparatus for measuring force, torque, work, mechanical power, or mechanical efficiency
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L27/00—Testing or calibrating of apparatus for measuring fluid pressure
- G01L27/002—Calibrating, i.e. establishing true relation between transducer output value and value to be measured, zeroing, linearising or span error determination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/146—Aligning or centring of the image pick-up or image-field
- G06V30/1475—Inclination or skew detection or correction of characters or of image to be recognised
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/18—Extraction of features or characteristics of the image
- G06V30/1801—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/18—Extraction of features or characteristics of the image
- G06V30/1801—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections
- G06V30/18076—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections by analysing connectivity, e.g. edge linking, connected component analysis or slices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/19007—Matching; Proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
- G06V30/19107—Clustering techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a pointer type pressure gauge automatic calibrator indication reading method based on machine vision, which comprises the following steps: the method comprises the steps of performing image acquisition and position calibration on an instrument through an airborne camera; performing inclination correction on the acquired instrument image; based on a calibration template, identifying the scale marks of the instrument dial plate, and completing scale mark slope calculation based on the positions of the maximum and minimum scale marks; preprocessing dial images and screening communication areas to initially obtain the approximate area of the pointer in the dial of the instrument. According to the invention, contour feature extraction is carried out through canny operator edge detection, after corner points are further extracted, css corner point matching is carried out on an instrument image to be corrected and a template instrument image, a surf algorithm is used for determining matching degree, and a ransac algorithm is used for removing errors, so that a projection transformation matrix is finally obtained, the effect of correcting the pointer of an instrument dial in an inclined state is realized, and the problem that errors are generated due to the influence of an observation angle on readings is reduced.
Description
Technical Field
The invention relates to the technical field of meter reading, in particular to a pointer type pressure meter automatic calibrator indication reading method based on machine vision.
Background
The pressure gauge is characterized in that the pressure gauge is through elastic deformation of a sensitive element in the gauge, the pressure deformation is transmitted to a pointer by a conversion mechanism of a movement in the gauge, the pointer is caused to rotate to display pressure, and a machine vision is to replace a human eye to measure and judge. The shot object is converted into an image signal through a machine vision product, the image signal is transmitted to a special image processing system, the form information of the shot object is obtained, and the image signal is converted into a digital signal according to the pixel distribution, the brightness, the color and other information. The subjective error generated by artificial observation can be eliminated by reading the indication number of the pressure gauge by using a machine vision method.
In the prior art, for example, the Chinese patent number is: the method uses the latest image processing technology at present and combines mathematical knowledge such as least square method and the like to realize automatic interpretation of the indicating value of the pressure instrument in the automatic pressure gauge calibrating instrument.
However, in the prior art, in the actual application process, the machine vision generally collects the indication of the dial by a station on-board camera, and the indication corresponding to the image is identified by a dial reading system, but the collected dial image is inclined to a certain extent except for the collected image at the right upper angle, so that the radian distribution among all scale values is inconsistent, and the error of the machine vision is generated to the error of the indication of the pointer, thereby generating the error of the machine reading.
Disclosure of Invention
The invention aims to provide a pointer type pressure gauge automatic calibrator indication reading method based on machine vision, which aims to solve the problem that the prior art has the influence on the position of a camera for collecting images, the collected dial images are inclined to a certain extent except for the position of the camera for collecting images at the right upper angle, so that radian distribution among scale values is inconsistent, the included angle of pointer indication is misjudged by the machine vision, and the error of mechanical reading is generated.
In order to achieve the above purpose, the present invention provides the following technical solutions: an indication reading method of an automatic calibrator for pointer pressure gauges based on machine vision comprises the following steps:
step one: the method comprises the steps of performing image acquisition and position calibration on an instrument through an airborne camera;
step two: performing inclination correction on the acquired instrument image;
step three: based on a calibration template, identifying the scale marks of the instrument dial plate, and completing scale mark slope calculation based on the positions of the maximum and minimum scale marks;
step four: the method of edge clustering and fitting is utilized to eliminate the defects of fuzzy images and noise of the meter dial plate;
step five: preprocessing dial images and screening communication areas to preliminarily obtain the approximate area of the pointer in the dial of the instrument;
step six: obtaining an accurate edge of a pointer by combining the Hough transformation with an edge clustering and fitting method, wherein the specific processing flow of the Hough transformation is as follows, a specified area is obtained according to the circle center, the radius, the minimum scale line and the maximum scale line of a meter dial plate, then all edge points are detected, whether edge pixel points are in the specified area or not is judged, the edge points in the area are stored in a point set, after all edge points are detected, the pixel points of the point set are mapped into a space line segment, the pixel points exceeding a threshold value are deleted, and finally the extraction of the line segment is completed, so that the straight line fitting of the pointer line segment is obtained;
step seven: and calculating an included angle between the pointer and the minimum scale mark, converting the included angle into pointer indication, digitizing the indication recognition result, and outputting the indication recognition result to a user software platform.
Preferably, in the first step, the onboard camera calibrates the meter range of the meter dial, the meter minimum scale mark, the minimum scale mark identification area, the meter maximum scale mark and the position of the maximum scale mark identification area.
Preferably, in the second step, the method includes the steps of:
performing edge detection on the obtained instrument picture, extracting contour features by using a canny operator, wherein the edge detection is mainly used for extracting data information on a dial, eliminating some irrelevant interference and useless information, and acquiring dial data through less data information quantity;
further extracting corner points on the extracted contour map, carrying out css corner point matching on the instrument image to be corrected and the template instrument image, and carrying out target identification, image matching and defect detection through the intersection points of two edges in the image so as to realize instrument dial image reconstruction;
determining the matching degree by utilizing a surf algorithm;
and errors are removed by using a ransac algorithm, so that the matching accuracy is improved.
Preferably, in the third step, the following steps are included:
after the instrument is calibrated, firstly reading corresponding calibration information in an instrument template library to obtain the position of a scale mark identification area;
then intercepting a corresponding sub-graph in the current instrument image, completing the identification of the maximum and minimum graduation lines of the instrument, and completing the calculation of the gradient of the graduation lines;
carrying out color gray level conversion on the instrument image, and then carrying out binarization treatment to obtain a preprocessed scale mark identification area diagram;
extracting line segments of the scale lines by adopting a Hough transformation method;
clustering and fitting the extracted line segments;
and calculating the slope of the scale mark according to the minimum scale mark identification area and the position information of the circle center of the dial plate.
Preferably, in the fourth step, the following steps are included:
reading the position information of a dial identification area in a template library file, and then intercepting a corresponding sub-graph from an input image to obtain a dial identification area graph;
carrying out preprocessing such as bilateral filtering, graying, binarization of a self-adaptive threshold value, region shielding, canny operator edge detection and the like on the surface disc identification region map;
searching the connected domain in the regional shielding diagram, removing the connected domain outside the measuring range of the instrument, and obtaining the minimum circumscribed rectangle of the connected domain where the pointer region is located.
Preferably, in the fifth step, the method includes the steps of:
intercepting a pointer image in a dial identification area diagram according to the pointer position rectangle;
carrying out preprocessing such as bilateral filtering, graying, binarization of a self-adaptive threshold value, region shielding, canny operator edge detection and the like on the surface disc identification region map;
searching a connected domain in the region shielding diagram, removing the connected domain outside the measuring range of the instrument, and obtaining the minimum circumscribed rectangle of the connected domain where the pointer region is located;
carrying out graying and binarization processing of a self-adaptive threshold value on the pointer image to obtain a pointer edge map;
performing straight line detection on the pointer edge map by adopting Hough transformation;
and carrying out edge clustering and fitting on the pointer line segments.
Preferably, in the sixth step, the method includes the steps of:
processing the surface disc image information by adopting a median filter, and removing noise on the premise of retaining main information of the preliminarily fitted pointer image;
carrying out color gray level conversion on the instrument image, and then carrying out binarization processing, wherein the function expression of the binarization processing is as follows:
wherein T is a selected threshold, and f (x, y) is a pixel value at a (x, y) point in the meter image;
and refining the binary pointer image by adopting a parallel rapid refining algorithm to obtain a skeletonized image of the pointer.
Preferably, in step S7, the following steps are included:
calculating the slope of a straight line where the pointer is located;
calculating the angle between the pointing direction of the pointer and the minimum scale mark;
calculating pointer readings according to the known minimum scale value and maximum scale value of the regional template library file, wherein the function expression of the pointer readings is as follows:
wherein V1 is the minimum scale value of the meter dial, V2 is the maximum scale value of the meter dial, V is the pointer indication number of the meter dial, theta is the included angle between the pointer and the minimum scale line, K min For minimum scale slope of meter dial, K max Is the maximum scale mark slope of the meter dial.
Compared with the prior art, the invention has the beneficial effects that:
1. in the method, contour feature extraction is carried out through canny operator edge detection, after corner points are further extracted, css corner point matching is carried out on an instrument image to be corrected and a template instrument image, a surf algorithm is used for determining matching degree, and a ransac algorithm is used for removing errors, so that a projection transformation matrix is finally obtained, the effect of correcting the pointer of an instrument dial in an inclined state is realized, and the problem that errors are generated due to the fact that readings are influenced by observation angles is solved.
2. In the method, a median filter is adopted to process the dial image information, noise is removed on the premise of retaining main information of the preliminarily fitted pointer image, color conversion gray scale is carried out on the instrument image, then binarization processing is carried out, a parallel rapid thinning algorithm is adopted to refine the binary pointer image, and judgment between the refined pointer image and a scale value is more accurate, so that errors generated by pointer identification are reduced, accuracy of judging an included angle between the pointer and the scale value is improved, and accuracy of dial indication reading is further improved.
Drawings
FIG. 1 is a general flow chart of a pointer-type pressure gauge automatic calibrator indication reading method based on machine vision;
fig. 2 is a process flow diagram of hough transform in a method for reading indication values of an automatic calibrator for pointer type pressure gauges based on machine vision.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1 and 2, the present invention provides a technical solution: an indication reading method of an automatic calibrator for pointer pressure gauges based on machine vision comprises the following steps:
1) The method comprises the steps of performing image acquisition and position calibration on an instrument through an airborne camera;
2) Performing inclination correction on the acquired instrument image;
3) Based on a calibration template, identifying the scale marks of the instrument dial plate, and completing scale mark slope calculation based on the positions of the maximum and minimum scale marks;
4) The method of edge clustering and fitting is utilized to eliminate the defects of fuzzy images and noise of the meter dial plate;
5) Preprocessing dial images and screening communication areas to preliminarily obtain the approximate area of the pointer in the dial of the instrument;
6) Obtaining an accurate edge of a pointer by combining the Hough transformation with an edge clustering and fitting method, wherein the specific processing flow of the Hough transformation is as follows, a specified area is obtained according to the circle center, the radius, the minimum scale line and the maximum scale line of a meter dial plate, then all edge points are detected, whether edge pixel points are in the specified area or not is judged, the edge points in the area are stored in a point set, after all edge points are detected, the pixel points of the point set are mapped into a space line segment, the pixel points exceeding a threshold value are deleted, and finally the extraction of the line segment is completed, so that the straight line fitting of the pointer line segment is obtained;
7) And calculating an included angle between the pointer and the minimum scale mark, converting the included angle into pointer indication, digitizing the indication recognition result, and outputting the indication recognition result to a user software platform.
In step 1, the onboard camera calibrates the instrument range of the instrument dial plate, the minimum scale mark of the instrument, the minimum scale mark identification area, the maximum scale mark of the instrument and the position of the maximum scale mark identification area.
In step 2, the following steps are included:
21 Edge detection is carried out on the obtained instrument picture, contour feature extraction is carried out by utilizing a canny operator, the edge detection is mainly used for extracting data information on a dial, eliminating some irrelevant interference and useless information, and dial data is obtained through less data information quantity;
22 Further extracting corner points on the extracted contour map, carrying out css corner point matching on the instrument image to be corrected and the template instrument image, and carrying out target identification, image matching and defect detection through the intersection points of two edges in the image so as to realize instrument dial image reconstruction;
23 Determining the matching degree by utilizing surf algorithm;
24 Error is removed by using a ransac algorithm, and the matching accuracy is improved.
In step 3, the following steps are included:
31 After the instrument is calibrated, firstly reading corresponding calibration information in an instrument template library to obtain the position of a scale mark identification area;
32 Then intercepting the corresponding subgraph in the current instrument image, completing the identification of the maximum and minimum graduation lines of the instrument, and completing the calculation of the gradient of the graduation lines, comprising the following steps:
321 Color converting the instrument image into gray level, and then binarizing to obtain a preprocessed scale mark recognition area diagram;
322 Extracting line segments of the scale lines by adopting a Hough transformation method;
323 Clustering and fitting the extracted line segments;
324 According to the minimum scale mark identification area and the dial plate circle center position information, calculating the slope of the scale mark.
In step 4, the following steps are included:
41 Reading the position information of the dial identification area in the template library file, and then intercepting the corresponding subgraph from the input image to obtain a dial identification area map;
42 Performing preprocessing such as bilateral filtering, graying, binarization of a self-adaptive threshold value, region shielding, canny operator edge detection and the like on the surface disc identification region map;
43 Searching the connected domain in the area shielding diagram, removing the connected domain outside the measuring range of the instrument, and obtaining the minimum circumscribed rectangle of the connected domain where the pointer area is located.
In step 5, the following steps are included:
51 According to the pointer position rectangle, intercepting a pointer image in the dial identification area diagram;
52 Performing preprocessing such as bilateral filtering, graying, binarization of a self-adaptive threshold value, region shielding, canny operator edge detection and the like on the surface disc identification region map;
53 Searching a connected domain in the area shielding diagram, removing the connected domain outside the measuring range of the instrument, and obtaining the minimum circumscribed rectangle of the connected domain where the pointer area is located;
54 Gray scale processing and binarization processing of the self-adaptive threshold value are carried out on the pointer image, and a pointer edge graph is obtained;
55 Using Hough transformation to carry out straight line detection on the pointer edge graph;
56 Edge clustering and fitting are carried out on the pointer line segments.
In step 6, the following steps are included:
61 Processing the surface disc image information by adopting a median filter, and removing noise on the premise of retaining the main information of the preliminarily fitted pointer image;
62 Color-to-gray scale conversion is carried out on the instrument image, and then binarization processing is carried out, wherein the function expression of the binarization processing is as follows:
wherein T is a selected threshold, and f (x, y) is a pixel value at a (x, y) point in the meter image;
63 And (3) refining the binary pointer image by adopting a parallel rapid refining algorithm to obtain a skeletonized image of the pointer.
In step S7, the following steps are included:
71 Calculating the slope of the straight line where the pointer is located;
72 Calculating an angle between the pointing direction of the pointer and the minimum scale line;
73 Calculating pointer indication according to the known minimum scale value and maximum scale value of the regional template library file, wherein the function expression of the pointer indication is as follows:
wherein V1 is the minimum scale value of the meter dial, V2 is the maximum scale value of the meter dial, V is the pointer indication number of the meter dial, theta is the included angle between the pointer and the minimum scale line, K min For minimum scale slope of meter dial, K max Is the maximum scale mark slope of the meter dial.
In the method, in the reading of an instrument dial, the positions of an instrument range, an instrument minimum scale mark, a minimum scale mark identification area, an instrument maximum scale mark and a maximum scale mark identification area of the instrument dial are calibrated through an airborne camera;
then, extracting contour features of readings of a dial by using a canny operator, further extracting corner points, performing css corner point matching on an instrument image to be corrected and a template instrument image, determining matching degree by using a surf algorithm, removing errors by using a ransac algorithm, and correcting the acquired instrument image in an inclined manner;
then, based on a calibration template, identifying the scale marks of the instrument dial plate, and completing scale mark slope calculation based on the positions of the maximum and minimum scale marks;
then screening the dial image to preliminarily obtain the approximate area of the pointer in the dial of the instrument, and obtaining the accurate edge of the pointer by using a Hough transformation and edge clustering and fitting method;
and finally, calculating the included angle between the pointer and the minimum scale mark, converting the included angle into pointer indication, digitizing the indication recognition result and outputting the indication recognition result to the user software platform.
Although the present invention has been described with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described, or equivalents may be substituted for elements thereof, and any modifications, equivalents, improvements and changes may be made without departing from the spirit and principles of the present invention.
Claims (9)
1. The indicating value reading method of the pointer type automatic calibrator for the pressure gauge based on machine vision is characterized by comprising the following steps of:
s1, performing image acquisition and position calibration on an instrument through an onboard camera;
s2, performing inclination correction on the acquired instrument image;
s3, identifying the scale marks of the instrument dial based on the calibration template, and completing scale mark slope calculation based on the positions of the maximum and minimum scale marks;
s4, eliminating the image blurring and noise defect of the instrument dial by using an edge clustering and fitting method;
s5, preprocessing an image of the dial plate and screening a communication area to preliminarily obtain an approximate area of the pointer in the dial plate of the instrument;
s6, obtaining an accurate pointer edge by using a Hough transformation and edge clustering and fitting method;
and S7, calculating an included angle between the pointer and the minimum scale mark, converting the included angle into pointer indication, digitizing the indication recognition result, and outputting the indication recognition result to the user software platform.
2. The method for reading the indicating value of the automatic calibrator for the pointer-type pressure gauge based on machine vision according to claim 1, wherein in the step S1, the onboard camera calibrates the positions of the meter measuring range, the meter minimum graduation mark, the minimum graduation mark identification area, the meter maximum graduation mark and the maximum graduation mark identification area of the meter dial plate.
3. The machine vision-based pointer-type pressure gauge automatic calibrator indication reading method according to claim 1, wherein in step S2, the method comprises the following steps:
s21, performing edge detection on the obtained instrument picture, and extracting contour features by using a canny operator;
s22, further extracting corner points on the extracted contour map, and performing css corner point matching on the instrument image to be corrected and the template instrument image;
s23, determining the matching degree by utilizing a surf algorithm;
s24, removing errors by using a ransac algorithm, and improving the matching accuracy.
4. The machine vision-based pointer-type pressure gauge automatic calibrator indication reading method according to claim 1, wherein in step S3, the method comprises the following steps:
s31, after the instrument is calibrated, firstly reading corresponding calibration information in an instrument template library to obtain the position of a scale mark identification area;
s32, intercepting a corresponding subgraph in the current instrument image, completing the identification of the maximum and minimum graduation lines of the instrument, and completing the calculation of the gradient of the graduation lines.
5. The machine vision based pointer pressure gauge automatic calibrator reading method according to claim 4, wherein in step S32, the method comprises the steps of:
s321, carrying out color gray level conversion on an instrument image, and then carrying out binarization processing to obtain a preprocessed scale line identification area diagram;
s322, extracting line segments of scale lines by adopting a Hough transformation method;
s323, clustering and fitting the extracted line segments;
s324, calculating the slope of the scale mark according to the minimum scale mark identification area and the dial plate circle center position information.
6. The machine vision-based pointer-type pressure gauge automatic calibrator indication reading method according to claim 1, wherein in step S4, the method comprises the following steps:
s41, reading position information of a dial identification area in a template library file, and then intercepting a corresponding sub-graph from an input image to obtain a dial identification area graph;
s42, carrying out preprocessing such as bilateral filtering, graying, binarization of a self-adaptive threshold value, region shielding, canny operator edge detection and the like on the surface disc identification region map;
s43, searching the connected domain in the area shielding diagram, and removing the connected domain outside the measuring range of the instrument to obtain the minimum circumscribed rectangle of the connected domain where the pointer area is located.
7. The machine vision-based pointer-type pressure gauge automatic calibrator indication reading method according to claim 1, wherein in step S5, the method comprises the following steps:
s51, intercepting a pointer image in a dial identification area diagram according to the pointer position rectangle;
s52, carrying out preprocessing such as bilateral filtering, graying, binarization of a self-adaptive threshold value, region shielding, canny operator edge detection and the like on the surface disc identification region map;
s53, searching a connected domain in the regional shielding diagram, and removing the connected domain outside the measuring range of the instrument to obtain the minimum circumscribed rectangle of the connected domain where the pointer region is located;
s54, carrying out grey-scale treatment and binarization treatment of a self-adaptive threshold value on the pointer image to obtain a pointer edge map;
s55, carrying out straight line detection on the pointer edge graph by adopting Hough transformation;
s56, carrying out edge clustering and fitting on the pointer line segments.
8. The machine vision-based pointer-type pressure gauge automatic calibrator indication reading method according to claim 1, wherein in step S6, the method comprises the following steps:
s61, processing the surface disc image information by adopting a median filter, and removing noise on the premise of retaining the primary information of the pointer image which is preliminarily fitted;
s62, carrying out color gray level conversion on the instrument image, and then carrying out binarization processing;
and S63, refining the binary pointer image by adopting a parallel rapid refining algorithm to obtain a skeletonized image of the pointer.
9. The machine vision-based pointer-type pressure gauge automatic calibrator indication reading method according to claim 1, wherein in step S7, the method comprises the following steps:
s71, calculating the slope of a straight line where the pointer is located;
s72, calculating an angle between the pointing direction of the pointer and the minimum scale mark;
s73, calculating pointer readings according to the known minimum scale value and maximum scale value of the regional template library file.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310934785.9A CN116958983A (en) | 2023-07-27 | 2023-07-27 | Pointer type pressure gauge automatic calibrator indication reading method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310934785.9A CN116958983A (en) | 2023-07-27 | 2023-07-27 | Pointer type pressure gauge automatic calibrator indication reading method based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116958983A true CN116958983A (en) | 2023-10-27 |
Family
ID=88452511
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310934785.9A Pending CN116958983A (en) | 2023-07-27 | 2023-07-27 | Pointer type pressure gauge automatic calibrator indication reading method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116958983A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117372937A (en) * | 2023-12-07 | 2024-01-09 | 江西理工大学南昌校区 | Data reading method based on pointer instrument |
-
2023
- 2023-07-27 CN CN202310934785.9A patent/CN116958983A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117372937A (en) * | 2023-12-07 | 2024-01-09 | 江西理工大学南昌校区 | Data reading method based on pointer instrument |
| CN117372937B (en) * | 2023-12-07 | 2024-03-29 | 江西理工大学南昌校区 | Data reading method based on pointer instrument |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112818988B (en) | Automatic identification reading method and system for pointer instrument | |
| CN103759758B (en) | A kind of method for detecting position of the automobile meter pointer based on mechanical angle and scale identification | |
| CN112699876B (en) | Automatic reading method for various meters of gas collecting station | |
| CN109558871B (en) | Pointer instrument reading identification method and device | |
| CN109635806B (en) | Ammeter value identification method based on residual error network | |
| CN111368906B (en) | Pointer type oil level meter reading identification method based on deep learning | |
| CN112257676A (en) | Pointer instrument reading method and system and inspection robot | |
| CN108775872A (en) | Deflection of bridge span detection method based on autozoom scan picture | |
| CN111814919A (en) | Instrument positioning and identifying system based on deep learning | |
| CN111598109B (en) | Intelligent identification method for reading of transformer substation pointer instrument | |
| CN111325164B (en) | Pointer representation number identification method and device and electronic equipment | |
| CN117237368B (en) | Bridge crack detection method and system | |
| CN112149667A (en) | Method for automatically reading pointer type instrument based on deep learning | |
| CN116958983A (en) | Pointer type pressure gauge automatic calibrator indication reading method based on machine vision | |
| CN112560837A (en) | Reading method, device, equipment and storage medium of pointer instrument | |
| CN114266764A (en) | Character integrity detection method and device for printed label | |
| CN110633620A (en) | Pointer instrument scale identification method and electronic equipment | |
| CN112734729A (en) | Water gauge water level line image detection method and device suitable for night light supplement condition and storage medium | |
| CN114005108A (en) | Pointer instrument degree identification method based on coordinate transformation | |
| CN112036391A (en) | Electronic inspection method and system based on shale gas field production station | |
| CN113554688B (en) | O-shaped sealing ring size measurement method based on monocular vision | |
| CN116310263A (en) | Pointer type aviation horizon instrument indication automatic reading implementation method | |
| CN115588196A (en) | Pointer type instrument reading method and device based on machine vision | |
| CN112051003B (en) | Automatic product detection device, detection method and reading method for hydraulic meter | |
| CN114898347A (en) | Machine vision identification method for pointer instrument |
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 |