CN105426809A - Method for automatically identifying instrument pointer - Google Patents
Method for automatically identifying instrument pointer Download PDFInfo
- Publication number
- CN105426809A CN105426809A CN201510504562.4A CN201510504562A CN105426809A CN 105426809 A CN105426809 A CN 105426809A CN 201510504562 A CN201510504562 A CN 201510504562A CN 105426809 A CN105426809 A CN 105426809A
- Authority
- CN
- China
- Prior art keywords
- pointer
- fan
- angle
- shaped
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000007704 transition Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000007423 decrease Effects 0.000 description 2
- 241000145637 Lepturus Species 0.000 description 1
- 241001494479 Pecora Species 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for automatically identifying an instrument pointer. The method comprises the steps: acquiring an image of an instrument panel, performing binary processing on the image of instrument panel, selecting one point in a preset area of the instrument panel, taking the point as the center to search a pointer, performing point-to-point scanning in the area, finding the most appropriate pointer rotating shaft position and a corresponding pointer direction, and obtaining pointer reading according to a corresponding pointer angle. The method can effectively identify reading of a pointer type instrument, and is relatively robust and rapid compared with a mode that a Hough change is used to search a straight line; even if the image has a certain non-rotation offset, the pointer direction can still be found accurately, and the instrument reading is obtained.
Description
Technical field
The invention belongs to computer image processing technology field, particularly a kind of gauge pointer knows method for distinguishing automatically.
Background technology
Pointer instrument, as a kind of traditional gauging instrument, has a large amount of application in the industry such as electric power, chemical industry.Although in some cases, have corresponding electronic instrument to exist, due to aspect factors such as expense, reliability and constructions, electronic instrument still seldom has alternative traditional pointer instrument.The needs of making a copy of of pointer instrument manually complete, and reading accuracy by observer's subjective impact, and affects by extraneous factors such as viewing angle, viewing distance, lights.The most important thing is, meter reading need complete at the scene, and instrument is often distributed in diverse location.The measurement data of instrument also needs record manually, and therefore meter reading, checking meter and recording all brings very large workload to worker.
Summary of the invention
For the existing issue of pointer instrument, the present invention proposes a kind of gauge pointer and automatically know method for distinguishing, after acquisition panel board image, carry out image recognition, find axis of rotation and the pointer direction of pointer, thus obtain the reading of instrument.By the mode of this automatic meter reading, on original pointer instrument basis, the function of automatic reading can be increased.Like this, on the guarantee original reliability basis of DATA REASONING, decrease the workload of personnel, reach timing, make a copy of the effect of all meter readings rapidly, greatly increase work efficiency.
In order to achieve the above object, technical solution of the present invention is as follows:
A kind of gauge pointer knows method for distinguishing automatically, and concrete steps are as follows:
Step 1: Acquisition Instrument dial plate image;
Step 2: binary conversion treatment is carried out to described panel board image;
Step 3: select in the predeterminable area of described panel board a bit, as center finding pointer;
Step 4: find home position the most suitable and corresponding pointer position;
Step 5: obtain total indicator reading according to described corresponding pointer angle.
Further, in described step 2, specifically comprising the steps: of binary conversion treatment is carried out to described panel board image
1) according to known dial plate outward appearance, pre-determine a pointer position region, and determine the optimum binaryzation threshold values in this region;
2) with described binaryzation threshold values for target, gained picture is carried out two dimension, and the color setting pointer is as white, and background color is black.
Further, select a bit in the predeterminable area of described panel board in described step 3, as specifically comprising the steps: of center finding pointer
1) preset one piece of region of picture centre, this region is the region that pointer turning axle is most likely at, and region can be plane or the lines of any shape;
2) select the 1st point in described region, and draw as center one fan-shaped: fan-shaped internal diameter is that the inner side of pointer visible location is to the distance of turning axle; Fan-shaped external diameter is the distance of outermost to turning axle of pointer visible location; Fan-shaped open beginning angle be pointer open beginning angle; Fan-shaped end angle is the termination point of pointer; Again this is fan-shapedly divided into very little fan-shaped of several angle.Because little fan-shaped angle is very little, fan-shapedly approximate straight line can be regarded as by each;
3) calculate each block little fan-shaped in white pixel quantity and the ratio of this fan-shaped all pixel quantity, that block looking for ratio the highest is little fan-shaped, and little fan-shaped corresponding angle: corresponding angle=(little fan-shaped open beginning angle+little fan-shaped end angle)/2;
4) select the 2nd point in picture centre region as fan shape center, repeat step 2-3, the rest may be inferred, the institute in picture centre region a little all scanned as fan shape center.
Further, the concrete grammar of home position the most suitable and corresponding pointer position is found to be in described step 4: all (centers obtained from described step 3, angle) combination in, find white pixel quantity to account for the highest combination of this little fan-shaped all sum of all pixels ratio, confirm as turning axle and the pointer angle of pointer.
Further, the concrete grammar obtaining total indicator reading according to described corresponding pointer angle in described step 5 is: according to pointer angle and the reading corresponding relation of instrument outward appearance, be meter reading by the pointer angular transition of identification.
More existing Meter recognition technology, " the digital instrument recognition system of view-based access control model and recognition methods thereof " (application number 201410216754.0), this invention is the image recognition based on seven segment digital tubes, can not identify pointer instrument.
Relatively " a kind of readings of pointer type meters automatic identifying method of robust " (application number 201510066208.8), be a kind of invention that can identify pointer instrument.First this invention finds dial plate and the center of circle (claim 2) thereof by Hough change, and find the straight line (claim 4) through dial scale by a Hough change again, finally need to identify (claim 8) the numeral in dial plate, and calculate the scale of pointer indication according to these information.With the method similar have " pointer instrument intelligent identification Method and device thereof " (application number 201310542287.6), " the SF6 density meter meter pointer identification equipment based on image acquisition " (application number 201410575673.X) be also after carrying out the pre-service such as dimensionality reduction, noise reduction to image, change straight-line detection method by Hough and find pointer.Compared with this kind of invention, the present invention does not use Hough to change straight-line detection, reduces operand, and owing to defining home position and the factor such as pointer length and range angle, can obtain the recognition effect changing straight-line detection more robust than Hough, reliability is stronger.
" a kind of detection algorithm of gauge pointer identification " (application number 201310752723.2) does not adopt Hough to change straight-line detection method to find pointer, but by find black picture element maximum, fan-shaped centered by the instrument center of circle.But this invention necessarily requires to provide concrete home position in advance.Once the home position of setting and the difference had a little of actual photographed, its success ratio also can decline greatly.By contrast, the present invention scans in certain area, and finding out is most possibly the position in the center of circle, and the angle that under this home position, pointer most possibly points to.When image have certain offset without spin, still can find pointer direction accurately, thus draw meter reading.Therefore, robustness is higher.
The present invention proposes the pointer instrument recognition methods that a kind of robustness is high, reliability is strong, calculated amount is little, when instrument has compared with thin tail sheep, still can keep the accuracy identified.
Below in conjunction with the drawings and specific embodiments, explanation is further expalined to the present invention.
Accompanying drawing explanation
Fig. 1 be gather instrument coloured image, and the pointer range pre-set, region, the center of circle.
Fig. 2 is the image after two dimensionization.
Fig. 3 is using first of region, the center of circle point as the center of circle, the sector region drawn.
Fig. 4 be find the center of circle, angle and correspondence identification pointer position.
Embodiment
See Fig. 1-Fig. 3, it is as follows that gauge pointer of the present invention knows method for distinguishing embodiment automatically:
Step 1: the black and white ratio preset value that the pointer range of known panel board, region, the center of circle and pointer district are set.In this example, black and white ratio preset value is 92% black: 8% is white.The pointer start angle preset is 135 °, termination point 45 °, and fan-shaped internal diameter is 65 pixels, external diameter 100 pixel;
Step 2: the coloured image obtaining panel board.As signal, the pointer range (large square frame above) pre-set in step 1, region, the center of circle (little square frame below) also draw in FIG.The size of image is 500 × 375;
Step 2: carry out two dimension to image, makes picture become black and white picture, and the monochrome pixels in pointer range is than the 92:8 for preset value.(as Fig. 2);
Step 3: using first of region, the center of circle point as the center of circle, draw a sector region (see figure 3), is subdivided into several fan-shaped (dividing in order to 184 in this example) that angle is very little;
Step 4: calculate each little fan-shaped interior white pixel quantity, and find maximum that of white pixel fan-shaped, and record its angle;
Step 5: to each point in region, the center of circle, repeat in the mode of step 3-4.Find the fan-shaped corresponding center of circle angle that white pixel is maximum.Find in this example be the center of circle in (205,174), angle is that 135(is shown in Fig. 4);
Step 6: be according to the fan angle found out, corresponding total indicator reading is: (135-135) × 3.0/(135-45)=0.0.
Claims (5)
1. gauge pointer knows a method for distinguishing automatically, it is characterized in that: concrete steps are as follows:
Step 1: Acquisition Instrument dial plate image;
Step 2: binary conversion treatment is carried out to described panel board image;
Step 3: select in the predeterminable area of described panel board a bit, as center finding pointer;
Step 4: find home position the most suitable and corresponding pointer position;
Step 5: obtain total indicator reading according to described corresponding pointer angle.
2. gauge pointer according to claim 1 knows method for distinguishing automatically, it is characterized in that: carry out specifically comprising the steps: of binary conversion treatment to described panel board image in described step 2
Step 1: according to known dial plate outward appearance, pre-determines a pointer position region, and determines the optimum binaryzation threshold values in this region;
Step 2: with described binaryzation threshold values for target, gained picture is carried out two dimension, set the color of pointer as white, and background color is black.
3. gauge pointer according to claim 1 knows method for distinguishing automatically, it is characterized in that: select a bit in the predeterminable area of described panel board in described step 3, as specifically comprising the steps: of center finding pointer
Step 1: the one piece of region presetting picture centre, this region is the region that pointer turning axle is most likely at, and region can be plane or the lines of any shape;
Step 2: select the 1st point in described region, and draw as center one fan-shaped: fan-shaped internal diameter is that the inner side of pointer visible location is to the distance of turning axle; Fan-shaped external diameter is the distance of outermost to turning axle of pointer visible location; Fan-shaped open beginning angle be pointer open beginning angle; Fan-shaped end angle is the termination point of pointer; Again this is fan-shapedly divided into very little fan-shaped of several angle;
Step 3: calculate each block little fan-shaped in white pixel quantity and the ratio of this fan-shaped all pixel quantity, that block looking for ratio the highest is little fan-shaped, and little fan-shaped corresponding angle: corresponding angle=(little fan-shaped open beginning angle+little fan-shaped end angle)/2;
Step 4: select the 2nd point in picture centre region as fan shape center, repeat step 2-3, the rest may be inferred, a little all scans the institute in picture centre region as fan shape center.
4. gauge pointer according to claim 1 knows method for distinguishing automatically, it is characterized in that: in described step 4, find the concrete grammar of home position the most suitable and corresponding pointer position for all (centers of obtaining from step described in claim 3, angle) combination in, find white pixel quantity to account for the highest combination of this little fan-shaped all sum of all pixels ratio, confirm as turning axle and the pointer angle of pointer.
5. gauge pointer according to claim 1 knows method for distinguishing automatically, it is characterized in that: the concrete grammar obtaining total indicator reading according to described corresponding pointer angle in described step 5 is: according to pointer angle and the reading corresponding relation of instrument outward appearance, be meter reading by the pointer angular transition of identification.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510504562.4A CN105426809B (en) | 2015-08-18 | 2015-08-18 | A kind of method of gauge pointer automatic identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510504562.4A CN105426809B (en) | 2015-08-18 | 2015-08-18 | A kind of method of gauge pointer automatic identification |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105426809A true CN105426809A (en) | 2016-03-23 |
CN105426809B CN105426809B (en) | 2019-02-22 |
Family
ID=55505010
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510504562.4A Active CN105426809B (en) | 2015-08-18 | 2015-08-18 | A kind of method of gauge pointer automatic identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105426809B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106295658A (en) * | 2016-08-13 | 2017-01-04 | 国网福建省电力有限公司 | A kind of transformer station readings of pointer type meters automatic recognition system |
CN106295665A (en) * | 2016-08-13 | 2017-01-04 | 国网福建省电力有限公司 | A kind of transformer station readings of pointer type meters automatic identifying method |
CN107092905A (en) * | 2017-03-24 | 2017-08-25 | 重庆邮电大学 | A kind of instrument localization method to be identified of electric inspection process robot |
CN107563263A (en) * | 2016-07-01 | 2018-01-09 | 珠海优特电力科技股份有限公司 | Video image identification method and system based on instrument |
CN108898632A (en) * | 2018-06-13 | 2018-11-27 | 浙江大华技术股份有限公司 | A kind of rotation angle of gauge pointer determines method and device |
CN109115399A (en) * | 2018-07-26 | 2019-01-01 | 国家电网公司 | meter reading device |
CN111104862A (en) * | 2019-11-22 | 2020-05-05 | 桂林金格电工电子材料科技有限公司 | Pointer identification method of coaxial special pointer instrument |
CN112639901A (en) * | 2018-08-30 | 2021-04-09 | 欧吉斯信息技术有限公司 | Meter reading apparatus, meter reading method, and computer program |
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 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102799867A (en) * | 2012-07-09 | 2012-11-28 | 哈尔滨工业大学 | Meter pointer angle identification method based on image processing |
CN103207987A (en) * | 2013-02-28 | 2013-07-17 | 华北电力大学 | Indicating value identification method of dial instrument |
CN103714329A (en) * | 2013-12-31 | 2014-04-09 | 长安大学 | Detecting algorithm for identifying meter needle |
CN104392206A (en) * | 2014-10-24 | 2015-03-04 | 南京航空航天大学 | Image processing method for automatic pointer-type instrument reading recognition |
-
2015
- 2015-08-18 CN CN201510504562.4A patent/CN105426809B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102799867A (en) * | 2012-07-09 | 2012-11-28 | 哈尔滨工业大学 | Meter pointer angle identification method based on image processing |
CN103207987A (en) * | 2013-02-28 | 2013-07-17 | 华北电力大学 | Indicating value identification method of dial instrument |
CN103714329A (en) * | 2013-12-31 | 2014-04-09 | 长安大学 | Detecting algorithm for identifying meter needle |
CN104392206A (en) * | 2014-10-24 | 2015-03-04 | 南京航空航天大学 | Image processing method for automatic pointer-type instrument reading recognition |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107563263A (en) * | 2016-07-01 | 2018-01-09 | 珠海优特电力科技股份有限公司 | Video image identification method and system based on instrument |
CN106295658B (en) * | 2016-08-13 | 2019-10-01 | 国网福建省电力有限公司 | A kind of substation's readings of pointer type meters automatic recognition system |
CN106295665A (en) * | 2016-08-13 | 2017-01-04 | 国网福建省电力有限公司 | A kind of transformer station readings of pointer type meters automatic identifying method |
CN106295658A (en) * | 2016-08-13 | 2017-01-04 | 国网福建省电力有限公司 | A kind of transformer station readings of pointer type meters automatic recognition system |
CN106295665B (en) * | 2016-08-13 | 2019-10-01 | 国网福建省电力有限公司 | A kind of substation's readings of pointer type meters automatic identifying method |
CN107092905A (en) * | 2017-03-24 | 2017-08-25 | 重庆邮电大学 | A kind of instrument localization method to be identified of electric inspection process robot |
CN107092905B (en) * | 2017-03-24 | 2020-04-14 | 重庆邮电大学 | Method for positioning instrument to be identified of power inspection robot |
CN108898632B (en) * | 2018-06-13 | 2020-09-29 | 浙江大华技术股份有限公司 | Method and device for determining rotation angle of instrument pointer |
CN108898632A (en) * | 2018-06-13 | 2018-11-27 | 浙江大华技术股份有限公司 | A kind of rotation angle of gauge pointer determines method and device |
CN109115399A (en) * | 2018-07-26 | 2019-01-01 | 国家电网公司 | meter reading device |
CN112639901A (en) * | 2018-08-30 | 2021-04-09 | 欧吉斯信息技术有限公司 | Meter reading apparatus, meter reading method, and computer program |
CN112639901B (en) * | 2018-08-30 | 2023-06-27 | 欧吉斯信息技术有限公司 | Meter reading device, meter reading method, and storage medium |
CN111104862A (en) * | 2019-11-22 | 2020-05-05 | 桂林金格电工电子材料科技有限公司 | Pointer identification method of coaxial special pointer instrument |
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 |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN105426809B (en) | 2019-02-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105426809A (en) | Method for automatically identifying instrument pointer | |
CN110580480B (en) | Meter reading identification method based on image processing | |
CN112906694B (en) | Reading correction system and method for transformer substation inclined pointer instrument image | |
Zheng et al. | A robust and automatic recognition system of analog instruments in power system by using computer vision | |
CN107220645B (en) | Water meter identification method based on dynamic image processing | |
CN100559131C (en) | A kind of method for automatically detecting pointer instrument | |
CN103714329B (en) | Detecting algorithm for identifying meter needle | |
CN110245654B (en) | Pointer reading identification method and device, computer device and readable storage medium | |
CN105303168A (en) | Multi-view pointer type instrument identification method and device | |
US20020067855A1 (en) | Method and arrangement for camera calibration | |
CN107145890B (en) | A kind of pointer dashboard automatic reading method under remote multi-angle of view environment | |
Yang et al. | An image-based intelligent system for pointer instrument reading | |
CN109508709B (en) | Single pointer instrument reading method based on machine vision | |
CN110688902B (en) | Method and device for detecting vehicle area in parking space | |
CN111401357B (en) | Pointer type instrument reading method based on text detection | |
CN110796095B (en) | Instrument template establishing method, terminal equipment and computer storage medium | |
CN109034170B (en) | Reading method for circular pointer type instrument of switch cabinet detection device | |
CN110852954B (en) | Image inclination correction method and system for pointer instrument | |
CN103729631A (en) | Vision-based connector surface feature automatically-identifying method | |
CN110211178A (en) | A kind of pointer instrument recognition methods calculated using projection | |
CN112215060A (en) | Hough transform-based high-precision mechanical instrument reading identification method | |
CN105783970B (en) | A kind of Digital identification method of automobile meter pointer | |
CN109784257B (en) | Transformer thermometer detection and identification method | |
CN116189194A (en) | Drawing enhancement segmentation method for engineering modeling | |
CN113591875B (en) | High-precision pointer type instrument identification method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20191126 Address after: 610021, No. 2, unit 7, building 5, 7 West Long Street, Chengdu, Sichuan, Jinjiang District Patentee after: Chengdu Ruichi Technology Co., Ltd Address before: 610021, No. 2, unit 7, building 5, 7 West Long Street, Chengdu, Sichuan, Jinjiang District Patentee before: Zhang Dakun |
|
TR01 | Transfer of patent right |