CN111354041A - System positioning method based on image recognition - Google Patents
System positioning method based on image recognition Download PDFInfo
- Publication number
- CN111354041A CN111354041A CN201811563341.4A CN201811563341A CN111354041A CN 111354041 A CN111354041 A CN 111354041A CN 201811563341 A CN201811563341 A CN 201811563341A CN 111354041 A CN111354041 A CN 111354041A
- Authority
- CN
- China
- Prior art keywords
- edge
- key slot
- mechanical structure
- coordinates
- control system
- 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
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
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0014—Image feed-back for automatic industrial control, e.g. robot with camera
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Robotics (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image recognition and positioning, and particularly discloses a system positioning method based on image recognition. The method comprises the following steps: 1. moving a mechanical structure to be positioned to a space calibration position, and obtaining a control system coordinate of the mechanical structure; 2. collecting an image of the tail end of a mechanical structure to be positioned when the tail end moves to a certain position, and recording the coordinates of a control system of the tail end of the mechanical structure; 3. obtaining the central position coordinates of the characteristic structure through the initial image; 4. acquiring images in real time according to the movement of the detection tool, analyzing to obtain the coordinates of the central position of the key slot, and calculating to obtain movement control parameters corresponding to single transverse and longitudinal pixel values according to the input value of movement control; 5. and extracting the center position coordinates of the edge of the key slot, obtaining the deviation from the center coordinates of the characterized key slot, and utilizing a control system to control the motion of machinery to complete system positioning. The method can shorten the calibration time of the mechanical system and greatly improve the operation efficiency of the system.
Description
Technical Field
The invention belongs to the technical field of image recognition and positioning, and particularly relates to a system positioning method based on image recognition.
Background
The reactor pressure vessel is used as a key component of a nuclear power station, and the radioactive environment of the reactor pressure vessel provides a requirement for remote automation of an ultrasonic inspection technology. The accuracy of the ultrasonic detection result is directly influenced by the motion precision of an automatic mechanical system, and the mechanical motion deviation needs to be continuously corrected before and during detection. At present, mechanical deviation is calibrated in a mode of observing marks on a mechanical motion assembly in a close range by artificial eyes in most nuclear power sites. This approach risks contamination by radioactive materials and is time consuming and inefficient.
Disclosure of Invention
The invention aims to provide a system positioning method based on image recognition, which can realize remote positioning of a mechanical system, shorten calibration time, avoid the risk of manual operation and improve the operation efficiency of the mechanical system.
The technical scheme of the invention is as follows: a system positioning method based on image recognition specifically comprises the following steps:
step 1, moving a mechanical structure to be positioned to a space calibration position, and obtaining a control system coordinate of the mechanical structure;
step 2, collecting an image when the tail end of the mechanical structure to be positioned moves to a certain position, taking the current position as a standard position, and recording the coordinates of a control system of the tail end of the mechanical structure;
step 3, obtaining the center position coordinates of the characteristic structure through the initial image;
step 4, acquiring images in real time according to the movement of the detection tool, analyzing to obtain coordinates of the center position of the key slot, and calculating to obtain movement control parameters corresponding to single transverse and longitudinal pixel values according to input values of movement control;
and 5, controlling the tail end of the mechanical structure to move, automatically identifying the key slot image, extracting the center position coordinates of the edge of the key slot when the key slot image appears in the visual field again, obtaining the deviation from the center coordinates of the representation key slot, and using a control system to control the movement of the machine to complete system positioning.
The step 3 specifically comprises:
step 3.1, obtaining the key slot edge information in the image by using an edge extraction algorithm;
step 3.2, performing expansion operation on the keyway edge information in the step 3.1 to obtain edge profile information with a more obvious mechanical structure to be positioned;
performing expansion operation by using structural elements, namely the n × n matrix of the key slot edge information obtained in the step 3.1, and acquiring edge profile information with a more obvious mechanical structure to be positioned;
3.3, acquiring the accurate position of the edge of the key slot in a longitudinal projection and transverse projection mode;
obtaining the accurate position of the edge of the key groove of the mechanical structure to be positioned by utilizing the conventional longitudinal projection and transverse projection modes;
and 3.4, acquiring the center coordinates of the representative key slot by using the edge median.
The specific steps of obtaining the accurate position of the edge of the key groove through longitudinal projection in the step 3.3 are as follows:
step 3.3.1, longitudinally projecting the edge contour information obtained by the expansion operation;
superposing numerical values on each row in a two-dimensional matrix of the edge contour information of the mechanical structure to be positioned, which is extracted by expansion operation, to obtain a one-dimensional array with the length equal to the number of rows and obtain a longitudinal projection of the edge contour of the mechanical structure to be positioned;
step 3.3.2, setting a window function, and carrying out a moving average curve on the longitudinal projection;
setting a Gaussian or rectangular window function according to the size n of a structural element used for expansion operation, and performing sliding average on the longitudinal projection to obtain a processed curve Cv;
step 3.3.3, acquiring the front and rear peak positions of the longitudinal projection sliding average curve, and acquiring the upper and lower edges of the corresponding characteristic structure;
and acquiring the pixel coordinates of the first peak position and the last peak position of the longitudinal projection moving average curve Cv by using a search algorithm, and acquiring the upper edge Pu and the lower edge Pd of the corresponding characteristic structure.
The step 3.3 of obtaining the accurate position of the edge of the key slot through transverse projection comprises the following specific steps:
step 3.3.4, performing transverse projection on the edge contour information obtained by the expansion operation;
superposing numerical values on each column in a two-dimensional matrix of the edge contour information of the mechanical structure to be positioned extracted by expansion operation to obtain a one-dimensional array with the length equal to the number of the columns and obtain a transverse projection of the edge contour of the mechanical structure to be positioned;
step 3.3.5, setting a window function, and carrying out a moving average curve on the transverse projection;
setting a Gaussian or rectangular window function according to the size n of the structural element used for the expansion operation, and performing sliding average on the transverse projection to obtain a processed curve Cu;
step 3.3.6, obtaining the front and rear peak positions of the transverse projection moving average curve, and obtaining the left and right edges of the corresponding characteristic structure;
and acquiring pixel coordinates of the first peak position and the last peak position of the transverse projection moving average curve Cu by utilizing a search algorithm, and acquiring the left edge Pl and the right edge Pr of the corresponding feature structure.
The specific steps of using the edge median value to obtain the center coordinates of the characterized key slot in the step 3.4 are as follows: characterizing the key slot center coordinate as P0 by using an edge median value, wherein the x coordinate axis value in the P0 pixel coordinate is (Pl + Pr)/2; the value of the y coordinate axis is (Pu + Pd)/2.
The step 5 specifically comprises:
step 5.1, controlling the mechanical tail end where the fixed-focus camera is located to move, acquiring images in real time, analyzing and identifying key slot images, extracting the center position coordinates of the edges of the key slots when the key slot images appear again, and obtaining position deviation;
and 5.2, controlling the movement of the machine by using the control system to enable the machine to reach the control system coordinate, and resetting the control system coordinate to complete system positioning.
The step 5.1 specifically comprises the following steps: when automatic positioning is implemented, the mechanical tail end where the fixed-focus camera is located is controlled to move, images are collected in real time, the key slot images are analyzed and recognized, when the key slot images appear in the visual field again, the key slot edge center position coordinate P1 is extracted and compared with the key slot edge center position coordinate P0, and the position deviation delta P (xy) is obtained; the step 5.2 specifically comprises the following steps: and controlling the mechanical motion delta P _ x Rx and delta P _ y Ry by using the control system, wherein the control system coordinate reached by the machine is Pos1, and the control system coordinate is reset to be Pos1, so that the system positioning can be completed.
The step 4 specifically comprises:
and detecting a tool for small-range circumferential or axial motion, acquiring images in real time, synchronously analyzing to obtain coordinates Pn (x, y) of the key slot center position, and obtaining motion control parameters corresponding to single transverse and longitudinal pixel values according to the input values of motion control, wherein the motion control parameters are recorded as Rx/Ry.
The step 1 specifically comprises:
and controlling the mechanical structure to move to a spatial calibration position by using a motion control system, and recording the control system coordinate of the mechanical structure as Pos0, wherein the spatial calibration position to which the mechanical structure moves is determined manually on site.
The step 2 specifically comprises:
and controlling the tail end of the mechanical structure to move to a certain position by using a motion control system, acquiring an image, setting the current position as a calibration position, and recording a control system coordinate Pos1 of the tail end of the mechanical structure, wherein the acquired image needs to enable the image of the characteristic structure to be clearly positioned in the middle of the view.
The invention has the following remarkable effects: the system positioning method based on image recognition can shorten the calibration time of a mechanical system and greatly improve the operation efficiency of the system.
Detailed Description
A system positioning method based on image recognition specifically comprises the following steps:
step 1, moving a mechanical structure to be positioned to a space calibration position, and obtaining a control system coordinate of the mechanical structure;
controlling the mechanical structure to move to a space calibration position by using a motion control system, and recording the control system coordinate of the mechanical structure as Pos0, wherein the space calibration position to which the mechanical structure moves is manually determined on site;
step 2, collecting an image when the tail end of the mechanical structure to be positioned moves to a certain position, taking the current position as a standard position, and recording the coordinates of a control system of the tail end of the mechanical structure;
controlling the tail end of the mechanical structure to move to a certain position by using a motion control system, collecting an image, setting the current position as a calibration position, and recording a control system coordinate Pos1 of the tail end of the mechanical structure, wherein the collected image needs to enable the image of the characteristic structure to be clearly positioned in the middle of a view;
step 3, obtaining the center position coordinates of the characteristic structure through the initial image;
step 3.1, obtaining the key slot edge information in the image by using an edge extraction algorithm;
step 3.2, performing expansion operation on the keyway edge information in the step 3.1 to obtain edge profile information with a more obvious mechanical structure to be positioned;
performing expansion operation by using structural elements, namely the n × n matrix of the key slot edge information obtained in the step 3.1, and acquiring edge profile information with a more obvious mechanical structure to be positioned;
3.3, acquiring the accurate position of the edge of the key slot in a longitudinal projection and transverse projection mode;
obtaining the accurate position of the edge of the key slot of the mechanical structure to be positioned, namely the pixel coordinate of the edge of the key slot, by utilizing the existing longitudinal projection and transverse projection modes;
step 3.3.1, longitudinally projecting the edge contour information obtained by the expansion operation;
superposing numerical values on each row in a two-dimensional matrix of the edge contour information of the mechanical structure to be positioned, which is extracted by expansion operation, to obtain a one-dimensional array with the length equal to the number of rows and obtain a longitudinal projection of the edge contour of the mechanical structure to be positioned;
step 3.3.2, setting a window function, and carrying out a moving average curve on the longitudinal projection;
setting a Gaussian or rectangular window function according to the size n of a structural element used for expansion operation, and performing sliding average on the longitudinal projection to obtain a processed curve Cv;
step 3.3.3, acquiring the front and rear peak positions of the longitudinal projection sliding average curve, and acquiring the upper and lower edges of the corresponding characteristic structure;
acquiring pixel coordinates of the first peak position and the last peak position of the longitudinal projection moving average curve Cv by using a search algorithm, and acquiring an upper edge Pu and a lower edge Pd of the corresponding characteristic structure;
step 3.3.4, performing transverse projection on the edge contour information obtained by the expansion operation;
superposing numerical values on each column in a two-dimensional matrix of the edge contour information of the mechanical structure to be positioned extracted by expansion operation to obtain a one-dimensional array with the length equal to the number of the columns and obtain a transverse projection of the edge contour of the mechanical structure to be positioned;
step 3.3.5, setting a window function, and carrying out a moving average curve on the transverse projection;
setting a Gaussian or rectangular window function according to the size n of the structural element used for the expansion operation, and performing sliding average on the transverse projection to obtain a processed curve Cu;
step 3.3.6, obtaining the front and rear peak positions of the transverse projection moving average curve, and obtaining the left and right edges of the corresponding characteristic structure;
acquiring pixel coordinates of a first peak position and a last peak position of a transverse projection moving average curve Cu by utilizing a search algorithm, and acquiring a left edge Pl and a right edge Pr of a corresponding feature structure;
step 3.4, obtaining a central coordinate of the representation key slot by using the edge median;
characterizing the key slot center coordinate as P0 by using an edge median value, wherein the x coordinate axis value in the P0 pixel coordinate is (Pl + Pr)/2; the value of the y coordinate axis is (Pu + Pd)/2;
step 4, acquiring images in real time according to the movement of the detection tool, analyzing to obtain coordinates of the center position of the key slot, and calculating to obtain movement control parameters corresponding to single transverse and longitudinal pixel values according to input values of movement control;
detecting a tool for small-range circumferential or axial motion, acquiring images in real time, synchronously analyzing to obtain coordinates Pn (x, y) of the key slot center position, and obtaining motion control parameters corresponding to single transverse and longitudinal pixel values according to the input value of motion control, and recording the parameters as Rx/Ry;
step 5, controlling the tail end of the mechanical structure to move, automatically identifying a key slot image, extracting the center position coordinates of the edge of the key slot when the key slot image appears in the visual field again, obtaining the deviation from the center coordinates of the representation key slot, and using a control system to control the movement of the machine to complete system positioning;
step 5.1, controlling the mechanical tail end where the fixed-focus camera is located to move, acquiring images in real time, analyzing and identifying key slot images, extracting the center position coordinates of the edges of the key slots when the key slot images appear again, and obtaining position deviation;
when automatic positioning is implemented, the mechanical tail end where the fixed-focus camera is located is controlled to move, images are collected in real time, the key slot images are analyzed and recognized, when the key slot images appear in the visual field again, the key slot edge center position coordinate P1 is extracted and compared with the key slot edge center position coordinate P0, and the position deviation delta P (xy) is obtained;
step 5.2, controlling the movement of the machine by using the control system to enable the machine to reach the control system coordinate, and resetting the control system coordinate to complete system positioning;
and controlling the mechanical motion delta P _ x Rx and delta P _ y Ry by using the control system, wherein the control system coordinate reached by the machine is Pos1, and the control system coordinate is reset to be Pos1, so that the system positioning can be completed.
Claims (10)
1. A system positioning method based on image recognition is characterized in that: the method specifically comprises the following steps:
step 1, moving a mechanical structure to be positioned to a space calibration position, and obtaining a control system coordinate of the mechanical structure;
step 2, collecting an image when the tail end of the mechanical structure to be positioned moves to a certain position, taking the current position as a standard position, and recording the coordinates of a control system of the tail end of the mechanical structure;
step 3, obtaining the center position coordinates of the characteristic structure through the initial image;
step 4, acquiring images in real time according to the movement of the detection tool, analyzing to obtain coordinates of the center position of the key slot, and calculating to obtain movement control parameters corresponding to single transverse and longitudinal pixel values according to input values of movement control;
and 5, controlling the tail end of the mechanical structure to move, automatically identifying the key slot image, extracting the center position coordinates of the edge of the key slot when the key slot image appears in the visual field again, obtaining the deviation from the center coordinates of the representation key slot, and using a control system to control the movement of the machine to complete system positioning.
2. The system positioning method based on image recognition as claimed in claim 1, wherein: the step 3 specifically comprises:
step 3.1, obtaining the key slot edge information in the image by using an edge extraction algorithm;
step 3.2, performing expansion operation on the keyway edge information in the step 3.1 to obtain edge profile information with a more obvious mechanical structure to be positioned;
performing expansion operation by using structural elements, namely the n × n matrix of the key slot edge information obtained in the step 3.1, and acquiring edge profile information with a more obvious mechanical structure to be positioned;
3.3, acquiring the accurate position of the edge of the key slot in a longitudinal projection and transverse projection mode;
obtaining the accurate position of the edge of the key groove of the mechanical structure to be positioned by utilizing the conventional longitudinal projection and transverse projection modes;
and 3.4, acquiring the center coordinates of the representative key slot by using the edge median.
3. The system positioning method based on image recognition as claimed in claim 2, wherein: the specific steps of obtaining the accurate position of the edge of the key groove through longitudinal projection in the step 3.3 are as follows:
step 3.3.1, longitudinally projecting the edge contour information obtained by the expansion operation;
superposing numerical values on each row in a two-dimensional matrix of the edge contour information of the mechanical structure to be positioned, which is extracted by expansion operation, to obtain a one-dimensional array with the length equal to the number of rows and obtain a longitudinal projection of the edge contour of the mechanical structure to be positioned;
step 3.3.2, setting a window function, and carrying out a moving average curve on the longitudinal projection;
setting a Gaussian or rectangular window function according to the size n of a structural element used for expansion operation, and performing sliding average on the longitudinal projection to obtain a processed curve Cv;
step 3.3.3, acquiring the front and rear peak positions of the longitudinal projection sliding average curve, and acquiring the upper and lower edges of the corresponding characteristic structure;
and acquiring the pixel coordinates of the first peak position and the last peak position of the longitudinal projection moving average curve Cv by using a search algorithm, and acquiring the upper edge Pu and the lower edge Pd of the corresponding characteristic structure.
4. The system positioning method based on image recognition as claimed in claim 2, wherein: the step 3.3 of obtaining the accurate position of the edge of the key slot through transverse projection comprises the following specific steps:
step 3.3.4, performing transverse projection on the edge contour information obtained by the expansion operation;
superposing numerical values on each column in a two-dimensional matrix of the edge contour information of the mechanical structure to be positioned extracted by expansion operation to obtain a one-dimensional array with the length equal to the number of the columns and obtain a transverse projection of the edge contour of the mechanical structure to be positioned;
step 3.3.5, setting a window function, and carrying out a moving average curve on the transverse projection;
setting a Gaussian or rectangular window function according to the size n of the structural element used for the expansion operation, and performing sliding average on the transverse projection to obtain a processed curve Cu;
step 3.3.6, obtaining the front and rear peak positions of the transverse projection moving average curve, and obtaining the left and right edges of the corresponding characteristic structure;
and acquiring pixel coordinates of the first peak position and the last peak position of the transverse projection moving average curve Cu by utilizing a search algorithm, and acquiring the left edge Pl and the right edge Pr of the corresponding feature structure.
5. The image recognition-based system positioning method according to claim 3 or 4, wherein: the specific steps of using the edge median value to obtain the center coordinates of the characterized key slot in the step 3.4 are as follows: characterizing the key slot center coordinate as P0 by using an edge median value, wherein the x coordinate axis value in the P0 pixel coordinate is (Pl + Pr)/2; the value of the y coordinate axis is (Pu + Pd)/2.
6. The system positioning method based on image recognition as claimed in claim 1, wherein: the step 5 specifically comprises:
step 5.1, controlling the mechanical tail end where the fixed-focus camera is located to move, acquiring images in real time, analyzing and identifying key slot images, extracting the center position coordinates of the edges of the key slots when the key slot images appear again, and obtaining position deviation;
and 5.2, controlling the movement of the machine by using the control system to enable the machine to reach the control system coordinate, and resetting the control system coordinate to complete system positioning.
7. The system positioning method based on image recognition as claimed in claim 6, wherein: the step 5.1 specifically comprises the following steps: when automatic positioning is implemented, the mechanical tail end where the fixed-focus camera is located is controlled to move, images are collected in real time, the key slot images are analyzed and recognized, when the key slot images appear in the visual field again, the key slot edge center position coordinate P1 is extracted and compared with the key slot edge center position coordinate P0, and the position deviation delta P (xy) is obtained; the step 5.2 specifically comprises the following steps: and controlling the mechanical motion delta P _ x Rx and delta P _ y Ry by using the control system, wherein the control system coordinate reached by the machine is Pos1, and the control system coordinate is reset to be Pos1, so that the system positioning can be completed.
8. The system positioning method based on image recognition as claimed in claim 1, wherein: the step 4 specifically comprises:
and detecting a tool for small-range circumferential or axial motion, acquiring images in real time, synchronously analyzing to obtain coordinates Pn (x, y) of the key slot center position, and obtaining motion control parameters corresponding to single transverse and longitudinal pixel values according to the input values of motion control, wherein the motion control parameters are recorded as Rx/Ry.
9. The system positioning method based on image recognition as claimed in claim 1, wherein: the step 1 specifically comprises:
and controlling the mechanical structure to move to a spatial calibration position by using a motion control system, and recording the control system coordinate of the mechanical structure as Pos0, wherein the spatial calibration position to which the mechanical structure moves is determined manually on site.
10. The system positioning method based on image recognition as claimed in claim 1, wherein: the step 2 specifically comprises:
and controlling the tail end of the mechanical structure to move to a certain position by using a motion control system, acquiring an image, setting the current position as a calibration position, and recording a control system coordinate Pos1 of the tail end of the mechanical structure, wherein the acquired image needs to enable the image of the characteristic structure to be clearly positioned in the middle of the view.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811563341.4A CN111354041A (en) | 2018-12-20 | 2018-12-20 | System positioning method based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811563341.4A CN111354041A (en) | 2018-12-20 | 2018-12-20 | System positioning method based on image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111354041A true CN111354041A (en) | 2020-06-30 |
Family
ID=71195336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811563341.4A Pending CN111354041A (en) | 2018-12-20 | 2018-12-20 | System positioning method based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111354041A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112529876A (en) * | 2020-12-15 | 2021-03-19 | 天津大学 | Method for detecting edge defects of contact lenses |
| CN113192081A (en) * | 2021-04-30 | 2021-07-30 | 北京达佳互联信息技术有限公司 | Image recognition method and device, electronic equipment and computer-readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103192386A (en) * | 2012-01-06 | 2013-07-10 | 沈阳新松机器人自动化股份有限公司 | Image-vision-based automatic calibration method of clean robot |
| JP2015094701A (en) * | 2013-11-13 | 2015-05-18 | 日本放送協会 | Mtf measurement device and mtf measurement program |
| CN105066884A (en) * | 2015-09-09 | 2015-11-18 | 大族激光科技产业集团股份有限公司 | Robot tail end positioning deviation correction method and system |
| CN105759720A (en) * | 2016-04-29 | 2016-07-13 | 中南大学 | Mechanical arm tracking and positioning on-line identification and correction method based on computer vision |
-
2018
- 2018-12-20 CN CN201811563341.4A patent/CN111354041A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103192386A (en) * | 2012-01-06 | 2013-07-10 | 沈阳新松机器人自动化股份有限公司 | Image-vision-based automatic calibration method of clean robot |
| JP2015094701A (en) * | 2013-11-13 | 2015-05-18 | 日本放送協会 | Mtf measurement device and mtf measurement program |
| CN105066884A (en) * | 2015-09-09 | 2015-11-18 | 大族激光科技产业集团股份有限公司 | Robot tail end positioning deviation correction method and system |
| CN105759720A (en) * | 2016-04-29 | 2016-07-13 | 中南大学 | Mechanical arm tracking and positioning on-line identification and correction method based on computer vision |
Non-Patent Citations (1)
| Title |
|---|
| 王鹏;彭琰举;李阿为;王莹;: "基于图像处理的数控机床运动控制系统", 现代电子技术, no. 12 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112529876A (en) * | 2020-12-15 | 2021-03-19 | 天津大学 | Method for detecting edge defects of contact lenses |
| CN112529876B (en) * | 2020-12-15 | 2023-03-14 | 天津大学 | Method for detecting edge defects of contact lenses |
| CN113192081A (en) * | 2021-04-30 | 2021-07-30 | 北京达佳互联信息技术有限公司 | Image recognition method and device, electronic equipment and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3404612B1 (en) | Monitoring object shape and deviation from design | |
| CN109800697B (en) | Transformer target detection and appearance defect identification method based on VGG-net style migration | |
| CN107263468B (en) | SCARA robot assembly method using digital image processing technology | |
| CN106897995B (en) | A kind of components automatic identifying method towards Automatic manual transmission process | |
| US20120303288A1 (en) | Mass spectrometry data analysis method and analysis device | |
| CN111354041A (en) | System positioning method based on image recognition | |
| CN111216124A (en) | Robot vision guiding method and device based on integration of global vision and local vision | |
| CN104316033A (en) | Visual inspection system for automobile parts | |
| CN113870217A (en) | Edge deviation vision measurement method based on machine vision and image detector | |
| CN113822810A (en) | Method for positioning workpiece in three-dimensional space based on machine vision | |
| CN114425776A (en) | Automatic labeling positioning and deviation rectifying method based on computer vision | |
| CN110688955A (en) | Building construction target detection method based on YOLO neural network | |
| CN103149087A (en) | Follow-up window and digital image-based non-contact real-time strain measurement method | |
| CN112037281B (en) | Visual system for guiding automatic hair follicle harvesting machine | |
| CN114235815A (en) | Method for detecting surface defects of outdoor electrical equipment of converter station based on scene filtering | |
| CN105092026A (en) | Automatic focusing method of pushbroom imaging spectrometer | |
| CN116862881A (en) | Multi-target real-time offset detection method based on image processing | |
| CN108705689A (en) | Heavy caliber precision optics plane of crystal microdefect reparation automatic tool preset process | |
| Yao et al. | High precision tuning device of microwave cavity filter based on hand-eye coordination | |
| Murray et al. | Automated video processing and image analysis software to support visual inspection of AGR cores | |
| CN103279953A (en) | Machine vision calibration system based on LabVIEW platform | |
| CN113752258A (en) | Machine vision-based shaft hole centering guide method for workpiece assembly process | |
| CN113843660A (en) | Numerical control machine tool workpiece detection method based on multi-line laser scanning | |
| Xue et al. | Method of electronic component location, grasping and inserting based on machine vision | |
| CN117047787B (en) | Water turbine top cover on-site robot programming method based on binocular structured light 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 |