CN109146806A - Gauge pointer position detection recognition methods based on shadow removing optimization in remote monitoriong of electric power - Google Patents
Gauge pointer position detection recognition methods based on shadow removing optimization in remote monitoriong of electric power Download PDFInfo
- Publication number
- CN109146806A CN109146806A CN201810851011.9A CN201810851011A CN109146806A CN 109146806 A CN109146806 A CN 109146806A CN 201810851011 A CN201810851011 A CN 201810851011A CN 109146806 A CN109146806 A CN 109146806A
- Authority
- CN
- China
- Prior art keywords
- pointer
- image
- carried out
- position detection
- electric power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000001514 detection method Methods 0.000 title claims abstract description 16
- 238000005457 optimization Methods 0.000 title claims abstract description 14
- 230000009466 transformation Effects 0.000 claims abstract description 31
- 230000000694 effects Effects 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 12
- 230000000877 morphologic effect Effects 0.000 claims abstract description 9
- 238000012216 screening Methods 0.000 claims abstract description 5
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 230000001131 transforming effect Effects 0.000 claims description 4
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 230000006870 function Effects 0.000 description 13
- 230000007797 corrosion Effects 0.000 description 4
- 238000005260 corrosion Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 241000566145 Otus Species 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000002902 bimodal effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004040 coloring Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
A kind of gauge pointer position detection recognition methods based on shadow removing optimization in remote monitoriong of electric power, belongs to field of data recognition.It carries out gray processing, denoising to image, greyscale transformation is carried out to image using greyscale transformation function, binaryzation is carried out using big law, burr is handled using opening operation, Morphological scale-space pointer edge is carried out, Hough transform is carried out, straight line where finally screening pointer edge, according to pointer straight incline angle, pointer degree is calculated.Its contrast that pointer and shade are stretched using greyscale transformation is carried out binaryzation using big law, the burr at pointer edge is finally filtered out using opening operation, achievees the effect that shadow removing.There is preferable performance under different shade degree, can more accurately find pointer edge, calculate total indicator reading and there is certain real-time.It can be widely applied to the remote collection of various transformer and distribution power station operating statuses, automatically analyze and the fields such as operational management.
Description
Technical field
The invention belongs to field of data recognition more particularly to a kind of for special object during remote monitoriong of electric power
Image recognition.
Background technique
Based on the considerations of reduce operating cost and save floor occupying area etc., with unattended operation transformer station (referred to as electricity
Power station, similarly hereinafter) be used more and more, various video monitoring systems are widely applied.
Since video monitoring can generate a large amount of live video or photograph image, then image processing, interpret or according to institute
Diagram piece is identified, is judged, is had become in the operation monitoring work of electric system necessary.
" visual analysis " technology is a kind of intelligence system, can by vision system (video camera) to locating environment into
The autonomous intellectualized technology observed and analyze of row is an important directions of artificial intelligence technology and machine vision technique development,
Substation inspection, remote centralized control, video image big data analysis and in terms of with boundless application before
Scape.
Pointer instrument is as measuring instrument most important in electric system, and there is no data-interfaces, can only be artificial
The drawbacks of reading reading.
For unmanned inspection, the unmanned operation for realizing electric power station, need to realize intelligence " the vision reason to pointer instrument
Solution ".
Since electric power station is not turned on light at the moment at nobody, single light source can only be carried by robotic arm, therefore shade becomes in electricity
Realize that the maximum of the identification to pointer hinders in power station.
For the research of shadow removing method, Wang Xiangyu et al. is " in conjunction with image area information in hsv color space
It is proposed first in target shadow removing method " (" computer engineering and application ", 2015:359-360-361-362-363.) text
It is converted using HSV space and determines shadow region, in conjunction with the area information elimination shadow region from outside to inside of image；Old tin
Et al. in " the shadow removing algorithm that bright spot, color and gradient combine " (Electronic Industry Press, 2010:556-557-558-
A kind of shadow removing for combining using bright spot, color and gradient and judging whether to cast shadow suppressing is proposed in 559-560-561.)
Algorithm；A kind of shadow removing method based on RGBY has been invented in eight-legged essay east et al., can accurately eliminate object in all cases
Shadow (referring to CN105869121A " a kind of shadow removing method based on RGBY ")；King Wenxiang is of heap of stone et al. " one kind is based on YUV
It is proposed in the adaptive shadow removing algorithm of color space " (micro computer and application, 2016, (7)) " a kind of new based on YUV
The adaptive shadow removing algorithm of color space has preferable adaptivity, but needs acquisition background image in advance.
Above-mentioned technical proposal in actual application discovery there are certain deficiency, cannot adapt to completely based on " depending on
The requirement of the remote monitoriong of electric power system of feel understanding " method building.
Summary of the invention
Technical problem to be solved by the invention is to provide a kind of in remote monitoriong of electric power based on shadow removing optimization
Gauge pointer position detection recognition methods.Its contrast that pointer and shade are stretched using greyscale transformation, is carried out using big law
Binaryzation is finally filtered out the burr at pointer edge using opening operation, achievees the effect that shadow removing.In different shade degree
Under have preferable performance, can more accurately find pointer edge, calculate total indicator reading and have certain real-time.
The technical scheme is that provide it is a kind of in remote monitoriong of electric power based on shadow removing optimization instrument refer to
Pin position detection recognition method, the image including obtaining power control cabinet or instrument board by video monitoring system or video camera；It is special
Sign is:
1) first against the instrument of every a kind of or each model, the tilt angle and instrument degree of a pointer are constructed
Mapping table or correspondence database；
2) gray processing, denoising are carried out to image；
3) greyscale transformation is carried out to image using greyscale transformation function, draws high contrast；
4) binaryzation is carried out using big law；
5) burr is handled using opening operation, has the function that eliminate shade；
6) Morphological scale-space pointer edge is carried out；
7) Hough transform is carried out；
8) straight line where screening pointer edge；
9) according to pointer straight incline angle, pointer degree is calculated；
10) by the mapping table of the pointer tilt angle and instrument degree that obtain, the degree of pointer meters is obtained.
Further, the gauge pointer position detection recognition methods, is improved using adaptive threshold binarization
The effect of shadow removing improves the accuracy of identification of gauge pointer position.
Specifically, the greyscale transformation is realized using following formula:
S=T (r), A≤r, s≤A+L
Wherein, the gray scale interval of image is [A, A+L], and variable r represents the gray level of original image, and variable behalf stretched
The gray level of later image.
Further, the form of the transforming function transformation function of the greyscale transformation is as follows:
Wherein 0 < a, b < 1, takes a=0.2, b=0.4.
Specifically, when carrying out the binaryzation of described image, it is assumed that the gray level image of a width M*N size has L difference
Gray level, niIndicate the number of the pixel of i-th of gray level, n is total pixel number, i.e.,
N=M*N=n0+n1+…+nL-1
When threshold value is t, the number of the pixel in C1 and C2 accounts for overall percentage and is respectively as follows:
At this point, the average gray value of C1 and C2 class is respectively as follows:
Then, the overall average gray value of image are as follows:
U=w1u1+w2u2
Then, calculating inter-class variance is carried out with different t in L gray level, formula is as follows:
σ2(t)=w1(u1-u)2+w2(u2-u)2=w1w2(u1-u2)2
The corresponding t value of maximum inter-class variance is exactly optimal threshold.
Specifically, the Morphological scale-space pointer edge is carried out as follows:
If E (x, y) and D (x, y) are that structural element B (x, y) corrodes and expands to the image f (x, y) of m*n size respectively
As a result；
Specifically, described screened by the slope of straight line and the position of straight line, select straight where pointer edge
Line.
In the image that the technical program obtains after the Hough transform, by the position of the slope of straight line and straight line into
Row screening, selects the straight line where pointer edge.
Compared with the prior art, the invention has the advantages that
1, the technical program stretches the contrast of pointer and shade using greyscale transformation, carries out binaryzation using big law,
The burr that pointer edge is finally filtered out using opening operation, achievees the effect that shadow removing；
2, this algorithm has preferable performance under different shade degree, can more accurately find pointer edge, calculate
Total indicator reading and have certain real-time.
Detailed description of the invention
Fig. 1 is process flow block diagram of the invention；
Fig. 2 is the effect picture carried out after gray processing and gaussian filtering to Instrument image；
Fig. 3 is the histogram of gradients of Fig. 2；
Fig. 4 is greyscale transformation function curve diagram；
Fig. 5 is the greyscale transformation effect picture using the technical program；
Fig. 6 is the grey level histogram of Fig. 5；
Fig. 7 is big law binary picture of the Instrument image without greyscale transformation；
Fig. 8 is the big law binary picture through greyscale transformation；
Fig. 9 is Canny edge detection graph；
Figure 10 is Hough transform figure.
Wherein, 1 be pointer first edge, 2 be pointer second edge.
Specific embodiment
The present invention will be further described with reference to the accompanying drawing.
In Fig. 1, technical solution of the present invention provides a kind of instrument based on shadow removing optimization in remote monitoriong of electric power
List index position detection recognition methods, the image including obtaining power control cabinet or instrument board by video monitoring system or video camera；
Its inventive point is:
1) first against the instrument of every a kind of or each model, the tilt angle and instrument degree of a pointer are constructed
Mapping table or correspondence database；
2) image of instrument board is obtained；
3) gray processing, denoising are carried out to image；
4) greyscale transformation is carried out to image using greyscale transformation function, draws high contrast；
5) binaryzation is carried out using big law；
6) burr is handled using opening operation, has the function that eliminate shade；
7) Morphological scale-space pointer edge is carried out；
8) Hough transform is carried out；
9) straight line where screening pointer edge；
10) according to pointer straight incline angle, pointer degree is calculated；
11) by the mapping table of the pointer tilt angle and instrument degree that obtain, the degree of pointer meters is obtained.
For the technical program, it is specifically described as follows:
1, greyscale transformation:
The image of camera acquisition is usually 24 true color, and RGB accounts for 8 respectively.
Since the colouring information of image is little for subsequent processing recognition reaction, to accelerate the speed calculated, by image
Carry out gray processing processing.
In addition, image generally can all be denoised by the interference of noise using gaussian filtering, image shown in Fig. 2 is obtained.
As shown in Figure 2 it is found that the gray value of pointer and shade is very close, if directly will lead to can not be clear for binaryzation
Pointer is plucked out clearly, influences the identification of pointer.So must inhibit to shade, that is, stretch the contrast of image.
Histogram is the important feature of one kind of gray level image.It is demonstrated by the distribution feelings of 256 gray values in the picture
Condition.
From figure 3, it can be seen that the effect picture through gray processing and gaussian filtering is integrally darker, the component of grey level histogram
The middle lower curtate of gray level is concentrated on, and the pixel of middle part distribution is most.And our region of interest, that is, pointer gray value is concentrated
In the low side of gray level, so needing to carry out the purposive gray value for drawing high region of interest using greyscale transformation function, with this
To increase the contrast of pointer and shade.
Assuming that the gray scale interval of image is [A, A+L], variable r represents the gray level of original image, and variable behalf stretched
The gray level of later image, then greyscale transformation formula is answered are as follows:
S-T (r), A≤r, s≤A+L
Here, the main purpose of transformation exactly separates pointer and shade, therefore gray scale interval is divided into three subintervals point
It is not converted, has reached the maximized effect for increasing picture contrast.
The form of transforming function transformation function is as follows:
Wherein 0 < a, b < 1.Due to the difference very little of pointer and the gray value of shade, therefore a=0.2 is taken in the technical program, b
=0.4.
The curve graph of above-mentioned transforming function transformation function is as shown in Figure 4.
Fig. 5 is the image carried out after grey scale change using the function.It is apparent that the brightness of pointer is kept substantially
It is constant, and the brightness of shade significantly improves, contrast increases, and pointer is highlighted out.Meanwhile if after in conjunction with greyscale transformation
The histogram analysis of image, gray value have been concentrated in the both ends of former gray scale interval, threshold when binaryzation after being more convenient in this way
The selection of value.
2, image binaryzation:
Image binaryzation, which refers to, is set as 0 or 255 for the gray value of the pixel of gray level image by a certain threshold value, i.e., black
Color and white.
The feature that the bianry image that binaryzation is formed has data volume few, clear-cut, accounts in digital image processing field
There is critical role.The effect of binaryzation directly depends on the selection of threshold value.
Common threshold value calculation method has Two-peak method, p parametric method and maximum variance between clusters (also referred to as big law, Otus
Method).
As seen from Figure 6, it is separated by the image of greyscale transformation with foreground and background, it is on the one hand and not formed complete
It is bimodal, and peak valley is too wide, can not calculate suitable threshold value, on the other hand can not determine the percentage between prospect and background
Than so selection carries out the binary conversion treatment of image using big law in the technical program.
Big law is that the scholar for being named as Otus by one proposed in 1979, if main thought will be schemed according to threshold value t
Pixel as in is divided into two class of C1 and C2, can make have maximum inter-class variance between two classes, then it is assumed that the threshold value is most
Good global threshold.
It is now assumed that the gray level image of a width M*N size has L different gray levels, niIndicate the picture of i-th of gray level
The number of vegetarian refreshments, n are total pixel number, i.e.,
N=M*N=n0+n1+…+nL-1
When threshold value is t, the number of the pixel in C1 and C2 accounts for overall percentage and is respectively as follows:
At this point, the average gray value of C1 and C2 class is respectively as follows:
Then, the overall average gray value of image are as follows:
U=w1u1+w2u2
Calculating inter-class variance is carried out with different t in L gray level, formula is as follows:
σ2(t)=w1(u1-u)2+w2(u1-u)2=w1w2(u1-u2)2
The corresponding t value of maximum inter-class variance is exactly optimal threshold.
3, Morphological scale-space pointer edge:
So-called Morphological scale-space is namely based on a series of images processing of shape, expands (Dilation) and corrodes
It (Erosion) is two kinds of wherein most basic operations.
If E (x, y) and D (x, y) are that structural element B (x, y) corrodes and expands to the image f (x, y) of m*n size respectively
As a result.
Corrosion is mainly used for eliminating the boundary point of object, on the one hand can disconnect the tiny connection between two objects, separately
On the one hand isolated noise and burr that width is less than structural element can be filtered out.
On the contrary, the background dot around object is mainly merged into object by the effect of expansion, it is possible to for connecting
Two, apart from close object, are restored the connectivity of image.
Open and close operator is then the combinatorial operation of expansion and corrosion.Opening operation is first to corrode reflation, and closed operation is complete
In contrast.
Since the purpose in the technical program using Morphological scale-space is to eliminate the burr of image border, so selection is opened
Operation.The burr at edge is weakened first with corrosion and is eliminated, then will be restored the lines to attenuate by corrosion with expansion.
4, embodiment and analysis:
Due to will receive the influence of instrument frame, the straight line obtained after Hough transform may have frame wheel
It is wide.
It can be screened at this time by the slope of straight line and the position of straight line, select the straight line where pointer edge.
It can be obtained by Fig. 7 and Fig. 8 comparison, greyscale transformation has stretched the contrast of foreground and background really, and it is suitable to be also convenient for
The searching of binarization threshold.
Fig. 9 shows the image obtained after Canny edge detection.
The first edge 1 and second edge 2 of the pointer eventually found are shown in Figure 10, it can be clearly by pointer
It is separated with shade.
For the validity for verifying this method, pointer identification experiment has been carried out to the sample acquired from electric power station.
Experimental situation is Visual Studio 2013, OpenCV 2.4.13, Intel Core i5 2.60GHzCPU, 4G memory.
1 pointer recognition result table of table
Seen from table 1, this method can accurately read pointer registration to each sample, and reliability is higher and knows
Not relatively rapidly, there is certain accuracy and real-time.
Technical solution of the present invention, when realizing unmanned inspection for electric power station, shade hinders asking for readings of pointer type meters
Topic, for image obtained, the comparison of pointer and shade is stretched by using greyscale transformation after obtaining monitoring image
Degree, big law are carried out binaryzation, the burr at pointer edge are finally filtered out using opening operation, achievees the effect that shadow removing.
The technical program has preferable performance under different shade degree, can more accurately find pointer edge, calculates
Out total indicator reading and have certain real-time.
It the composite can be widely applied to the remote collection of various transformer and distribution power station operating statuses, automatically analyze and run pipe
The fields such as reason.
Claims (8)
1. a kind of gauge pointer position detection recognition methods based on shadow removing optimization in remote monitoriong of electric power, including pass through
Video monitoring system or video camera obtain the image of power control cabinet or instrument board；It is characterized in that:
1) first against the instrument of every a kind of or each model, the tilt angle pass corresponding with instrument degree of a pointer is constructed
It is table or correspondence database；
2) gray processing, denoising are carried out to image；
3) greyscale transformation is carried out to image using greyscale transformation function, draws high contrast；
4) binaryzation is carried out using big law；
5) burr is handled using opening operation, has the function that eliminate shade；
6) Morphological scale-space pointer edge is carried out；
7) Hough transform is carried out；
8) straight line where screening pointer edge；
9) according to pointer straight incline angle, pointer degree is calculated；
10) by the mapping table of the pointer tilt angle and instrument degree that obtain, the degree of pointer meters is obtained.
2. the gauge pointer position detection described in accordance with the claim 1 based on shadow removing optimization in remote monitoriong of electric power is known
Other method, it is characterized in that the gauge pointer position detection recognition methods, improves yin using adaptive threshold binarization
The effect that shadow is eliminated improves the accuracy of identification of gauge pointer position.
3. the gauge pointer position detection described in accordance with the claim 1 based on shadow removing optimization in remote monitoriong of electric power is known
Other method, it is characterized in that the greyscale transformation is realized using following formula:
S=T (r), A≤r, s≤A+L
Wherein, the gray scale interval of image is [A, A+L], and variable r represents the gray level of original image, after variable behalf stretched
Image gray level.
4. the gauge pointer position detection based on shadow removing optimization in remote monitoriong of electric power is known according to claim 4
Other method, it is characterized in that the form of the transforming function transformation function of the greyscale transformation is as follows:
Wherein 0 < a, b < 1 take a=0.2, b=0.4.
5. the gauge pointer position detection described in accordance with the claim 1 based on shadow removing optimization in remote monitoriong of electric power is known
Other method, it is characterized in that when carrying out the binaryzation of described image, it is assumed that the gray level image of a width M*N size has L difference
Gray level, niIndicate the number of the pixel of i-th of gray level, n is total pixel number, i.e.,
N=M*N=n0+n1+…nL-1
When threshold value is t, the number of the pixel in C1 and C2 accounts for overall percentage and is respectively as follows:
At this point, the average gray value of C1 and C2 class is respectively as follows:
Then, the overall average gray value of image are as follows:
U=w1u1+w2u2
Then, calculating inter-class variance is carried out with different t in L gray level, formula is as follows:
σ2(t)=w1(u1-u)2+w2(u2-u)2=w1w2(u1-u2)2
The corresponding t value of maximum inter-class variance is exactly optimal threshold.
6. the gauge pointer position detection described in accordance with the claim 1 based on shadow removing optimization in remote monitoriong of electric power is known
Other method, it is characterized in that the Morphological scale-space pointer edge is carried out as follows:
If R (x, y) and D (x, y) are the knot that structural element R (x, y) corrodes and expands to the image f (x, y) of m*n size respectively
Fruit；
7. the gauge pointer position detection described in accordance with the claim 1 based on shadow removing optimization in remote monitoriong of electric power is known
Other method is selected straight where pointer edge it is characterized in that described screened by the slope of straight line and the position of straight line
Line.
8. the gauge pointer position detection described in accordance with the claim 1 based on shadow removing optimization in remote monitoriong of electric power is known
Other method, it is characterized in that being sieved in the image obtained after the Hough transform by the slope of straight line and the position of straight line
Choosing, selects the straight line where pointer edge.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810851011.9A CN109146806A (en) | 2018-07-29 | 2018-07-29 | Gauge pointer position detection recognition methods based on shadow removing optimization in remote monitoriong of electric power |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810851011.9A CN109146806A (en) | 2018-07-29 | 2018-07-29 | Gauge pointer position detection recognition methods based on shadow removing optimization in remote monitoriong of electric power |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109146806A true CN109146806A (en) | 2019-01-04 |
Family
ID=64799272
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810851011.9A Pending CN109146806A (en) | 2018-07-29 | 2018-07-29 | Gauge pointer position detection recognition methods based on shadow removing optimization in remote monitoriong of electric power |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109146806A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114663434A (en) * | 2022-05-25 | 2022-06-24 | 国家海洋局北海海洋技术保障中心 | Shadow discrimination method of side-scan sonar image |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101620682A (en) * | 2008-06-30 | 2010-01-06 | 汉王科技股份有限公司 | Method and system for automatically identifying readings of pointer type meters |
| CN103759758A (en) * | 2014-01-26 | 2014-04-30 | 哈尔滨工业大学 | Method for detecting position of automobile meter needle based on mechanical angle and scale identification |
| CN103955907A (en) * | 2014-04-17 | 2014-07-30 | 国家电网公司 | Method for telemetering pointer type SF6 gas density meter |
| CN104615972A (en) * | 2013-11-05 | 2015-05-13 | 深圳中兴力维技术有限公司 | Intelligent indication method of pointer instrument and device thereof |
| CN105740829A (en) * | 2016-02-02 | 2016-07-06 | 暨南大学 | Scanning line processing based automatic reading method for pointer instrument |
| CN106570948A (en) * | 2016-11-01 | 2017-04-19 | 东南大学 | Transformer substation intelligent meter reading system provided with portable device |
| CN106951900A (en) * | 2017-04-13 | 2017-07-14 | 杭州申昊科技股份有限公司 | A kind of automatic identifying method of arrester meter reading |
| US9916538B2 (en) * | 2012-09-15 | 2018-03-13 | Z Advanced Computing, Inc. | Method and system for feature detection |
-
2018
- 2018-07-29 CN CN201810851011.9A patent/CN109146806A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101620682A (en) * | 2008-06-30 | 2010-01-06 | 汉王科技股份有限公司 | Method and system for automatically identifying readings of pointer type meters |
| US9916538B2 (en) * | 2012-09-15 | 2018-03-13 | Z Advanced Computing, Inc. | Method and system for feature detection |
| CN104615972A (en) * | 2013-11-05 | 2015-05-13 | 深圳中兴力维技术有限公司 | Intelligent indication method of pointer instrument and device thereof |
| CN103759758A (en) * | 2014-01-26 | 2014-04-30 | 哈尔滨工业大学 | Method for detecting position of automobile meter needle based on mechanical angle and scale identification |
| CN103955907A (en) * | 2014-04-17 | 2014-07-30 | 国家电网公司 | Method for telemetering pointer type SF6 gas density meter |
| CN105740829A (en) * | 2016-02-02 | 2016-07-06 | 暨南大学 | Scanning line processing based automatic reading method for pointer instrument |
| CN106570948A (en) * | 2016-11-01 | 2017-04-19 | 东南大学 | Transformer substation intelligent meter reading system provided with portable device |
| CN106951900A (en) * | 2017-04-13 | 2017-07-14 | 杭州申昊科技股份有限公司 | A kind of automatic identifying method of arrester meter reading |
Non-Patent Citations (3)
| Title |
|---|
| WENBIN ZHENG 等: "Development of an automatic reading method and software for pointer instruments", 《2017 FIRST INTERNATIONAL CONFERENCE ON ELECTRONICS INSTRUMENTATION & INFORMATION SYSTEMS》 * |
| 尹力: "基于图像的指针式仪表读数自动识别技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 杨帆: "《普通高校"十二五"规划教材——数字图像处理与分析（第3版）》", 31 May 2015, 北京航空航天大学出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114663434A (en) * | 2022-05-25 | 2022-06-24 | 国家海洋局北海海洋技术保障中心 | Shadow discrimination method of side-scan sonar image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108921176B (en) | Pointer instrument positioning and identifying method based on machine vision | |
| CN107507173B (en) | No-reference definition evaluation method and system for full-slice image | |
| CN111008961B (en) | Transmission line equipment defect detection method and system, equipment and medium thereof | |
| CN112862744B (en) | Intelligent detection method for internal defects of capacitor based on ultrasonic image | |
| CN102324099A (en) | Step edge detection method oriented to humanoid robot | |
| CN110726725A (en) | Transmission line hardware corrosion detection method and device | |
| CN111539980B (en) | Multi-target tracking method based on visible light | |
| CN113920097A (en) | Power equipment state detection method and system based on multi-source image | |
| CN113177924A (en) | Industrial production line product flaw detection method | |
| CN111369570A (en) | Multi-target detection tracking method for video image | |
| CN116309562B (en) | Board defect identification method and system | |
| CN112991374A (en) | Canny algorithm-based edge enhancement method, device, equipment and storage medium | |
| CN115601379A (en) | Surface crack accurate detection technology based on digital image processing | |
| CN116385353B (en) | Camera module abnormality detection method | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN111027564A (en) | Low-illumination imaging license plate recognition method and device based on deep learning integration | |
| CN114529906A (en) | Method and system for detecting abnormity of digital instrument of power transmission equipment based on character recognition | |
| CN109146806A (en) | Gauge pointer position detection recognition methods based on shadow removing optimization in remote monitoriong of electric power | |
| CN114331961A (en) | Method for defect detection of an object | |
| CN114596242A (en) | Defect detection method, defect detection device, electronic equipment and computer readable storage medium | |
| CN117079286A (en) | Identification method and identification system for pointer instrument | |
| CN105844651A (en) | Image analyzing apparatus | |
| CN117788874A (en) | Contour recognition model training method and porosity calculation method | |
| Jidong et al. | Research on the recognition method for obscured apple in natural environment | |
| CN118037696B (en) | Sand grain detection and mesh number classification method based on edge detection and S3N network |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190104 |
|
| RJ01 | Rejection of invention patent application after publication |