CN113888572A - Visual plane hole measuring method - Google Patents
Visual plane hole measuring method Download PDFInfo
- Publication number
- CN113888572A CN113888572A CN202111104572.0A CN202111104572A CN113888572A CN 113888572 A CN113888572 A CN 113888572A CN 202111104572 A CN202111104572 A CN 202111104572A CN 113888572 A CN113888572 A CN 113888572A
- Authority
- CN
- China
- Prior art keywords
- detected
- round hole
- image
- pixel
- ellipse
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000000007 visual effect Effects 0.000 title claims abstract description 14
- 238000001914 filtration Methods 0.000 claims abstract description 19
- 230000002146 bilateral effect Effects 0.000 claims abstract description 13
- 238000001514 detection method Methods 0.000 claims abstract description 12
- 238000003708 edge detection Methods 0.000 claims abstract description 8
- 238000013507 mapping Methods 0.000 claims abstract description 6
- 239000011521 glass Substances 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 7
- 238000000691 measurement method Methods 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 4
- 208000004350 Strabismus Diseases 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 2
- 238000005259 measurement Methods 0.000 description 34
- 238000010586 diagram Methods 0.000 description 7
- 230000003190 augmentative effect Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000002474 experimental method Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 229910000838 Al alloy Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 208000013860 rhabdoid tumor of the kidney Diseases 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/08—Measuring arrangements characterised by the use of optical techniques for measuring diameters
- G01B11/12—Measuring arrangements characterised by the use of optical techniques for measuring diameters internal diameters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20028—Bilateral filtering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a visual plane hole measuring method, which comprises the steps of firstly, obtaining a rough positioning circle center coordinate and a rough positioning diameter by adopting Hough circle detection; acquiring an image around the to-be-detected round hole by taking the rough positioning circle center as a center, and acquiring an image contour around the rough positioning circle center through bilateral filtering and Canny edge detection; then fitting the image contour into an ellipse by using a least square method; calculating the length of the oval major axis pixel as the pixel diameter of the round hole to be detected, and sensing the camera and the depth through the environment of the cameraThe camera carries out space mapping to obtain an environment mesh grid, then the environment mesh grid is used as a collision layer, and the distance between the circle center of the to-be-detected circular ring and the origin of the camera coordinate system is obtained by collision between a cursor point and a grid map; finally obtaining the aperture W of the final round hole to be detectedd. The invention has short measuring period and simple operation, and effectively improves the working efficiency.
Description
Technical Field
The invention belongs to the technical field of computer vision, and particularly relates to a plane hole measuring method.
Background
At present, in the production and manufacturing links of the aircraft industry, circular hole parts are widely used, and the production quality and the assembly precision of the circular hole parts are strictly controlled when the circular hole parts are small as gaskets and when the circular hole parts are large as reinforced wall plates with circular holes. In the quality inspection process of circular hole parts at the present stage, the circular hole aperture is generally measured in a contact measurement mode, and the adopted quantity comprises a digital display caliper, a plug gauge and the like; aiming at the dimension measurement in the manual assembly process of the round hole type part, a contact type measurement mode is also adopted; for some precisely manufactured round hole parts of an airplane, a contact type three-coordinate measuring machine is generally adopted for dimension measurement, or non-contact visual measurement is adopted for dimension measurement.
Among the measurement methods related to the various aperture measurement links, the three-coordinate measurement is the highest in precision, but the method has no general applicability due to higher equipment manufacturing and maintenance cost and disjointed measurement process and industrial production.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a visual plane hole measuring method, which comprises the steps of firstly, obtaining a rough positioning circle center coordinate and a rough positioning diameter by adopting Hough circle detection; acquiring an image around the to-be-detected round hole by taking the rough positioning circle center as a center, and acquiring an image contour around the rough positioning circle center through bilateral filtering and Canny edge detection; then fitting the image contour into an ellipse by using a least square method; calculating the length of a long-axis pixel of the ellipse as the pixel diameter of the round hole to be detected, performing space mapping through an environment sensing camera and a depth camera of a camera to obtain an environment mesh grid, and colliding a cursor point with a grid map by using the environment mesh grid as a collision layer to obtain the distance between the center of the circle of the round ring to be detected and the origin of a coordinate system of the camera; finally obtain the final productAperture W of round hole to be detectedd. The invention has short measuring period and simple operation, and effectively improves the working efficiency.
The technical scheme adopted by the invention for solving the technical problem comprises the following steps:
step 1: roughly positioning an image which is acquired by VR glasses and contains a round hole to be detected by adopting Hough circle detection to obtain a rough positioning circle center coordinate and a rough positioning diameter of the round hole to be detected in a pixel coordinate system;
the circular hole to be detected is an ellipse in squint, and the ellipse equation is expressed as formula (1):
wherein x is0、y0Respectively representing the abscissa and the ordinate of the midpoint of the two focuses, theta represents the included angle between the long axis and the x axis, and a and b respectively represent the long axis and the short axis of the ellipse;
step 2: then, taking the rough positioning circle center as a center, taking a long axis which is twice of the ellipse in the formula (1) as the image width to obtain an image around the round hole to be detected, and then obtaining an image outline around the rough positioning circle center through bilateral filtering and Canny edge detection;
and step 3: fitting the image contour obtained in the step 2 into an ellipse by using a least square method;
and 4, step 4: calculating the length of the ellipse major axis pixel as the pixel diameter e of the round hole to be detectedlThe intersection point of the major axis and the minor axis of the ellipse is used as the circle center pixel coordinate of the round hole to be detected;
and 5: calibrating a camera of the VR glasses by using a Zhangyingyou calibration method to perform internal reference calibration;
step 6: spatial mapping is carried out through an environment perception camera and a depth camera of a camera to obtain an environment mesh grid, so that environment simulation, three-dimensional reconstruction and feature matching are realized, and modeling and digitization of the real world are realized;
and 7: performing man-machine interaction with VR glasses by using a staring function, and projecting a cursor point on a plane where the round hole to be detected is located;
and 8: the environment mesh grid is used as a collision layer, and the distance Z between the circle center of the ring to be detected and the origin of the camera coordinate system is obtained by collision between the cursor point and the grid map0；
And step 9: obtaining the aperture W of the final round hole to be detecteddComprises the following steps:
Wd＝0.8766-2.393Z0+0.0178el+1.724Z0 2+1.001Z0·el (1)
when parameter elAnd Z0When determined, the only diameter W of the circular hole can be determinedd。
Preferably, the VR glasses are HoloLens mixed reality head mounted displays.
Preferably, the bilateral filtering method specifically includes:
bilateral filtering is compromise processing of spatial proximity and pixel value similarity of an image, and simultaneously considers spatial information and gray level similarity to achieve the purpose of edge-preserving and denoising; the specific formula is as follows:
wherein
p, q-pixel point coordinates of the center point and the surrounding points of the template window;
Ip,Iq-pixel values of the template window center point and surrounding points;
σs(p-q) is the spatial distance weight of the pixel point;
σr(|Ip-Iq|) -pixel value weight of an image point.
The invention has the following beneficial effects:
1. the method is non-contact measurement, can well avoid part damage in the measurement process aiming at round hole parts with higher surface quality requirements, and has good applicability;
2. the method is applied to the detection of the round hole in the assembly process, and the size of the round hole is measured by wearing VR virtual glasses, so that the time for manually measuring by using a measuring tool is shortened, hands are successfully liberated, the influence of human factors is reduced, and the working efficiency is improved.
3. The method has the advantages of short measurement period and simple operation, does not need operations such as zero setting and the like after the initialization and repeated measurement, and effectively improves the working efficiency.
4. Adopt VR glasses plane hole measuring module easy operation, only need wear the back and visualize the round hole and keep static relatively and can measure, this module has good suitability to the measuring environment of many visual angles, has reduced the requirement of visual measurement to the environment.
Drawings
FIG. 1 is a flow chart of the present invention.
Fig. 2 is a frame diagram of a HoloLens planar aperture measurement module.
Fig. 3 is a diagram of a HoloLens vision measurement model.
FIG. 4 is a graph of the effect of Gaussian filtering, median filtering and bilateral filtering; (a) gaussian filtering, (b) median filtering, (c) bilateral filtering.
FIG. 5 is a comparison graph of edge detection performed by a Sobel operator, a LOG operator and a Canny operator; wherein (a) the input image, (b) the Sobel operator, (c) the LOG operator, and (d) the Canny operator.
Fig. 6 is a diagram showing the detection effect of the round hole of the test part, wherein (a) is a front view, (b) a view angle is deflected to fig. 1, (c) a view angle is deflected to fig. 2, and (d) a view angle is deflected to fig. 3.
Fig. 7 is an augmented reality framework diagram.
Fig. 8 is a plot of the HoloLens sensor position distribution according to an embodiment of the present invention.
Fig. 9 is a spatial mesh grid established by a spatial mapping function according to an embodiment of the present invention.
FIG. 10 is a schematic view of Unity simulating HoloLens gaze rays according to an embodiment of the present invention.
FIG. 11 is a schematic diagram of a Unity simulation HoloLens wall cursor according to an embodiment of the present invention.
Fig. 12 is a HoloLens module display in accordance with an embodiment of the present invention.
Fig. 13 shows a measurement sample according to an embodiment of the present invention.
FIG. 14 is a graph of measurement results according to an embodiment of the present invention.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
The invention is researched aiming at a mobile vision measurement method, designs a mobile measurement module which can be deployed on VR glasses, solves the problem of aperture measurement facing to a plane round hole, provides a plane round hole aperture measurement method based on Hough transform by combining image processing and augmented reality technologies, and has better applicability.
As shown in fig. 1 and 2, a visual plane hole measuring method includes the steps of:
step 1: roughly positioning an image which is acquired by VR glasses and contains a round hole to be detected by adopting Hough circle detection to obtain a rough positioning circle center coordinate and a rough positioning diameter of the round hole to be detected in a pixel coordinate system;
the circular hole to be detected is an ellipse in squint, and the ellipse equation is expressed as formula (1):
step 2: then, taking the rough positioning circle center as a center, taking the two times of the rough positioning diameter as the image width to obtain an image around the round hole to be detected, and then obtaining an image outline around the rough positioning circle center through bilateral filtering and Canny edge detection;
and step 3: fitting the image contour obtained in the step 2 into an ellipse by using a least square method;
and 4, step 4: calculating the length of the ellipse major axis pixel as the pixel diameter e of the round hole to be detectedlThe intersection point of the major axis and the minor axis of the ellipse is used as the circle center pixel coordinate of the round hole to be detected;
and 5: calibrating a camera of the VR glasses by using a Zhangyingyou calibration method to perform internal reference calibration;
step 6: as shown in fig. 8, an environment mesh grid is obtained by performing spatial mapping on an environment sensing camera and a depth camera of a camera, so as to realize environment simulation, three-dimensional reconstruction and feature matching, and realize real world modeling and digitization;
and 7: performing man-machine interaction with VR glasses by using a staring function, and projecting a cursor point on a plane where the round hole to be detected is located;
and 8: as shown in fig. 9, the environment mesh grid is used as a collision layer, and the distance Z between the center of the circle to be detected and the origin of the camera coordinate system is obtained by collision between the cursor point and the grid map0；
And step 9: obtaining the aperture W of the final round hole to be detecteddComprises the following steps:
Wd＝0.8766-2.393Z0+0.0178el+1.724Z0 2+1.001Z0·el (1)
when parameter elAnd Z0When determined, the only diameter W of the circular hole can be determinedd。
The specific embodiment is as follows:
as shown in fig. 7, which is an augmented reality frame diagram, the method of the present invention can obtain the required depth data through the augmented reality function of HoloLnes, and can complete the aperture calculation work of the measurement module by combining with the image processing technology.
1. Opening the HoloLens, opening the plane hole measuring module, and when the ray distance is displayed on the UI interface, indicating that the map initialization is finished and the measuring operation can be executed;
2. clicking a button for displaying a measurement picture in a module function interface presented by HoloLens, adjusting the head pose in the picture after starting picture display so that the measurement center point is contained in the outline of the round hole to be measured, starting to perform circle center rough positioning, and successfully acquiring image outline data after detecting the circle center;
2.1, carrying out graying processing on the image to reduce useless information;
2.2 circle center coarse positioning is carried out by adopting Hough circle detection;
2.3, adopting bilateral filtering denoising, as shown in FIG. 4; and 4, the bilateral filtering effect is best.
2.4 adopting canny operator edge detection; comparing fig. 5, the Canny edge detection works best.
2.5 adopting a findContours function to search the contour and outputting a two-dimensional point set of pixels in the image;
2.6 fitting the two-dimensional point sets into an ellipse by using a least square method;
3. after image contour data are successfully acquired, the UI first displays the diameter of the round hole subjected to Hough detection, meanwhile, contour fitting is carried out on the image, the contour and the central point of the round hole are displayed, the measuring central point is overlapped with the elliptic central point subjected to contour fitting, the relative stillness is kept for about 1s, and the background server can conveniently carry out aperture calculation;
4. in the design of the plane hole measuring module based on the HoloLens, an embedded module program is adopted, an image processing program, an augmented reality program and an aperture calculation program are integrated in Unity3D software, and are released as a UWP (Universal Windows Platform, Windows Universal Platform) application program and are deployed in a HoloLens of the HoloLens generation of the HoloLens to carry out plane empty hole diameter measuring experiment operation.
The HoloLens parameter applies an image processing low power mode of 896 x 504 resolution, 30FPS (30 frames per second transport), horizontal field of view (H-FOV)48 degrees.
The choice was Unity3D personal edition (2019.2.8f1), Visual Studio Community 2019 (16.7.2).
The programming work can be completed through C # language, open source computer vision library OpenCV and augmented reality development tool MRTK.
4.1 building a module frame;
4.2 module interface design, namely a UI interface designed by using Unity3D and an operation interface in the HoloLens glasses;
4.3 the method is realized by program, after the framework of the HoloLens plane hole measuring method is determined, corresponding functions are realized by writing the program by using a corresponding algorithm.
For background data processing, writing a code file through C # language, and adding the code into related components of a design interface to realize corresponding functions. Table 1 describes the functions or components called to implement the various framework programs.
TABLE 1 implementation of functions or Components called by various framework programs
5. After the calculation is finished, the UI display interface displays the background calculation result, the measurement result is reserved, and if the next measurement operation is not executed, the HoloLens continuously displays the measurement data.
Fig. 3 is a view of a HoloLens vision measurement model, wherein A, B, C is the original point of the coordinate system of three types of cameras, and the three types of coordinate systems represent the camera viewing angles including all the viewing angles of the measurement module described in the present invention, which are measured by the circular hole of the HoloLens worn by the user, and the center of the default circular hole passes through the main optical axis of the camera. The view angle A is the ideal state view angle of the traditional model, but when an observer is in the view angle B or C for observation, the observed circular hole imaging is different from the formal projection, and the imaging can be changed into an ellipse with corresponding distortion. The imaging ellipses are different due to different camera visual angles, but the major axes of all the imaging ellipses are equal to the diameter of a real circular hole. Ellipse detection is further performed on the basis of circle detection.
Fig. 12 is a HoloLens module display. The following are shown: object distance/m, pixel coordinate system diameter/pixel, real calculation size/m, Hough rough positioning round hole diameter and measurement deflection angle.
Fig. 13 is a measurement sample, fig. 6 is a diagram illustrating the detection effect of the circular hole of the test part, wherein (a) is a front view, (b) the view angle is deflected to fig. 1, (c) the view angle is deflected to fig. 2, and (d) the view angle is deflected to fig. 3; fig. 14 is a graph of the measurement results.
Experiment step 1: the method comprises the following steps of preparing an experiment, wherein a sample piece is an aluminum alloy round hole test piece, a vernier caliper and a HoloLens, and the sample piece is measured by the vernier caliper, and the diameters of four groups of round holes are respectively 11.50mm, 18.00mm, 27.50mm and 35.00 mm.
Experiment step 2: and (3) wearing HoloLens to carry out a measurement experiment on the test piece, and recording five items of data of the diameter of the coarse positioning hole, the size of the long axis of ellipse fitting, the ray distance of the current measurement frame, the included angle between the ray and the plane normal and the finally calculated diameter data. The results are shown in tables 2 to 5:
table 2: hole 11.5mm
TABLE 3 holes 18.00mm
TABLE 4 holes 27.50mm
TABLE 5 holes 35.00mm
From the above data, one can obtain:
1. the result of multi-angle measurement tends to be stable, and the measurement module is proved to have better applicability to deflection visual angles;
and 2, errors measured by the HoloLens measuring module are all maintained below 1%, and the measured errors are less than or equal to 0.30mm, so that the measuring requirements in the assembling and detecting process are met.
Claims (3)
1. A visual planar bore measurement method, comprising the steps of:
step 1: roughly positioning an image which is acquired by VR glasses and contains a round hole to be detected by adopting Hough circle detection to obtain a rough positioning circle center coordinate and a rough positioning diameter of the round hole to be detected in a pixel coordinate system;
the circular hole to be detected is an ellipse in squint, and the ellipse equation is expressed as formula (1):
wherein x is0、y0Respectively representing the abscissa and the ordinate of the midpoint of the two focuses, theta represents the included angle between the long axis and the x axis, and a and b respectively represent the long axis and the short axis of the ellipse;
step 2: then, taking the rough positioning circle center as a center, taking a long axis which is twice of the ellipse in the formula (1) as the image width to obtain an image around the round hole to be detected, and then obtaining an image outline around the rough positioning circle center through bilateral filtering and Canny edge detection;
and step 3: fitting the image contour obtained in the step 2 into an ellipse by using a least square method;
and 4, step 4: calculating the length of the ellipse major axis pixel as the pixel diameter e of the round hole to be detectedlThe intersection point of the major axis and the minor axis of the ellipse is used as the circle center pixel coordinate of the round hole to be detected;
and 5: calibrating a camera of the VR glasses by using a Zhangyingyou calibration method to perform internal reference calibration;
step 6: spatial mapping is carried out through an environment perception camera and a depth camera of a camera to obtain an environment mesh grid, so that environment simulation, three-dimensional reconstruction and feature matching are realized, and modeling and digitization of the real world are realized;
and 7: performing man-machine interaction with VR glasses by using a staring function, and projecting a cursor point on a plane where the round hole to be detected is located;
and 8: the environment mesh grid is used as a collision layer, and the distance Z between the circle center of the ring to be detected and the origin of the camera coordinate system is obtained by collision between the cursor point and the grid map0；
And step 9: obtaining the aperture W of the final round hole to be detecteddComprises the following steps:
Wd＝0.8766-2.393Z0+0.0178el+1.724Z0 2+1.001Z0·el (1)
when parameter elAnd Z0When determined, the only diameter W of the circular hole can be determinedd。
2. A visual planometer measurement method as claimed in claim 1, wherein the VR glasses are HoloLens mixed reality head mounted displays.
3. A visual planar hole measurement method as claimed in claim 1, wherein said bilateral filtering method is as follows:
bilateral filtering is compromise processing of spatial proximity and pixel value similarity of an image, and simultaneously considers spatial information and gray level similarity to achieve the purpose of edge-preserving and denoising; the specific formula is as follows:
wherein
p, q-pixel point coordinates of the center point and the surrounding points of the template window;
Ip,Iq-pixel values of the template window center point and surrounding points;
σs(p-q) is the spatial distance weight of the pixel point;
σr(|Ip-lq|) -pixel value weight of an image point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111104572.0A CN113888572A (en) | 2021-09-22 | 2021-09-22 | Visual plane hole measuring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111104572.0A CN113888572A (en) | 2021-09-22 | 2021-09-22 | Visual plane hole measuring method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113888572A true CN113888572A (en) | 2022-01-04 |
Family
ID=79010141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111104572.0A Pending CN113888572A (en) | 2021-09-22 | 2021-09-22 | Visual plane hole measuring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113888572A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114719772A (en) * | 2022-03-22 | 2022-07-08 | 奕目(上海)科技有限公司 | Method and system for acquiring inclined angle of inclined hole |
| WO2023226481A1 (en) * | 2022-05-26 | 2023-11-30 | 之江实验室 | Monocrystalline-silicon diameter measurement method and apparatus based on chord length ratio of concentric ellipses |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002183739A (en) * | 2000-12-14 | 2002-06-28 | Tsubakimoto Chain Co | Ellipse detection method and ellipse detection device |
| CN102061517A (en) * | 2010-12-13 | 2011-05-18 | 浙江长兴众成电子有限公司 | Czochralski single crystal silicon diameter measurement method |
| CN111062940A (en) * | 2019-12-31 | 2020-04-24 | 西南交通大学 | Screw positioning and identifying method based on machine vision |
| CN111121655A (en) * | 2019-12-18 | 2020-05-08 | 浙江大学 | Visual detection method for pose and aperture of coplanar workpiece with equal large hole patterns |
| WO2021138990A1 (en) * | 2020-01-10 | 2021-07-15 | 大连理工大学 | Adaptive detection method for checkerboard sub-pixel corner points |
-
2021
- 2021-09-22 CN CN202111104572.0A patent/CN113888572A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002183739A (en) * | 2000-12-14 | 2002-06-28 | Tsubakimoto Chain Co | Ellipse detection method and ellipse detection device |
| CN102061517A (en) * | 2010-12-13 | 2011-05-18 | 浙江长兴众成电子有限公司 | Czochralski single crystal silicon diameter measurement method |
| CN111121655A (en) * | 2019-12-18 | 2020-05-08 | 浙江大学 | Visual detection method for pose and aperture of coplanar workpiece with equal large hole patterns |
| CN111062940A (en) * | 2019-12-31 | 2020-04-24 | 西南交通大学 | Screw positioning and identifying method based on machine vision |
| WO2021138990A1 (en) * | 2020-01-10 | 2021-07-15 | 大连理工大学 | Adaptive detection method for checkerboard sub-pixel corner points |
Non-Patent Citations (2)
| Title |
|---|
| 郭成成;郑守住;: "一种有效的影像中椭圆形目标提取方法", 电子测量技术, no. 04, 15 April 2017 (2017-04-15) * |
| 闫笑颜;林群煦;倪费杰;吴月玉;: "基于机器视觉盘纸直径和宽度尺寸检测研究", 机械工程师, no. 05, 10 May 2020 (2020-05-10) * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114719772A (en) * | 2022-03-22 | 2022-07-08 | 奕目(上海)科技有限公司 | Method and system for acquiring inclined angle of inclined hole |
| CN114719772B (en) * | 2022-03-22 | 2024-02-02 | 奕目(上海)科技有限公司 | Method and system for acquiring inclined angle of inclined hole |
| WO2023226481A1 (en) * | 2022-05-26 | 2023-11-30 | 之江实验室 | Monocrystalline-silicon diameter measurement method and apparatus based on chord length ratio of concentric ellipses |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111414798B (en) | Head posture detection method and system based on RGB-D image | |
| CN110276808B (en) | Method for measuring unevenness of glass plate by combining single camera with two-dimensional code | |
| CN109949899B (en) | Image three-dimensional measurement method, electronic device, storage medium, and program product | |
| Xu et al. | Line structured light calibration method and centerline extraction: A review | |
| CN110866969B (en) | Engine blade reconstruction method based on neural network and point cloud registration | |
| CN107025663B (en) | Clutter scoring system and method for 3D point cloud matching in vision system | |
| CN107155341B (en) | Three-dimensional scanning system and frame | |
| CN110689579A (en) | Rapid monocular vision pose measurement method and measurement system based on cooperative target | |
| CN111932678B (en) | Multi-view real-time human motion, gesture, expression and texture reconstruction system | |
| JP2004127239A (en) | Method and system for calibrating multiple cameras using calibration object | |
| CN113888572A (en) | Visual plane hole measuring method | |
| CN112686877B (en) | Binocular camera-based three-dimensional house damage model construction and measurement method and system | |
| CN101697233A (en) | Structured light-based three-dimensional object surface reconstruction method | |
| CN109272555B (en) | External parameter obtaining and calibrating method for RGB-D camera | |
| CN109448043A (en) | Standing tree height extracting method under plane restriction | |
| JP2021168143A (en) | System and method for efficiently scoring probe in image by vision system | |
| CN111602177B (en) | Method and apparatus for generating a 3D reconstruction of an object | |
| CN110276791B (en) | Parameter-configurable depth camera simulation method | |
| CN110608685A (en) | Object size rapid measurement method based on raspberry pie | |
| JP2019185730A (en) | Image processing device, image processing method, and program | |
| CN115330712A (en) | Intelligent quality inspection method and system for prefabricated components of fabricated building based on virtual-real fusion | |
| CN114998448A (en) | Method for calibrating multi-constraint binocular fisheye camera and positioning space point | |
| CN114037987A (en) | Intelligent identification method, device, medium and equipment for scrap steel | |
| CN112802208A (en) | Three-dimensional visualization method and device in terminal building | |
| CN117218192A (en) | Weak texture object pose estimation method based on deep learning and synthetic data |
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 |