CN111695551A - Dial reading method and device, computer equipment and readable storage medium - Google Patents
Dial reading method and device, computer equipment and readable storage medium Download PDFInfo
- Publication number
- CN111695551A CN111695551A CN202010459613.7A CN202010459613A CN111695551A CN 111695551 A CN111695551 A CN 111695551A CN 202010459613 A CN202010459613 A CN 202010459613A CN 111695551 A CN111695551 A CN 111695551A
- Authority
- CN
- China
- Prior art keywords
- scale
- dial
- pointer
- circle
- value
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 241000668842 Lepidosaphes gloverii Species 0.000 claims abstract description 117
- 239000013598 vector Substances 0.000 claims description 39
- 238000004590 computer program Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 abstract description 4
- 230000002349 favourable effect Effects 0.000 abstract 2
- 238000010586 diagram Methods 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001965 increasing effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
- G06V10/507—Summing image-intensity values; Histogram projection analysis
-
- 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
- G06V20/63—Scene text, e.g. street names
-
- 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
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a dial reading method, a dial reading device, computer equipment and a readable storage medium, wherein the method comprises the following steps: collecting an image on the front face of the dial plate; identifying scale values of long scale marks closest to a pointer within a preset range of the vertex position of the pointer in a pointer and dial plate based on the edge image of the image; and reading the dial according to the position of the pointer and the identified scale value of the long scale mark. This scheme is based on the positive image of dial plate of collection carries out the identification analysis and realizes, whether has peculiar table shape outward appearance with the dial plate irrelevantly, can realize the reading of other dial plates except that the electron LED dial plate that shows the digital reading, is favorable to avoiding the unicity that is suitable for, is favorable to satisfying the reading demand to diversified dial plate.
Description
Technical Field
The invention relates to the technical field of meters, in particular to a dial reading method and device, computer equipment and a readable storage medium.
Background
At present, many equipment still adopt the mode display data of instrument, need the manual work to carry out the reading to the instrument dial plate, however, the mode that the manual work read the dial plate data is consuming time and is laboursome, and the human error that easily exists influences the accuracy of reading.
Some reports for reading the dial by adopting a machine vision method exist in the prior art, but some schemes can be realized only under the condition that the dial has a special appearance, the applicable dial is single, and the application range of the schemes is limited; in addition, the scheme can only read the electronic LED dial plate displaying digital reading, the applicable dial plate is single, the application range of the scheme is limited, and the reading requirement on diversified dial plates cannot be met.
Disclosure of Invention
The embodiment of the invention provides a dial reading method, which aims to solve the technical problems that when a machine vision method is adopted to read a dial in the prior art, the applicable dial is single, and the reading requirements of diversified dials cannot be met.
The method comprises the following steps:
collecting an image on the front face of the dial plate;
identifying scale values of long scale marks closest to a pointer within a preset range of the vertex position of the pointer in a pointer and dial plate based on the edge image of the image;
and reading the dial according to the position of the pointer and the identified scale value of the long scale mark.
The embodiment of the invention also provides a dial reading device, which is used for solving the technical problems that the dial reading is single in application and cannot meet the reading requirements of diversified dials when a machine vision method is adopted to read the dial in the prior art.
The device includes:
the image acquisition module is used for acquiring images on the front surface of the dial plate;
the identification module is used for identifying a scale value of a long scale mark closest to a pointer within a preset range of the vertex position of the pointer in the pointer and the dial plate based on the edge image of the image;
and the reading module is used for reading the dial according to the position of the pointer and the identified scale value of the long scale mark.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the reading method of any dial plate when executing the computer program, so that the technical problems that the dial plate is single in application and cannot meet the reading requirements of diversified dial plates when a machine vision method is adopted to read the dial plate in the prior art are solved.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program for executing the reading method of any dial plate, so as to solve the technical problems that the dial plate is single in application and cannot meet the reading requirements of diversified dial plates when the dial plate is read by adopting a machine vision method in the prior art.
In the embodiment of the invention, the dial face reading method comprises the steps of acquiring an image of the front face of the dial, carrying out identification analysis based on the edge image of the image to obtain a scale value of a pointer and a long scale mark closest to the pointer within a preset range of the vertex position of the pointer in the dial, and reading the dial according to the position of the pointer and the scale value of the identified long scale mark so as to read the dial by adopting a machine vision method.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
fig. 1 is a flowchart of a dial reading method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an image graying provided by an embodiment of the present invention;
FIG. 3 is a schematic diagram of image binarization according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of image denoising according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an edge image according to an embodiment of the present invention;
fig. 6 is a schematic diagram of detecting the center positions of the hands and the dial plate according to the embodiment of the present invention;
FIG. 7 is a schematic diagram of an inner circle defining a scale ring according to an embodiment of the present invention;
FIG. 8 is a schematic view of an inside circle of a scale ring provided by an embodiment of the present invention;
FIG. 9 is a schematic diagram of a method for determining the position of a long scale corresponding to a scale value according to an embodiment of the present invention;
FIG. 10 is a schematic illustration of a dial reading provided by an embodiment of the present invention;
fig. 11 is a flowchart of a method for implementing the dial reading according to an embodiment of the present invention;
FIG. 12 is a block diagram of a computer device according to an embodiment of the present invention;
fig. 13 is a block diagram of a dial reading device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the following embodiments and accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
In an embodiment of the present invention, there is provided a method for reading a dial plate, as shown in fig. 1, the method including:
step 102: collecting an image on the front face of the dial plate;
step 104: identifying scale values of long scale marks closest to a pointer within a preset range of the vertex position of the pointer in a pointer and dial plate based on the edge image of the image;
step 106: and reading the dial according to the position of the pointer and the identified scale value of the long scale mark.
As can be seen from the flow shown in fig. 1, in the embodiment of the present invention, an image of the front surface of a dial plate is collected, and identification and analysis are performed based on an edge image of the image to obtain a scale value of a pointer and a long scale closest to the pointer within a preset range of a vertex position of the pointer in the dial plate, and then the dial plate is read according to the position of the pointer and the scale value of the long scale identified, so as to read the dial plate by using a machine vision method.
In specific implementation, the image of the front surface of the acquisition dial plate is acquired by taking the right front side of the dial plate as a visual angle, and the image only needs to comprise scale marks, scale values, pointers and the like of the dial plate.
In specific implementation, in order to recognize the pointer in the image, the following steps are implemented in this embodiment:
carrying out graying and binarization processing on the image; specifically, the grayed image is shown in fig. 2, and then the grayed image is binarized according to the characteristic that the dial pointer and the scale mark have obvious color difference with the dial background, the binarized image is shown in fig. 3, and the scale value, the scale mark, the dial central area and the like can be extracted from the binarized image. In addition, denoising processing can be performed on the binarized image, and the denoised image is shown in fig. 4, so that scale values, scale lines, a dial plate central area and the like in fig. 4 are clearer;
calculating an edge image based on the processed image; specifically, the canny operator can be used to calculate the edge, and the calculated edge image is shown in fig. 5;
detecting straight lines in the edge image, and determining the intersection point of the two detected straight lines as the vertex of the pointer; specifically, as shown in fig. 6, the intersection point of the detected 3 straight lines is the vertex of the pointer;
and performing circle detection in a specified range at the center of the edge image, determining the circle center of the detected circle (as shown in fig. 6, namely the circle center of the circle for fixing the pointer on the center of the dial) as the center position of the dial, and identifying the pointer by using a connecting line between the center position of the dial and the vertex of the pointer as the pointer.
In specific implementation, in the process of detecting a circle in the edge image, the specified range at the center of the edge image may be a circle of a specified range in the center area of the dial plate, where the center of the edge image is used as an origin and a preset length is used as a radius, and the size of the specified range may be determined according to an actual situation, which is not specifically limited in this application.
In specific implementation, the method for detecting the straight line through the change of hough can be adopted in the process of detecting the straight line, because the influence of environmental parameters on the hough transformation method is large, the method for automatically correcting the parameters can be adopted, automatic adjustment is carried out according to the number of the detected straight lines until the number of the detected straight lines is 2 or 3, the intersection point of the 2 or 3 straight lines is calculated, and the intersection point is the position of the vertex of the pointer. And (4) carrying out hough circle detection in a preset range near the pointer and at the center of the edge image, wherein the detected circle is determined as the center position of the dial plate.
In specific implementation, in order to realize the reading of the dial, in this embodiment, the scale value of the long scale mark closest to the pointer within the preset range of the vertex position of the pointer in the dial is identified by the following steps:
determining an inner side circle of a scale ring by taking the central position of the dial plate as the center of a circle and taking the distance between the vertex of the pointer and the central position of the dial plate as a reference radius in the edge image of the image, wherein the scale ring is in an annular shape formed by scale marks, and the inner side circle of the scale ring is a circle which is arranged on the inner side of the scale ring and only intersects with the long scale marks;
the method comprises the following steps that the position of a long scale mark is determined according to the intersection of an inner circle of a scale ring and the long scale mark, specifically, the scale mark generally comprises the long scale mark and a short scale mark, the long scale mark and the short scale mark are generally uniformly distributed in a dial plate, the short scale mark is uniformly distributed between adjacent long scale marks, namely when the scale marks with two lengths are distributed in the dial plate, the longer scale mark is determined as the long scale mark; or only long scale marks are distributed in the dial plate, so that when only scale marks with one length are distributed in the dial plate, the scale marks are confirmed to be long scale marks;
according to the position of the pointer in the dial and the position of the long scale mark, identifying the position of the long scale mark closest to the pointer within a preset range of the vertex position of the pointer in the dial; specifically, the size of the preset range of the vertex position of the pointer may be determined according to an actual calculation condition, for example, the preset range may be a circle determined by taking the vertex of the pointer as a center and a certain length as a radius, and the preset range at least includes one long scale mark;
and determining the scale value of the identified long scale mark according to the position of the identified long scale mark.
In specific implementation, in order to improve the accuracy of the reading, in this embodiment, the process of determining the inner circle of the scale ring may be implemented by the following steps:
in the edge image of the image, a plurality of candidate circles with different radiuses are set by taking the central position of the dial plate as the center of a circle and taking the distance between the vertex of the pointer and the central position of the dial plate as a reference radius; specifically, based on the characteristics that the scale marks around the disc have obvious consistent width and are uniformly distributed, the inventor of the application proposes to search the inner side position of the scale ring (namely the inner side circle of the scale ring) in the area near the vertex of the pointer, further proposes to use the central position of the dial as the center of a circle, and sets a plurality of candidate circles with different radiuses by taking the distance between the vertex of the pointer and the central position of the dial as a reference radius, wherein the radius range of the candidate circles can be rminTo rmaxThen, it is determined that the search width is d, and the smaller the value of d is set, the higher the accuracy of the search is. Radius is rmin、rmin+d、rmin+2d......rmin+ nd (where r ismin+nd<＝rmax,rmin+(n+1)*d>rmax) The n circles of (2) are used as candidate circles for searching the inner circle of the scale ring, and as shown in fig. 7, a plurality of candidate circles with different radiuses are distributed on the dial.
Aiming at each candidate circle, establishing a polar coordinate system by taking a circle center as a pole and taking a horizontal direction as a polar axis, starting from a position on the candidate circle where the polar coordinate angle is 0, calculating pixel values at each position on the candidate circle by taking a preset polar coordinate angle X as an interval, determining positions where the pixel values are a plurality of continuous 1 as scale marks, and forming a dimension vector of the candidate circle by taking the pixel values at each position as elements; for example, starting from a position where the polar coordinate angle on the candidate circle is 0, the radius length of the candidate circle is unchanged, pixel values at a plurality of positions where the polar coordinate angle on the candidate circle is x (i.e., the preset polar coordinate angle), 2x, 3x to mx (where mx < >2 × pi and (m +1) × >2 × pi, the larger the m value is, the more accurate the calculation is, and x represents a multiplier) are sequentially calculated, positions where the pixel values are consecutive 1 are determined as graduation lines, that is, each graduation line includes a plurality of consecutive pixel values 1, and then the pixel values at each position are taken as elements to form a dimension vector S of the candidate circle, for example, the dimension vector S of one candidate circle is: 0001110000111000001111000;
for each candidate circle, extracting a plurality of pixel value segments comprising 1 from the dimension vector of the candidate circle, using the position ordinal number in the dimension vector of the first 1 in each pixel value segment as an element to form a position sequence of the candidate circle, using the number value comprising 1 in each pixel value segment as an element to form a length sequence of the candidate circle, calculating the statistic value of the position sequence, and forming the statistic vector by the statistic value and the number of the pixel value segments; for example, the dimension vector S of a candidate circle is: 0001110000111000001111000, a plurality of continuous 1 in the dimension vector S form a pixel value segment, that is, three continuous 1 in the dimension vector S form a pixel value segment, there are 3 pixel value segments in the dimension vector S, positions of the continuous 1 are determined as scale marks, and then one pixel value segment corresponds to one scale mark, and for each pixel value segment, a position ordinal number of a first 1 in the dimension vector in each pixel value segment is determined, for example, a position ordinal number of the first 1 in the dimension vector in the first pixel value segment is 4, and then the position ordinal numbers corresponding to the pixel value segments are sequentially used as elements to form a position sequence of the candidate circle, for example, a position sequence p of the obtained candidate circle is {4, 11, 17 }; meanwhile, for each pixel value segment, determining the number value of 1 included in each pixel value segment, for example, the number value of 1 included in the first pixel value segment in the dimension vector S is 3, and further sequentially using the number value corresponding to each pixel value segment as an element to form a length sequence l of the candidate circle, for example, the length sequence l of the obtained candidate circle is {3, 3, 4}, and the number g of the pixel value segments is 3;
screening candidate circles of which the statistical vectors accord with a preset threshold, wherein the preset threshold shows the width consistency degree and the distribution uniformity degree of the scale marks corresponding to the multiple elements on the candidate circles, and the candidate circles accord with the preset threshold show that the scale marks on the circles meet the characteristics of width consistency, distribution uniformity and the like;
among the candidate circles selected, the candidate circle having the smallest radius is determined as the inner circle of the scale ring, as shown in fig. 8.
In specific implementation, in order to finally determine the inner circle of the scale ring, in this embodiment, the statistical value of the position sequence is calculated through the following steps, and a candidate circle with a statistical vector meeting a preset threshold is screened out; screening candidate circles of which the statistical vectors meet a preset threshold value:
calculating a mean and a root mean square error of the sequence of positions;
and determining a circle of which the mean value meets a first threshold, the root mean square error is smaller than a second threshold and the number g of the pixel value segments is larger than a third threshold as a circle of which the statistical vector meets a preset threshold.
Specifically, a pixel value segment consisting of a plurality of continuous 1S is extracted from a dimension vector S of a candidate circle, a position sequence p of the candidate circle is obtained, for example, the position sequence p is {4, 11, 17}, a mean value p1 and a root mean square error p2 of the position sequence p are calculated, a statistical vector (p1, p2, g) is formed by combining g, candidate circles of p1> b, p1< c, p2< e, g > f are screened out, wherein b and c are the first threshold values, b and c are constants and are related to the width range of a single scale mark, b represents a lower limit of the width range of the single scale mark, and c represents an upper limit of the width range of the single scale mark; f is the third threshold, f is a constant, and f is related to the number of scale lines; e is the second threshold, and e is a constant and generally ranges from 4 to 7. And if the number of the screened candidate circles is more than 1, the candidate circle with the smallest radius is the inner circle of the scale ring.
In this embodiment, for example, the position of the scale value of the identified long scale mark may be determined according to the identified position of the long scale mark, and the scale value of the identified long scale mark may be determined according to the position of the scale value of the long scale mark by the following steps:
for example, the position of the scale value of the long scale mark identified above may be determined by a method of locating the scale value on the inner side of the scale ringThe circle has a polar angle of (p)m+lm/2) X, polar radius rcA rectangular coordinate system is established with the point of (a) as the origin, the abscissa axis is the horizontal direction, the ordinate axis is the vertical direction, a square with q as the side length and the coordinate point (-q/2,0) as the upper left corner point is determined, and the square marks the position of the long scale corresponding to the scale value, as shown in fig. 9, wherein pmIs the corresponding position ordinal number, l, of the pixel value segment m corresponding to the long scale mark in the position sequence of the inner circle of the scale ringmThe number value of the pixel value segment m corresponding to the long scale mark in the length sequence of the inner circle of the scale ring is X, the preset polar coordinate angle rc＝gr-q*20.5/2，grIs the radius of the inner circle of the scale ring, q is a constant, rcIs a constant number rcThe value of (a) is related to the size of the scale value font.
In a specific implementation, for example, for a certain long graduation mark corresponding to the mth pixel value segment in the dimension vector of the inner circle of the graduation ring, the position ordinal number corresponding to the mth pixel value segment is the element p in the position sequence p of the inner circle of the graduation ringmThen the number value corresponding to the mth pixel value segment is the element l in the length sequence l of the inner circle of the scale ringmWherein the value of m is 1,2 and 3 … … g. And when the position of the long scale line corresponding to the scale value is determined, the scale value is calculated by (p)m+lm/2) X, polar radius rcAnd (3) establishing a rectangular coordinate system by taking the point as the original point, taking the abscissa axis as the horizontal direction and taking the ordinate axis as the vertical direction, determining a square with the side length of q and the coordinate point (-q/2,0) as the upper left angular point, and calibrating the position of the long scale line corresponding to the scale value by the square.
And determining the scale value of the identified long scale mark according to the position of the scale value of the identified long scale mark.
In specific implementation, the positions of the scale values of all the long scale marks on the dial can be identified, and only the position of the scale value of the long scale mark closest to the pointer within the preset range of the vertex position of the pointer can be identified.
During specific implementation, after the position of the long scale corresponding to the scale value is determined, the scale value of the long scale can be identified by identifying the number according to the position of the scale value of the long scale, and the identified scale value of the long scale can be determined according to the identified position of the scale value of the long scale by the following steps in this embodiment:
inputting the recognized hog features of the positions of the scale values of the long scale marks into an SVM classifier, and outputting the recognized scale values of the long scale marks by the SVM classifier, wherein training data of the SVM classifier are images marked with the scale values at the positions of the long scale marks, the hog features of the positions of the scale values of the long scale marks in the images are extracted, the adopted SVM type is a multi-classification type C _ SVC, and a kernel function of the SVM classifier can adopt a linear kernel function.
In specific implementation, the scale values of all the long scale marks on the dial plate can be output by the SVM classifier based on the position hog characteristics of the scale values of all the long scale marks on the dial plate, and the scale values of the long scale marks closest to the pointer in the preset range of the vertex position of the pointer can also be output based on the position hog characteristics of the scale values of the long scale marks closest to the pointer in the preset range of the vertex position of the pointer.
In specific implementation, in order to ensure the accuracy of the reading, in this embodiment, the dial reading is performed by, for example, reading the dial according to the position of the pointer and the scale value of the identified long scale mark, including:
acquiring a polar coordinate angle corresponding to the long scale mark on the inner circle of the scale ring;
calculating the polar coordinate angle difference between the long scale mark and the position of the pointer on the inner circle of the scale ring according to the polar coordinate angle corresponding to the long scale mark on the inner circle of the scale ring and the position of the pointer;
obtaining pre-stored interval value information, wherein the interval value information comprises a polar coordinate angle interval corresponding to adjacent scale values and a scale value interval value corresponding to the polar coordinate angle interval, and specifically, the polar coordinate angle interval and the scale value interval value corresponding to the polar coordinate angle interval can be determined according to specific conditions, and the smaller the polar coordinate angle interval and the scale value interval value is, the higher the reading precision is, for example, the polar coordinate angle interval is 1 degree, and the scale value interval value corresponding to the polar coordinate angle interval is 30 seconds or 1 minute;
calculating a scale value difference corresponding to the polar coordinate angle difference according to the pre-stored interval value information;
and calculating the reading of the dial plate according to the scale value of the long scale mark and the scale value difference.
In specific implementation, when the long scale mark is on the left side of the pointer, the scale value difference can be added to the scale value of the long scale mark to obtain the reading of the dial plate; when the long tick mark is to the right of the pointer, the tick mark difference may be subtracted from the tick mark value of the long tick mark.
During specific implementation, the precision of dial reading can be further improved, for example, the dial reading can be corrected, and scale mark information can be prestored, wherein the scale mark information comprises a polar coordinate angle corresponding to each long scale mark on the inner circle of the scale ring and a scale value corresponding to each long scale mark; and correcting the reading according to the pre-stored scale mark information and the pre-stored interval value information.
Specifically, due to the influence of the external environment, there may be some noises in the dial image, so that there may be problems of omission and repeated detection in the determined scale lines and scale values. To overcome this problem, a correction is performed after the graduation marks and scale values are completely extracted. And extracting abnormal points according to the characteristics that the scale marks are uniformly distributed in the dial and the scale values are uniformly increased and decreased, and supplementing or eliminating the abnormal points. The polar angle on the inner circle of the scale ring is listed as ali(i 1.. m1), and the corresponding scale value identification value is set to kvj(j 1.. m1), calculating an angle interval list al1 ═ alq-alq-1(q 2.. m1), scale interval list kv1 ═ kvz-kvz-1M1, (z 2.. m1), calculating al1And kv1List of the highest frequency data location points apAnd kp, the calculation list j ═ ap∩kpLet gf be alj+1-aljAs the polar coordinate angle interval corresponding to the adjacent scale values, kf is equal to kvj+1-kvjCalculating a correct position point set jf (j + {1}) ∪ j with scale values matched with the scale positions, wherein the correct position point set to be corrected is pj {1,2,3.. the position points m1-1} -jf, and the set is al1 according to the characteristic that scale lines are uniformly distributed according to the scale valuespjAnd kv1pjAnd deleting and correcting, eliminating abnormal points and supplementing missed selection points.
From the position of the pointer's vertex and the list of scale location points al determined aboveiAnd scale value list kvj(namely the pre-stored scale mark information), determining the nearest scale mark of the pointer, then determining the polar coordinate angle between the nearest scale mark and the pointer, determining the corresponding scale value difference between the nearest scale mark and the pointer according to the polar coordinate angle interval corresponding to the adjacent scale value and the scale value interval value (namely the pre-stored interval value information) corresponding to the polar coordinate angle interval, further calculating and determining the meter reading according to the scale value and the scale value difference of the nearest scale mark, and correcting the reading obtained by the dial reading method by adopting the meter reading.
In specific implementation, as shown in fig. 11, the process of implementing the dial reading method includes the following steps:
acquiring an image on the front face of a dial, wherein the image can be a color image, performing graying, binarization and smooth denoising on the image, calculating an edge image based on the processed image, detecting the vertex of a pointer by a hough change straight line detection method in the edge image, performing hough circle detection to determine the central position of the dial, and obtaining the position of the pointer by taking the connecting line between the central position of the dial and the vertex of the pointer as the pointer; in the edge image, taking the center position of a dial as a circle center, taking the distance between the vertex of the pointer and the center position of the dial as a reference radius, setting a plurality of candidate circles with different radii, calculating pixel values at positions on the candidate circles by taking a preset polar coordinate angle as an interval for each candidate circle, determining positions with continuous pixel values of a plurality of 1 as scale marks, forming a dimension vector of the candidate circle by taking the position information of each scale mark as an element, calculating a statistical vector based on a plurality of continuous elements in each dimension vector, screening out candidate circles of which the statistical vectors accord with a preset threshold value, and determining the candidate circle with the smallest radius as an inner circle of the scale ring in the screened candidate circles; calibrating the position of each long scale mark based on the inner circle of the scale ring, and further determining the position of the scale value of the long scale mark; extracting the hog features of the positions of the long scale marks corresponding to the scale values and inputting the hog features into an SVM classifier, outputting the scale values corresponding to the long scale marks by the SVM classifier, calculating dial readings according to the positions of the pointers and the scale values of the long scale marks closest to the pointers by combining the prestored interval value information, and correcting the calculated dial readings to obtain final dial readings, for example, the dial readings shown in FIG. 10.
In this embodiment, a computer device is provided, as shown in fig. 12, which includes a memory 1202, a processor 1204, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the reading method of any of the above-mentioned dials.
In particular, the computer device may be a computer terminal, a server or a similar computing device.
In the present embodiment, there is provided a computer-readable storage medium storing a computer program for executing the reading method of any of the dials described above.
In particular, computer-readable storage media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable storage medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
Based on the same inventive concept, the embodiment of the present invention further provides a dial reading device, as described in the following embodiments. Because the principle of the dial reading device for solving the problems is similar to the dial reading method, the implementation of the dial reading device can refer to the implementation of the dial reading method, and repeated parts are not described again. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 13 is a block diagram showing a structure of a reading device of a dial plate according to an embodiment of the present invention, and as shown in fig. 13, the device includes:
the image acquisition module 1302 is used for acquiring an image on the front surface of the dial plate;
the identification module 1304 is used for identifying a scale value of a long scale mark closest to a pointer within a preset range of the vertex position of the pointer in the dial plate and the pointer based on the edge image of the image;
and a reading module 1306, configured to read a dial according to the position of the pointer and the identified scale value of the long scale mark.
In one embodiment, the identification module includes:
an image processing unit for performing graying and binarization processing on the image;
an image calculation unit for calculating an edge image based on the processed image;
the straight line detection unit is used for detecting a straight line in the edge image and determining the intersection point of the two detected straight lines as the vertex of the pointer;
and the circle detection unit is used for detecting a circle in a preset range at the center of the edge image, determining the circle center of the detected circle as the center position of the dial plate, and taking a connecting line between the center position of the dial plate and the vertex of the pointer as the pointer.
In one embodiment, the identification module includes:
an inner circle determining unit, configured to determine an inner circle of a scale ring in an edge image of the image, using a center position of the dial as a center of a circle, and using a distance between a vertex of the pointer and the center position of the dial as a reference radius, where the scale ring is an annular ring formed by scale marks, and the inner circle of the scale ring is a circle that is inside the scale ring and intersects only the long scale marks;
the scale mark position determining unit is used for determining the position of the long scale mark according to the intersection of the inner circle of the scale ring and the long scale mark, and identifying the position of the long scale mark closest to the pointer within a preset range of the vertex position of the pointer in the dial plate according to the position of the pointer in the dial plate and the position of the long scale mark;
and the scale value determining unit of the scale mark is used for determining the scale value of the identified long scale mark according to the position of the identified long scale mark.
In one embodiment, the inner circle determining unit includes:
a circle setting subunit, configured to set, in the edge image of the image, a plurality of candidate circles with different radii, with a center position of the dial as a center of a circle, and with a distance between a vertex of the pointer and the center position of the dial as a reference radius;
the pixel calculation subunit is used for establishing a polar coordinate system by taking the circle center as a pole and the horizontal direction as a polar axis for each candidate circle, calculating pixel values of positions on the candidate circle by taking a preset polar coordinate angle as an interval from a position where the polar coordinate angle on the candidate circle is 0, determining positions where the pixel values are a plurality of continuous 1 s as a scale mark, and forming a dimension vector of the candidate circle by taking the pixel values of the positions as elements;
the statistical vector calculating subunit is used for extracting pixel value segments comprising a plurality of continuous 1 from the dimension vector of each candidate circle, using the position ordinal number of the first 1 in the dimension vector in each pixel value segment as an element to form a position sequence of the candidate circle, using the number value of the 1 included in each pixel value segment as an element to form a length sequence of the candidate circle, calculating the statistical value of the position sequence, and using the statistical value and the number of the pixel value segments to form a statistical vector;
the screening subunit is used for screening out candidate circles of which the statistical vectors accord with a preset threshold, wherein the preset threshold indicates the width consistency degree and the distribution uniformity degree of scale marks corresponding to a plurality of elements on the candidate circles;
and an inner circle determining unit for determining a candidate circle having the smallest radius among the selected candidate circles as an inner circle of the scale ring.
In one embodiment, the scale value determination unit of the graduation mark includes:
the statistical vector calculating subunit is specifically configured to calculate a mean value and a root mean square error of the position sequence;
the screening subunit determines, as a candidate circle whose statistical vector meets a preset threshold, a candidate circle whose mean value meets a first threshold, whose root mean square error is smaller than a second threshold, and whose number of pixel value segments is greater than a third threshold.
In one embodiment, the scale value determination unit of the graduation mark includes:
a scale value position determining subunit for determining, for each long scale line, a polar angle of (p) on the inner circle of the scale ringm+lm/2) X, polar radius rcThe point of (a) is used as an original point to establish a rectangular coordinate system, the abscissa axis is the horizontal direction, the ordinate axis is the vertical direction, a square which takes q as the side length and takes a coordinate point (-q/2,0) as the upper left angular point is determined, the square marks the position of the long scale line corresponding to the scale value, wherein pmThe pixel value segment m corresponding to the long scale mark is positioned on the inner circle of the scale ringCorresponding position ordinal number, l, in the sequence of positions of (1)mThe number value of the pixel value segment m corresponding to the long scale mark in the length sequence of the inner circle of the scale ring is X, the preset polar coordinate angle rc＝gr-q*20.5/2，grIs the radius of the inner circle of the scale ring, and q is a constant;
and the scale value determination subunit is used for determining the scale value of the identified long scale mark according to the position of the scale value of the identified long scale mark.
In one embodiment, the scale value determination subunit of the scale mark is configured to input the hog feature of the identified position of the scale value of the long scale mark into an SVM classifier, and the SVM classifier outputs the identified scale value of the long scale mark.
In one embodiment, the reading module comprises:
the angle difference calculation unit is used for acquiring the corresponding polar coordinate angle of the long scale mark on the inner circle of the scale ring, and calculating the polar coordinate angle difference between the long scale mark and the position of the pointer on the inner circle of the scale ring according to the corresponding polar coordinate angle of the long scale mark on the inner circle of the scale ring and the position of the pointer;
the device comprises an information acquisition unit, a calculation unit and a control unit, wherein the information acquisition unit is used for acquiring prestored interval value information, and the interval value information comprises a polar coordinate angle interval corresponding to adjacent scale values and a scale value interval value corresponding to the polar coordinate angle interval;
the scale value difference calculating unit is used for calculating the scale value difference corresponding to the polar coordinate angle difference according to the pre-stored interval value information;
and the reading unit is used for calculating the reading of the dial plate according to the scale value of the long scale mark and the scale value difference.
The embodiment of the invention realizes the following technical effects: the dial reading method comprises the steps of collecting images on the front face of a dial, carrying out identification and analysis based on the images to obtain a scale value of a long scale closest to a pointer within a preset range of the pointer and the vertex position of the pointer in the dial, and reading the dial according to the position of the pointer and the scale value of the identified long scale, so as to read the dial by adopting a machine vision method.
It will be apparent to those skilled in the art that the modules or steps of the embodiments of the invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, embodiments of the invention are not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes may be made to the embodiment of the present invention by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (11)
1. A method for reading a dial, comprising:
collecting an image on the front face of the dial plate;
identifying scale values of long scale marks closest to a pointer within a preset range of the vertex position of the pointer in a pointer and dial plate based on the edge image of the image;
and reading the dial according to the position of the pointer and the identified scale value of the long scale mark.
2. The method for reading a dial according to claim 1, wherein identifying a pointer based on said image comprises:
carrying out graying and binarization processing on the image;
calculating an edge image based on the processed image;
detecting straight lines in the edge image, and determining the intersection point of the two detected straight lines as the vertex of the pointer;
and performing circle detection in a specified range at the center of the edge image, determining the center of the detected circle as the center position of the dial plate, and using a connecting line between the center position of the dial plate and the vertex of the pointer as the pointer.
3. A method for reading a dial according to claim 1, wherein identifying the scale value of the long scale closest to the hand within a preset range of the position of the vertex of the hand in the dial comprises:
determining an inner side circle of a scale ring by taking the central position of the dial plate as the center of a circle and taking the distance between the vertex of the pointer and the central position of the dial plate as a reference radius in the edge image of the image, wherein the scale ring is in an annular shape formed by scale marks, and the inner side circle of the scale ring is a circle which is arranged on the inner side of the scale ring and only intersects with the long scale marks;
determining the position of the long scale mark according to the intersection of the inner circle of the scale ring and the long scale mark;
according to the position of the pointer in the dial and the position of the long scale mark, identifying the position of the long scale mark closest to the pointer within a preset range of the vertex position of the pointer in the dial;
and determining the scale value of the identified long scale mark according to the position of the identified long scale mark.
4. The method for reading a dial according to claim 3, wherein determining an inner circle of the dial ring in the edge image with a distance between a vertex of the pointer and a central position of the dial as a reference radius from the central position of the dial as a center of the circle comprises:
in the edge image of the image, a plurality of candidate circles with different radiuses are set by taking the central position of the dial plate as the center of a circle and taking the distance between the vertex of the pointer and the central position of the dial plate as a reference radius;
aiming at each candidate circle, establishing a polar coordinate system by taking a circle center as a pole and taking a horizontal direction as a polar axis, starting from a position on the candidate circle where a polar coordinate angle is 0, calculating pixel values at each position on the candidate circle by taking a preset polar coordinate angle as an interval, determining positions where the pixel values are a plurality of continuous 1 as scale marks, and forming a dimension vector of the candidate circle by taking the pixel values at each position as elements;
for each candidate circle, extracting a pixel value segment comprising a plurality of continuous 1's from the dimension vector of the candidate circle, using the position ordinal number of the first 1 in the dimension vector in each pixel value segment as an element to form a position sequence of the candidate circle, using the number value of the 1 included in each pixel value segment as an element to form a length sequence of the candidate circle, calculating the statistic value of the position sequence, and using the statistic value and the number of the pixel value segments to form a statistic vector;
screening candidate circles of which the statistical vectors accord with a preset threshold, wherein the preset threshold shows the width consistency degree and the distribution uniformity degree of scale marks corresponding to a plurality of elements on the candidate circles;
and determining the candidate circle with the smallest radius as the inner circle of the scale ring.
5. The method for reading a dial according to claim 4, wherein calculating the statistical values of the sequence of positions, and screening candidate circles whose statistical vectors meet a preset threshold value, comprises:
calculating a mean and a root mean square error of the sequence of positions;
and determining the candidate circle of which the mean value meets a first threshold, the root mean square error is smaller than a second threshold and the number of the pixel value segments is larger than a third threshold as the candidate circle of which the statistical vector meets a preset threshold.
6. The method for reading a dial according to claim 4, wherein determining the scale value of the identified long tick mark based on the identified position of the long tick mark comprises:
for each long graduation mark, the polar angle on the inner circle of the graduation ring is (p)m+lm/2) X, polar radius rcThe point of (a) is used as an original point to establish a rectangular coordinate system, the abscissa axis is the horizontal direction, the ordinate axis is the vertical direction, a square which takes q as the side length and takes a coordinate point (-q/2,0) as the upper left angular point is determined, the square marks the position of the long scale line corresponding to the scale value, wherein pmIs the corresponding position ordinal number, l, of the pixel value segment m corresponding to the long scale mark in the position sequence of the inner circle of the scale ringmThe number value of the pixel value segment m corresponding to the long scale mark in the length sequence of the inner circle of the scale ring is X, the preset polar coordinate angle rc＝gr-q*20.5/2，grIs the radius of the inner circle of the scale ring, and q is a constant;
and determining the scale value of the identified long scale mark according to the position of the scale value of the identified long scale mark.
7. The method for reading a dial according to claim 6, wherein determining the identified scale value of the long scale mark based on the identified position of the scale value of the long scale mark comprises:
and inputting the hog features of the positions of the scale values of the identified long scale marks into an SVM classifier, and outputting the scale values of the identified long scale marks by the SVM classifier.
8. A method for reading a dial according to any one of claims 3 to 6, wherein reading the dial according to the position of the hands and the scale value of the long marks identified comprises:
acquiring a polar coordinate angle corresponding to the long scale mark on the inner circle of the scale ring;
calculating the polar coordinate angle difference between the long scale mark and the position of the pointer on the inner circle of the scale ring according to the polar coordinate angle corresponding to the long scale mark on the inner circle of the scale ring and the position of the pointer;
obtaining pre-stored interval value information, wherein the interval value information comprises a polar coordinate angle interval corresponding to adjacent scale values and a scale value interval value corresponding to the polar coordinate angle interval;
calculating a scale value difference corresponding to the polar coordinate angle difference according to the pre-stored interval value information;
and calculating the reading of the dial plate according to the scale value of the long scale mark and the scale value difference.
9. A device for reading a dial, comprising:
the image acquisition module is used for acquiring images on the front surface of the dial plate;
the identification module is used for identifying a scale value of a long scale mark closest to a pointer within a preset range of the vertex position of the pointer in the pointer and the dial plate based on the edge image of the image;
and the reading module is used for reading the dial according to the position of the pointer and the identified scale value of the long scale mark.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method for reading a dial according to any one of claims 1 to 8 when executing the computer program.
11. A computer-readable storage medium, characterized in that it stores a computer program to execute the method of reading a dial according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010459613.7A CN111695551B (en) | 2020-05-27 | 2020-05-27 | Method and device for reading dial, computer equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010459613.7A CN111695551B (en) | 2020-05-27 | 2020-05-27 | Method and device for reading dial, computer equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111695551A true CN111695551A (en) | 2020-09-22 |
| CN111695551B CN111695551B (en) | 2023-09-01 |
Family
ID=72478322
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010459613.7A Active CN111695551B (en) | 2020-05-27 | 2020-05-27 | Method and device for reading dial, computer equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111695551B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114119980A (en) * | 2021-12-07 | 2022-03-01 | 杭州涿溪脑与智能研究所 | Diaphragm capsule pressure gauge pressure reading method and system based on deep learning |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245654A (en) * | 2018-11-20 | 2019-09-17 | 浙江大华技术股份有限公司 | Total indicator reading recognition methods and device, computer installation and readable storage medium storing program for executing |
| CN110378326A (en) * | 2019-07-08 | 2019-10-25 | 宁波大学科学技术学院 | A kind of mechanical indicating pointer pressure gauge reading recognition methods |
| CN111160337A (en) * | 2019-12-12 | 2020-05-15 | 武汉工程大学 | Automatic identification method, system, medium and equipment for reading of pointer instrument |
-
2020
- 2020-05-27 CN CN202010459613.7A patent/CN111695551B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245654A (en) * | 2018-11-20 | 2019-09-17 | 浙江大华技术股份有限公司 | Total indicator reading recognition methods and device, computer installation and readable storage medium storing program for executing |
| CN110378326A (en) * | 2019-07-08 | 2019-10-25 | 宁波大学科学技术学院 | A kind of mechanical indicating pointer pressure gauge reading recognition methods |
| CN111160337A (en) * | 2019-12-12 | 2020-05-15 | 武汉工程大学 | Automatic identification method, system, medium and equipment for reading of pointer instrument |
Non-Patent Citations (1)
| Title |
|---|
| JIANNAN CHI等: "Machine Vision Based Automatic Detection Method of Indicating Values of a Pointer Gauge" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114119980A (en) * | 2021-12-07 | 2022-03-01 | 杭州涿溪脑与智能研究所 | Diaphragm capsule pressure gauge pressure reading method and system based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111695551B (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107609557B (en) | Pointer instrument reading identification method | |
| CN107590498B (en) | Self-adaptive automobile instrument detection method based on character segmentation cascade two classifiers | |
| CN110659636B (en) | Pointer instrument reading identification method based on deep learning | |
| CN103759758B (en) | A kind of method for detecting position of the automobile meter pointer based on mechanical angle and scale identification | |
| CN111488874A (en) | Method and system for correcting inclination of pointer instrument | |
| CN109558871B (en) | Pointer instrument reading identification method and device | |
| CN112801094B (en) | Pointer instrument image inclination correction method | |
| CN114549835A (en) | Pointer instrument correction identification method and device based on deep learning | |
| CN110378227B (en) | Method, device and equipment for correcting sample labeling data and storage medium | |
| CN110211178A (en) | A kind of pointer instrument recognition methods calculated using projection | |
| CN112836726B (en) | Pointer instrument indication reading method and device based on video information | |
| CN111695551B (en) | Method and device for reading dial, computer equipment and readable storage medium | |
| CN115511718A (en) | PCB image correction method and device, terminal equipment and storage medium | |
| CN111199191A (en) | Pointer instrument automatic reading method based on scale searching | |
| CN111401377A (en) | Instrument data reading method and device, electronic equipment and storage medium | |
| CN115452845B (en) | LED screen surface damage detection method based on machine vision | |
| CN114565911B (en) | Instrument reading method and device, computer equipment and storage medium | |
| Yi et al. | A clustering-based algorithm for automatic detection of automobile dashboard | |
| CN114742849B (en) | Leveling instrument distance measuring method based on image enhancement | |
| CN116188960A (en) | Instrument intelligent reading method, device, equipment and medium based on key point identification | |
| CN115588196A (en) | Pointer type instrument reading method and device based on machine vision | |
| CN113408551A (en) | Pointer instrument reading identification method, system, equipment and computer storage medium | |
| CN113610086A (en) | Reading correction method and device for vertical-scale pointer instrument and terminal equipment | |
| CN114255458A (en) | Method and system for identifying reading of pointer instrument in inspection scene | |
| CN113920305A (en) | Lightning arrester instrument identification method and device |
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 |