CN114693705B - Pointer instrument measured value reading method, device and system - Google Patents
Pointer instrument measured value reading method, device and system Download PDFInfo
- Publication number
- CN114693705B CN114693705B CN202210366137.3A CN202210366137A CN114693705B CN 114693705 B CN114693705 B CN 114693705B CN 202210366137 A CN202210366137 A CN 202210366137A CN 114693705 B CN114693705 B CN 114693705B
- Authority
- CN
- China
- Prior art keywords
- image
- centroid
- instrument
- pointer
- connected domain
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000003287 optical effect Effects 0.000 claims abstract description 59
- 238000009826 distribution Methods 0.000 claims abstract description 10
- 238000005259 measurement Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 19
- 238000004891 communication Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 7
- 230000003993 interaction Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 13
- 238000010586 diagram Methods 0.000 description 15
- 239000002184 metal Substances 0.000 description 4
- 229910052751 metal Inorganic materials 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012824 chemical production Methods 0.000 description 2
- 150000002739 metals Chemical class 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a method, a device and a system for reading a measured value of a pointer instrument, wherein the method comprises the following steps: calculating the central position of the instrument by using a geometric method; calculating a first centroid; creating a first mask image on the pixel region with the first centroid as a center of circle; obtaining a difference image after the difference between the optical image and the image with the filled gray level; acquiring a hole filling image of the difference image, and performing AND operation on the hole filling image and the first mask image to obtain a disc image of the instrument optical image; acquiring the pointer length corresponding to the pointer region according to the distribution characteristics of the pixel points in the pointer region; performing AND operation on the second mask image and the disc image to obtain a target image; and acquiring a second centroid of each connected domain area in the target image, and identifying a measured value of the instrument according to an included angle between a connecting line of the first centroid and each second centroid. Compared with manual reading, the invention does not need to carry out a naked eye distinguishing process, and has higher speed.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a method, an apparatus, and a system for reading a measurement value of a pointer instrument.
Background
The pointer instrument has the advantages of simple structure and low cost and is widely applied to the fields of petrochemical industry, ventilation and heating equipment, power plants and the like. However, since pointer meters are mostly used in environments with complex environments, especially in chemical production, there are a lot of monitoring parameters such as pressure, temperature, humidity, fluid velocity, etc. in the chemical production process. If the reading is completely performed manually, on the one hand, the reading speed is low, errors are easy to occur, and the data is easy to forge.
Therefore, how to realize the rapid reading of the measured value of the pointer instrument through technical means is a technical problem to be solved.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method and a device for reading the measured value of a pointer instrument so as to realize the rapid reading of the measured value of the pointer instrument.
The invention solves the technical problems through the following technical scheme:
the invention provides a pointer instrument measured value reading method, which comprises the following steps:
Acquiring an optical image of an instrument indication area, and sequentially performing median filtering, gray filling and Hough transformation on the optical image to obtain edge information of an instrument, wherein the instrument comprises one or a combination of a bimetal instrument and a magnetoelectric instrument;
calculating the central position of the instrument by using a geometric method according to the edge information;
Extracting a pixel region corresponding to the instrument according to the central position and the shape of the instrument, performing binarization processing on the pixel region, and calculating a first centroid corresponding to the pixel region according to a binarization image;
Creating a first mask image on the pixel region with the first centroid as a center of circle; obtaining a difference image after the difference between the optical image and the image with the filled gray level; performing hole filling processing on the difference image to obtain a hole filling image, and performing AND operation on the hole filling image and the first mask image to obtain a disc image of the instrument optical image;
Acquiring a pointer region in the disc image by using a connected domain algorithm, and acquiring the pointer length corresponding to the pointer region according to the distribution characteristics of the pixel points in the pointer region;
Creating a second mask image by taking the first centroid as the center of a circle and the pointer length as the radius, and performing AND operation on the second mask image and the disc image to obtain a target image; and acquiring a second centroid of each connected domain area in the target image, and identifying a measured value of the instrument according to an included angle between a connecting line of the first centroid and each second centroid.
Optionally, the acquiring the optical image of the meter indication area includes:
and placing the indication area of the instrument in the center of a picture of the camera, and acquiring an optical image of the indication area of the instrument by using the camera.
Optionally, the calculating the first centroid corresponding to the pixel area according to the binarized image includes:
By means of the formula (i), A first centroid corresponding to the pixel region is calculated, wherein,
X 2 is the first centroid abscissa; a is the number of pixel points in the image corresponding to the binarized image; m is the abscissa of the pixel point in the corresponding image of the binarized image; sigma is a sum function; g is a binarized image corresponding to the image; n is the ordinate of the pixel point in the corresponding image of the binarized image; y 2 is the first centroid ordinate.
Optionally, the obtaining a difference image after the difference between the optical image and the image after gray filling includes:
And obtaining a difference image by using a formula I 3(x,y)＝I2(x,y)-I1 (x, y) and performing difference between the optical image and the image filled with gray scale, wherein,
I 3 (x, y) is a difference image; i 2 (x, y) is the gray-scale filled image; i 1 (x, y) is an optical image.
Optionally, the obtaining the pointer length corresponding to the pointer region according to the distribution characteristics of the pixel points in the pointer region Z (u, v) includes:
using the formula according to the pointer region Z (u, v), The pointer length corresponding to the pointer region is obtained, wherein,
R 2 is the pointer length; x 3 is the abscissa of the point in the pointer region Z (u, v) furthest from the first centroid (x 2,y2); y 3 is the ordinate of the point in the pointer region Z (u, v) furthest from the first centroid (x 2,y2); x 2 is the first centroid abscissa; y 2 is the first centroid ordinate.
Optionally, an included angle between a line connecting the first centroid and each second centroid includes:
By means of the formula (i), Calculating an included angle between the connection lines of the first centroid and each of the second centroids, wherein,
A direction vector of a first straight line L 1 between a second centroid of the connected domain corresponding to the initial scale and the first centroid (x 2,y2); a is the abscissa of the second centroid of the connected domain corresponding to the starting scale in the target image F (p, q); b is the ordinate of the second centroid of the connected domain in the target image F (p, q) corresponding to the starting scale; c is the abscissa of the second centroid of the connected domain corresponding to the measurement scale in the target image F (p, q); d is the ordinate of the second centroid of the connected domain in the target image F (p, q) corresponding to the measurement scale; Is the direction vector of the central axis of the pointer area Z (u, v); a direction vector of a second straight line L 2 between a second centroid of the connected domain corresponding to the measurement scale and the first centroid (x 2,y2); arccos is an inverse cosine function; alpha is the included angle between the pointer and the first straight line L 1; beta is the angle between the pointer and the second straight line L 2.
Optionally, the identifying the measured value of the meter according to the included angle between the connecting lines of the first centroid and the second centroids includes:
According to the included angle between the connecting lines of the first centroid and each second centroid, using a formula, The measured value of the meter is identified, wherein,
T is the measured value of the instrument; s is the measuring range of the instrument.
The invention also provides a pointer instrument measured value reading device, which comprises:
The acquisition module is used for acquiring an optical image of the instrument indication area, and sequentially carrying out median filtering, gray filling and Hough conversion on the optical image to obtain edge information of the instrument, wherein the instrument comprises one or a combination of a bimetal instrument and a magnetoelectric instrument;
The calculating module is used for calculating the central position of the instrument by using a geometric method according to the edge information;
The processing module is used for extracting a pixel area corresponding to the instrument according to the central position and the shape of the instrument, performing binarization processing on the pixel area, and calculating a first centroid corresponding to the pixel area according to a binarized image;
The difference module is used for creating a first mask image on the pixel area by taking the first centroid as a circle center; obtaining a difference image after the difference between the optical image and the image with the filled gray level; performing hole filling processing on the difference image to obtain a hole filling image, and performing AND operation on the hole filling image and the first mask image to obtain a disc image of the instrument optical image;
The communication module is used for acquiring a pointer region in the disc image by using a communication domain algorithm and acquiring the pointer length corresponding to the pointer region according to the distribution characteristics of the pixel points in the pointer region;
The identification module is used for creating a second mask image by taking the first centroid as the center of a circle and the pointer length as the radius, and performing AND operation on the second mask image and the disc image to obtain a target image; and acquiring a second centroid of each connected domain area in the target image, and identifying a measured value of the instrument according to an included angle between a connecting line of the first centroid and each second centroid.
The invention also provides a pointer instrument measured value reading system, which comprises: a camera, a computer, wherein,
The camera is used for shooting an optical image of the instrument indication area and sending the optical image to the computer;
the computer is configured to perform the method of any of the above.
Optionally, the system further comprises: communication equipment, storage equipment and man-machine interaction equipment, wherein,
The communication device is used for sending the optical image and the measured value of the instrument to the storage device;
the storage device is used for storing the optical image and the measured value of the instrument;
The man-machine interaction device is used for receiving a query instruction of a user and acquiring a corresponding optical image and a meter measured value from the storage device according to the query instruction.
Compared with the prior art, the invention has the following advantages:
By using the invention, the measured value of the pointer of the instrument is read by using the image recognition calculation based on the camera, and the measured value can be obtained by photographing, compared with manual reading, the invention does not need to carry out a naked eye distinguishing process, and has higher speed.
Moreover, the invention provides a method for identifying the measured value, which is completely different from the prior art, not only can identify the measured value, but also can avoid errors caused by manual reading.
Drawings
Fig. 1 is a flow chart of a method for reading a measured value of a pointer instrument according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a method for reading measured values of a pointer instrument according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a system for reading measurement values of a pointer instrument according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a process of extracting the edge of a disk and roughly locating the center of a circle of a metal thermometer in an embodiment of the invention;
FIG. 5 is a schematic diagram of a process for precisely locating a center of a circle in an embodiment of the invention;
FIG. 6 is a schematic diagram of a thermometer dial extraction process in an embodiment of the invention;
FIG. 7 is a schematic diagram of a process for marking thermometer pointers in an embodiment of the invention;
fig. 8 is a schematic diagram of another process of extracting a thermometer dial in an embodiment of the present invention.
Detailed Description
The following describes in detail the examples of the present invention, which are implemented on the premise of the technical solution of the present invention, and detailed embodiments and specific operation procedures are given, but the scope of protection of the present invention is not limited to the following examples.
Example 1
Fig. 1 is a flow chart of a method for reading a measured value of a pointer instrument according to an embodiment of the present invention; fig. 2 is a schematic diagram of a method for reading measured values of a pointer instrument according to an embodiment of the present invention; FIG. 3 is a schematic diagram of a system for reading measurement values of a pointer instrument according to an embodiment of the present invention; as shown in fig. 1 to 3, a bimetal thermometer is exemplified in example 1 of the present invention. The bimetal thermometer indicates temperature by driving the deflection angle change of the pointer by two metals with different expansion coefficients. When the temperature changes, the pointer deflection on the driving shaft generates angle change due to the difference of the thermal expansion coefficients of the two metals, and the corresponding temperature is indicated on the dial. The bimetal thermometer has the advantages of small volume, good linearity, high response speed and good stability.
S101: and acquiring an optical image of an instrument indication area by using a camera, such as an industrial camera, and sequentially performing median filtering, gray filling and Hough conversion on the optical image to obtain edge information of the instrument, wherein the instrument comprises one or a combination of a bimetal instrument and a magnetoelectric instrument.
The method comprises the steps of building a bimetal thermometer temperature real-time reading system, comprising a bimetal thermometer, a camera and a computer, wherein the optical axis of the camera is perpendicular to a dial plate of the bimetal thermometer, and ensuring that the bimetal thermometer is in the visual field range of the camera; in practical application, the indication area of the instrument can be placed in the center of the picture of the camera, and the camera is used for acquiring an optical image of the indication area of the instrument.
The camera captures an original optical image I 1 (x, y) of the bimetal thermometer and transmits the optical image I 1 (x, y) to the computer.
Fig. 4 is a schematic diagram of a process of extracting a disc edge and roughly locating a center of a circle of a metal thermometer in the embodiment of the present invention, as shown in fig. 4, performing median filtering processing on an optical image I 1 (x, y) to obtain a (a) image in fig. 4, and performing gray filling on the filtered image to obtain a (b) image I 2 (x, y) in fig. 4; then, the disk edge C (x, y) of the bimetal thermometer was extracted using the Hough transform detection method, as shown in fig. 4 (C). The basic principle of the disc radius R 1 is that a parameter plane which is the same as an image plane is taken, each non-zero point on the image is taken as a circle center, a circle is drawn on the parameter plane by a known radius, and finally, the peak value on the parameter plane is found out, so that the peak value corresponds to the circle center in the original image.
In practical applications, when the central axis of the camera is not completely perpendicular to the dial of the instrument, a certain optical distortion may exist in the photographed picture, and therefore, an affine transformation method may be used to transform the image into an optical image for front view.
S102: and calculating the central position of the instrument by using a geometric method according to the edge information.
The circle center of the fitted disk is (x 1,y1) with the disk edge C (x, y) as the circumference and the disk radius R 1 as the radius.
S103: and extracting a pixel region corresponding to the instrument according to the central position and the shape of the instrument, performing binarization processing on the pixel region by using a maximum inter-class algorithm, and calculating a first centroid corresponding to the pixel region according to a binarized image.
A rectangular ROI image is extracted from the (c) image in fig. 4 centering on the center (x 1,y1) as the (b) image J 1 (m, n) in fig. 5, and the length of the rectangular ROI image J 1 (m, n) is larger than the disk diameter, that is, 2R 1, and the height of the rectangular ROI image J 1 (m, n) is also larger than the disk diameter. In practical applications, a circular ROI image J 1 (m, n) may also be extracted, it being understood that the diameter of the circular ROI image J 1 (m, n) should be slightly larger than the disk diameter.
Fig. 5 is a schematic diagram of a process of precisely locating a circle center in the embodiment of the present invention, as shown in fig. 5, a binarized image obtained by performing binarization processing on an ROI image J 1 (m, n) is a (c) image J 2 (m, n) in fig. 5, and then a first centroid (x 2,y2) is obtained according to the coordinate distribution characteristics of pixel points in the binarized image J 2 (m, n) as shown in a (d) image in fig. 5, where the centroid is a precisely located circle center (x 2,y2), and the circle center (x 2,y2) corresponds to a circle center of a pointer dial in a (e) image in fig. 5. In practice, the average of the coordinates of the pixels in the binarized image J 2 (m, n) may be used as the first centroid, for example, a formula may be used,A first centroid corresponding to the pixel region is calculated, wherein,
X 2 is the first centroid abscissa; a is the number of pixel points in the image corresponding to the binarized image; m is the abscissa of the pixel point in the corresponding image of the binarized image; sigma is a sum function; g is a binarized image corresponding to the image; n is the ordinate of the pixel point in the corresponding image of the binarized image; y 2 is the first centroid ordinate. It is emphasized that when the binarized image is a rectangular ROI image J 1 (m, n), G is a region surrounded by the disk edge C (x, y) inside the rectangular ROI image J 1 (m, n).
S104: a first mask image M 1 (x, y) is created over the pixel area with the first centroid (x 2,y2) as the center of circle and R 1 as the radius.
Fig. 6 is a schematic diagram of a process of extracting a thermometer dial in an embodiment of the present invention, as shown in fig. 6, using a formula I 3(x,y)＝I2(x,y)-I1 (x, y), to obtain a difference image by differentiating the optical image and the image after gray filling, where,
I 3 (x, y) is a difference image, as in (c) of fig. 6; i 2 (x, y) is a gray-scale filled image, as in (b) of fig. 6; i 1 (x, y) is an optical image, as shown in fig. 6 (a).
Hole filling processing is carried out on the difference image I 3 (x, y) to obtain a hole filling image I 4 (x, y), and the hole filling image I 4 (x, y) and the first mask image M 1 (x, y) are subjected to AND operation to obtain a disc image I 5 (x, y) of the instrument optical image.
S105: and acquiring a pointer region Z (u, v) in the disc image I 5 (x, y) by using a connected domain algorithm, and acquiring the pointer length corresponding to the pointer region according to the distribution characteristics of the pixel points in the pointer region Z (u, v).
The identification of the pointer region can be implemented by using the existing connected domain algorithm, fig. 7 is a schematic diagram of a process of identifying a thermometer pointer in the embodiment of the present invention, as shown in fig. 7, a disc image I 5 (x, y) is a (a) diagram in fig. 7; fig. 7 (c) shows the pointer region Z (u, v).
The distances between all points in the pointer region Z (u, v) and the first centroid (x 2,y2) are calculated according to the triangular relationship, wherein the farthest distance corresponding point is denoted as (x 3,y3), and the distance from the farthest distance corresponding point to the first centroid (x 2,y2) is denoted as R 2, namely the pointer length.
In particular, the formula may be utilized according to the pointer region Z (u, v),The pointer length corresponding to the pointer region is obtained, wherein,
R 2 is the pointer length; x 3 is the abscissa of the point in the pointer region Z (u, v) furthest from the first centroid (x 2,y2); y 3 is the ordinate of the point in the pointer region Z (u, v) furthest from the first centroid (x 2,y2); x 2 is the first centroid abscissa; y 2 is the first centroid ordinate.
S106: a second mask image M 2 (x, y) is created with the first centroid (x 2,y2) as the center of the circle and the pointer length R 2 as the radius.
FIG. 8 is a schematic diagram of another process of extracting a thermometer dial in an embodiment of the present invention, as shown in FIG. 8, and FIG. 8 (a) is a disk image I 5 (x, y); the image (b) in fig. 8 is a second mask image M 2 (x, y); the image (c) in fig. 8 is a second mask image M 2 (x, y); two straight lines other than the pointer in the image (d) in fig. 8 are a first straight line L 1 and a second straight line L 2, respectively.
Performing an AND operation on the second mask image M 2 (x, y) and the disc image I 5 (x, y) to obtain a target image F (p, q); acquiring a second centroid (a, b) of each connected domain region in the target image F (p, q), wherein the second centroid (a, b) is the centroid of the initial graduation mark in the image F (p, q), and the second centroid (c, d) is the centroid of the final graduation mark in the image F (p, q);
Connecting the second centroid (a, b) with the first centroid (x 2,y2), the second centroid (c, d) with the center of a circle (x 2,y2) results in a first straight line L 1 and a second straight line L 2, respectively.
Then, using the formula,Calculating an included angle between the connection lines of the first centroid and each of the second centroids, wherein,
A direction vector of a first straight line L 1 between a second centroid of the connected domain corresponding to the initial scale and the first centroid (x 2,y2); a is the abscissa of the second centroid of the connected domain corresponding to the starting scale in the target image F (p, q); b is the ordinate of the second centroid of the connected domain in the target image F (p, q) corresponding to the starting scale; c is the abscissa of the second centroid of the connected domain corresponding to the measurement scale in the target image F (p, q); d is the ordinate of the second centroid of the connected domain in the target image F (p, q) corresponding to the measurement scale; Is the direction vector of the central axis of the pointer area Z (u, v); a direction vector of a second straight line L 2 between a second centroid of the connected domain corresponding to the measurement scale and the first centroid (x 2,y2); arccos is an inverse cosine function; alpha is the included angle between the pointer and the first straight line L 1; beta is the angle between the pointer and the second straight line L 2.
Then according to the included angle between the connecting lines of the first mass center and each second mass center, using a formula,The measured value of the meter is identified, wherein,
T is the measured value of the instrument; s is the measuring range of the instrument.
By using the invention, the measured value of the pointer of the instrument is read by using the image recognition calculation based on the camera, and the measured value can be obtained by photographing, compared with manual reading, the invention does not need to carry out a naked eye distinguishing process, and has higher speed.
Moreover, the invention provides a method for identifying the measured value, which is completely different from the prior art, not only can identify the measured value, but also can avoid errors caused by manual reading.
Furthermore, in the technical scheme of the invention, a measurer can stand at a longer distance, and the high resolution of the camera is utilized to read a long-distance measured value, so that the measurer does not need to walk near the thermometer to read, and the personal safety of the measurer is further ensured.
Meanwhile, in a region where the meters are dense or a data monitoring panel for arranging a large number of meters, a camera can be used for shooting two or more meters into one image, and meanwhile, measured values of the two or more meters are identified, and compared with manual reading, the reading speed can be improved. ,
Finally, the image processing algorithm adopted by the embodiment of the invention has simple principle, less calculated amount, higher operation efficiency and low requirement on hardware parameters of the equipment.
Example 2
Embodiment 2 of the present invention provides a pointer instrument measurement value reading device, which includes:
The acquisition module is used for acquiring an optical image of the instrument indication area, and sequentially carrying out median filtering, gray filling and Hough conversion on the optical image to obtain edge information of the instrument, wherein the instrument comprises one or a combination of a bimetal instrument and a magnetoelectric instrument;
The calculating module is used for calculating the central position of the instrument by using a geometric method according to the edge information;
The processing module is used for extracting a pixel area corresponding to the instrument according to the central position and the shape of the instrument, performing binarization processing on the pixel area, and calculating a first centroid corresponding to the pixel area according to a binarized image;
The difference module is used for creating a first mask image on the pixel area by taking the first centroid as a circle center; obtaining a difference image after the difference between the optical image and the image with the filled gray level; performing hole filling processing on the difference image to obtain a hole filling image, and performing AND operation on the hole filling image and the first mask image to obtain a disc image of the instrument optical image;
The communication module is used for acquiring a pointer region in the disc image by using a communication domain algorithm and acquiring the pointer length corresponding to the pointer region according to the distribution characteristics of the pixel points in the pointer region;
The identification module is used for creating a second mask image by taking the first centroid as the center of a circle and the pointer length as the radius, and performing AND operation on the second mask image and the disc image to obtain a target image; and acquiring a second centroid of each connected domain area in the target image, and identifying a measured value of the instrument according to an included angle between a connecting line of the first centroid and each second centroid.
Example 3
Embodiment 3 of the present invention provides a pointer instrument measurement value reading system, which includes: a camera, a computer, wherein,
The camera is used for shooting an optical image of the instrument indication area and sending the optical image to the computer;
the computer is configured to perform the method of any one of embodiments 1 or 2.
Optionally, the system further comprises: communication equipment, storage equipment and man-machine interaction equipment, wherein,
The communication device is used for sending the optical image and the measured value of the instrument to the storage device;
the storage device is used for storing the optical image and the measured value of the instrument;
The man-machine interaction device is used for receiving a query instruction of a user and acquiring a corresponding optical image and a meter measured value from the storage device according to the query instruction.
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 (9)
1. A method for reading a measurement value of a pointer instrument, the method comprising:
Acquiring an optical image of an instrument indication area, and sequentially performing median filtering, gray filling and Hough transformation on the optical image to obtain edge information of an instrument, wherein the instrument comprises one or a combination of a bimetal instrument and a magnetoelectric instrument;
calculating the central position of the instrument by using a geometric method according to the edge information;
Extracting a pixel region corresponding to the instrument according to the central position and the shape of the instrument, performing binarization processing on the pixel region, and calculating a first centroid corresponding to the pixel region according to a binarization image;
Creating a first mask image on the pixel region with the first centroid as a center of circle; obtaining a difference image after the difference between the optical image and the image with the filled gray level; performing hole filling processing on the difference image to obtain a hole filling image, and performing AND operation on the hole filling image and the first mask image to obtain a disc image of the instrument optical image;
Acquiring a pointer region in the disc image by using a connected domain algorithm, and acquiring the pointer length corresponding to the pointer region according to the distribution characteristics of the pixel points in the pointer region;
Creating a second mask image by taking the first centroid as the center of a circle and the pointer length as the radius, and performing AND operation on the second mask image and the disc image to obtain a target image; acquiring a second centroid of each connected domain area in the target image, and identifying a measured value of the instrument according to an included angle between a connecting line of the first centroid and each second centroid;
An angle between lines of the first centroid and each second centroid, comprising:
By means of the formula (i), Calculating an included angle between the connection lines of the first centroid and each of the second centroids, wherein,
A direction vector of a first straight line L 1 between a second centroid of the connected domain corresponding to the initial scale and the first centroid (x 2,y2); a is the abscissa of the second centroid of the connected domain corresponding to the starting scale in the target image F (p, q); b is the ordinate of the second centroid of the connected domain in the target image F (p, q) corresponding to the starting scale; c is the abscissa of the second centroid of the connected domain corresponding to the measurement scale in the target image F (p, q); d is the ordinate of the second centroid of the connected domain in the target image F (p, q) corresponding to the measurement scale; Is the direction vector of the central axis of the pointer area Z (u, v); a direction vector of a second straight line L 2 between a second centroid of the connected domain corresponding to the measurement scale and the first centroid (x 2,y2); arccos is an inverse cosine function; alpha is the included angle between the pointer and the first straight line L 1; beta is the angle between the pointer and the second straight line L 2.
2. The method for reading a measurement value of a pointer instrument according to claim 1, wherein the step of obtaining an optical image of an indication area of the instrument comprises:
and placing the indication area of the instrument in the center of a picture of the camera, and acquiring an optical image of the indication area of the instrument by using the camera.
3. The method for reading a measurement value of a pointer instrument according to claim 1, wherein the calculating a first centroid corresponding to a pixel area from a binarized image includes:
By means of the formula (i), A first centroid corresponding to the pixel region is calculated, wherein,
X 2 is the first centroid abscissa; a is the number of pixel points in the image corresponding to the binarized image; m is the abscissa of the pixel point in the corresponding image of the binarized image; sigma is a sum function; g is a binarized image corresponding to the image; n is the ordinate of the pixel point in the corresponding image of the binarized image; y 2 is the first centroid ordinate.
4. The method for reading a measurement value of a pointer instrument according to claim 1, wherein the step of obtaining a difference image by differentiating the optical image and the gray-scale-filled image comprises:
And obtaining a difference image by using a formula I 3(x,y)＝I2(x,y)-I1 (x, y) and performing difference between the optical image and the image filled with gray scale, wherein,
I 3 (x, y) is a difference image; i 2 (x, y) is the gray-scale filled image; i 1 (x, y) is an optical image.
5. The method for reading a measurement value of a pointer instrument according to claim 1, wherein the step of obtaining the pointer length corresponding to the pointer region according to the distribution characteristics of the pixels in the pointer region comprises:
using the formula according to the pointer region Z (u, v), The pointer length corresponding to the pointer region is obtained, wherein,
R 2 is the pointer length; x 3 is the abscissa of the point in the pointer region Z (u, v) furthest from the first centroid (x 2,y2); y 3 is the ordinate of the point in the pointer region Z (u, v) furthest from the first centroid (x 2,y2); x 2 is the first centroid abscissa; y 2 is the first centroid ordinate.
6. The method of claim 1, wherein identifying the meter measurement based on the angle between the first centroid and the line connecting the respective second centroids, comprises:
According to the included angle between the connecting lines of the first centroid and each second centroid, using a formula, The measured value of the meter is identified, wherein,
T is the measured value of the instrument; s is the measuring range of the instrument.
7. A pointer instrument measurement reading apparatus, the apparatus comprising:
The acquisition module is used for acquiring an optical image of the instrument indication area, and sequentially carrying out median filtering, gray filling and Hough conversion on the optical image to obtain edge information of the instrument, wherein the instrument comprises one or a combination of a bimetal instrument and a magnetoelectric instrument;
The calculating module is used for calculating the central position of the instrument by using a geometric method according to the edge information;
The processing module is used for extracting a pixel area corresponding to the instrument according to the central position and the shape of the instrument, performing binarization processing on the pixel area, and calculating a first centroid corresponding to the pixel area according to a binarized image;
The difference module is used for creating a first mask image on the pixel area by taking the first centroid as a circle center; obtaining a difference image after the difference between the optical image and the image with the filled gray level; performing hole filling processing on the difference image to obtain a hole filling image, and performing AND operation on the hole filling image and the first mask image to obtain a disc image of the instrument optical image;
The communication module is used for acquiring a pointer region in the disc image by using a communication domain algorithm and acquiring the pointer length corresponding to the pointer region according to the distribution characteristics of the pixel points in the pointer region;
the identification module is used for creating a second mask image by taking the first centroid as the center of a circle and the pointer length as the radius, and performing AND operation on the second mask image and the disc image to obtain a target image; acquiring a second centroid of each connected domain area in the target image, and identifying a measured value of the instrument according to an included angle between a connecting line of the first centroid and each second centroid;
The identification module is further configured to:
By means of the formula (i), Calculating an included angle between the connection lines of the first centroid and each of the second centroids, wherein,
A direction vector of a first straight line L 1 between a second centroid of the connected domain corresponding to the initial scale and the first centroid (x 2,y2); a is the abscissa of the second centroid of the connected domain corresponding to the starting scale in the target image F (p, q); b is the ordinate of the second centroid of the connected domain in the target image F (p, q) corresponding to the starting scale; c is the abscissa of the second centroid of the connected domain corresponding to the measurement scale in the target image F (p, q); d is the ordinate of the second centroid of the connected domain in the target image F (p, q) corresponding to the measurement scale; Is the direction vector of the central axis of the pointer area Z (u, v); a direction vector of a second straight line L 2 between a second centroid of the connected domain corresponding to the measurement scale and the first centroid (x 2,y2); arccos is an inverse cosine function; alpha is the included angle between the pointer and the first straight line L 1; beta is the angle between the pointer and the second straight line L 2.
8. A pointer meter measurement reading system, the system comprising: a camera, a computer, wherein,
The camera is used for shooting an optical image of the instrument indication area and sending the optical image to the computer;
The computer being adapted to perform the method of any one of claims 1-6.
9. The pointer-type meter measurement reading system of claim 8 wherein said system further comprises: communication equipment, storage equipment and man-machine interaction equipment, wherein,
The communication device is used for sending the optical image and the measured value of the instrument to the storage device;
the storage device is used for storing the optical image and the measured value of the instrument;
The man-machine interaction device is used for receiving a query instruction of a user and acquiring a corresponding optical image and a meter measured value from the storage device according to the query instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210366137.3A CN114693705B (en) | 2022-04-08 | 2022-04-08 | Pointer instrument measured value reading method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210366137.3A CN114693705B (en) | 2022-04-08 | 2022-04-08 | Pointer instrument measured value reading method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114693705A CN114693705A (en) | 2022-07-01 |
| CN114693705B true CN114693705B (en) | 2024-08-27 |
Family
ID=82142613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210366137.3A Active CN114693705B (en) | 2022-04-08 | 2022-04-08 | Pointer instrument measured value reading method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114693705B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116092088A (en) * | 2022-12-05 | 2023-05-09 | 山西科达自控股份有限公司 | Meter pointer reading identification method |
| CN117058390B (en) * | 2023-08-28 | 2024-05-14 | 北京航空航天大学 | High-robustness circular pointer type dial plate image state segmentation method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108256524A (en) * | 2018-01-24 | 2018-07-06 | 国家电网公司 | A kind of automatic reading method of multilist index formula instrument |
| CN111476246A (en) * | 2020-04-07 | 2020-07-31 | 杭州国彪超声设备有限公司 | Robust and efficient intelligent reading method for pointer instrument applied to complex environment |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112097686B (en) * | 2020-08-10 | 2022-03-11 | 安徽农业大学 | Camouflage object detection method based on binary fringe projection |
| CN112149667B (en) * | 2020-09-15 | 2024-05-28 | 浙江师范大学 | Automatic reading method of pointer instrument based on deep learning |
-
2022
- 2022-04-08 CN CN202210366137.3A patent/CN114693705B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108256524A (en) * | 2018-01-24 | 2018-07-06 | 国家电网公司 | A kind of automatic reading method of multilist index formula instrument |
| CN111476246A (en) * | 2020-04-07 | 2020-07-31 | 杭州国彪超声设备有限公司 | Robust and efficient intelligent reading method for pointer instrument applied to complex environment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114693705A (en) | 2022-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114693705B (en) | Pointer instrument measured value reading method, device and system | |
| CN110580480B (en) | Meter reading identification method based on image processing | |
| CN110659636B (en) | Pointer instrument reading identification method based on deep learning | |
| CN112906694B (en) | Reading correction system and method for transformer substation inclined pointer instrument image | |
| CN107167169B (en) | Readings of pointer type meters based on NI Vision Builder for Automated Inspection identifies measurement method | |
| CN112257676B (en) | Pointer type instrument reading method and system and inspection robot | |
| CN110245654B (en) | Pointer reading identification method and device, computer device and readable storage medium | |
| CN111368906B (en) | Pointer type oil level meter reading identification method based on deep learning | |
| CN105894002B (en) | A kind of instrument registration recognition methods based on machine vision | |
| CN104657711B (en) | A kind of readings of pointer type meters automatic identifying method of robust | |
| CN104392206A (en) | Image processing method for automatic pointer-type instrument reading recognition | |
| CN103927507A (en) | Improved multi-instrument reading identification method of transformer station inspection robot | |
| CN103955694A (en) | Image recognition meter reading system and method | |
| CN109508709B (en) | Single pointer instrument reading method based on machine vision | |
| CN112215060B (en) | Hough transform-based high-precision mechanical instrument reading identification method | |
| CN110852954B (en) | Image inclination correction method and system for pointer instrument | |
| CN105426809A (en) | Method for automatically identifying instrument pointer | |
| CN113269193A (en) | Pointer type meter reading method, device and storage medium | |
| WO2024093287A1 (en) | Instrument identification method based on improved u2 network | |
| CN112036409A (en) | Reading identification method and device of liquid level meter | |
| CN116844147A (en) | Pointer instrument identification and abnormal alarm method based on deep learning | |
| CN105423975A (en) | Calibration system and method of large-size workpiece | |
| CN112464986A (en) | Reading method and device for pointer type disc instrument | |
| CN114782852A (en) | Reading method, reading device and reading system of pointer type industrial instrument | |
| CN115239952A (en) | Method for reading industrial table based on YOLOV5 and U2-Net framework assistance |
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 |