CN113962961A - Screw loosening detection method based on high-speed machine - Google Patents
Screw loosening detection method based on high-speed machine Download PDFInfo
- Publication number
- CN113962961A CN113962961A CN202111235074.XA CN202111235074A CN113962961A CN 113962961 A CN113962961 A CN 113962961A CN 202111235074 A CN202111235074 A CN 202111235074A CN 113962961 A CN113962961 A CN 113962961A
- Authority
- CN
- China
- Prior art keywords
- camera
- screw
- image
- speed machine
- distance
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 19
- 238000003384 imaging method Methods 0.000 claims description 19
- 238000000034 method Methods 0.000 claims description 8
- 230000003287 optical effect Effects 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 239000004744 fabric Substances 0.000 abstract description 4
- 239000011295 pitch Substances 0.000 description 9
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification 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
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/04—Interpretation of pictures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
-
- 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
- G06T2207/20228—Disparity calculation for image-based rendering
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to the technical field of screw looseness detection, in particular to a screw looseness detection method based on a high-speed machine, which comprises the following steps: arranging a binocular camera, and carrying out color marking on the screw to be detected; acquiring images by using a binocular camera, matching feature points of the two acquired frames of images, calculating the distance from the matched feature points to the origin of an image coordinate system, and calculating the parallax values of a left camera and a right camera; establishing a geometric model according to the similar triangular function, and calculating the vertical distance H of the screw relative to the left camera and the right camera; the change of the vertical distance H between the screw and the camera light spot in the collected image data is analyzed in real time, so that the screw looseness can be found conveniently and timely, the weft yarn needle block is prevented from falling, and the cloth cover quality is ensured.
Description
Technical Field
The invention relates to the technical field of screw loosening detection, in particular to a screw loosening detection method based on a high-speed machine.
Background
The high-speed machine can be because long-time operation in the in-process of production, the screw of above-mentioned fixed weft yarn piece can become flexible to lead to the weft yarn needle piece to drop, can greatly influence the quality of cloth cover like this, consequently need propose a method based on vision to detect the screw of weft yarn needle piece and become flexible and detect now.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the screw looseness detection method based on the high-speed machine is used for detecting whether a screw for fixing a weft needle block on the high-speed machine is loosened.
In order to achieve the purpose, the invention adopts the technical scheme that: a screw loosening detection method based on a high-speed machine comprises the following steps:
arranging a binocular camera, and carrying out color marking on the screw to be detected;
acquiring images by using a binocular camera, matching feature points of the two acquired frames of images, calculating the distance from the matched feature points to the origin of an image coordinate system, and calculating the parallax values of a left camera and a right camera;
establishing a geometric model according to the characteristic matching relation between the camera coordinates and the image coordinates in binocular vision, and calculating the vertical distance H of the screw relative to the left camera and the right camera;
and analyzing the change of the vertical distance H between the screw and the camera light spot in the acquired image data in real time, and judging whether the screw is loosened.
Furthermore, before images are collected by using a binocular camera, the binocular is corrected, so that the left and right optical centers of the binocular camera are corrected to the same horizontal line, and polar lines are parallel. The horizontal position between the two images has been corrected.
Further, the matching of the feature points of the two frames of images collected by the left camera and the right camera is specifically as follows:
marking the screw to be detected with red;
establishing a pixel coordinate system for two frames of images, setting first image data as f (x, y) and second image data as g (x, y), and finding R in f (x, y)>200,G<80,B<80 and is noted as (x)1,y1) Finding R in g (x, y) in the same way>200,G<80,B<80 characteristic pointAnd is noted as (x)2,y2)。
Further, calculating the image coordinates of the feature points according to the pixel coordinates of the matched feature points, specifically:
setting the widths of two frames of images acquired by a left camera and a right camera to be m, and establishing an image coordinate system, wherein the transverse distance of the feature points in the two frames of images is as follows:
wherein u is1And u2The imaging points of the left camera and the right camera on the corresponding image plane are spaced from the transverse distance of the origin of the image coordinate system in the x-axis direction, x1And x2The distance between the left and right imaging points on the left and right image planes from the left edge of the image,the distance of the image center point from the image left edge.
Further, the parallax value calculation process of the left and right cameras is specifically as follows:
the coordinates of the corresponding points of the corrected image only have horizontal parallax in the x direction, and the vertical parallax in the y direction is 0, so that the parallax value is the difference of the abscissa of two pixel points in two frames of images, namely:
d=x1-x2 (3)
wherein: x is the number of1Andx2the distance between the left imaging point and the left imaging point on the left image plane and the distance between the left imaging point and the left imaging point on the right image plane are shown.
Further, the vertical distance H is calculated by:
by using the principle of similar triangles, we can obtain:
substituting equation (1), equation (2), and equation (3) into equation (4) can result in:
wherein f isxFocal length between two eyes of the camera, unit: pixel;
b is the base line between the two eyes of the camera, and the unit is: mm;
s is the conversion coefficient between the camera sensor pixel and mm, unit: mm/pixel;
u1and u2The imaging points of the left camera and the right camera on the corresponding image plane are away from the original point of the image coordinate system by the transverse distance in the x-axis direction.
Further, the pixel coordinate system is established at the upper left corner of the image data, and the image coordinate system is established at the center of the image data.
Further, whether the screw loosens or not is judged, and the method specifically comprises the following steps:
setting the initial vertical distance of the screw from the camera light spot as H when the high speed machine is in the initial state and the screw is completely screwed in0;
When the high-speed machine is in an operating state, the binocular camera collects image data every 1min, and the calculated real-time vertical distance is H;
calculating the vertical distance H and the initial vertical distance H in real time0Performing a difference calculation, i.e.
H0-H>hq (6)
When the inequality is established, judging that the screw is loosened;
wherein hq is the critical height allowed to lift when the screw starts to loosen, q is a proportionality coefficient and is recorded as a constant, H is the actual screwing depth of the screw thread, and H0Is the initial vertical distance and H is the real-time vertical distance.
Further, the value range of the proportionality coefficient q is 0.3-0.4.
The invention has the beneficial effects that: according to the invention, the color of the screw to be detected is marked, the feature point matching is carried out in the two collected frame images, the corresponding pixel point coordinates of the feature point in the left and right image data are extracted, the parallax value of the left and right cameras is calculated, the geometric model is established according to the similar triangular function, the vertical distance H of the screw relative to the left and right cameras is calculated, the change of the vertical distance H of the screw from the light spot of the camera in the collected image data is analyzed in real time, the screw looseness can be conveniently found in time, the weft yarn needle block is prevented from falling off, and the cloth cover quality is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a screw loosening detection method based on a high-speed machine according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the disparity values and distances according to an embodiment of the present invention;
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like as used herein are for illustrative purposes only and do not represent the only embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The screw loosening detection method based on the high-speed machine as shown in fig. 1 comprises the following steps:
s10: arranging a binocular camera, and carrying out color marking on the screw to be detected;
s20: acquiring images by using a binocular camera, matching feature points of the two acquired frames of images, calculating the distance from the matched feature points to the origin of an image coordinate system, and calculating the parallax values of a left camera and a right camera;
s30: establishing a geometric model according to the characteristic matching relation between the camera coordinates and the image coordinates in binocular vision, and calculating the vertical distance H of the screw relative to the left camera and the right camera;
s40: and analyzing the change of the vertical distance H between the screw and the camera light spot in the acquired image data in real time, and judging whether the screw is loosened.
According to the invention, the color of the screw to be detected is marked, the feature point matching is carried out in the two collected frame images, the corresponding pixel point coordinates of the feature point in the left and right image data are extracted, the parallax value of the left and right cameras is calculated, the geometric model is established according to the similar triangular function, the vertical distance H of the screw relative to the left and right cameras is calculated, the change of the vertical distance H of the screw from the light spot of the camera in the collected image data is analyzed in real time, the screw looseness can be conveniently found in time, the weft yarn needle block is prevented from falling off, and the cloth cover quality is ensured.
As shown in fig. 2, Image1 and Image2 are two images captured by two optical lenses at the left and right of a binocular camera, and a binocular stereo vision model is corrected to be an ideal parallel geometric model through epipolar line so that the two images are corrected to be in a horizontal position; o is1And O2 is the optical center of the optical lens, which collects images with a binocular cameraFirstly, correcting the two eyes to enable the left and right optical centers of the two-eye camera to be corrected to the same horizontal line, and polar lines are parallel; p is a characteristic point of the screw to be tested, u1And u2And establishing a pixel coordinate system at the upper left corner of the Image data and establishing an Image coordinate system at the center of the Image data for imaging points, namely pixel points, of the feature point P on the left and right Image1 and Image2 Image planes.
The method comprises the following steps of carrying out feature point matching on left and right image data shot by a binocular camera, finding a common point in the two frames of image data, namely an imaging point of the feature point on the two frames of images, wherein the matching of the feature points of the two frames of images collected by the left and right cameras is specifically as follows:
marking the screw to be detected with red;
establishing a pixel coordinate system for two frames of images, setting first image data as f (x, y) and second image data as g (x, y), and finding R in f (x, y)>200,G<80,B<80 and is noted as (x)1,y1) Finding R in g (x, y) in the same way>200,G<80,B<80 and is noted as (x)2,y2)。
Calculating the image coordinates of the feature points according to the pixel coordinates of the matched feature points, specifically:
setting the widths of two frames of images acquired by a left camera and a right camera to be m, and establishing an image coordinate system, wherein the transverse distance of the feature points in the two frames of images is as follows:
wherein u is1And u2The imaging points of the left camera and the right camera on the corresponding image plane are spaced from the transverse distance of the origin of the image coordinate system in the x-axis direction, x1And x2The distance between the left and right imaging points on the left and right image planes from the left edge of the image,the distance of the image center point from the image left edge.
The optical centers of the imaging devices corresponding to the two frames of images after epipolar correction are parallel and the optical axes are parallel, meanwhile, the heights of the pixel points in the two images are consistent, namely the vertical coordinates are the same, and at the moment, the parallax value is the difference value between the two parallel pixel points in the two frames of images after correction (when the vertical coordinates of the two pixel points are the same, the two pixel points are defined as parallel pixel points).
The parallax value calculation process of the left camera and the right camera specifically comprises the following steps: the coordinates of the corresponding points of the corrected image only have horizontal parallax in the x direction, and the vertical parallax in the y direction is 0, so that the parallax value is the difference of the abscissa of two pixel points in two frames of images, namely:
d=x1-x2 (3)
establishing a geometric model according to the characteristic matching relation between the camera coordinates and the image coordinates in binocular vision, and calculating a vertical distance H, namely obtaining the following by utilizing a similar triangle principle:
wherein f isxFocal length between two eyes of the camera, unit: pixel; b is the base line between the two eyes of the camera, and the unit is: mm; s is the conversion coefficient between the camera sensor pixel and mm, unit: mm/pixel;
substituting equation (1), equation (2), and equation (3) into equation (4) can result in:
from this, it is understood that the smaller the distance between the feature point P and the Image planes of the left and right images 1 and 2, that is, the larger the H, the larger the parallax value d of the feature point in the left and right cameras, and conversely, the larger H, the smaller the parallax value d.
The change of the vertical distance H from the screw to the camera light spot in the collected image data is analyzed in real time, whether the screw is loosened or not is judged, and the method specifically comprises the following steps:
setting the initial vertical distance of the screw from the camera light spot as H when the high speed machine is in the initial state and the screw is completely screwed in0;
When the high-speed machine is in an operating state, the binocular camera collects image data every 1min, and the calculated real-time vertical distance is H;
calculating the vertical distance H and the initial vertical distance H in real time0Performing a difference calculation, i.e.
H0-H>hq (6)
When the inequality is established, judging that the screw is loosened;
wherein hq is the critical height allowed to be lifted when the screw starts to be loosened, H is the actual screwing depth of the screw thread, and H0The initial vertical distance, H, the real-time vertical distance and q are proportional coefficients, and the value range of q is 0.3-0.4.
According to the force decreasing rule of the screw, the actual screwing depth h of the screw is 8-10P, for the screwing depth of the screw, the length of the first three screw pitches can bear more than 80% of force, when the screw thread bears axial force, the force borne by the 1 st screw pitch is the largest, the screw thread sequentially decreases downwards, the screw thread hardly bears force when reaching the 8 th-10 th screw pitches, the third screw pitch is the critical position of the screw loosening, therefore, when the current three screw pitch length is separated from the screw hole, the residual screw pitch bears the axial force, the screw loosens along with the residual screw pitch, and if the screw pitch P is 2, the screwing depth h is 16-20 mm, the corresponding third screw pitch length is 6mm, and the optimal critical height of the screw when loosening is achieved.
It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. A screw loosening detection method based on a high-speed machine is characterized by comprising the following steps:
arranging a binocular camera, and carrying out color marking on the screw to be detected;
acquiring images by using a binocular camera, matching feature points of the two acquired frames of images, calculating the distance from the matched feature points to the origin of an image coordinate system, and calculating the parallax values of a left camera and a right camera;
establishing a geometric model according to the characteristic matching relation between the camera coordinates and the image coordinates in binocular vision, and calculating the vertical distance H of the screw relative to the left camera and the right camera;
and analyzing the change of the vertical distance H between the screw and the camera light spot in the acquired image data in real time, and judging whether the screw is loosened.
2. The high-speed machine-based screw loosening detection method according to claim 1, wherein binocular correction is performed before images are collected by using a binocular camera, so that left and right optical centers of the binocular camera are corrected to the same horizontal line, and epipolar lines are parallel.
3. The screw loosening detection method based on the high-speed machine according to claim 1, wherein the matching of the feature points of the two frames of images collected by the left camera and the right camera is specifically as follows:
marking the screw to be detected with red;
establishing a pixel coordinate system for two frames of images, setting first image data as f (x, y) and second image data as g (x, y), and finding R in f (x, y)>200,G<80,B<80 and is noted as (x)1,y1) Finding R in g (x, y) in the same way>200,G<80,B<80 and is noted as (x)2,y2)。
4. The screw loosening detection method based on the high-speed machine according to claim 3, wherein image coordinates of the feature points are calculated according to pixel coordinates of matched feature points, specifically:
setting the widths of two frames of images acquired by a left camera and a right camera to be m, and establishing an image coordinate system, wherein the transverse distance of the feature points in the two frames of images is as follows:
wherein u is1And u2The imaging points of the left camera and the right camera on the corresponding image plane are spaced from the transverse distance of the origin of the image coordinate system in the x-axis direction, x1And x2The distance between the left and right imaging points on the left and right image planes from the left edge of the image,the distance of the image center point from the image left edge.
5. The screw loosening detection method based on the high-speed machine as claimed in claim 4, wherein the parallax value calculation process of the left and right cameras is specifically:
the coordinates of the corresponding points of the corrected image only have horizontal parallax in the x direction, and the vertical parallax in the y direction is 0, so that the parallax value is the difference of the abscissa of two pixel points in two frames of images, namely:
d=x1-x2 (3)
wherein: x is the number of1And x2The distance between the left imaging point and the left imaging point on the left image plane and the distance between the left imaging point and the left imaging point on the right image plane are shown.
6. The screw loosening detection method based on the high-speed machine according to claim 5, wherein the vertical distance H is calculated by:
by using the principle of similar triangles, we can obtain:
substituting equation (1), equation (2), and equation (3) into equation (4) can result in:
wherein f isxFocal length between two eyes of the camera, unit: pixel;
b is the base line between the two eyes of the camera, and the unit is: mm;
s is the conversion coefficient between the camera sensor pixel and mm, unit: mm/pixel;
u1and u2The imaging points of the left camera and the right camera on the corresponding image plane are away from the original point of the image coordinate system by the transverse distance in the x-axis direction.
7. The high-speed machine-based screw loosening detection method according to claim 6, wherein the pixel coordinate system is established at the upper left corner position of the image data, and the image coordinate system is established at the center position of the image data.
8. The screw loosening detection method based on the high-speed machine as claimed in claim 1, wherein the step of judging whether the screw is loosened specifically comprises the following steps:
setting the initial vertical distance of the screw from the camera light spot as H when the high speed machine is in the initial state and the screw is completely screwed in0;
When the high-speed machine is in an operating state, the binocular camera collects image data every 1min, and the calculated real-time vertical distance is H;
calculating the vertical distance H and the initial vertical distance H in real time0Performing a difference calculation, i.e.
H0-H>hq (6)
When the inequality is established, judging that the screw is loosened;
wherein hq is the critical height allowed to lift when the screw starts to loosen, q is a proportionality coefficient and is recorded as a constant, H is the actual screwing depth of the screw thread, and H0Is the initial vertical distance and H is the real-time vertical distance.
9. The high-speed machine-based screw loosening detection method according to claim 8, wherein the value range of the proportionality coefficient q is 0.3-0.4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111235074.XA CN113962961A (en) | 2021-10-22 | 2021-10-22 | Screw loosening detection method based on high-speed machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111235074.XA CN113962961A (en) | 2021-10-22 | 2021-10-22 | Screw loosening detection method based on high-speed machine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113962961A true CN113962961A (en) | 2022-01-21 |
Family
ID=79466389
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111235074.XA Pending CN113962961A (en) | 2021-10-22 | 2021-10-22 | Screw loosening detection method based on high-speed machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113962961A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116067555A (en) * | 2023-04-06 | 2023-05-05 | 西南交通大学 | Bolt looseness detection system and method for urban rail transit and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110246132A (en) * | 2019-06-23 | 2019-09-17 | 中车青岛四方车辆研究所有限公司 | Rail vehicle bolt looseness detection method and system |
CN111127401A (en) * | 2019-11-29 | 2020-05-08 | 西安工程大学 | Robot stereoscopic vision mechanical part detection method based on deep learning |
CN112991347A (en) * | 2021-05-20 | 2021-06-18 | 西南交通大学 | Three-dimensional-based train bolt looseness detection method |
CN113009878A (en) * | 2019-12-20 | 2021-06-22 | 中国科学院沈阳计算技术研究所有限公司 | Monocular vision-based moving workpiece attitude estimation method and device |
CN113034456A (en) * | 2021-03-18 | 2021-06-25 | 北京百度网讯科技有限公司 | Bolt looseness detection method, device, equipment and storage medium |
-
2021
- 2021-10-22 CN CN202111235074.XA patent/CN113962961A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110246132A (en) * | 2019-06-23 | 2019-09-17 | 中车青岛四方车辆研究所有限公司 | Rail vehicle bolt looseness detection method and system |
CN111127401A (en) * | 2019-11-29 | 2020-05-08 | 西安工程大学 | Robot stereoscopic vision mechanical part detection method based on deep learning |
CN113009878A (en) * | 2019-12-20 | 2021-06-22 | 中国科学院沈阳计算技术研究所有限公司 | Monocular vision-based moving workpiece attitude estimation method and device |
CN113034456A (en) * | 2021-03-18 | 2021-06-25 | 北京百度网讯科技有限公司 | Bolt looseness detection method, device, equipment and storage medium |
CN112991347A (en) * | 2021-05-20 | 2021-06-18 | 西南交通大学 | Three-dimensional-based train bolt looseness detection method |
Non-Patent Citations (2)
Title |
---|
JUNHUA SUN ET AL.: "A Fast Bolt-Loosening Detection Method of Running Train’s Key Components Based on Binocular Vision", 《IEEE ACCESS》 * |
刘志峰 等: "一种开放环境下的螺栓位姿测量方法", 《北京工业大学学报》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116067555A (en) * | 2023-04-06 | 2023-05-05 | 西南交通大学 | Bolt looseness detection system and method for urban rail transit and storage medium |
CN116067555B (en) * | 2023-04-06 | 2023-06-23 | 西南交通大学 | Bolt looseness detection system and method for urban rail transit and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101207833B (en) | Method for checking optical centre bias of lens of digital camera | |
CN110555878B (en) | Method and device for determining object space position form, storage medium and robot | |
US9332247B2 (en) | Image processing device, non-transitory computer readable recording medium, and image processing method | |
CN113689401A (en) | Method and device for detecting diameter of crystal bar of czochralski silicon single crystal furnace | |
CN109136912A (en) | A kind of laser melting coating defocusing amount on-line monitoring and negative-feedback state identification method | |
CN104760812A (en) | Monocular vision based real-time location system and method for products on conveying belt | |
CN113962961A (en) | Screw loosening detection method based on high-speed machine | |
CN113313116A (en) | Vision-based accurate detection and positioning method for underwater artificial target | |
CN105701809A (en) | Flat-field correction method based on line-scan digital camera scanning | |
US20120257816A1 (en) | Analysis of 3d video | |
JP3008875B2 (en) | Subject extraction device | |
CN113706522B (en) | Glass fiber surface paperboard chip detection method and device, storage medium and electronic equipment | |
CN111131801B (en) | Projector correction system and method and projector | |
KR20230108774A (en) | Vision inspection system for detecting defects of electrodes for secondary batteries using depth camera and stereo camera | |
CN116596987A (en) | Workpiece three-dimensional size high-precision measurement method based on binocular vision | |
CN107330877B (en) | Method and system for adjusting offset of optical fiber display area | |
CN115546072A (en) | Image distortion correction method | |
CN110148141A (en) | A kind of silk-screen optical filter small pieces detection method of counting and equipment | |
CN112837285B (en) | Edge detection method and device for panel image | |
CN108489469A (en) | A kind of monocular distance measuring device and method | |
CN111340891B (en) | Method and system for calibrating camera by using LED screen | |
KR102295987B1 (en) | Calibration method and apparatus of stereo camera module, computer readable storage medium | |
CN113393383B (en) | Splicing method for photographed images of double-depth camera | |
KR20110100568A (en) | Method and system for shroud nozzle centering guidance | |
CN117522784B (en) | Gear part image detection method and system based on tooth distance segmentation compensation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220121 |
|
RJ01 | Rejection of invention patent application after publication |