CN106529559A - Pointer-type circular multi-dashboard real-time reading identification method - Google Patents
Pointer-type circular multi-dashboard real-time reading identification method Download PDFInfo
- Publication number
- CN106529559A CN106529559A CN201611258521.2A CN201611258521A CN106529559A CN 106529559 A CN106529559 A CN 106529559A CN 201611258521 A CN201611258521 A CN 201611258521A CN 106529559 A CN106529559 A CN 106529559A
- Authority
- CN
- China
- Prior art keywords
- image
- dial plate
- pointer
- line
- circular
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
-
- 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
- G06V10/443—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 by matching or filtering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the pointer-type instrument reading automatic interpretation field and particularly provides a method for accurately identifying the reading of each pointer-type instrument through analyzing and processing the videos of a plurality of pointer-type instrument panels based on the combination of dashboard video acquisition, image processing and computer vision. According to the technical scheme of the multi-dashboard reading identification method based on the combination of image video acquisition, image processing and computer vision, a mobile device/ tablet device of a certain resolution is adopted for video shooting. During the video shooting process, the readings of a plurality of dashboards are simultaneously identified. The method has the advantages of good robustness, good real-time performance, high efficiency, low cost and the like. The video acquisition and the reading identification are carried out simultaneously, so that the real-time performance is improved. Since the video images of a plurality of dashboards are acquired at the same time each time, the efficiency is improved. The method effectively improves the industrial production efficiency, reduces the industrial overhead, and provides a reliable technical guarantee for the subsequent industrial production.
Description
Technical field
The present invention relates to readings of pointer type meters automatic interpretation field, specifically a kind of to utilize dial plate video acquisition, image
The mode that process is combined with computer vision is analyzed process to multiple pointer dashboard videos, and then is accurately identified
The method of each readings of pointer type meters.
Background technology
Pointer instrument identification obtains image of gauge with pointer by dial plate IMAQ towards industrial pointer instrument,
Using image processing techniques, relevant with reading is asked for information in image is detected, instrument board reading is automatically identified, to improve
The accuracy of reading, the artificial expense of reduction, raising efficiency.With the development of modernization industry, the increase of data volume, pointer instrument
The universalness of table, it is desirable to which the automatic indication recognition of pointer instrument has higher performance, speed and reliability, therefore proposes one
Plant and be particularly important with the intelligent pointer formula Meter recognition method of reliability with more high real-time.
Existing pointer instrument recognition methods is mainly concerned with the technology of following several respects：IMAQ, image are located in advance
Content in terms of reason, circular dial plate and cursor line identification, cursor line angle calculation, Recognition of Reading five.
In prior art, disclosed mode has：1.《Automatic Alignment System Based on
Center Point Recognition of Analog Measuring Instruments Dial》, Industrial
Electronics Society,IECON 2013–39th Annual Conference of the IEEE；2.《Pointer-
Type Meter Reading Method Research Based on Image Processing Technology》,
Second International Conference on Networks Security, Wireless Communications
And Trusted Computing (NSWCTC), vol.1, pp.107,110,24-25, April 2010；3.《Auto-
recognition method for point-type meter based on binocular vision》, Journal of
The International Measurement Confederation, 2016；4.《Automatic Calibration of
Analog and Digital Measuring Instruments Using Computer Vision》, IEEE
Transactions on Instrumentation and Measurement, VOL.49, NO.1, February 2000；5.
《some results on condition numbers of the scaled total least squares
problem》, Linear Algebra and its applications, vol.435, pp.674-686, August 2011；
6. master's thesis：《The research of intelligent substation pointer instrument automatic identifying method》, electrical engineering, electrical engineering
2016；7.《Computer vision applied to the automatic calibration of measuring
instruments》, Journal of the International Measurement Confederation (IMEKO),
Measurement 28(2000)185-195；8.《Study on the calibration of analog measuring
instrument system》, Acta Metrologica Sinica, vol.30 (z1), pp.192-195, December
2009；9《Ellipse Detection Using Randomized Hough Transform》,Final Project
Introduction to Computer Vision,2002；10.《Scalable object detection using deep
neural networks》, In Computer Vision and Pattern Recognition, 2014.CVPR
2014.IEEE Conference on,2014；11.《Novel Method of Automatic Recognition for
Analog Measuring Instruments》, International Conference on Manufacturing
Science and Engineering(ICMSE)2015；12.《Segmentation as selective search for
object recognition》, In Proceedings of the 2011International Conference on
Computer Vision,ICCV’11,pages 1879–1886,Washington,DC,USA,2011.IEEE Computer
Society；13.《Going deeper with convolutions》, Computer Science, Computer Vision
and Pattern Recognition,2014；14.《Segmentation-free approaches of computer
vision for automatic calibration of digital and analog instruments》,
International Measurement Confederation,Institute of Measurement and Control
Elsevier,Measurement 46(1):177-184 2013；15.《Readings of pointer type meters based on machine vision is recognized
System research》, Mechanical Design and Theory, Jilin University, 2015, Master's thesis.
IMAQ is first step of pointer Meter recognition, subsequently to recognize that reading provides raw material.Industrially
The general collection that pointer dial plate image is carried out using camera and fixed position, later with the development of infrared camera,
Light filling shooting is carried out on the basis of fixing camera position so that the image for collecting is more clear.
Image semantic classification is the second step for carrying out Meter recognition, and carry out dial plate detection with cursor line detection it is important
Precursor step.It mainly includes following several steps：(1) image denoising：By certain filtering algorithm such as Gaussian filter algorithm,
Image to collecting carries out denoising operation, obtains the more visible coloured image of an amplitude ratio.(2) binaryzation：Due to as RGB this
The coloured image of sample is all three-channel image, and the process to image is generally based on pixel, and the process to image is exactly
Based on matrix, colored triple channel image is converted into into gray scale single channel image, amount of calculation is largely reduced, is improve
The speed of subsequent treatment.(3) morphological image process and image thinning：Operated by Morphological scale-space and image thinning so that
Circular dial plate profile and cursor line are more projected, and facilitate the detection of follow-up dial plate and cursor line.
After the completion of pretreatment, the 3rd step is located using Computer Vision Detection circle dial plate profile and pointer
Straight line.General method is the mode using Hough loop truss and Hough straight-line detections, by the size threshold value for arranging circle,
The circle at dial plate place is found out, by the threshold value for arranging straight line length, the straight line at pointer place is found out.
After finding the circle at dial plate place and the straight line at cursor line place, the 4th step is to calculate cursor line to justify in dial plate
In slope, and then calculate pointer point to reading angle shared by sum ratio.
Last step is to calculate reading, is calculated by the shared ratio in whole range of the number of cursor line sensing and is worked as
Front reading.
It is industrially general to adopt camera or infrared camera to gather the image of pointer instrument, and camera and finger
Pin type instrument is man-to-man.Adopt the dial plate image for collecting in this way more clear, but generally there are in the industry
The pointer instrument of multiple same types, carries out identical image if adopting and being accomplished by the camera of equal number in this way
Acquisition tasks, cost it is relatively costly.
Pointer instrument recognition methods in current industrial, typically all collecting device are connected with computer by interface,
The dial plate image information for collecting is transferred to computer to be stored, and then image procossing, identification is carried out using related algorithm
Reading.This mode needs substantial amounts of image information to be stored in relational database, further takes out and is analyzed, one during analysis
Determine in degree, to reduce recognition speed, increased storage overhead, recognition speed can be subject to very big when photo resolution is higher
Affect.
When instrument board IMAQ is carried out, often a piece image, only one of which dial plate in each image, detect
When be also that single dial plate is detected, it is less efficient.If the parameter for having substantial amounts of dial plate in industry is all identical, then can
Carry out carry out otherwise automatic reading while knowing to adopt while shooting several dial plates, so can more improve relevant work stream
The efficiency of journey.
Due to the increase of data volume, requirement of all kinds of instrument and meters to accuracy is higher.Current most pointer-type
Instrument automatic identification system has not often reached the high requirement in industrial production to precision, causes industrial production error to increase
Greatly, What is more can have undesirable effect to industrial production.
The content of the invention
It is an object of the invention to overcome the deficiencies in the prior art, the high intelligence of a kind of low cost, efficiency high, accuracy is designed
Can pointer round meter recognition methods.It is that a kind of image/video collection, image procossing and computer vision of being based on combines
Many meter reading recognition methods, using with certain resolution mobile device or flat board carry out video capture, video clap
While recognizing multiple dial readings during taking the photograph.The method has preferable robustness, real-time, high efficiency, cost low
Feature, due to being that Recognition of Reading is carried out while video acquisition, thus improves real-time；Due to gathering multiple every time
Instrument board video image, thus improve efficiency.Comprehensive says that the invention effectively raises industrial production efficiency, reduces
Industrial expense, for after, industrial production provides reliable technology and ensures.
The invention provides a kind of pointer circular many instrument board real time readouts recognition methods, in turn include the following steps：
Step 1：The image/video of the circular many instrument boards of pointer-type is obtained in real time using mobile device；
Step 2：The image/video of the pointer circular many instrument boards to obtaining carries out framing pretreatment；
Step 3：To carrying out, framing is pretreated to carry out rim detection per frame image data；
Step 4：Multiple circles that the circular dial plate of the circular many instrument boards of pointer-type is located are detected using Hough transform, if
Detect corresponding circle, then into next step, return to step 2 if it can't detect；
Step 5：Dial plate area-of-interest is split, the boundary rectangle area that each circular dial plate is located is partitioned into respectively
Domain；
Step 6：Inclination dial plate in the image of the circumscribed rectangular region being located to each circular dial plate respectively is corrected；
Step 7：The straight line that pointer is located in each circular dial plate is detected respectively using Hough transform, if detect it is right
The straight line answered, then into next step, return to step 2 if it can't detect；
Step 8：Two extreme coordinates according to the corresponding straight line for detecting, are obtained using the slope-intercept form of an equation of straight line respectively
The value of the slope k of the straight line being located to correspondence cursor line, calculates the inswept angle, θ in range region of correspondence pointer；
Step 9：The slope k of the straight line being located according to correspondence cursor line, minimum scale is vmin, maximum scale is vmax, refer to
Angle a between the scale and minimum scale of needlework indication, the angle, θ that pointer is inswept, reading to be solved is v, using formula：
V=vmin+(vmax-vmin)×(a÷θ)
Calculate corresponding reading in the circular many instrument boards of current correspondence pointer-type.
Further, the pretreatment of framing described in step 2 is to be filtered denoising, two-value successively to each two field picture
Change process, edge detection process, Morphological scale-space process, image thinning process and image enhancement processing.
Further, described in step 3 to carry out framing it is pretreated per frame image data carry out rim detection be into
Row canny rim detections, specifically include：
3.1. the convolution of image and Gaussian filter, wherein S [i, j] is asked to obtain convolution value, G [i, j for required；σ]
For Gaussian filter, I [i, j] is image slices vegetarian refreshments：
S [i, j]=G [i, j；σ]*I[i,j]
3.2. be divided to two matrixes of calculating partial derivative using first difference, wherein S [i, j] is tried to achieve in step 3.1
Convolution value, P [i, j] and Q [i, j] are two calculative partial derivative matrixs respectively：
P[i,j]≈(S[i,j+1]-S[i,j]+S[i+1,j+1]-S[i+1,j])÷2
Q[i,j]≈(S[i,j]-S[i+1,j]+S[i,j+1]-S[i+1,j+1])÷2
3.3. amplitude and azimuth are asked, wherein M [i, j] is gradient magnitude, and θ [i, j] is required gradient direction：
θ [i, j]=arctan (Q [i, j] ÷ P [i, j])
3.4. the data to obtaining after step 3.3 process carry out non-maxima suppression process；
3.5. threshold value is taken, all values that will be less than threshold value assign zero, obtain the edge array of image.
Further, step 4 includes justifying using Hough transform detection per two field picture to pretreated in step 2, passes through
The size threshold value of the dial plate circle related to image pixel is set, the central coordinate of circle of the circle and the circle at circular dial plate place is found.
Further, by the way of tilted character on the circular dial plate of correction obtaining the angle of inclination of dial plate.
Further, the angle of inclination for obtaining dial plate is to pluck out partly incline on dial plate by using rotation rectangular area
Oblique character, carries out the calculating at angle of inclination, then carries out balance drawing the anglec of rotation respectively.
Further, step 7 detects 0 in being specially the image of the circumscribed rectangular region being located for each circular dial plate
During the cursor line of bar or 3 and the above, illustrate that correspondence is not fully found cursor line information, come back for next frame process,
When 1 or 2 cursor lines is detected, illustrate that correspondence have found cursor line, carry out respective algorithms and calculate real cursor line
And cursor line angle.
Further, the image of the circumscribed rectangular region being located to each circular dial plate carries out straight-line detection, if correspondence
2 cursor lines are detected, then obtains the intersection point of two straight lines, the line segment formed by intersection point and the line in the center of circle is used as real
Cursor line.
The present invention is a kind of pointer round meter disk based on video image acquisition, image procossing and computer vision
The integrated approach of automatic identification, mainly has the advantages that following several respects：
1. the present invention is, based on video, to effectively raise the clear of the circular dial plate image of collection in terms of IMAQ
The real-time with identification process is spent, also, the present invention is mainly carried out using the equipment with camera function such as mobile device, flat board
The collection of image/video, is compared relative to traditional shooting using expensive camera, effectively reduces IMAQ cost.
2. the present invention is after video image acquisition, it is not necessary to which video or image file are stored, but is regarding
After frequency image is acquired, the video that direct processing is collected, and then meter reading is obtained, and traditional Meter recognition
System then needs the image information to collecting to store, and occupies a large amount of memory spaces, and expense is very big.Using directly process
The method of image information can substantially reduce industrial production expense, improve industrial efficiency.
3. the present invention is, based on image procossing and machine vision, by arranging appropriate threshold parameter, can to make instrument
Accuracy of identification reaches very high level, and for comparing the relatively not high accuracy of identification of current various Meter recognitions, the present invention is adopted
Method can meet the industrial high requirement to precision.
4. the present invention is based on machine vision, towards bottom, effectively raises the step of dial plate detection and identification, current work
In industry, most Meter recognition system running speed is affected very big by environment, memory capacity, and speed is relatively low, compare and
Speech, the executions speed of the inventive method due to not affected with the operation such as exterior read-write by storing, therefore with very high execution
Speed.
5. during image/video collection is carried out using handheld device or flat board, due to the shadow of the factors such as shooting angle
Sound often makes the dial plate inclination in image, is unfavorable for the calculating of follow-up cursor line angle.Image procossing is added in the system
In the step of carry out rotation correction to image, the image tilt problem that any shooting angle is caused can be corrected so as to
Recover standard dial plate image, more improve the degree of accuracy.
6. the inventive method can process multiple instrument boards simultaneously, you can to have multiple tables in processing per two field picture simultaneously
The scene of disk.Process identification is carried out to the dial plate in scene respectively, while reading is returned to into user, relative to current great majority
Method is all, towards for single instrument board, to have great convenience for the user, and further improves the field with the detection of many instrument
In scape, the efficiency of dial plate identification, on the other hand also reduces the expense of user.
Description of the drawings
Fig. 1 is the circular many instrument board real time readouts recognition methods flow charts of pointer-type；
Fig. 2 is the design flow diagram of many dial plate processing sequences；
Fig. 3 is the design flow diagram of the rotation correction for inclining dial plate；
Fig. 4 is the flow chart that Hough detects hand of dial line；
Flow charts of the Fig. 5 for cursor line angle calculation；
The original image of round pressure tables of the Fig. 6 by detecting；
Images of the Fig. 7 by the round pressure table that detects Jing after binary conversion treatment；
Fig. 8 is converted to the pointer round pressure table image of YUV color spaces for RGB color；
Fig. 9 is the image of the circle that 3 Jing Hough transforms of pressure gauge are detected and cursor line.
Specific embodiment
The following detailed description of being embodied as the present invention, it is necessary to it is pointed out here that, below implement to be only intended to this
Bright further illustrates, it is impossible to be interpreted as limiting the scope of the invention, and art skilled person is according to above-mentioned
Some nonessential modifications and adaptations that the content of the invention is made to the present invention, still fall within protection scope of the present invention.
The present invention is a kind of method suitable for industrial pointer-type round meter automatic indication recognition, and it is based at image
Reason, with reference to various cutting edge technologies such as video analysis, machine vision, the pointer dashboard video to photographing is analyzed place
Reason, so as to identify readings of pointer type meters.The invention mainly includes video image acquisition, Image semantic classification, image border inspection
Survey, Hough loop truss, extraction area-of-interest, dial plate rotation correction, Hough straight-line detections, cursor line angle calculation and reading
Nine steps such as number identification.
Flow charts of the Fig. 1 for the Recognition of Reading process of the inventive method, mainly including following nine steps：
Step 1：Many dial plate video image acquisitions.
Using flat board or the camera function of taking pictures of handheld device, video image bat is carried out to the pointer instrument in scene
Take the photograph, at present, the image resolution ratio of general flat board or handheld device can meet the needs of the inventive method.In video image
In shooting process, camera is focusing in real time.
Step 2：Every frame pretreatment is carried out to dial plate video image.
In this step, need for the pointer dashboard video image for photographing to carry out every frame pretreatment.Image
Preprocessing process includes that filtering and noise reduction, binaryzation etc. are operated.
During video capture is carried out using flat board or handheld device, each frame image data of generation is more or less
All there is noise, it is therefore desirable to the filtering and noise reduction of image is carried out to each two field picture.
In order to improve processing speed, colored RGB triple channels figure is carried out binary conversion treatment by needs so as to be converted to single channel
Image.Here we carry out binary conversion treatment to image using threshold method.
Step 3：Rim detection is carried out to the image after binaryzation.
For gray-scale map, before dial plate loop truss and cursor line detection is carried out, needs carry out edge inspection to every two field picture
Survey, the object unrelated with the target studied is thought to reduce data volume and reject.
The algorithm flow of Canny rim detections approximately as：
1. seek the convolution of image and Gaussian filter, wherein S [i, j] is required convolution value, G [i, j；σ] be
Gaussian filter, values of the I [i, j] for pixel：
S [i, j]=G [i, j；σ]*I[i,j] (1)
2. it is divided to two matrix G for calculating partial derivative using first differenceX[i, j] and GY[i,j]：
GX[i,j]≈(S[i,j+1]-S[i,j]+S[i+1,j+1]-S[i+1,j])/2 (2)
GY[i,j]≈(S[i,j]-S[i+1,j]+S[i,j+1]-S[i+1,j+1])/2 (3)
3. amplitude G [i, j] and azimuth angle theta [i, j], two variables therein is asked to be respectively two local derviations in (2) (3) formula
Number：
θ [i, j]=arctan (GX[i,j]/GY[i,j]) (5)
4. non-maxima suppression；
5. take threshold value：The all values that will be less than threshold value assign zero, obtain the edge array of image.
Next need to carry out every two field picture Morphological scale-space, project dial plate profile and cursor line, be that detection refers to below
The profile and cursor line of pin type dial plate is prepared.
Step 4：The circle that circular dial plate is located is detected using Hough transform.
Hough transform is the key technology in the inventive method used by the circular pointer dashboard of detection.Hough transform is examined
Surveying round basic thought is：Using image space and the duality of parameter space.Such as detection is justified, and round equation is：(x-a)2+
(y-b)2=R2, it is the equation for being changed into the point with regard to a, b in mapping that to parameter.Looked for according to parametric equation in parameter space
If to do, using statistics correlation technique, these points are counted, find and be gathered in what the most points of certain point were met
Relation, these points are exactly the circle for needing detection in image space.
Every two field picture after for rim detection in step 3 detects the principle of circle using Hough transform, by arranging and figure
As the size threshold value of the related dial plate circle of pixel, circle and the center of circle of the circle at the circular dial plate place of our needs can be found
Coordinate.If the circle of our needs is can not find in this step, then the next frame return to step 2 for intercepting video image is circulated
Process.
Step 5：Dial plate region of interest regional partition.
After dial plate circle is detected in the 4th step, dial plate image is split, pluck out the outer of circular dial plate place
Rectangular area is connect, we are referred to as the area-of-interest of image.So when straight-line detection is subsequently carried out, effectively can filter not
Straight line in circular dial plate, it is also possible to effectively calculate the central coordinate of circle of circular dial plate, further increases detection and calculates
Efficiency.
Step 6：Image rectification.
Due to the impact of the factors such as shooting angle, the dial plate in video image is often inclined, therefore is carrying out image
After the extraction of area-of-interest, need to be corrected the inclination dial plate in image, be the angle for accurately calculating cursor line below
Degree lays the foundation.
The inventive method is that, for circular dial plate, and circular dial plate does not have the clear and definite characteristic point as rectangle dial plate.
Therefore the present invention obtains the angle of inclination of dial plate by the way of tilted character on the circular dial plate of correction, inclines so as to reach correction
The purpose of oblique dial plate.Some inclined characters on dial plate are plucked out by using rotation rectangle, the calculating at angle of inclination is carried out respectively,
Weighed again, so as to draw the anglec of rotation.
Step 7：The straight line that Hough transform detection pointer is located.
Similar with Hough transform detection circle in step 4, the principle of Hough detection of straight lines is also with image space and ginseng
The duality of number space.Difference is the equation that the equation of circle now is changed into straight line：Y=kx+b, by the image from figure
Image space is mapped to k, parameter spaces of the b for parameter, and then is obtained in parameter space in image space using statistical law
For the point of straight line, to obtain corresponding straight line in image space.
Obtained after straight line using this principle, be similarly obtained the corresponding coordinate of two end points of straight line.Using pointer institute
Straight line to the distance in the center of circle, filter out real cursor line.Further, since the pointer of some pointer instruments is thicker,
When Hough straight-line detection cursor lines are carried out, a plurality of cursor line is often detected.The present invention has been done clearly for this case
Judgement, discuss the processing method that the pointer number of lines for detecting is 0,1,2,3 and the above respectively.If at this
Corresponding straight line is can not find in one step, then the next frame return to step 2 for intercepting video image is circulated process.
Step 8：Cursor line angle calculation.
Straight line is found by Hough transform in step 7, and real cursor line is filtered out by threshold method, and
And the pointer number of lines detected by point situation discussion, an accurately real cursor line is finally determined, obtains true
The extreme coordinates at cursor line line segment two ends.According to the transverse and longitudinal coordinate of two end points of line segment, using slope-intercept form of an equation y of straight line1-y2
=k (x1-x2) obtain straight line slope k value, and then calculate the inswept angle in range region of pointer.
Step 9：Recognition of Reading.
The slope k of the straight line being located according to the cursor line obtained in step 8, minimum scale is vmin, maximum scale is vmax,
The parameters such as the angle a between the scale and minimum scale of cursor line indication, the angle, θ that pointer is inswept, using formula
V=vmin+(vmax-vmin)×(a÷θ) (6)
Calculate the reading v of current pointer formula instrument.
In addition, Fig. 2 is the design flow diagram of many dial plate processing sequences, mainly including the content of following several respects：
Step 1：Detect the circle of defined amount.
Step 2：Dial plate is stored in order.
Step 3：Each dial plate is processed respectively.
Fig. 3 is the design flow diagram of the rotation correction for inclining dial plate, mainly including the content of following several respects：
Step 1：Pluck out dial plate area-of-interest.
Step 2：Pluck out the character of area-of-interest.
Step 3：Character rotation correction.
Step 4：Obtain the character anglec of rotation.
Step 5：The circular dial plate of correction.
Fig. 4 is the flow chart that Hough detects hand of dial line, mainly including the content of following several respects：
Step 1：Pluck out dial plate area-of-interest.
Step 2：Hough transform detection of straight lines.
Step 3：Screening cursor line.
Step 4：Find true pointer line.
Step 5：Calculate cursor line angle.
Flow charts of the Fig. 5 for cursor line angle calculation, mainly including the content of following several respects：
Step 1：The calculating of cursor line angle.
Step 2：If detecting 1, directly as cursor line；If detecting 2, intersection point and the company in the center of circle
Line is used as cursor line.
Step 3：Calculate line segment slope.
Step 4：Angle is calculated using slope.
Embodiment
The present embodiment with the circular pointer pressure in northern certain thermal power plant as identification object, circular pointer instrument
It is the important measuring instrument of power plant.Elaborating by the present embodiment, further illustrates the implementation process of the present invention.
The embodiment of the present invention is as follows to the implementation steps of the automatic interpretation of certain power plant's pointer-type round pressure table：
Step 1：The video capture of pointer round pressure table is carried out using the camera function in handheld device or flat board, just
During the beginning, the several relevant parameters of instrument board are configured first：Least count, full-scale reading, the angle without range etc..Needing to three
When individual dial plate is detected simultaneously, can increase by two parameter configuration lists carries out the information configuration of pointer round pressure table.Such as Fig. 6
Show a certain two field picture of the three pressure gauge dial plate video images for photographing, be from left to right followed successively by pressure gauge 1, pressure gauge 2,
Pressure gauge 3.
Step 2：Each frame of the pointer round meter disk image to shooting in step 1 is processed.First, carry out every
The filtering and noise reduction operation of two field picture.Because due to the impact of the factors such as illumination, environment temperature, each two field picture for photographing is often
It is not apparent from, the denoising operation of every two field picture is carried out by the filtering algorithm for responding.
Then binary conversion treatment is carried out to filtered image.As usual each color image frame is all three-channel
RGB image, and the detection for image is all based on what pixel was carried out with processing, and is so calculating three-channel coloured image
During the computing of vegetarian refreshments, can serious elapsed time and space.If carrying out binaryzation to colored triple channel image, image is changed into single-pass
The binary map in road, so deals with just relatively time-consuming and space, therefore selects before processing, first every two field picture is carried out
Binaryzation.The binary picture of three dial plates obtained by being illustrated in figure 7 Fig. 6 after binary conversion treatment is carried out.Fig. 8 is YUV colors
Binary picture in space.
Step 3：Each two field picture after to binaryzation carries out rim detection, it is therefore an objective to prominent circle dial plate profile and pointer
Place straight line, is easy to follow-up Hough transform to detect the operation of circle and Hough transform detection of straight lines.
Step 4：By step 3, the dial plate circle contour in every two field picture is high-visible with pointer line profile.Utilize
The circle that Hough transform detection dial plate is located, the dial plate circle gone out in every two field picture by the radius size threshold test for arranging circle, such as
Shown in Fig. 9, the circle having been detected by is drawn with white circle.
Step 5：The dial plate circle of specified quantity detected by step 4, each instrument board is plucked out with rotation rectangle and is located
Boundary rectangle, this boundary rectangle with circular dial plate is referred to as the area-of-interest of dial plate.According to each round meter disk
The abscissa of central coordinate of circle order from small to large is ranked up, and processes each circular dial plate for plucking out respectively.
Step 6：Due to shooting reason, each instrument board may have an inclination, therefore in this step, need to plucking out
Round meter disk carries out rotation correction operation.The numerical character in area-of-interest is plucked out using rotation rectangle, by character
The rotation rectangle at place is corrected, and obtains the anglec of rotation of character.
Step 7：By step 6, the circular dial plate in the dial plate area-of-interest of gained is the instrument board after correction.To table
Disk area-of-interest carries out Hough straight-line detections, detects a number of cursor line, and white line as shown in Figure 9 is
Two cursor lines detected using Hough transform.
Step 8：By step 7, a number of cursor line is detected, point situation discussion：1. when detecting 1 pointer
During line, as true pointer line；2. the intersection point of this two straight lines when 2 cursor lines are detected, is obtained, intersection point and institute
The round center of circle line as real cursor line；3., when the cursor line of 3 and the above is detected, illustrate due to noise etc.
Disturbing factor fails and detects the straight line at pointer place, returns the process that next frame continues above step.
Step 9：The suitable cursor line detected by step 8, is calculated the slope of pointer straight line, and then passes through formula
(6) reading of now instrument board is calculated, following table is three manometric true plots in Fig. 6, identification reading, accuracy rate.
To pressure gauge true plot and the statistics of identification reading in above step and upper table, it is able to observe that：Should
The accuracy rate of the reading of the instrument board that inventive method can be calculated can reach more than 96%, meet in industrial production to pointer
The requirement of formula instrument board reading accuracy.
Although for illustrative purposes, it has been described that the illustrative embodiments of the present invention, those skilled in the art
Member will be understood that, in the case of the scope and spirit without departing from the invention disclosed in claims, can be in form and details
On carry out various modifications, addition and replace etc. change, and it is all these change should all belong to claims of the present invention
Protection domain, and each department of claimed product and each step in method, can be in any combination
Form is combined.Therefore, to disclosed in this invention embodiment description be not intended to limit the scope of the present invention,
But for describing the present invention.Correspondingly, the scope of the present invention is not limited by embodiment of above, but by claim or
Its equivalent is defined.
Claims (8)
1. the circular many instrument board real time readouts recognition methods of a kind of pointer-type, it is characterised in that in turn include the following steps：
Step 1：The image/video of the circular many instrument boards of pointer-type is obtained in real time using mobile device；
Step 2：The image/video of the pointer circular many instrument boards to obtaining carries out framing pretreatment；
Step 3：To carrying out, framing is pretreated to carry out rim detection per frame image data；
Step 4：Multiple circles that the circular dial plate of the circular many instrument boards of pointer-type is located are detected using Hough transform, if detection
To corresponding circle, then into next step, return to step 2 if it can't detect；
Step 5：Dial plate area-of-interest is split, the circumscribed rectangular region that each circular dial plate is located is partitioned into respectively；
Step 6：Inclination dial plate in the image of the circumscribed rectangular region being located to each circular dial plate respectively is corrected；
Step 7：The straight line that pointer is located in each circular dial plate is detected respectively using Hough transform, if detected corresponding
Straight line, then into next step, return to step 2 if it can't detect；
Step 8：Two extreme coordinates according to the corresponding straight line for detecting, obtain right using the slope-intercept form of an equation of straight line respectively
The value of the slope k of the straight line at cursor line place is answered, the inswept angle, θ in range region of correspondence pointer is calculated；
Step 9：The slope k of the straight line being located according to correspondence cursor line, minimum scale is vmin, maximum scale is vmax, cursor line
Angle a between the scale and minimum scale of indication, the angle, θ that pointer is inswept, reading to be solved is v, using formula：
V=vmin+(vmax-vmin)×(a÷θ)
Calculate corresponding reading in the circular many instrument boards of current correspondence pointer-type.
2. the method for claim 1, it is characterised in that：Framing described in step 2 pretreatment be to each two field picture according to
It is secondary to be filtered denoising, binary conversion treatment, edge detection process, Morphological scale-space process, image thinning process and image
Enhancing is processed.
3. method as claimed in claim 1 or 2, it is characterised in that：It is pretreated per frame to carrying out framing described in step 3
It is to carry out canny rim detections that view data carries out rim detection, is specifically included：
3.1. the convolution of image and Gaussian filter, wherein S [i, j] is asked to obtain convolution value, G [i, j for required；σ] for height
This smoothing filter, I [i, j] are image slices vegetarian refreshments：
S [i, j]=G [i, j；σ]*I[i,j]
3.2. be divided to two matrixes of calculating partial derivative using first difference, wherein S [i, j] is the convolution tried to achieve in step 3.1
Value, P [i, j] and Q [i, j] is two calculative partial derivative matrixs respectively：
P[i,j]≈(S[i,j+1]-S[i,j]+S[i+1,j+1]-S[i+1,j])÷2
Q[i,j]≈(S[i,j]-S[i+1,j]+S[i,j+1]-S[i+1,j+1])÷2
3.3. amplitude and azimuth are asked, wherein M [i, j] is gradient magnitude, and θ [i, j] is required gradient direction：
θ [i, j]=arctan (Q [i, j] ÷ P [i, j])
3.4. the data to obtaining after step 3.3 process carry out non-maxima suppression process；
3.5. threshold value is taken, all values that will be less than threshold value assign zero, obtain the edge array of image.
4. the method as described in claim 1-3, it is characterised in that：Step 4 is included to pretreated per two field picture in step 2
Justified using Hough transform detection, by the size threshold value for arranging the dial plate circle related to image pixel, find circular dial plate and be located
Circle and the circle central coordinate of circle.
5. the method as described in claim 1-4, it is characterised in that：Obtained by the way of tilted character on the circular dial plate of correction
Take the angle of inclination of dial plate.
6. method as claimed in claim 5, it is characterised in that：The angle of inclination for obtaining dial plate is by using spin moment
Shape region plucks out the inclined character in part on dial plate, carries out the calculating at angle of inclination respectively, then carry out balance drawing the anglec of rotation.
7. the method for claim 1, it is characterised in that：Step 7 is specially for what each circular dial plate was located is external
When the cursor line of 0 or 3 and the above is detected in the image of rectangular area, illustrate that correspondence is not fully found cursor line letter
Breath, comes back for next frame process, when 1 or 2 cursor lines is detected, illustrates that correspondence have found cursor line, carries out phase
Algorithm is answered to calculate real cursor line and cursor line angle.
8. method as claimed in claim 7, it is characterised in that：The image of the circumscribed rectangular region is located by each circular dial plate
Straight-line detection is carried out, if correspondence detects 2 cursor lines, the intersection point of two straight lines is obtained, intersection point and the line in the center of circle
The line segment for being formed is used as real cursor line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611258521.2A CN106529559A (en) | 2016-12-30 | 2016-12-30 | Pointer-type circular multi-dashboard real-time reading identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611258521.2A CN106529559A (en) | 2016-12-30 | 2016-12-30 | Pointer-type circular multi-dashboard real-time reading identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106529559A true CN106529559A (en) | 2017-03-22 |
Family
ID=58336303
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611258521.2A Pending CN106529559A (en) | 2016-12-30 | 2016-12-30 | Pointer-type circular multi-dashboard real-time reading identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106529559A (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107092863A (en) * | 2017-03-24 | 2017-08-25 | 重庆邮电大学 | A kind of readings of pointer type meters recognition methods of Intelligent Mobile Robot |
| CN107292310A (en) * | 2017-06-19 | 2017-10-24 | 电子科技大学 | A kind of circular pointer dial plate vision positioning and automatic reading method |
| CN107292871A (en) * | 2017-06-08 | 2017-10-24 | 国网青海省电力公司检修公司 | A kind of real-time correction algorithm of transformer station's round meter |
| CN107301412A (en) * | 2017-05-08 | 2017-10-27 | 浙江工业大学 | A kind of readings of pointer type meters method based on image procossing |
| CN107358237A (en) * | 2017-07-21 | 2017-11-17 | 东南大学 | A kind of more instrument board automatic reading methods for going environmental disturbances |
| CN108256524A (en) * | 2018-01-24 | 2018-07-06 | 国家电网公司 | A kind of automatic reading method of multilist index formula instrument |
| CN108399416A (en) * | 2018-01-19 | 2018-08-14 | 武汉科技大学 | A kind of substation's pointer instrument automatic identifying method having circular arc boundary |
| CN109190473A (en) * | 2018-07-29 | 2019-01-11 | 国网上海市电力公司 | The application of a kind of " machine vision understanding " in remote monitoriong of electric power |
| CN109448053A (en) * | 2018-08-30 | 2019-03-08 | 南京理工大学 | A kind of method of the instrument board and reading numerical values of video reading |
| CN109632055A (en) * | 2019-01-16 | 2019-04-16 | 杭州丹纳计量科技有限公司 | A kind of mechanical water meter dynamic vision measurement method based on intelligent terminal |
| CN110135420A (en) * | 2019-05-16 | 2019-08-16 | 北京灵汐科技有限公司 | Dial plate state identification method and device, readable storage medium storing program for executing and electronic equipment |
| CN110363202A (en) * | 2019-07-23 | 2019-10-22 | 深圳中科捷飞科技有限公司 | Pointer instrument numerical value read method and terminal |
| CN110633679A (en) * | 2019-09-19 | 2019-12-31 | 湘潭大学 | Automatic pointer instrument indicating identification method and system based on genetic algorithm |
| CN111199229A (en) * | 2019-12-30 | 2020-05-26 | 中国广核电力股份有限公司 | Reading identification method and device for instrument panel |
| CN111582187A (en) * | 2020-05-11 | 2020-08-25 | 昆明能讯科技有限责任公司 | Automatic meter reading method based on mixed Gaussian background modeling |
| CN111618873A (en) * | 2020-05-29 | 2020-09-04 | 杭州申昊科技股份有限公司 | Explosion-proof inspection robot with instrument identification function and identification method thereof |
| CN111868740A (en) * | 2018-03-23 | 2020-10-30 | 株式会社东芝 | Reading system, reading method and storage medium |
| CN111950330A (en) * | 2019-05-16 | 2020-11-17 | 杭州测质成科技有限公司 | Pointer instrument indicating number detection method based on target detection |
| CN113792616A (en) * | 2021-08-26 | 2021-12-14 | 南方电网深圳数字电网研究院有限公司 | Remote meter reading system based on edge calculation and working method thereof |
| CN113792727A (en) * | 2021-07-30 | 2021-12-14 | 华能大理风力发电有限公司 | Reading estimation method, device and system based on pointer instrument video image |
| CN114037993A (en) * | 2021-09-26 | 2022-02-11 | 佛山中科云图智能科技有限公司 | Substation pointer instrument reading method and device, storage medium and electronic equipment |
| CN114549835A (en) * | 2022-02-15 | 2022-05-27 | 中国人民解放军海军工程大学 | Pointer instrument correction identification method and device based on deep learning |
| CN114663680A (en) * | 2022-05-25 | 2022-06-24 | 天津大学四川创新研究院 | System and method for recognizing temperature and humidity meter readings |
| CN114782852A (en) * | 2022-06-16 | 2022-07-22 | 深圳中集智能科技有限公司 | Reading method, reading device and reading system of pointer type industrial instrument |
| US20220284690A1 (en) * | 2018-03-23 | 2022-09-08 | Kabushiki Kaisha Toshiba | Reading system, reading method, and storage medium |
| 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 |
| US11928812B2 (en) | 2021-09-03 | 2024-03-12 | Caterpillar Inc. | Systems and methods for inspecting multi-mode asset status in communication-denied environments |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101660932A (en) * | 2009-06-15 | 2010-03-03 | 浙江大学 | Automatic calibration method of pointer type automobile meter |
| CN102722166A (en) * | 2012-06-29 | 2012-10-10 | 山东电力集团公司电力科学研究院 | Intelligent vision detection system and state detection method of transformer substation device |
| CN103020627A (en) * | 2012-11-14 | 2013-04-03 | 中国人民解放军63963部队 | Extraction method for gauge pointer of special vehicle |
| CN103927507A (en) * | 2013-01-12 | 2014-07-16 | 山东鲁能智能技术有限公司 | Improved multi-instrument reading identification method of transformer station inspection robot |
| CN103984930A (en) * | 2014-05-21 | 2014-08-13 | 南京航空航天大学 | Digital meter recognition system and method based on vision |
| CN106127205A (en) * | 2016-06-22 | 2016-11-16 | 山东鲁能智能技术有限公司 | A kind of recognition methods of the digital instrument image being applicable to indoor track machine people |
| CN106228170A (en) * | 2016-09-20 | 2016-12-14 | 山东省计量科学研究院 | A kind of pointer position extracting method of pointer instrument |
-
2016
- 2016-12-30 CN CN201611258521.2A patent/CN106529559A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101660932A (en) * | 2009-06-15 | 2010-03-03 | 浙江大学 | Automatic calibration method of pointer type automobile meter |
| CN102722166A (en) * | 2012-06-29 | 2012-10-10 | 山东电力集团公司电力科学研究院 | Intelligent vision detection system and state detection method of transformer substation device |
| CN103020627A (en) * | 2012-11-14 | 2013-04-03 | 中国人民解放军63963部队 | Extraction method for gauge pointer of special vehicle |
| CN103927507A (en) * | 2013-01-12 | 2014-07-16 | 山东鲁能智能技术有限公司 | Improved multi-instrument reading identification method of transformer station inspection robot |
| CN103984930A (en) * | 2014-05-21 | 2014-08-13 | 南京航空航天大学 | Digital meter recognition system and method based on vision |
| CN106127205A (en) * | 2016-06-22 | 2016-11-16 | 山东鲁能智能技术有限公司 | A kind of recognition methods of the digital instrument image being applicable to indoor track machine people |
| CN106228170A (en) * | 2016-09-20 | 2016-12-14 | 山东省计量科学研究院 | A kind of pointer position extracting method of pointer instrument |
Non-Patent Citations (4)
| Title |
|---|
| 侯宏花: "《数字图像处理与分析》", 30 September 2011 * |
| 肖世德等: "《高等机械CAD/CAM》", 31 January 2015, 西南交通大学出版社 * |
| 邱金红等: "一种圆形指针式仪表倾斜检测方法", 《自动化与信息工程》 * |
| 陶冰洁等: "一种实用的指针式仪表读数识别方法", 《光电工程》 * |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107092863A (en) * | 2017-03-24 | 2017-08-25 | 重庆邮电大学 | A kind of readings of pointer type meters recognition methods of Intelligent Mobile Robot |
| CN107301412A (en) * | 2017-05-08 | 2017-10-27 | 浙江工业大学 | A kind of readings of pointer type meters method based on image procossing |
| CN107301412B (en) * | 2017-05-08 | 2019-12-17 | 浙江工业大学 | Pointer instrument reading method based on image processing |
| CN107292871A (en) * | 2017-06-08 | 2017-10-24 | 国网青海省电力公司检修公司 | A kind of real-time correction algorithm of transformer station's round meter |
| CN107292310A (en) * | 2017-06-19 | 2017-10-24 | 电子科技大学 | A kind of circular pointer dial plate vision positioning and automatic reading method |
| CN107358237A (en) * | 2017-07-21 | 2017-11-17 | 东南大学 | A kind of more instrument board automatic reading methods for going environmental disturbances |
| CN108399416A (en) * | 2018-01-19 | 2018-08-14 | 武汉科技大学 | A kind of substation's pointer instrument automatic identifying method having circular arc boundary |
| CN108256524B (en) * | 2018-01-24 | 2021-12-17 | 国家电网公司 | Automatic reading method of multi-dial pointer instrument |
| CN108256524A (en) * | 2018-01-24 | 2018-07-06 | 国家电网公司 | A kind of automatic reading method of multilist index formula instrument |
| CN111868740B (en) * | 2018-03-23 | 2024-07-26 | 株式会社东芝 | Reading system, reading method and storage medium |
| US12080037B2 (en) * | 2018-03-23 | 2024-09-03 | Kabushiki Kaisha Toshiba | Reading system, reading method, and storage medium |
| US20220284690A1 (en) * | 2018-03-23 | 2022-09-08 | Kabushiki Kaisha Toshiba | Reading system, reading method, and storage medium |
| CN111868740A (en) * | 2018-03-23 | 2020-10-30 | 株式会社东芝 | Reading system, reading method and storage medium |
| CN109190473A (en) * | 2018-07-29 | 2019-01-11 | 国网上海市电力公司 | The application of a kind of " machine vision understanding " in remote monitoriong of electric power |
| CN109448053A (en) * | 2018-08-30 | 2019-03-08 | 南京理工大学 | A kind of method of the instrument board and reading numerical values of video reading |
| CN109632055A (en) * | 2019-01-16 | 2019-04-16 | 杭州丹纳计量科技有限公司 | A kind of mechanical water meter dynamic vision measurement method based on intelligent terminal |
| CN111950330A (en) * | 2019-05-16 | 2020-11-17 | 杭州测质成科技有限公司 | Pointer instrument indicating number detection method based on target detection |
| CN111950330B (en) * | 2019-05-16 | 2023-09-29 | 杭州测质成科技有限公司 | Pointer instrument indication detection method based on target detection |
| CN110135420A (en) * | 2019-05-16 | 2019-08-16 | 北京灵汐科技有限公司 | Dial plate state identification method and device, readable storage medium storing program for executing and electronic equipment |
| CN110363202A (en) * | 2019-07-23 | 2019-10-22 | 深圳中科捷飞科技有限公司 | Pointer instrument numerical value read method and terminal |
| CN110633679A (en) * | 2019-09-19 | 2019-12-31 | 湘潭大学 | Automatic pointer instrument indicating identification method and system based on genetic algorithm |
| CN110633679B (en) * | 2019-09-19 | 2022-04-08 | 湘潭大学 | Automatic pointer instrument indicating identification method and system based on genetic algorithm |
| CN111199229A (en) * | 2019-12-30 | 2020-05-26 | 中国广核电力股份有限公司 | Reading identification method and device for instrument panel |
| CN111582187A (en) * | 2020-05-11 | 2020-08-25 | 昆明能讯科技有限责任公司 | Automatic meter reading method based on mixed Gaussian background modeling |
| CN111618873A (en) * | 2020-05-29 | 2020-09-04 | 杭州申昊科技股份有限公司 | Explosion-proof inspection robot with instrument identification function and identification method thereof |
| CN113792727A (en) * | 2021-07-30 | 2021-12-14 | 华能大理风力发电有限公司 | Reading estimation method, device and system based on pointer instrument video image |
| CN113792616A (en) * | 2021-08-26 | 2021-12-14 | 南方电网深圳数字电网研究院有限公司 | Remote meter reading system based on edge calculation and working method thereof |
| US11928812B2 (en) | 2021-09-03 | 2024-03-12 | Caterpillar Inc. | Systems and methods for inspecting multi-mode asset status in communication-denied environments |
| CN114037993A (en) * | 2021-09-26 | 2022-02-11 | 佛山中科云图智能科技有限公司 | Substation pointer instrument reading method and device, storage medium and electronic equipment |
| CN114549835A (en) * | 2022-02-15 | 2022-05-27 | 中国人民解放军海军工程大学 | Pointer instrument correction identification method and device based on deep learning |
| CN114549835B (en) * | 2022-02-15 | 2023-01-24 | 中国人民解放军海军工程大学 | Pointer instrument correction identification method and device based on deep learning |
| CN114663680A (en) * | 2022-05-25 | 2022-06-24 | 天津大学四川创新研究院 | System and method for recognizing temperature and humidity meter readings |
| CN114782852A (en) * | 2022-06-16 | 2022-07-22 | 深圳中集智能科技有限公司 | Reading method, reading device and reading system of pointer type industrial instrument |
| CN114782852B (en) * | 2022-06-16 | 2023-04-25 | 深圳中集智能科技有限公司 | Pointer type industrial instrument reading method, reading device and reading system |
| CN115655576B (en) * | 2022-12-13 | 2023-03-10 | 成都千嘉科技股份有限公司 | Automatic sensing method for displacement abnormity of pointer type pressure gauge |
| 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 |
|---|---|---|
| CN106529559A (en) | Pointer-type circular multi-dashboard real-time reading identification method | |
| CN107066998A (en) | A kind of pointer-type circular single instrument board real-time identification method of utilization mobile device | |
| CN112818988B (en) | Automatic identification reading method and system for pointer instrument | |
| CN102176228B (en) | Machine vision method for identifying dial plate information of multi-pointer instrument | |
| CN103164692B (en) | A kind of special vehicle instrument automatic identification system based on computer vision and method | |
| CN103207987B (en) | A kind of registration recognition methods of pointer instrument | |
| CN103034838B (en) | A kind of special vehicle instrument type identification based on characteristics of image and scaling method | |
| CN106909941A (en) | Multilist character recognition system and method based on machine vision | |
| CN108921163A (en) | A kind of packaging coding detection method based on deep learning | |
| CN112257676A (en) | Pointer instrument reading method and system and inspection robot | |
| CN112149667A (en) | Method for automatically reading pointer type instrument based on deep learning | |
| CN107153848A (en) | Instrument image automatic identifying method based on OpenCV | |
| CN108564092A (en) | Sunflower disease recognition method based on SIFT feature extraction algorithm | |
| CN105740829A (en) | Scanning line processing based automatic reading method for pointer instrument | |
| CN108764134A (en) | A kind of automatic positioning of polymorphic type instrument and recognition methods suitable for crusing robot | |
| CN110533654A (en) | The method for detecting abnormality and device of components | |
| CN108257124A (en) | A kind of white blood cell count(WBC) method and system based on image | |
| CN112699824B (en) | Method and device for detecting constant of electric energy meter and storage medium | |
| CN110197113A (en) | A kind of method for detecting human face of high-precision anchor point matching strategy | |
| Khamael et al. | Using adapted JSEG algorithm with fuzzy C mean for segmentation and counting of white blood cell and nucleus images | |
| CN115019294A (en) | Pointer instrument reading identification method and system | |
| CN114898347A (en) | Machine vision identification method for pointer instrument | |
| CN110059573A (en) | Wild ginseng based on image recognition is classified calibration method | |
| CN111507177B (en) | Identification method and device for metering turnover cabinet | |
| Yi et al. | A clustering-based algorithm for automatic detection of automobile dashboard |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170322 |
|
| RJ01 | Rejection of invention patent application after publication |