CN109544628B - Accurate reading identification system and method for pointer instrument - Google Patents
Accurate reading identification system and method for pointer instrument Download PDFInfo
- Publication number
- CN109544628B CN109544628B CN201811406269.4A CN201811406269A CN109544628B CN 109544628 B CN109544628 B CN 109544628B CN 201811406269 A CN201811406269 A CN 201811406269A CN 109544628 B CN109544628 B CN 109544628B
- Authority
- CN
- China
- Prior art keywords
- pointer
- instrument
- image
- dimensional
- camera
- 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.)
- Active
Links
Images
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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to an accurate reading identification system and method of a pointer instrument, which extracts a pointer point of the instrument through image processing, calculates and obtains three-dimensional information of the pointer point by using a binocular detection means and constructs an instrument panel plane, realizes repositioning of the instrument pointer according to a relative position relation, finishes correction before reading identification of the instrument pointer, and finally improves identification accuracy. The invention can solve the problems that when a certain height difference exists between the instrument pointer and the instrument plane, the projection position of the pointer on the dial plate in the image acquired when the acquisition equipment inclines is not consistent with the actual position, so that the reading accuracy is reduced and even the reading is wrong.
Description
Technical Field
The invention relates to the field of machine vision, in particular to an accurate reading identification system and method for a pointer instrument.
Background
With the rapid development of the instrument and meter technology, instruments and meters are widely applied to various industries, and the quantity of the instruments is large, and the demand is large. The use of pointer type instruments is still irreplaceable in many factories and traffic equipment in China. The pointer instrument has the advantages of being firm and durable, low in price, and capable of visually representing parameter changes through the fluctuation of the indication number (namely the swinging of the pointer), and has the prominent advantages that: for some special occasions, the mechanical pointer instrument can work well in cold places due to the anti-freezing property of the mechanical pointer instrument, can work underwater due to the waterproof property of the mechanical pointer instrument, and has the advantage that the mechanical pointer instrument can still work normally in severe environment due to the characteristics.
Some digital meters have built-in data transmission modules for automatically transmitting the meter reading to a control center, but the technology has to build in corresponding modules, is high in cost and cannot be used in fixed meters installed at present. Therefore, there is a need to develop an accurate reading identification system and method for a pointer instrument, which not only changes the defects of high labor intensity and low production efficiency of the traditional manual instrument identification, but also effectively reduces the manpower consumption in the detection process, saves the resources, and simultaneously eliminates the different reading results and the larger deviation caused by the different observers during manual reading without modifying the existing instrument. Therefore, instead of manual reading, we can use machine vision to capture an image with a camera and identify the reading of the position pointed by the pointer instrument in the image using an algorithm.
Most of the existing solutions are to process the meter image directly, reading directly the indication of the pointer in the picture. However, this type of solution presents problems when there is a significant difference in height between the pointer plane and the dashboard plane. This is due to the different viewing angles of the capturing devices, which results in different imaging positions of the pointer on the instrument plane, which means that the optical axis is tilted from the instrument center point when the optical axis of the image capturing device is not perpendicular to the instrument plane or not directly above the instrument center (i.e., the camera is tilted and the center of the optical axis of the camera is not aligned with the center of the dial). At this time, the acquired pointer image may have variations in view angle, scale, tilt, etc., so that there is a significant deviation in reading the value indicated by the pointer directly from the image. This problem causes erroneous recognition and reduced accuracy of the reading of the pointer instrument, and remains to be solved.
Disclosure of Invention
In view of the above, the present invention provides a system and a method for identifying an accurate reading of a pointer instrument, which solve the problem of deviation when the existing reading identification technology directly reads a value indicated by a pointer from an image.
In order to achieve the purpose, the invention adopts the following technical scheme:
an accurate reading identification system of a pointer instrument comprises an image acquisition module, an image preprocessing module, a three-dimensional correction module and an identification result output module which are sequentially connected;
the image acquisition module: the device is used for acquiring binocular images of the instrument dial plate and finishing stable transmission of image data;
an image preprocessing module: the device is used for preprocessing the image and extracting the main scales of the dial and the pixel coordinates of the pointer tip image;
the three-dimensional detection and correction module: the pointer position correction device is used for acquiring three-dimensional information of the needle point and realizing three-dimensional repositioning of the pointer needle point and pointer position correction before reading identification;
and an identification result output module: and calculating a reading result according to the position relation between the needle point of the pointer and the main scale.
Furthermore, the image acquisition module adopts a binocular camera consisting of two identical cameras.
An identification method of an accurate reading identification system of a pointer instrument comprises the following steps:
step S1: carrying out binocular calibration on a binocular camera to obtain internal parameters and external parameters of the binocular camera;
step S2, acquiring images through the calibrated binocular camera, realizing three-dimensional horizontal correction by using the acquired internal parameters, aligning the left and right images, and inputting the images to an image preprocessing module;
step S3: the initial image quality is improved through the image preprocessing module, the pixel coordinates of the dial main scale and the pointer needle point image are extracted and input to the three-dimensional detection module;
step S4: the three-dimensional detection correction module realizes instrument three-dimensionality by using a binocular detection algorithm, calculates the three-dimensional information of the pointer needle point and the three-dimensional information of the dial plate plane, and constructs the relative position relationship between the instrument panel plane and the pointer needle point;
step S5: the three-dimensional detection and correction module repositions the pointer on the plane of the instrument panel through the coordinate system conversion relation and the vertical projection so as to finish the correction of the position of the pointer;
step S6: and the recognition result output module calculates and outputs a final reading recognition result according to the extracted main scales and the coordinate position information of the needle point of the pointer.
Further, the internal reference of the binocular camera comprises focal lengths in two camera directions and a camera imaging center; the parameters of the binocular camera include a rotation matrix, a translation vector, and a disparity.
Further, the step S3 is specifically:
step S31, performing enhancement processing on the image by adopting a piecewise linear transformation method;
s32, performing denoising processing on the image by adopting two-dimensional median filtering to eliminate or reduce the influence caused by noise in the acquisition process;
step S33, determining an optimal threshold value according to the HSV value to carry out segmentation, and reducing interference data near the needle point by using corrosion operation and expansion operation;
step S34, extracting the main scale information of the pointer instrument, thereby determining the start and end range of the dial and obtaining any 3-point pixel coordinates;
and step S35, acquiring the instrument pointer through Hough transformation, and calculating the intersection point of the straight line obtained through Hough transformation, namely the pixel coordinate position of the pointer tip in the image.
Further, the step S4 specifically includes:
step S41, carrying out horizontal correction on the binocular image by using a Bouquet correction algorithm according to the internal reference of the camera;
step S42, obtaining the depth information of the needle point and the depth information of the instrument panel by using a binocular detection algorithm;
step S43, calculating the depth z corresponding to each point by using a binocular detection algorithm according to the obtained arbitrary 3-point pixel coordinates and the camera parallax D through the conversion relation among 4 coordinate systems of a pixel coordinate system, an image coordinate system, a camera coordinate system and a world coordinate system, wherein the calculation formula is as follows:
wherein, x, y and z are the coordinates of the corresponding points in the three-dimensional space coordinate system after the two-dimensional plane points are calculated.
And step S44, reconstructing a plane S where the instrument panel is located according to the pointer point and the coordinate information of the 3 pairs of pixels on the instrument panel, establishing a space equation of the instrument panel plane, and acquiring the three-dimensional coordinates of the intersection point of the pointer point vertically projected on the instrument panel space plane position by using the space relation.
Further, the step S5 specifically includes:
obtaining a mapping point of the pointer needle point on an image pixel plane according to the obtained three-dimensional coordinate of the intersection point of the pointer needle point vertically projected on the spatial plane position of the instrument panel;
further, the step S6 specifically includes:
step S61, converting the circular scale axis into a Cartesian coordinate system by using a polar coordinate and Cartesian coordinate system corresponding equation;
step S62: according to the product of the ratio of the position of the needle tip to the measuring range and the measuring range, namely the accurate reading t pointed by the pointer at the current moment, the following can be obtained:
wherein the content of the first and second substances,X p water as needle point of pointerThe pixel coordinate values in the square direction are,X start is the pixel value in the horizontal direction of the starting position of the scale,X end the pixel value of the end position of the scale in the horizontal direction is shown, and the range is the measuring range of the pointer instrument.
Compared with the prior art, the invention has the following beneficial effects:
the invention can solve the problems that when a certain height difference exists between the instrument pointer and the instrument plane, the projection position of the pointer on the dial plate in the image acquired when the acquisition equipment inclines is not consistent with the actual position, so that the reading accuracy is reduced and even the reading is wrong.
Drawings
FIG. 1 is a schematic diagram of a pointer instrument according to an embodiment of the present invention;
FIG. 2 is a flow chart of the method of the present invention;
FIG. 3 is a schematic diagram of binocular stereo vision imaging in an embodiment of the present invention;
FIG. 4 is a schematic diagram of pointer relocation in an embodiment of the present invention.
Detailed Description
The invention is further explained below with reference to the drawings and the embodiments.
Referring to fig. 1, the invention provides an accurate reading identification system for a pointer instrument, which comprises an image acquisition module, an image preprocessing module, a three-dimensional correction module and an identification result output module, which are connected in sequence; the image acquisition module: the device is used for acquiring binocular images of the instrument dial plate and finishing stable transmission of image data; an image preprocessing module: the device is used for preprocessing the image and extracting the main scales of the dial and the pixel coordinates of the pointer tip image; the three-dimensional detection and correction module: the pointer position correction device is used for acquiring three-dimensional information of the needle point and realizing three-dimensional repositioning of the pointer needle point and pointer position correction before reading identification; and an identification result output module: and calculating a reading result according to the position relation between the needle point of the pointer and the main scale.
In this embodiment, the image acquisition module is formed by two CMOS cameras with the same specification, which are arranged in parallel at a certain distance to form a binocular camera, and then the relative position of the binocular camera is not changed. For example, the pixel of the CMOS camera is 1080 × 720 pixels, and the data is transmitted to the computer through the USB3.0 interface.
In this embodiment, an identification method of an accurate reading identification system for a pointer instrument specifically includes the following steps:
step S1, before the measurement reading is formally started, calibration work needs to be performed on the binocular camera. In performing dual calibration, there are two common databases: a Matlab visual processing library and an OpenCV open source visual library; which encapsulates the available camera calibration algorithms. And (3) acquiring 20 calibration plate images in different postures by using a CMOS camera, and calibrating by using the software. Usually, the result of the calibration in Matlab is relatively stable, and the calibration in Matlab can be performed before the OpenCV calibration. Through binocular calibration, the following parameters can be obtained: camera internal parameters, distortion including radial distortion and tangential distortion, camera external parameters including 3 × 3 rotation matrix and 3 × 1 translation vector, and parallax between two camerasD. In effect, the internal parameter matrix is used for obtaining information of a lens and eliminating distortion so as to obtain an accurate image, and the external parameter matrix is used for obtaining a relation between a camera and world coordinates and finally measuring distance.
Step S2: after the calibration is completed, the image acquisition and identification process can be implemented. The two cameras are controlled by the computer to shoot pictures at the same time, and the image data are transmitted to the host computer through the data line to be processed by an OpenCV program. Internal reference of two cameras obtained by calibration work, including focal lengths in two directionsf x 、f y Center of camera imagingC x 、C y And (5) carrying out image stereo horizontal correction on the two images by using the equal parameters. The projection points of the object on the imaging planes of the two cameras meet the limit constraint theorem, and the corresponding points can be on the same horizontal plane.
And step S3, preprocessing the image, and processing the image after the image is acquired by the camera. Not only for improving image quality, but also for extracting useful information in the image. Firstly, processing a left image: (1) image enhancement using piecewise linear transformationAnd (5) performing strong treatment. (2) And denoising the initial image containing the noise by adopting two-dimensional median filtering, and eliminating or reducing the influence caused by the noise in the acquisition process. (3) And corrosion operation and expansion operation are applied to reduce interference data near the needle point. (4) Determining the optimal threshold value according to HSV value by using prior knowledge of instrument example, extracting main scale information of pointer instrument so as to determine the starting range and ending range of dial scale and obtain any three points (1)N x1-left ,N y1- left ）、（N x2- left ,N y2- left ）、（N x3- left , N y3- left ) (5) obtaining the instrument pointer through Hough transformation, and further calculating the intersection point of the straight lines obtained through Hough transformation, namely the pixel coordinate position of the pointer needle point required by people in the image (P x-left ,P y-left ). At this time, the program is obtained by a stereo matching algorithm, and three points (a, b, c, d, and d, corresponding to the left image are obtained in the right imageN x1-right ,N y1-right ）、（N x2-right ,N y2-right ）、（N x3-right , N y3-right ) And pointer tip pixel coordinate positionP x-right ,P y-right ). Here, it is very time-consuming to match the corresponding points in the two-dimensional space, and in order to reduce the search range for matching, we can use the epipolar constraint theory to reduce the matching of the corresponding points from two-dimensional search to one-dimensional search.
And step S4, entering a three-dimensional detection stage according to the determined points.
During the imaging process of the camera, there are four coordinate systems, respectively: a pixel coordinate system, an image coordinate system, a camera coordinate system, and a world coordinate system. As shown, the pixel coordinate system is with the upper left corner of the image as the originOAbscissa and ordinate (u, v) Respectively representing the column number and the row number of the pixel point in the image; (ii) the point where the origin of the image coordinate system is the intersection of the optical axis of the camera and the image planeu 0 ,v 0 ) The following relationship exists between the two coordinate systems:
expressed as a homogeneous matrix, then:
further, the conversion formula from the camera coordinate system to the image coordinate system is:
expressed as a homogeneous matrix (whereinSIs a scale factor, and is a function of,fas focal length):
the conversion relation from the world coordinate to the camera coordinate system is as follows:
and step S5, the repositioning of the needle point of the instrument pointer on the plane of the instrument panel is realized by means of binocular camera three-dimensional detection. (1) 3 pairs of points and camera parallax obtained according to the calculationDCalculating to obtain the depth corresponding to each point by using the binocular ranging principleZ. Reconstructing the plane of the dial by using the three-dimensional information of 3 pointsS 1 . Wherein the three-dimensional coordinates of the object can be determined by binocular stereo vision techniques, as shown in fig. 3OLAndORare the optical centers of the left and right cameras, their optical axes and their respective imaging planes. Assuming that the internal and external parameters of the two cameras are identical, the focal length isfOptical center of lightAt a distance (base line) ofBThe two cameras are on the same plane, so the Y-axis coordinates of their projection centers are equal. Spatial points at the same timeP(x,y,z)The imaging points on the two cameras are respectivelyP left AndP right。
introducing parametric parallaxDThe following can be obtained:
(2) obtaining the center of a circle on the plane of the dialO 2 Passing through the center of circle and perpendicular to the planeS 1 Perpendicular line ofL(ii) a Determining the tip of a pointerPAnd making a passing of the needle pointPOn the same dial planeS 1 Parallel planesS 2 . Plane surfaceS 2 Perpendicular to the lineLPoint of intersection ofO 2 Calculating and recordingO 2 PThe slope of (a); in the plane of the dialS 1 Go through the center of a circleO 1 Do and doO 2 PThe same slope, i.e. the true position of the hands with respect to the plane of the dial, is shown in fig. 4.
Step S6: reading identification of a pointer instrument: and (4) solving the mapping point of the space three-dimensional coordinate of the pointer tip after three-dimensional repositioning in the image pixel plane. After the pixel position of the pointer on the imaging plane is determined, the circular (arc) coordinate axis is converted into a polar coordinate system by using a polar coordinate and Cartesian coordinate system corresponding equation on the basis of the character and scale identification. The image pointer reading can be calculated according to the distance from the pointer to the nearest scale mark.
Wherein the content of the first and second substances,X p is the pixel coordinate value of the pointer needle point in the horizontal direction,X start is the pixel value in the horizontal direction of the starting position of the scale,X end the horizontal direction pixel values are the scale end positions,rangethe range of the pointer instrument is measured.
In this embodiment, a program for reading identification is written by using OpenCV, and the functions of the method described above can be implemented: (1) reading an effective picture obtained by shooting by a camera; (2) reading and recording the position of the needle point of the instrument pointer and the coordinate position of each scale from the picture by using an image processing algorithm; (3) converting two-dimensional coordinates of the needle point of the pointer in the image into three-dimensional coordinates with depth information by using a binocular detection algorithm; (4) and vertically projecting the needle point of the pointer to a three-dimensional plane where the instrument panel is located, and mapping the needle point with an image pixel plane. And according to the position of the needle point of the pointer and the scale position information, the function of accurate reading is realized.
The above description is only a preferred embodiment of the present invention, and all equivalent changes and modifications made in accordance with the claims of the present invention should be covered by the present invention.
Claims (4)
1. An identification method of an accurate reading identification system of a pointer instrument is characterized by comprising the following steps:
step S1: carrying out binocular calibration on a binocular camera to obtain internal parameters and external parameters of the binocular camera;
step S2, acquiring images through the calibrated binocular camera, realizing three-dimensional horizontal correction by using the acquired internal parameters, aligning the left and right images, and inputting the images to an image preprocessing module;
step S3: the initial image quality is improved through the image preprocessing module, the pixel coordinates of the dial main scale and the pointer needle point image are extracted and input to the three-dimensional detection module;
step S4: the three-dimensional detection correction module calculates three-dimensional information of the needle point of the pointer and three-dimensional information of the plane of the dial plate by using a binocular detection algorithm, and establishes a relative position relationship between the plane of the instrument panel and the needle point of the pointer to realize three-dimensionality of the instrument;
the step S4 specifically includes:
step S41, carrying out horizontal correction on the binocular image by using a Bouquet correction algorithm according to the internal reference of the camera;
step S42, obtaining the depth information of the needle point and the depth information of the instrument panel by using a binocular detection algorithm;
step S43, calculating the depth z corresponding to each point by using a binocular detection algorithm according to the obtained arbitrary 3-point pixel coordinates and the camera parallax D through the conversion relation among 4 coordinate systems of a pixel coordinate system, an image coordinate system, a camera coordinate system and a world coordinate system, wherein the calculation formula is as follows:
wherein, x, y and z are coordinates of corresponding points in a three-dimensional space coordinate system after the two-dimensional plane points are calculated, f is a focal length, and B is a distance between optical centers of two cameras;
step S44, reconstructing a plane S where the instrument panel is located according to the pointer point and the coordinate information of the 3 pairs of pixels on the instrument panel, establishing a space equation of the instrument panel plane, and acquiring the three-dimensional coordinates of the intersection point of the pointer point vertically projected on the instrument panel space plane position by using the space relation;
step S5: the three-dimensional detection and correction module relocates the pointer on the plane of the instrument panel through the coordinate system conversion relation and the vertical projection so as to finish the correction of the position information of the pointer;
step S6: and the recognition result output module calculates and outputs a final reading recognition result according to the extracted main scales and the coordinate position information of the needle point of the pointer.
2. The identification method of the accurate reading identification system of the pointer instrument as claimed in claim 1, wherein: the internal reference of the binocular camera comprises focal lengths in the x direction and the y direction of the camera and a camera imaging center; the parameters of the binocular camera include a rotation matrix, a translation vector, and a disparity.
3. The identification method of the accurate reading identification system of the pointer instrument as claimed in claim 2, characterized in that: the step S3 specifically includes:
step S31, performing enhancement processing on the image by adopting a piecewise linear transformation method;
s32, performing denoising processing on the image by adopting two-dimensional median filtering to eliminate or reduce the influence caused by noise in the acquisition process;
step S33, determining an optimal threshold value according to the HSV value to carry out segmentation, and reducing interference data near the needle point by using corrosion operation and expansion operation;
step S34, extracting the main scale information of the pointer instrument, thereby determining the start and end range of the dial and obtaining any 3-point pixel coordinates;
and step S35, acquiring the instrument pointer through Hough transformation, and calculating the intersection point of the straight line obtained through Hough transformation, namely the pixel coordinate position of the pointer tip in the image.
4. The identification method of the accurate reading identification system of the pointer instrument as claimed in claim 1, wherein: the step S6 specifically includes:
step S61, converting the circular scale axis into a Cartesian coordinate system by using a polar coordinate and Cartesian coordinate system corresponding equation;
step S62: according to the product of the ratio of the position of the needle tip to the measuring range and the measuring range, namely the accurate reading t pointed by the pointer at the current moment, the following can be obtained:
wherein, XpIs the pixel coordinate value, X, of the pointer tip in the horizontal directionstartIs the pixel value in the horizontal direction of the start position of the scale, XendThe pixel value of the end position of the scale in the horizontal direction is shown, and the range is the measuring range of the pointer instrument.
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 CN109544628A (en) | 2019-03-29 |
| CN109544628B true 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) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111103533B (en) * | 2019-12-12 | 2020-09-25 | 常州机电职业技术学院 | Reset method of ten-position rotary dial switch reset system based on 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 |
| 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 |
| CN112329770B (en) * | 2020-10-30 | 2024-02-23 | 江苏理工学院 | Instrument scale identification method and device |
| 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 |
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 |
|---|
| Auto-recognition Method for Pointer-type Meter Based on Binocular Vision;Biao Yang et al.;《Journal of computers》;20170430;第9卷(第4期);第787-793页 * |
| 基于双目立体视觉的指针式仪表判读算法;赵焱 等;《传感器与微系统( Transducer and Microsystem Technologies)》;20200702;第39卷(第7期);第119-126页 * |
| 基于机器视觉的指针式仪表读数识别系统研究;孙浩晏;《中国优秀硕士学位论文全文数据库 信息科技辑》;20150915(第9期);第I138-1413页 * |
| 指针式仪表自动读数技术研究;李稷芳;《万方》;20101222;第1-60页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109544628A (en) | 2019-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109544628B (en) | Accurate reading identification system and method for pointer instrument | |
| CN112894832B (en) | Three-dimensional modeling method, three-dimensional modeling device, electronic equipment and storage medium | |
| CN110276808B (en) | Method for measuring unevenness of glass plate by combining single camera with two-dimensional code | |
| US11521311B1 (en) | Collaborative disparity decomposition | |
| CN107154014B (en) | Real-time color and depth panoramic image splicing method | |
| CN109163657B (en) | Round target pose detection method based on binocular vision three-dimensional reconstruction | |
| CN109040736B (en) | Method, device, equipment and storage medium for calibrating spatial position of human eye | |
| CN110827392B (en) | Monocular image three-dimensional reconstruction method, system and device | |
| CN110672020A (en) | Stand tree height measuring method based on monocular vision | |
| JP2004127239A (en) | Method and system for calibrating multiple cameras using calibration object | |
| Kunz et al. | Hemispherical refraction and camera calibration in underwater vision | |
| KR101589167B1 (en) | System and Method for Correcting Perspective Distortion Image Using Depth Information | |
| CN111192235A (en) | Image measuring method based on monocular vision model and perspective transformation | |
| US11989827B2 (en) | Method, apparatus and system for generating a three-dimensional model of a scene | |
| CN109974659A (en) | A kind of embedded range-measurement system based on binocular machine vision | |
| CN116129037B (en) | Visual touch sensor, three-dimensional reconstruction method, system, equipment and storage medium thereof | |
| CN112184811A (en) | Monocular space structured light system structure calibration method and device | |
| Krutikova et al. | Creation of a depth map from stereo images of faces for 3D model reconstruction | |
| Morita et al. | Measurement in three dimensions by motion stereo and spherical mapping | |
| CN102881040A (en) | Three-dimensional reconstruction method for mobile photographing of digital camera | |
| US20220405968A1 (en) | Method, apparatus and system for image processing | |
| CN113379815A (en) | Three-dimensional reconstruction method and device based on RGB camera and laser sensor and server | |
| CN109493378B (en) | Verticality detection method based on combination of monocular vision and binocular vision | |
| CN111738971A (en) | Circuit board stereo scanning detection method based on line laser binocular stereo vision | |
| Chen et al. | Finding optimal focusing distance and edge blur distribution for weakly calibrated 3-D vision |
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 |