CN109544628A - A kind of the accurate reading identifying system and method for pointer instrument - Google Patents
A kind of the accurate reading identifying system and method for pointer instrument Download PDFInfo
- Publication number
- CN109544628A CN109544628A CN201811406269.4A CN201811406269A CN109544628A CN 109544628 A CN109544628 A CN 109544628A CN 201811406269 A CN201811406269 A CN 201811406269A CN 109544628 A CN109544628 A CN 109544628A
- Authority
- CN
- China
- Prior art keywords
- pointer
- image
- needle point
- instrument
- dimensional
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06T7/85—Stereo camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
- G06V10/30—Noise filtering
-
- 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
- G06V10/48—Extraction of image or video features by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation
Abstract
The present invention relates to the accurate reading identifying systems and method of a kind of pointer instrument, gauge pointer needle point is extracted by image procossing, it is calculated using binocular detection means and obtains pointer needle point three-dimensional information and building instrument panel plane, reorientation of the relational implementation to gauge pointer depending on the relative position, correction before completing gauge pointer Recognition of Reading, it is final to improve identification accuracy.The present invention is able to solve when that there are certain altitudes is poor for gauge pointer and instrument plane, and pointer projected position on dial plate is not inconsistent with physical location in acquired image when acquiring device inclined, and reading accuracy is caused to decline or even error in reading problem.
Description
Technical field
The present invention relates to field of machine vision, and in particular to a kind of accurate reading identifying system of pointer instrument and side
Method.
Background technique
With the fast development of technology of instrument and meter, instrument and meter is widely used in all trades and professions, and metered quantity is numerous
More, demand is big.The use of pointer instrument still has irreplaceable status in many factories, China, transit equipment.Refer to
The advantages of pin type instrument be it is durable, cheap, and its registration fluctuation (i.e. the swing of pointer) can image expression
The variation of parameter out, furthermore its more prominent advantage be: for some special occasions, its antifreeze spy of mechanical indicating pointer instrument
Property can allow it can be allowed to work under water in the local work of weather cold, its fire resistance characteristic well, these characteristics allow it
Play the advantage for remaining to work normally in the presence of a harsh environment.
Certain digital instrument onboard data sending modules send control centre for meter reading automatically, but this skill
Art has to built-in corresponding module, and higher cost, it is impossible in installed fixed instrumentation at this stage.Therefore,
It is necessary to develop the accurate reading identifying system and method for a kind of pointer instrument, on the basis that do not reequiped to existing instrument
On, not only change the low defect of traditional artificial implementation Meter recognition large labor intensity, production efficiency, effectively reduces detection process
In manpower consumption, by the may cause readings of difference of Observation personnel when saving resource, while eliminating artificial read
As a result different and there are relatively large deviations.Therefore, the method that we can use machine vision acquires image by camera and utilizes
Algorithm identifies the reading of position pointed by pointer instrument in image, substitutes artificial reading with this.
Existing many solution majorities are direct processing Instrument images, and what pointer was directed toward directly in reading picture shows
Number.However, this kind of solution will just go wrong when pointer plane and instrument panel plane are there are when obvious difference in height.
This is because acquisition equipment visual angle is different, cause pointer different in the imaging position of instrument plane, it means that work as Image Acquisition
Equipment optical axis is not vertical with instrument plane or (camera inclination and the misalignment of camera optical axis center when not right above instrument center
Dial plate center) so that optical axis is with instrument central point, there are inclination angles.At this moment, visual angle, ruler may occur for the pointer image collected
The variations such as degree, inclination, lead to directly read numerical value indicated by pointer from image that there are obvious deviations.This problem is led
The identification mistake and accuracy rate for causing readings of pointer type meters reduce, and still have at present to be solved.
Summary of the invention
In view of this, the purpose of the present invention is to provide the accurate reading identifying system and method for a kind of pointer instrument,
It solves existing Recognition of Reading technology and directly reads existing offset issue when numerical value indicated by pointer from image.
To achieve the above object, the present invention adopts the following technical scheme:
A kind of accurate reading identifying system of pointer instrument, including sequentially connected image capture module, image preprocessing mould
Block, three-dimensional correction module and recognition result output module;
Described image acquisition module: being used for acquisition instrument dial plate binocular image, and that completes image data stablizes transmission;
Image pre-processing module: it is sat for dial plate major division and pointer needle point image pixel to be pre-processed and extracted to image
Mark;
Three dimensional detection correction module: for obtaining needle point three-dimensional information, three-dimensional reorientation and the Recognition of Reading of pointer needle point are realized
Preceding pointer position correction;
Recognition result output module: by the positional relationship of pointer needle point and major division, reading result is calculated.
Further, the binocular camera that described image acquisition module is formed using two identical video cameras.
A kind of recognition methods of the accurate reading identifying system of pointer instrument, comprising the following steps:
Step S1: to binocular camera carry out binocular calibration, obtain binocular camera internal reference and outer ginseng;
Step S2: image is collected by calibrated binocular camera, and realizes stereoscopic horizontal school using the internal reference obtained
Just, so that left images are aligned, and image is input to image pre-processing module;
Step S3: locate module in advance by image and improve initial pictures quality, extract dial plate major division and pointer needle point image slices
Plain coordinate, and it is input to three dimensional detection module;
Step S4: three dimensional detection correction module utilizes binocular detection algorithm, realizes instrument three dimensional stress, and it is three-dimensional to calculate pointer needle point
Information and dial plate plane three-dimensional information, construct instrument panel plane and pointer needle point relative positional relationship;
Step S5: three dimensional detection correction module is by coordinate system transformational relation and upright projection, to pointer in instrument panel plane weight
Positioning, to complete the correction to pointer position;
Step S6: recognition result output module calculates output according to major division and pointer needle point co-ordinate position information has been extracted
Final reading recognition result.
Further, the internal reference of the binocular camera includes the focal length and camera imaging center of two camera directions;
The outer ginseng of binocular camera includes spin matrix, translation vector and parallax.
Further, the step S3 specifically:
Step S31: enhancing processing is carried out to image using piecewise linear transform method;
Step S32: carrying out denoising to image using two dimension median filter, eliminates or reduces noise in collection process and is made
At influence;
Step S33: determining that optimal threshold is split according to the value of HSV, and with erosion operation, dilation operation, it is attached to reduce needle point
Nearly interference data;
Step S34: extracting the major division information of pointer meters, so that it is determined that dial starting and ending range, must take office
It anticipates 3 pairs of point pixel coordinates;
Step S35: gauge pointer is obtained by Hough transform, calculates and the intersection point of straight line, i.e. pointer is obtained by Hough transform
The pixel coordinate position of needle point in the picture.
The further step S4 specifically:
Step S41: level correction is carried out to binocular image according to the internal reference of video camera, and using Bouquet correcting algorithm;
Step S42: binocular detection algorithm is utilized, the depth information of needle point and the depth information of instrument board are obtained;
Step S43: pass through turning between 4 kinds of pixel coordinate system, image coordinate system, camera coordinates system and world coordinate system coordinate systems
Relationship is changed, according to any 3 pairs of point pixel coordinates and camera parallax D is obtained, using binocular detection algorithm, it is corresponding to calculate acquisition each point
Depth z, calculation formula is as follows:
Wherein, x, y, z are the coordinates of two-dimensional surface point corresponding points in three-dimensional coordinate system after calculating.
Step S44: plane where going out instrument board according to 3 pairs of point pixel coordinate information reconstructions on pointer needle point point and instrument board
S establishes the space equation of instrument panel plane, and utilizes spatial relationship, obtains pointer needle point on instrument panel space plan-position
The intersection point three-dimensional coordinate of upright projection.
The further step S5 specifically:
According to obtained pointer needle point, the intersection point three-dimensional coordinate of upright projection is sought it and is being schemed on instrument panel space plan-position
As the mapping point of pixel planes;
The further step S6 specifically:
Step S61: using polar coordinates and cartesian coordinate system corresponding equation, limbus axis is converted into cartesian coordinate system;
Step S62: the ratio of range and the product of range are accounted for according to needle point present position, are standard pointed by current time pointer
Really reading t, available:
Wherein,X p For pointer needle point horizontal direction pixel coordinate value,X start For scale initial position horizontal direction pixel value,X end
For scale terminal position horizontal direction pixel value, range is the pointer instrument range.
Compared with the prior art, the invention has the following beneficial effects:
The present invention is able to solve when that there are certain altitudes is poor for gauge pointer and instrument plane, acquires collected figure when device inclined
Pointer projected position on dial plate is not inconsistent with physical location as in, and leads to reading accuracy decline even error in reading problem.
Detailed description of the invention
Fig. 1 is a kind of pointer instrument schematic diagram in the embodiment of the present invention;
Fig. 2 is the method for the present invention flow chart;
Fig. 3 is binocular stereo vision imaging schematic diagram in the embodiment of the present invention;
Fig. 4 is that pointer relocates schematic diagram in the embodiment of the present invention.
Specific embodiment
The present invention will be further described with reference to the accompanying drawings and embodiments.
Fig. 1 is please referred to, the present invention provides a kind of accurate reading identifying system of pointer instrument, including sequentially connected figure
As acquisition module, image pre-processing module, three-dimensional correction module and recognition result output module;Described image acquisition module: it uses
In acquisition instrument dial plate binocular image, that completes image data stablizes transmission;Image pre-processing module: pre- for being carried out to image
Processing and extraction dial plate major division and pointer needle point image pixel coordinates;Three dimensional detection correction module: for obtaining needle point three
Information is tieed up, the three-dimensional reorientation and the pointer position correction before Recognition of Reading for realizing pointer needle point;Recognition result output module: logical
The positional relationship of pointer needle point and major division is crossed, reading result is calculated.
In the present embodiment, image capture module is put by the identical CMOS camera of two specifications according to a certain distance in parallel
It sets, is assembled into a binocular camera, and no longer change its relative position later.Such as CMOS camera pixel be 1080 ×
720 pixels, data reach computer by USB3.0 interface.
In the present embodiment, the recognition methods of the accurate reading identifying system of a kind of pointer instrument, specifically includes following
Step:
Step S1: it before formally starting survey measurements, needs first to carry out staking-out work to binocular camera.Carrying out Bi-objective
Periodically, there are two types of common databases: Matlab visual processes library and OpenCV open source vision library;Its enclosed inside is available to be taken the photograph
Camera calibration algorithm.The scaling board image of 20 width in different positions is acquired using cmos camera, above-mentioned software is given to be marked
It is fixed.The result demarcated in usual Matlab is more stable, and OpenCV calibration is reused after can demarcating in Matlab.Pass through
Binocular calibration can obtain following parameter: camera internal reference, distortion, including radial distortion and tangential distortion, Camera extrinsic,
Including parallax between 3*3 spin matrix and 3*1 translation vector, two camerasD.From effect, Intrinsic Matrix be terrible
To the information of camera lens, and eliminate distortion, the image made is more accurate, outer parameter matrix be in order to obtain camera relative to generation
The connection of boundary's coordinate is for final ranging.
Step S2: after the completion of staking-out work, it is possible to implement the acquisition and identification process of image.Pass through computer control two
A camera shoots picture simultaneously, image data is reached host by data line, OpenCV program is given to handle.Utilize calibration
The internal reference for two cameras that work obtains, the focal length including both directionf x 、f y , camera imaging centerC x 、C y Etc. parameters, to two
Width image carries out the correction of image stereoscopic horizontal.So that object two camera imaging planes subpoint to meet limit restraint fixed
While reason, corresponding point can be in same level.
Step S3: image preprocessing is needed to handle image after obtaining image by video camera.Be not only for
Raising picture quality, it is often more important that extract useful information in image.First left figure is handled: (1) using piecewise linearity
Converter technique carries out enhancing processing to image.(2) denoising is carried out to noise-containing initial pictures using two dimension median filter,
Eliminate or reduce influence caused by noise in collection process.(3) erosion operation, dilation operation are used, is reduced near needle point
Interfere data.(4) using the priori knowledge to instrument example, optimal threshold is determined according to HSV value, extracts the master of pointer meters
Want calibration information, so that it is determined that dial starting and ending range, obtain any 3 points (N x1-left ,N y1- left ),
(N x2- left ,N y2- left ), (N x3- left , N y3- left ) (5) by Hough transform obtain gauge pointer, further calculate logical
It crosses Hough transform and obtains the intersection point of straight line, be the pixel coordinate position of the pointer needle point of our needs in the picture
(P x-left ,P y-left ).At this point, program can be obtained by Stereo Matching Algorithm, one-to-one three point are obtained with left figure in right figure
(N x1-right ,N y1-right ), (N x2-right ,N y2-right ), (N x3-right , N y3-right ) and pointer needle point pixel coordinate position
(P x-right ,P y-right ).Here, on two-dimensional space match corresponding points be it is very time-consuming, in order to reduce matching search range,
We can use epipolar-line constraint theory and the matching of corresponding points made to be reduced to linear search by two-dimensional search.
Step S4: according to aforementioned identified point, into the three dimensional detection stage.
In the imaging process of video camera, there is four coordinate systems, are respectively: pixel coordinate system, image coordinate system, phase
Machine coordinate system and world coordinate system.As shown, pixel coordinate system is using the upper left corner of image as originO, transverse and longitudinal coordinate (u, v) respectively indicate pixel columns in the picture and line number;The origin of image coordinate system is the optical axis and the plane of delineation of camera
Intersection point, then point (u 0 ,v 0 ) there are following relationships between Two coordinate system:
It is indicated then with homogeneous matrix are as follows:
Further, by the conversion formula of camera coordinate system to image coordinate system are as follows:
It is expressed as follows (wherein with homogeneous matrixSFor scale factor,fFor focal length):
Transformational relation of the world coordinates to camera coordinates system are as follows:
Step S5: by the means of binocular camera three dimensional detection, realize that gauge pointer needle point is relocated in instrument panel plane.
(1) according to aforementioned 3 be calculated pair point and camera parallaxD, using binocular range measurement principle, calculate and obtain the corresponding depth of each pointZ.Plane where going out this dial plate using 3 points of Studies About Reconstruction of Three-Dimension InformationS 1 .Wherein, the three-dimensional coordinate of object can be vertical by binocular
Body vision technology determines to have as shown in Figure 3OLWithORIt is the optical center of left and right camera, their optical axis and respective imaging are flat
Face.Assuming that the inside and outside parameter of two cameras is identical, focal length isf, the distance between optical center (baseline) isB, two phases
In the same plane, therefore the Y axis coordinate of their projection centre is equal for machine.Synchronization spatial pointP(x,y,z)In two cameras
Upper imaging point is respectivelyP left WithP right。
Introduce parameter parallaxDAfter can obtain:
(2) center of circle in dial plate plane is obtainedO 2 , made by the center of circle perpendicular to planeS 1 Vertical lineL;Determine pointer needle pointP's
Space coordinate, and make the mistake needle pointPIt puts and with dial plate planeS 1 Parallel planeS 2 .PlaneS 2 With vertical lineLIntersection pointO 2 ,
It calculates and recordsO 2 PSlope;In dial plate planeS 1 On, pass through the center of circleO 1 Make withO 2 PSame slope, as pointer is relative to table
The actual position of disk plane, is shown in Fig. 4.
Step S6: readings of pointer type meters identification: the 3 d space coordinate of the pointer needle point after three-dimensional reorientation is sought
Its mapping point in image pixel plane.Pointer is being determined after the location of pixels of imaging plane, in aforementioned character, scale knowledge
On the basis of other, using polar coordinates and cartesian coordinate system corresponding equation, circle (arc) reference axis is converted into polar coordinate system.
According to pointer to the distance of nearest graduation mark, image cursor reading can be calculated.
Wherein,X p For pointer needle point horizontal direction pixel coordinate value,X start For scale initial position horizontal direction pixel value,X end For scale terminal position horizontal direction pixel value,rangeFor the pointer instrument range.
In the present embodiment, using OpenCV write Recognition of Reading program, it can be achieved that approach described above function:
(1) effective picture that camera shooting obtains is read;(2) image processing algorithm is utilized, is read from photo and recording apparatus refers to
The position of needle needle point and each scale coordinate position;(3) binocular detection algorithm is utilized, aforementioned image middle finger needle needle point two dimension is sat
Mark is converted to the three-dimensional coordinate for having depth information;(4) by the three-dimensional planar where pointer needle point upright projection to instrument board, and
It is mapped with image pixel Planar realization.According to pointer tip position at this time and graduation position information, the function of accurate reading is realized.
The foregoing is merely presently preferred embodiments of the present invention, all equivalent changes done according to scope of the present invention patent with
Modification, is all covered by the present invention.
Claims (7)
1. a kind of accurate reading identifying system of pointer instrument, it is characterised in that: including sequentially connected image capture module,
Image pre-processing module, three-dimensional correction module and recognition result output module;
Described image acquisition module: being used for acquisition instrument dial plate binocular image, and that completes image data stablizes transmission;
Image pre-processing module: it is sat for dial plate major division and pointer needle point image pixel to be pre-processed and extracted to image
Mark;
Three dimensional detection correction module: for obtaining needle point three-dimensional information, three-dimensional reorientation and the Recognition of Reading of pointer needle point are realized
Preceding pointer position correction;
Recognition result output module: by the positional relationship of pointer needle point and major division, reading result is calculated.
2. a kind of accurate reading identifying system of pointer instrument according to claim 1, it is characterised in that: described image
The binocular camera that acquisition module is formed using two identical video cameras.
3. a kind of recognition methods of the accurate reading identifying system of pointer instrument according to claim 2, feature exist
In, comprising the following steps:
Step S1: to binocular camera carry out binocular calibration, obtain binocular camera internal reference and outer ginseng;
Step S2: image is collected by calibrated binocular camera, and realizes stereoscopic horizontal school using the internal reference obtained
Just, so that left images are aligned, and image is input to image pre-processing module;
Step S3: locate module in advance by image and improve initial pictures quality, extract dial plate major division and pointer needle point image slices
Plain coordinate, and it is input to three dimensional detection module;
Step S4: three dimensional detection correction module utilizes binocular detection algorithm, calculates pointer needle point three-dimensional information and dial plate plane three
Information is tieed up, instrument panel plane and pointer needle point relative positional relationship are constructed, realizes instrument three dimensional stress;
Step S5: three dimensional detection correction module is by coordinate system transformational relation and upright projection, to pointer in instrument panel plane weight
Positioning, to complete the correction to pointer position information;
Step S6: recognition result output module calculates output according to major division and pointer needle point co-ordinate position information has been extracted
Final reading recognition result.
4. a kind of recognition methods of the accurate reading identifying system of pointer instrument according to claim 3, feature exist
In: the internal reference of the binocular camera includes focal length and the camera imaging center of video camera x, y both direction;Binocular camera
Outer ginseng includes spin matrix, translation vector and parallax.
5. a kind of recognition methods of the accurate reading identifying system of pointer instrument according to claim 4, feature exist
In: the step S3 specifically:
Step S31: enhancing processing is carried out to image using piecewise linear transform method;
Step S32: carrying out denoising to image using two dimension median filter, eliminates or reduces noise in collection process and is made
At influence;
Step S33: determining that optimal threshold is split according to the value of HSV, and with erosion operation, dilation operation, it is attached to reduce needle point
Nearly interference data;
Step S34: extracting the major division information of pointer meters, so that it is determined that dial starting and ending range, must take office
It anticipates 3 pairs of point pixel coordinates;
Step S35: gauge pointer is obtained by Hough transform, calculates and the intersection point of straight line, i.e. pointer is obtained by Hough transform
The pixel coordinate position of needle point in the picture.
6. a kind of recognition methods of the accurate reading identifying system of pointer instrument according to claim 5, feature exist
In: the step S4 specifically:
Step S41: level correction is carried out to binocular image according to the internal reference of video camera, and using Bouquet correcting algorithm;
Step S42: binocular detection algorithm is utilized, the depth information of needle point and the depth information of instrument board are obtained;
Step S43: pass through turning between 4 kinds of pixel coordinate system, image coordinate system, camera coordinates system and world coordinate system coordinate systems
Relationship is changed, according to any 3 pairs of point pixel coordinates and camera parallax D is obtained, using binocular detection algorithm, it is corresponding to calculate acquisition each point
Depth z, calculation formula is as follows:
Wherein, x, y, z are the coordinates of two-dimensional surface point corresponding points in three-dimensional coordinate system after calculating,fFor focal length,B
For the distance between optical center;
Step S44: plane S where going out instrument board according to 3 pairs of point pixel coordinate information reconstructions on pointer needle point point and instrument board builds
The space equation of vertical instrument panel plane, and spatial relationship is utilized, it is vertical on instrument panel space plan-position to obtain pointer needle point
The intersection point three-dimensional coordinate of projection.
7. a kind of recognition methods of the accurate reading identifying system of pointer instrument according to claim 7, feature exist
In: the step S6 specifically:
Step S61: using polar coordinates and cartesian coordinate system corresponding equation, limbus axis is converted into cartesian coordinate system;
Step S62: the ratio of range and the product of range are accounted for according to needle point present position, are standard pointed by current time pointer
Really reading t, available:
Wherein,X p For pointer needle point horizontal direction pixel coordinate value,X start For scale initial position horizontal direction pixel value,X end
For scale terminal position horizontal direction pixel value, range is the pointer instrument range.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811406269.4A CN109544628B (en) | 2018-11-23 | 2018-11-23 | Accurate reading identification system and method for pointer instrument |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811406269.4A CN109544628B (en) | 2018-11-23 | 2018-11-23 | Accurate reading identification system and method for pointer instrument |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109544628A true CN109544628A (en) | 2019-03-29 |
CN109544628B CN109544628B (en) | 2021-08-31 |
Family
ID=65849722
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811406269.4A Active CN109544628B (en) | 2018-11-23 | 2018-11-23 | Accurate reading identification system and method for pointer instrument |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109544628B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110414510A (en) * | 2019-07-26 | 2019-11-05 | 华中科技大学 | A kind of readings of pointer type meters bearing calibration |
CN111797909A (en) * | 2020-06-22 | 2020-10-20 | 上海工程技术大学 | Pointer instrument reading method based on machine vision |
CN112257676A (en) * | 2020-11-19 | 2021-01-22 | 南京天创电子技术有限公司 | Pointer instrument reading method and system and inspection robot |
CN112307887A (en) * | 2020-09-02 | 2021-02-02 | 国网浙江省电力有限公司嘉兴供电公司 | SF (sulfur hexafluoride)6Intelligent online gas pressure monitoring and early warning method and system |
CN112329770A (en) * | 2020-10-30 | 2021-02-05 | 江苏理工学院 | Instrument scale identification method and device |
CN112749598A (en) * | 2019-10-31 | 2021-05-04 | 中移物联网有限公司 | Information processing method, terminal and data platform of pointer type meter |
WO2021114521A1 (en) * | 2019-12-12 | 2021-06-17 | 常州机电职业技术学院 | Vision-based ten-bit rotary dial switch reset system and reset method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4582863B2 (en) * | 2000-05-22 | 2010-11-17 | 株式会社バンダイナムコゲームス | Stereoscopic image display device and information storage medium |
CN107145890A (en) * | 2017-05-02 | 2017-09-08 | 南通大学 | A kind of pointer dashboard automatic reading method under remote various visual angles environment |
CN107167169A (en) * | 2017-07-03 | 2017-09-15 | 吉林大学 | Readings of pointer type meters identification measuring method based on NI Vision Builder for Automated Inspection |
CN108009535A (en) * | 2017-11-21 | 2018-05-08 | 武汉中元华电科技股份有限公司 | A kind of simple pointer meter reading method based on machine vision |
-
2018
- 2018-11-23 CN CN201811406269.4A patent/CN109544628B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4582863B2 (en) * | 2000-05-22 | 2010-11-17 | 株式会社バンダイナムコゲームス | Stereoscopic image display device and information storage medium |
CN107145890A (en) * | 2017-05-02 | 2017-09-08 | 南通大学 | A kind of pointer dashboard automatic reading method under remote various visual angles environment |
CN107167169A (en) * | 2017-07-03 | 2017-09-15 | 吉林大学 | Readings of pointer type meters identification measuring method based on NI Vision Builder for Automated Inspection |
CN108009535A (en) * | 2017-11-21 | 2018-05-08 | 武汉中元华电科技股份有限公司 | A kind of simple pointer meter reading method based on machine vision |
Non-Patent Citations (4)
Title |
---|
BIAO YANG ET AL.: "Auto-recognition Method for Pointer-type Meter Based on Binocular Vision", 《JOURNAL OF COMPUTERS》 * |
孙浩晏: "基于机器视觉的指针式仪表读数识别系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
李稷芳: "指针式仪表自动读数技术研究", 《万方》 * |
赵焱 等: "基于双目立体视觉的指针式仪表判读算法", 《传感器与微系统( TRANSDUCER AND MICROSYSTEM TECHNOLOGIES)》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110414510A (en) * | 2019-07-26 | 2019-11-05 | 华中科技大学 | A kind of readings of pointer type meters bearing calibration |
CN110414510B (en) * | 2019-07-26 | 2021-10-08 | 华中科技大学 | Reading correction method for pointer instrument |
CN112749598A (en) * | 2019-10-31 | 2021-05-04 | 中移物联网有限公司 | Information processing method, terminal and data platform of pointer type meter |
WO2021114521A1 (en) * | 2019-12-12 | 2021-06-17 | 常州机电职业技术学院 | Vision-based ten-bit rotary dial switch reset system and reset method |
CN111797909A (en) * | 2020-06-22 | 2020-10-20 | 上海工程技术大学 | Pointer instrument reading method based on machine vision |
CN111797909B (en) * | 2020-06-22 | 2024-03-29 | 上海工程技术大学 | Pointer type instrument reading method based on machine vision |
CN112307887A (en) * | 2020-09-02 | 2021-02-02 | 国网浙江省电力有限公司嘉兴供电公司 | SF (sulfur hexafluoride)6Intelligent online gas pressure monitoring and early warning method and system |
CN112307887B (en) * | 2020-09-02 | 2023-04-21 | 国网浙江省电力有限公司嘉兴供电公司 | SF (sulfur hexafluoride) 6 Intelligent on-line monitoring and early warning method and system for gas pressure |
CN112329770A (en) * | 2020-10-30 | 2021-02-05 | 江苏理工学院 | Instrument scale identification method and device |
CN112329770B (en) * | 2020-10-30 | 2024-02-23 | 江苏理工学院 | Instrument scale identification method and device |
CN112257676A (en) * | 2020-11-19 | 2021-01-22 | 南京天创电子技术有限公司 | Pointer instrument reading method and system and inspection robot |
CN112257676B (en) * | 2020-11-19 | 2023-10-24 | 南京天创电子技术有限公司 | Pointer type instrument reading method and system and inspection robot |
Also Published As
Publication number | Publication date |
---|---|
CN109544628B (en) | 2021-08-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109544628A (en) | A kind of the accurate reading identifying system and method for pointer instrument | |
CN109741405B (en) | Depth information acquisition system based on dual structured light RGB-D camera | |
CN102376089B (en) | Target correction method and system | |
CN106599897B (en) | Readings of pointer type meters recognition methods and device based on machine vision | |
US20210319588A1 (en) | Method and Apparatus for Calibrating External Parameters of Image Acquisition Device, Device and Storage Medium | |
CN102364299B (en) | Calibration technology for multiple structured light projected three-dimensional profile measuring heads | |
CN103473771B (en) | A kind of camera scaling method | |
CN103743352B (en) | A kind of 3 D deformation measuring method based on polyphaser coupling | |
CN101311963B (en) | Round mark point center picture projection point position acquiring method for positioning video camera | |
Wang et al. | Single view metrology from scene constraints | |
CN109579695B (en) | Part measuring method based on heterogeneous stereoscopic vision | |
CN105931234A (en) | Ground three-dimensional laser scanning point cloud and image fusion and registration method | |
CN102221331B (en) | Measuring method based on asymmetric binocular stereovision technology | |
CN102901444B (en) | Method for detecting component size based on matching pursuit (MP) wavelet filtering and detecting system thereof | |
CN110672020A (en) | Stand tree height measuring method based on monocular vision | |
CN110223355B (en) | Feature mark point matching method based on dual epipolar constraint | |
CN103106661B (en) | Two, space intersecting straight lines linear solution parabolic catadioptric camera intrinsic parameter | |
CN103177442A (en) | Calibrating method for two-dimensional laser and camera without overlapped viewing fields | |
CN109920009B (en) | Control point detection and management method and device based on two-dimensional code identification | |
CN104036542A (en) | Spatial light clustering-based image surface feature point matching method | |
CN102930551B (en) | Camera intrinsic parameters determined by utilizing projected coordinate and epipolar line of centres of circles | |
CN103116892A (en) | Linear solving of video camera internal parameters by utilizing two intersected same circles and common tangent | |
CN109448043A (en) | Standing tree height extracting method under plane restriction | |
CN102930548A (en) | Method for linearly solving camera inner parameter by using two identical intersected ellipses | |
CN103438834A (en) | Hierarchy-type rapid three-dimensional measuring device and method based on structured light projection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |