CN114898198A - Image processing method for automatic reading of pointer type pressure gauge - Google Patents

Image processing method for automatic reading of pointer type pressure gauge Download PDF

Info

Publication number
CN114898198A
CN114898198A CN202210554435.5A CN202210554435A CN114898198A CN 114898198 A CN114898198 A CN 114898198A CN 202210554435 A CN202210554435 A CN 202210554435A CN 114898198 A CN114898198 A CN 114898198A
Authority
CN
China
Prior art keywords
image
pointer
pressure gauge
scale
arc
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210554435.5A
Other languages
Chinese (zh)
Inventor
陈爱军
蔡嘉乐
袁治未
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Jiliang University
Original Assignee
China Jiliang University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Jiliang University filed Critical China Jiliang University
Priority to CN202210554435.5A priority Critical patent/CN114898198A/en
Publication of CN114898198A publication Critical patent/CN114898198A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • 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
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • 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
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/02—Recognising information on displays, dials, clocks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses an image processing method for automatic reading of a pointer type pressure gauge, which comprises the following specific steps: firstly, carrying out binarization processing on a pointer type pressure gauge image collected in advance, and detecting a circular arc connected with a scale mark through Hough transform to obtain an image of a region of interest; screening the lengths of the long and short scale marks in the image of the region of interest according to the geometric characteristics of the scale marks, and constructing different mask images to obtain images of local and local pointers of the scale marks; and (3) performing polar coordinate transformation on the image, acquiring the central abscissa of the scale mark in the transformed image and the central abscissa of the pointer, comparing the central abscissas of the two most adjacent scale marks of the pointer one by one, and calculating to obtain the pressure reading of the pointer type pressure gauge. The method can replace manual work to automatically read the indication value of the pointer type pressure gauge, and improves the reading precision and the reading efficiency.

Description

Image processing method for automatic reading of pointer type pressure gauge
Technical Field
The invention relates to a reading method of a pointer type pressure gauge, in particular to an automatic reading method of the pointer type pressure gauge based on an image processing technology in the field of computer vision.
Background
The pointer type pressure gauge is used as a pressure measuring device, has the advantages of simple structure, high reliability, no electromagnetic interference, low price and the like, and is widely applied to conveying pipelines and pressure containers in the industrial fields of aviation, aerospace, energy, special equipment, transportation and the like. In order to ensure that the pressure measurement units of the scientific research and production system are uniform and the measurement values are accurate and reliable, periodic verification is carried out according to the pressure gauge measurement and verification rules.
The number of pointer pressure gauges for forced verification is huge, the types of pointer pressure gauges are various, pressure is mainly manufactured by a manual pressurizing device at present, the indication value of the pressure gauge is read by human eyes, the average time for verifying one pressure gauge is about 10 minutes, long-time high-intensity manual verification easily causes visual fatigue, the probability of errors of manually estimated data is increased, and the labor cost is huge; moreover, when data is estimated, the measurement result is subject to the influence of human eye resolution, observation distance, observation angle, psychological state of the examinees and the like, resulting in the dispersion of the measurement result.
The measurement mode in the world is required to be more intelligent, the interference of personnel is reduced, and the automation and the measurement efficiency are improved. The reading of the pointer type pressure gauge is identified by utilizing a machine vision technology to become a mainstream, for example, the center and the radius of a dial plate are determined by contour scanning and least square fitting in the Schedule of the power engineering Limited company of Wuling, Hunan, and the corresponding indication value is calculated by obtaining a scale line and the angle position of a pointer through circumferential scanning; what the Hubei industry university steadily uses edge extraction and circle fitting to obtain the fitting information of the pointer rotation center and the dial circle, and uses a central projection method to extract the pointer and scale mark information to obtain the pointer reading; the Li ancestor of Zhengzhou light industry institute carries out dial center positioning based on Hough primary detection, then detects the pointer centroid by adopting a three-frame difference method, and finally connects the pointer centroid and the dial center to calculate the pointer deflection angle and identify reading.
From the research of recognizing the reading of the pointer type pressure gauge by using the machine vision technology at present, most methods need to extract the position information of the rotation center of the pointer or the center of the dial plate, and the pointing position of the pointer is determined by the rotation center of the pointer or the center of the dial plate to finally obtain the reading value of the pressure gauge.
Disclosure of Invention
Aiming at the defects in the background technology, the invention aims to provide a method for automatically reading the readings of a pointer type pressure gauge based on an image processing technology, so that the reading efficiency and the reading precision are improved.
In order to achieve the purpose, the invention adopts the technical scheme that the pointer type pressure gauge visual reading method is implemented according to the following steps:
step 1: carrying out image binarization processing on an original image;
step 2: detecting an arc connected with the scale mark and acquiring an image of the region of interest;
and step 3: acquiring a local pointer image and a local pointer image of a scale mark;
and 4, step 4: performing polar coordinate transformation on the pointer and the scale mark image;
and 5: acquiring a central abscissa of the pointer and central abscissas of two scale marks closest to the pointer in the polar coordinate transformation result image;
step 6: and calculating according to the division value of the pressure gauge, the lower limit value of the measuring range of the pressure gauge and the position relation between the pointer and each scale mark to obtain the reading of the pressure gauge.
Compared with the background art, the gain effect of the invention is as follows:
1. the invention does not need to obtain the pointer center on the pressure gauge dial plate and calculate the angle between the pointer and the scale mark, only needs to obtain the local image of the pointer and the scale mark and carry out polar coordinate transformation on the local image, converts the angle proportional relation of the pointer between the scale marks into the distance size proportional relation of the pointer between the scale marks, can effectively solve the problem that the scale mark angle and pointer angle error caused by inaccurate positioning of the pointer rotation center greatly influence the reading result of the pressure gauge, and improves the reading precision.
2. The invention only needs to provide the lower limit value of the measuring range of the pressure gauge, namely the scale value of the first main scale mark and the division value of the pressure gauge, and can read the pressure reading of the pressure gauge without character recognition of the scale value, thereby simplifying the flow of the reading method and improving the reading efficiency.
Drawings
FIG. 1 is a flow chart of a reading identification method for a pointer pressure gauge according to the present invention.
Fig. 2 is an original image of the pointer pressure gauge to be read according to the present invention.
FIG. 3 is a preprocessed pointer pressure gauge binary image of the present invention.
FIG. 4 is a circular arc and end point image of the present invention.
Fig. 5 is a region-of-interest image of the present invention.
FIG. 6 is a preliminary selected tick mark image of the present invention.
Fig. 7 is a tick mark partial image of the invention.
FIG. 8 is a local pointer segment image of the present invention.
FIG. 9 is a pointer and tick mark image of the invention.
Fig. 10 is a polar coordinate transformation result image of the present invention.
FIG. 11 shows the center line of the hand and the center lines of the left and right scale lines according to the present invention.
Fig. 12 is an image of the pressure gauge reading of the present invention.
Detailed Description
The present invention will be further described with reference to the following drawings and detailed description (examples), but the invention is not limited thereto.
As shown in fig. 1, the method of the present invention comprises the steps of:
step 1: carrying out image binarization processing on an original image
Reading an original image src which is acquired in advance and contains a pointer pressure gauge dial and a pointer as shown in fig. 2, and performing binarization segmentation processing on the original image by using a fixed threshold value determined through experiments to obtain a binary image bw as shown in fig. 3.
Step 2: detecting arcs connected with the scale lines and acquiring images of the region of interest
21) And detecting an arc connected with the scale mark in the binarized image bw by using Hough transform, and determining two end points of the arc, wherein the arc and the end point image are shown in FIG. 4.
22) Creating an image of the same size as the binary image bwThe background is black, the foreground is a circle center Cen of an arc arc Radius r of circular arc with radius value as center of circle arc Then subtracting the center Cen of the arc arc As the center of a circle, the left and right end points of the arc and the center Cen of the arc arc The connecting line of (a) is a sector drawn by two side lines, and finally, a sector mask image mask1 corresponding to the arc is obtained.
23) The mask image mask1 is used for carrying out mask operation on the binary image bw to obtain a new binary image bw2, and an image in a white fan-shaped circumscribed rectangular region in the mask image is intercepted in the image bw2 to obtain a region-of-interest image roiImg, as shown in fig. 5.
And step 3: obtaining scale mark local and local pointer image
31) Extracting the outline of the interested image roiImg, and calculating each outline C i Height H of the minimum bounding rectangle i And a contour C i Height H of i And width W i Ratio of (i.e. aspect ratio R) i ，i＝1,2,3,…,n 1 ，n 1 The number of contours. When a certain contour C i Minimum circumscribed rectangle aspect ratio R i Greater than a threshold value R low And the height H of the profile i In the interval [ H low ，H high ]Then, the contour C is determined i The area corresponding to the image roiImg of interest is the initially selected scale mark, contour C i Minimum circumscribed rectangle height of (H) i The length L of the initially selected scale mark i ，R low 、H low And H high Obtained through experiments, R in the embodiment low ＝5、H low 20 and H high 200. After all contour determinations, the initially selected scale lines are obtained as shown in fig. 6. Sorting all the initially selected scale marks in ascending order according to the length, and calculating the average length of the scale marks which are 30-70% of the total number of the initially selected scale marks, wherein the average length is the length L of the short scale marks short Calculating the average length of the longest 3 scale marks of the primary selection scale marks, wherein the average length is the length L of the long scale mark long 。
32) Creating a roiImg ruler for image of region of interestAn image mask2 with the same size, black background, and a foreground centered on Cen arc Radius r of circular arc with outer diameter value as circle center arc The inner diameter value is the arc radius r arc Minus the short scale length L short White circles. Masking the region-of-interest image roiImg with a mask image mask2 to obtain a tick mark local image slImg containing a tick mark local, as shown in fig. 7.
33) Creating an image mask3 with the same size as the binary image bw, wherein the background is black, and the foreground is an arc center Cen arc Radius r of circular arc with radius value as center of circle arc The mask image mask3 is used for performing bitwise and operation on the binary image bw to obtain a local image bw3 of the pressure dial containing the whole pointer.
34) In the image bw3, the length of each line segment is calculated by performing line segment detection using cumulative probability hough transform, wherein the longest line segment is the pointer line segment. Creating an image with black background and the same size as the binary image bw, and drawing the pointer line segment in white to obtain a pointer line segment image nlImg.
35) Creating an image mask4 with the same size as the binary image bw, wherein the background is black, and the foreground is an arc center Cen arc Radius r of circular arc with outer diameter value as circle center arc Minus the length L of the long scale lines long The inner diameter value is the radius r of the circular arc arc Minus the length L of the long scale lines long One white circle of a is subtracted, where a is determined experimentally, and in this example a is 50. The pointer segment image nlImg is subjected to a bitwise and operation using the mask image mask4, and a local pointer segment image pnimg containing only local pointer segments is obtained, as shown in fig. 8.
And 4, step 4: polar coordinate transformation of pointer and scale mark image
And (3) performing image summation operation on the scale mark local image slImg obtained in the step 32 and the local pointer line segment image pnlImg obtained in the step 35 to obtain a pointer and scale mark image nsImg, as shown in fig. 9. If the scale marks of the upper and lower limits of the pressure measuring range on the pressure gauge dial in the original image src are not positioned on the upper and lower sides of the central horizontal line of the dial, the pointer and the scale mark image nsImg need to be rotated. In this embodiment, since the scale lines of the upper and lower limits of the pressure measurement range on the dial of the pressure gauge are located on the upper and lower sides of the horizontal line at the center of the dial, the pointer and the scale line image nsImg are rotated by 90 ° counterclockwise. The center of the pointer and scale mark image nsImg is used as an origin, and a half of the height of the pointer and scale mark image nsImg is used as a boundary circle radius, so that the pointer and scale mark image nsImg are subjected to polar coordinate transformation, and the pointer and scale mark image nsImg are changed from the original point to the center of the scale to be distributed in parallel on the upper edge of a polar coordinate transformation result image ploarImg, as shown in fig. 10.
And 5: acquiring the central abscissa of the pointer and the central abscissas of the two scale marks nearest to the pointer in the polar coordinate transformation result image
51) In the pointer-to-scale mark image nsImg polar coordinate transformation result image ploarImg, the first b rows of pixel regions are extracted in the order from top to bottom, where b is the length L of the long scale mark obtained in step 31 long A tick mark area image slaeaimg including only tick marks is obtained.
52) Counting the number of pixels in each row of pixels in the scale mark area image slaeaimg from left to right and storing the number of the pixels in an array, searching the values of the array elements according to the sequence of the index numbers of the array elements from small to large, and if the value of the array element is larger than the length L of the short scale mark obtained in the step 31 short And if the index number of the array element is half of the index number of the array element, the index number of the array element is the left-side horizontal coordinate of the first scale mark, searching backwards continuously until the value of the array element is equal to 0, the index number corresponding to the previous element of the array element is the right-side coordinate of the first scale mark, calculating the mean value of the left-side horizontal coordinate and the right-side horizontal coordinate of the first scale mark to obtain the center horizontal coordinate of the first scale mark, and searching backwards in sequence according to the method of calculating the center horizontal coordinate of the first scale mark until all elements of the array are traversed to obtain the center horizontal coordinate of each scale mark.
53) In the image ploarImg of the transform result of polar coordinates of pointer and scale mark image nsImgThe pixel regions from the line b starting to the last line are extracted from the top to the bottom in this order, where b is the length L of the long scale line obtained in step 31 long A pointer area image needlearea img containing only pointers is obtained.
54) And carrying out contour screening on the pointer region image needleAreaImg, wherein the contour with the largest area is judged as the pointer contour, acquiring a circumscribed rectangle of the pointer contour, and calculating the mean value of the horizontal coordinates of the top left corner vertex and the bottom right corner vertex of the circumscribed rectangle of the pointer contour, namely the horizontal coordinate of the center of the pointer.
55) And comparing the central abscissa of the pointer with the central abscissas of the scale marks one by one, wherein the central abscissa of the scale marks is smaller than the central abscissa of the pointer, the scale mark closest to the central abscissa of the pointer is the left scale mark line1, and the central abscissa of the scale mark is larger than the central abscissa of the pointer, and the scale mark closest to the central abscissa of the pointer is the right scale mark line 2. The center line of the pointer and the center lines of the left and right scale lines are schematically shown in FIG. 11.
Step 6: according to the division value of the pressure gauge, the lower limit value of the measuring range of the pressure gauge and the position relation between the pointer and each scale mark, the reading of the pressure gauge is calculated
The pressure gauge reading p can be calculated by:
p＝sv+dv×(pIp+pDp)
wherein sv is the lower limit value of the pressure gauge range, dv is the indexing value of the pressure gauge, and pIp is the difference value of the position sequence numbers of the scale line0 corresponding to the left scale line1 closest to the pointer and the lower limit value of the pressure gauge range; pDp is the ratio of the difference between the center abscissa of the pointer and the abscissa of the left scale line1 to the difference between the center abscissas of the two scale lines line2 and line1 that are closest to the pointer. The result of the pressure gauge reading obtained by superimposing the read pressure gauge indication on the original image is shown in fig. 12.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (7)

1. An image processing method for automatic reading of a pointer type pressure gauge is characterized by comprising the following steps: the method for processing the acquired pointer type pressure gauge image comprises the following steps:
step 1: carrying out image binarization processing on an original image;
step 2: detecting an arc connected with the scale mark and acquiring an image of the region of interest;
and step 3: acquiring a local pointer image and a local pointer image of a scale mark;
and 4, step 4: performing polar coordinate transformation on the pointer and the scale mark image;
and 5: acquiring a central abscissa of the pointer and central abscissas of two scale marks closest to the pointer in the polar coordinate transformation result image;
step 6: and calculating according to the division value of the pressure gauge, the lower limit value of the measuring range of the pressure gauge and the position relation between the pointer and each scale mark to obtain the reading of the pressure gauge.
2. The image processing method for automatic reading of pointer type pressure gauge as claimed in claim 1, wherein:
the step 2 comprises the following steps: 21) detecting an arc connected with a scale mark in the binarized image bw by utilizing Hough transform; 22) constructing a fan-shaped mask image mask1 corresponding to the circular arc; 23) the region-of-interest image roiImg is acquired in the image bw using the mask image mask 1.
3. The image processing method for automatic reading of pointer type pressure gauge as claimed in claim 1, wherein:
the step 3 comprises the following steps: 31) preliminarily selecting scale marks in the region-of-interest image roiImg according to the geometric characteristics of the scale marks, and respectively calculating the length L of the short scale marks short And length L of the long scale mark long (ii) a 32) Constructing a mask image 2, using the mask image to map the region of interestAcquiring a scale mark local image slImg containing a scale mark local part from the image roiImg; 33) constructing a mask image 3, and acquiring an image bw3 containing the whole pointer from the image bw by using the mask image; 34) detecting line segments in the image bw3 by using Hough transform, wherein the longest line segment is a pointer line segment, and redrawing the pointer line segment in white in a black background image nlImg with the same size as the image bw; 35) constructing a mask image mask4, and acquiring a local pointer line segment image pnlImg containing a local pointer line segment from the image nlImg by using the mask image; 36) and (3) intercepting a sub-image with the same position and size as the region-of-interest image roiImg in the image bw from the local pointer line segment image pnlImg, and superposing the sub-image with the scale mark local image slImg to obtain an image containing the scale mark local and the local pointer line segment, namely a pointer and scale mark image nsImg.
4. The image processing method for automatic reading of pointer type pressure gauge as claimed in claim 3, wherein:
in the step 3, the size of the mask image mask2 is the same as that of the region-of-interest image roiImg, the background is black, and the foreground is one circle center Cen of the arc arc Radius r of circular arc with outer diameter value as circle center arc The inner diameter value is the arc radius r arc Minus the short scale length L short The white ring of (2); the mask image mask3 has the same size as the image bw, the background is black, and the foreground is an arc with a center Cen arc Radius r of circular arc with radius value as center of circle arc White circle of (2); the mask image mask4 has the same size as the image bw, the background is black, and the foreground is an arc with a center Cen arc Radius r of circular arc with outer diameter value as circle center arc Minus the length L of the long scale lines long Radius r of arc arc Minus the length L of the long scale lines long And subtracting a white ring of a, wherein the value of a is 30-60.
5. The image processing method for automatic reading of pointer type pressure gauge as claimed in claim 1, wherein:
in the step 4, before polar coordinate transformation is performed on the pointer and scale mark image nsImg, it is required to ensure that the scale marks of the upper and lower limits of the pressure measurement range in the original image are positioned at the upper and lower sides of the horizontal line of the center of the dial, and if the condition cannot be met, rotation processing needs to be performed on the pointer and scale mark image nsImg.
6. The image processing method for automatic reading of pointer type pressure gauge as claimed in claim 1, wherein:
the step 5 specifically comprises the following steps: 51) acquiring a scale mark area image slaeaimg only containing scale marks from a pointer and scale mark image nsImg polar coordinate transformation result image ploarImg; 52) acquiring the central abscissa of each scale mark in the image slAreaImg of the scale mark area by a projection method; 53) acquiring a pointer area image needleAREAImg only containing a pointer from a pointer and scale mark image nsImg polar coordinate transformation result image ploarImg; 54) acquiring a central abscissa of the pointer in the pointer area image needleAreaImg by searching a maximum outline; 55) according to the size relationship between the central abscissa of the pointer and the central abscissas of the scale marks, the central abscissas of the two scale marks line1 and line2 which are most adjacent to the pointer are obtained.
7. The image processing method for automatic reading of pointer type pressure gauge as claimed in claim 1, wherein:
the pressure gauge reading p in step 6 can be calculated by the following formula:
p＝sv+dv×(pIp+pDp)
wherein sv is the lower limit value of the pressure gauge range; dv is the division value of the pressure gauge; the pIP is the difference value of the position sequence number of a scale line0 corresponding to the left scale line1 closest to the pointer and the lower limit value of the range of the pressure gauge; pDp is the ratio of the difference between the center abscissa of the pointer and the abscissa of the left scale line1 to the difference between the center abscissas of the two scale lines line2 and line1 that are closest to the pointer.
CN202210554435.5A 2022-05-19 2022-05-19 Image processing method for automatic reading of pointer type pressure gauge Pending CN114898198A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210554435.5A CN114898198A (en) 2022-05-19 2022-05-19 Image processing method for automatic reading of pointer type pressure gauge

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210554435.5A CN114898198A (en) 2022-05-19 2022-05-19 Image processing method for automatic reading of pointer type pressure gauge

Publications (1)

Publication Number Publication Date
CN114898198A true CN114898198A (en) 2022-08-12

Family

ID=82724309

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210554435.5A Pending CN114898198A (en) 2022-05-19 2022-05-19 Image processing method for automatic reading of pointer type pressure gauge

Country Status (1)

Country Link
CN (1) CN114898198A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115655576A (en) * 2022-12-13 2023-01-31 成都千嘉科技股份有限公司 Automatic sensing method for displacement abnormity of pointer type pressure gauge

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115655576A (en) * 2022-12-13 2023-01-31 成都千嘉科技股份有限公司 Automatic sensing method for displacement abnormity of pointer type pressure gauge

Similar Documents

Publication Publication Date Title
CN110580480B (en) Meter reading identification method based on image processing
US11551341B2 (en) Method and device for automatically drawing structural cracks and precisely measuring widths thereof
CN108460327B (en) Automatic identification method for reading of pointer instrument based on image processing
CN114549835B (en) Pointer instrument correction identification method and device based on deep learning
CN112906694B (en) Reading correction system and method for transformer substation inclined pointer instrument image
CN104990926A (en) TR element locating and defect detecting method based on vision
CN109900711A (en) Workpiece, defect detection method based on machine vision
CN104392206A (en) Image processing method for automatic pointer-type instrument reading recognition
CN109115800B (en) Method for rapidly detecting burrs of product and accurately measuring length
CN111507186B (en) Method for recognizing reading of pointer instrument of transformer substation
CN111368906B (en) Pointer type oil level meter reading identification method based on deep learning
CN105335973A (en) Visual processing method for strip steel processing production line
CN111476246B (en) Robust and efficient intelligent reading method for pointer instrument applied to complex environment
US20230090846A1 (en) Method and device for detecting defects in aircraft template
CN107145890A (en) A kind of pointer dashboard automatic reading method under remote various visual angles environment
CN110211178B (en) Pointer instrument identification method using projection calculation
CN109034170A (en) A kind of round readings of pointer type meters method of switch cubicle detection device
CN115937203A (en) Visual detection method, device, equipment and medium based on template matching
CN114898198A (en) Image processing method for automatic reading of pointer type pressure gauge
Wang et al. Pointer meter recognition in UAV inspection of overhead transmission lines
CN112036391B (en) Electronic inspection method and system based on shale gas field production station
CN116740060A (en) Method for detecting size of prefabricated part based on point cloud geometric feature extraction
CN113554688B (en) O-shaped sealing ring size measurement method based on monocular vision
CN113989513A (en) Method for recognizing reading of square pointer type instrument
CN113378814A (en) Method and system for automatically identifying instrument

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination