CN109118529B - Screw hole image rapid positioning method based on vision - Google Patents
Screw hole image rapid positioning method based on vision Download PDFInfo
- Publication number
- CN109118529B CN109118529B CN201810915432.3A CN201810915432A CN109118529B CN 109118529 B CN109118529 B CN 109118529B CN 201810915432 A CN201810915432 A CN 201810915432A CN 109118529 B CN109118529 B CN 109118529B
- Authority
- CN
- China
- Prior art keywords
- image
- screw hole
- region
- area
- template
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G06T7/344—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving models
-
- 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
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a screw hole image rapid positioning method based on vision, which comprises screw hole region rapid search based on parallel operation and screw hole position accurate positioning of a local region, wherein the screw hole region rapid search based on the parallel operation mainly comprises selection of an interested region template, division of image blocks, parallel region image template matching and optimal region selection; the accurate positioning of the screw hole position of the local area mainly comprises the steps of local area rapid ellipse detection and optimal central point selection. The method can be effectively applied to the robot hand on the production line, meets the positioning real-time performance and accuracy, and can realize real-time plug-in by the robot hand, thereby solving the problems of quick detection and accurate positioning of the screw holes of the electric appliance back plate on the production line in the assembly process of the household electrical appliance products, informing the robot hand of the positioning result of the screw holes, completing the automatic assembly of the screws, realizing the improvement of the production efficiency and saving the labor resources.
Description
Technical Field
The invention relates to the technical field of robots and artificial intelligence, in particular to a screw hole image rapid positioning method based on vision.
Background
In the manufacturing process of mechanical and electronic equipment, each part needs to be assembled, the assembly process flow directly influences the equipment manufacturing efficiency, and the mounting screws are the most basic assembly process. The efficiency of screw assembly directly affects the efficiency of manufacturing. The screw machine based on visual positioning is used for automatically screwing the screw holes of the back plates and the main plates of the household appliances and various electrical appliances on a production line, so that the labor is greatly saved; the screw hole image real-time detection and accurate positioning technology based on vision directly influences the performance of the screw machine.
Chinese patent application No. 201711237446.6 discloses a screw positioning and screw locking and unlocking method based on visual servo. The method comprises the steps that a screw hole positioning and screw locking and unlocking device based on visual servo is used for positioning screw holes and locking and unlocking screws, the screw hole positioning and screw locking and unlocking device based on visual servo comprises a visual measurement module and a control execution module, and data transmission and communication are carried out between the visual measurement module and the control execution module through a network; the vision measuring module comprises a binocular camera, a coarse positioning camera and a laser dotter; the control execution module comprises a mechanical arm unit and a computer, wherein the mechanical arm unit comprises a large-torque tightening gun, a mechanical arm small arm, a mechanical arm large arm, a mechanical arm control box, a base and a screw sleeve; the high-torque tightening gun, the screw sleeve, the binocular camera and the laser dotter are located at the tail end of the mechanical arm unit.
The method comprises the steps of acquiring an image of a target screw or a screw hole on a workpiece to be overhauled by means of a coarse positioning camera, obtaining coordinates of the image, and driving servo control; calculating the difference between the current position of the large-torque tightening gun or the screw sleeve or the binocular camera or the laser dotting device and the target position, judging whether the difference is within a threshold range, and if not, performing repeated iteration. The method has relatively complex flow, needs repeated iteration to reach the required precision, and is difficult to meet the precision of real-time monitoring and positioning on a production line.
Chinese patent application No. 201510352012.5 discloses a virtual screw positioning system and method, the method includes: shooting a global picture, and calculating position information of all screws or screw holes; the micro control unit transmits the position information of the screw or the screw hole to be locked to the controller; the controller moves the camera to a photographing position of a screw or a screw hole to be locked; triggering a camera to take a picture by the micro control unit; calculating again to obtain the corrected position information of the screw or the screw hole to be locked, and transmitting the corrected position information to the controller; the servo motor controls the screw machine to move to the position of the screw or the screw hole to be locked according to the second control information.
The method adopts a virtual instrument positioning technology, has the defect of low positioning precision compared with a coordinate calibration technology, and the whole process of the method is only positioned twice, namely rough positioning and secondary positioning respectively, so that the positioning times are too few, and the positioning precision is difficult to ensure.
Chinese patent application No. 201610625090.2 discloses a machine vision positioning method for automatic screw assembly. The method is characterized by adopting optical method as metering equipment, and comprises the following steps: inputting data, acquiring an image, preprocessing the image, carrying out Hough transformation, calibrating a camera, and calculating the position;
the method searches for a circle in an image by using a Hough transform method, and outputs the circle by taking the center of the circle as a positioning point. Firstly, the global Hough transform method is adopted to carry out circle detection on the whole image, so that a large amount of time is consumed, and the online real-time detection and positioning effects are difficult to achieve; secondly, the back plate and the like on the production line are conveyed to the position below the camera through the conveying belt, certain deviation exists in the position and the angle of the back plate and the like, the circular screw hole is inclined to be in an elliptical shape after imaging, and certain deviation possibly exists in the precision of the back plate and the like through traditional Hough circle detection.
Disclosure of Invention
The invention aims to overcome the defects in the background technology, and provides a screw hole image rapid positioning method based on vision, so as to solve the problems of rapid detection and accurate positioning of the screw hole of the electric appliance backboard on a production line in the process of assembling a household electric appliance, inform a robot hand of the positioning result of the screw hole, finish the automatic assembly of the screw and improve the production efficiency.
In order to achieve the technical effects, the invention adopts the following technical scheme:
a screw hole image rapid positioning method based on vision specifically comprises the following steps:
A. a screw hole area fast searching step based on parallel operation;
B. accurately positioning the position of a screw hole in a local area;
the screw hole image rapid positioning method based on vision can be used for real-time positioning of screw holes such as electric appliance back plates and the like on a production line and real-time plug-in of the screw holes by means of a robot hand, so that the purposes of saving labor resources and improving production efficiency are achieved.
Further, the step a specifically includes the following steps:
A1. selecting a region-of-interest template;
A2. dividing the image into blocks;
A3. matching parallel regional image templates;
A4. and selecting an optimal area.
Further, the step a1 specifically includes the following steps:
a1.1, calibrating a camera before carrying a machine carrying a CCD camera, and sending an instruction to the CCD camera by an upper computer to obtain an original picture;
a1.2, fixing a station, acquiring an original picture for multiple times through a CCD camera, and screening the regular and clear picture with a small angle as a reference template through comparing the pictures;
a1.3, intercepting a local interested area and storing the local interested area into a template picture;
a1.4, performing angle rotation on the template pictures, horizontally generating a pair of template pictures at intervals of two degrees by plus and minus 4 degrees, and generating 5 template pictures; and when the upper computer is electrified, the upper computer program firstly reads the template picture in the hard disk into the memory.
Further, the selection of the local region of interest in step a1.3 requires a circumscribed circle covering a complete screw hole, and has uniqueness.
Further, the step a2 specifically includes the following steps:
a2.1, recording a two-dimensional array of an original Image acquired by a CCD camera as Image [ N, M ], wherein N is the height of the Image, and M is the width of the Image;
a2.2, after the station is fixed, calculating the maximum external radius R of the screw hole by combining the actual size imaging size of the screw hole; in practice, after a station is fixed, a back plate is deviated when being transmitted to a specified position through a conveyor belt, so that offset exists after a camera images, and therefore the method calculates the maximum external radius R of the screw hole by combining the actual size of the screw hole;
a2.3, equally dividing an original Image [ N, M ] into four Image blocks, wherein the upper left corner region is marked as Image [1: N/2,1: M/2], the upper right corner region is marked as Image [1: N/2, M/2: M ], the lower left corner region is marked as Image [ N/2: N,1: M/2], and the lower right corner region is marked as Image [ N/2: N, M/2: M ];
a2.4, expanding each area block according to the maximum radius R, wherein the expanded areas are as follows: the upper left corner region is marked as Image [1: N/2+ R,1: M/2+ R ], the upper right corner region is marked as Image [1: N/2+ R, M/2-R: M ], the lower left corner region is marked as Image [ N/2-R: N,1: M/2+ R ], the lower right corner region is marked as Image [ N/2-R: N, M/2-R: M ]; in the invention, each area block is expanded according to the maximum radius R, so that the screw hole area is completely positioned in a certain block area.
Further, in the step A2.2, the maximum circumscribed radius R < min { N/2, M/2}, where min represents N, M to be the minimum value.
Further, the step a3 is specifically:
a3.1, if the number of image blocks is L and the number of templates is K, starting the threads/processes is L x K, and the size of a photographed image ROI area is basically fixed at a fixed station but has small-angle rotation;
and A3.2, respectively matching the template image and the block area image by using a matching algorithm in each thread/process in a thread/process parallel processing mode.
Further, the matching algorithm in step a3.2 may select an average absolute difference algorithm, an absolute error sum algorithm, an error sum of squares algorithm, an average error sum of squares algorithm, a normalized product correlation algorithm, a sequential similarity detection algorithm, and a Hadamard transform algorithm.
Further, the step a4 specifically includes the following steps:
a4.1, combining the matching results of each region, arranging the results from large to small according to the correlation, and selecting the region with the maximum correlation as a final matching region;
and A4.2, recording the matched block area and the position, obtaining the coordinates of the upper left corner of the matched area in the original picture through inverse operation, and intercepting the matched area.
Further, the step B specifically includes the following steps:
B1. local area rapid ellipse detection: performing rapid ellipse detection on the matched local area to obtain the values of the coordinates of the central point, the major axis and the minor axis of the ellipse;
B2. selecting an optimal central point: and selecting the ellipse with the minimum distance error as an optimal detection result by combining the actually measured radius of the station screw hole and the values of the long axis and the short axis after the rapid ellipse detection, and recording the center of the ellipse as the center of the screw hole for final detection.
Compared with the prior art, the invention has the following beneficial effects:
the invention relates to a screw hole image rapid positioning method based on vision, which comprises the steps of screw hole region rapid search based on parallel operation and screw hole position accurate positioning of a local region, wherein the screw hole region rapid search based on the parallel operation mainly comprises the selection of an interested region template, the division of image blocks, the matching of parallel region image templates and the selection of an optimal region; the accurate positioning of the screw hole position of the local area mainly comprises the steps of local area rapid ellipse detection and optimal central point selection;
the vision-based screw hole image rapid positioning method is realized by dividing the traditional screw hole detection into two flows of screw hole rapid detection and local area precise screw hole positioning; the method has the advantages that the rapid detection adopts a parallel operation mode, the accurate positioning adopts a rapid ellipse center detection mode to carry out, the method can be effectively applied to a mechanical hand on a production line, the real-time performance and the accuracy of the positioning are met, the real-time plug-in is carried out on the mechanical hand, the rapid detection and the accurate positioning of the screw hole of the electric appliance back plate on the production line can be realized in the assembly process of household electrical products, the result of the screw hole positioning is informed to the mechanical hand, the automatic assembly of the screw is completed, the production efficiency can be improved, and the labor resources are saved.
Drawings
FIG. 1 is a schematic flow chart of the method for quickly positioning a screw hole image based on vision according to the present invention.
Detailed Description
The invention will be further elucidated and described with reference to the embodiments of the invention described hereinafter.
Example (b):
as shown in fig. 1, a method for fast positioning a screw hole image based on vision includes two parts, namely fast searching of a screw hole region based on parallel operation and accurate positioning of a screw hole position of a local region.
A first part: screw hole area fast search based on parallel operation
The camera is calibrated before a machine carrying the CCD camera is carried, and the upper computer sends an instruction to the CCD camera to obtain an original picture.
The first step is as follows: selection of region of interest template
The method comprises the steps Of fixing a station, obtaining an original picture for many times through a CCD camera, selecting a local Region Of Interest (ROI for short), hereinafter called ROI Region for short, and selecting an outer circle which needs to cover a complete screw hole and has uniqueness.
Meanwhile, the template pictures are rotated by an angle, horizontally rotated by plus or minus 4 degrees, and a pair of template pictures is regenerated every two degrees to generate 5 template pictures; when the upper computer is powered on, the upper computer program firstly reads the template picture in the hard disk into the memory.
The second step is that: image block division
The two-dimensional array of the original Image collected by the CCD camera is recorded as Image [ N, M ], wherein N is the height of the Image, and M is the width of the Image.
After the station is fixed, the back plate is conveyed to a designated position through the conveying belt to have deviation, so that offset exists after camera imaging, and the maximum external radius R of the screw hole can be calculated by combining the actual size of the screw hole imaging; under normal conditions, R < min { N/2, M/2}, and min represents the minimum value.
Equally dividing an original Image [ N, M ] into four Image blocks, wherein the upper left corner region is marked as Image [1: N/2,1: M/2], the upper right corner region is marked as Image [1: N/2, M/2: M ], the lower left corner region is marked as Image [ N/2: N,1: M/2], and the lower right corner region is marked as Image [ N/2: N, M/2: M ];
meanwhile, each area block is expanded according to the maximum radius R, so that the screw hole area is completely positioned in a certain block area;
the expanded regions are: the upper left region is marked as Image [1: N/2+ R,1: M/2+ R ], the upper right region is marked as Image [1: N/2+ R, M/2-R: M ], the lower left region is marked as Image [ N/2-R: N,1: M/2+ R ], and the lower right region is marked as Image [ N/2-R: N, M/2-R: M ]. In this embodiment, N is 1920, M is 1280, and R is 42.
The third step: parallel region image template matching
Under a fixed station, the size of the ROI of the photographed image is basically fixed, but a small-angle rotation exists. The number of image blocks is L, the number of templates is K, and the number of thread/process starting is L x K; matching the template image and the block area image in each thread/process through a matching algorithm by means of thread/process parallel processing;
in the embodiment, the time for image matching and searching is greatly saved by using a parallel regional image template matching method.
Specifically, the matching algorithm may be selected from, but not limited to, mean absolute difference algorithm (MAD), sum of absolute difference algorithm (SAD), sum of squared error algorithm (SSD), mean sum of squared error algorithm (MSD), normalized product correlation algorithm (NCC), Sequential Similarity Detection Algorithm (SSDA), and Hadamard transform algorithm (SATD).
For example, in this embodiment, taking the NCC algorithm as an example, the matching degree between the template graph and the original graph is calculated by the normalized correlation metric:
wherein S (S, t) is a search graph; t (s, T) is a template map; n and M are respectively the height and width of the original image; e (S)i,j) And E (T) respectively representing the average gray values of the subgraph and the template at the position (i, j); r (i, j) represents the similarity result after matching.
The fourth step: optimal region selection
Combining the results of matching of each region, arranging the results from large to small according to the correlation, and selecting the region with the maximum correlation as the final matching region; and simultaneously, recording the matched block area and the matched position, obtaining the coordinates of the upper left corner of the matched area in the original picture through inverse operation, and intercepting the matched area.
A second part: accurate positioning of screw hole position in local area
The first step is as follows: local area fast ellipse detection
And carrying out rapid ellipse detection on the matched local area to obtain the coordinates of the center point of the ellipse, the sizes of the long axis and the short axis.
The second step is that: optimal center point selection
And combining the actually measured radius of the station screw hole and the sizes of the long shaft and the short shaft after the rapid ellipse detection, selecting the ellipse with the minimum distance error as an optimal detection result through the minimum absolute error value, and recording the center of the ellipse as the screw hole center of the final detection.
From the above, the screw hole image rapid positioning method based on vision of the invention mainly comprises two steps of screw hole region rapid search based on parallel operation and screw hole position precise positioning of a local region, wherein the screw hole region rapid search based on parallel operation mainly comprises selection of an interested region template, division of image blocks, parallel region image template matching and optimal region selection; the accurate positioning of the screw hole position of the local area mainly comprises the steps of local area rapid ellipse detection and optimal central point selection.
The vision-based screw hole image rapid positioning method is realized by dividing the traditional screw hole detection into two flows of screw hole rapid detection and local area precise screw hole positioning; the method can be effectively applied to robots on a production line, meets the positioning real-time performance and accuracy, and can realize real-time plug-in by means of the robots, so that the problem of quick detection and accurate positioning of screws of electric appliance back plates on the production line in the assembling process of household electrical appliances can be solved, the result of screw positioning is informed to the robots, the automatic assembly of screws is completed, the production efficiency can be improved, and the labor resources are saved.
It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and substance of the invention, and these modifications and improvements are also considered to be within the scope of the invention.
Claims (5)
1. A screw hole image rapid positioning method based on vision is characterized by comprising the following steps:
A. a screw hole area fast searching step based on parallel operation;
B. accurately positioning the position of a screw hole in a local area;
the step A specifically comprises the following steps:
A1. selecting a region-of-interest template;
A2. dividing the image into blocks;
A3. matching parallel regional image templates;
A4. selecting an optimal area;
the step a1 specifically includes the following steps:
a1.1, calibrating a camera before carrying a machine carrying a CCD camera, and sending an instruction to the CCD camera by an upper computer to obtain an original picture;
a1.2, fixing a station, acquiring original pictures for multiple times through a CCD camera, and screening out regular and clear pictures with small angles as a reference template through comparing the pictures;
a1.3, intercepting a local interested area and storing the local interested area into a template picture;
a1.4, performing angle rotation on the template pictures, specifically, horizontally rotating the template pictures by plus or minus 4 degrees, and regenerating one template picture every two degrees to generate 5 template pictures; when the upper computer is powered on, the upper computer program firstly reads the template picture in the hard disk into the memory;
selecting a circumscribed circle which needs to cover a complete screw hole in the local interested area in the step A1.3, wherein the circumscribed circle has uniqueness;
the step a2 specifically includes the following steps:
a2.1, recording a two-dimensional array of an original Image acquired by a CCD camera as Image [ N, M ], wherein N is the height of the Image, and M is the width of the Image;
a2.2, after the station is fixed, calculating the maximum external radius R of the screw hole by combining the actual size imaging size of the screw hole;
a2.3, equally dividing an original Image [ N, M ] into four Image blocks, wherein the upper left corner region is marked as Image [1: N/2,1: M/2], the upper right corner region is marked as Image [1: N/2, M/2: M ], the lower left corner region is marked as Image [ N/2: N,1: M/2], and the lower right corner region is marked as Image [ N/2: N, M/2: M ];
a2.4, expanding each area block according to the maximum radius R, wherein the expanded areas are as follows: the upper left corner region is marked as Image [1: N/2+ R,1: M/2+ R ], the upper right corner region is marked as Image [1: N/2+ R, M/2-R: M ], the lower left corner region is marked as Image [ N/2-R: N,1: M/2+ R ], the lower right corner region is marked as Image [ N/2-R: N, M/2-R: M ];
the step a3 specifically includes:
a3.1, if the number of image blocks is L and the number of templates is K, the number of thread/process starting is L x K;
and A3.2, respectively matching the template image and the block area image by using a matching algorithm in each thread/process in a thread/process parallel processing mode.
2. The method as claimed in claim 1, wherein the maximum circumscribed radius R < min { N/2, M/2} in step a2.2, min represents N, M to take the minimum value.
3. The vision-based screw hole image rapid positioning method as claimed in claim 1, wherein the matching algorithm in step a3.2 can be selected from a mean absolute difference algorithm, a sum of absolute differences algorithm, a sum of squared errors algorithm, a sum of squared average errors algorithm, a normalized product correlation algorithm, a sequential similarity detection algorithm, and a Hadamard transform algorithm.
4. The vision-based screw hole image rapid positioning method according to claim 1, wherein said step a4 specifically comprises the following steps:
a4.1, combining the matching results of each region, arranging the results from large to small according to the correlation, and selecting the region with the maximum correlation as a final matching region;
and A4.2, recording the matched block area and the position, obtaining the coordinates of the upper left corner of the matched area in the original picture through inverse operation, and intercepting the matched area.
5. The vision-based screw hole image rapid positioning method of claim 4, wherein the step B comprises the following steps:
B1. local area rapid ellipse detection: performing rapid ellipse detection on the matched local area to obtain the coordinates of the central point of the ellipse, the length values of the major axis and the minor axis;
B2. selecting an optimal central point: and selecting the ellipse with the minimum distance error as an optimal detection result through the minimum absolute error value by combining the actually measured radius of the station screw hole and the length values of the long axis and the short axis after the rapid ellipse detection, and recording the center of the ellipse as the center of the screw hole which is finally detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810915432.3A CN109118529B (en) | 2018-08-13 | 2018-08-13 | Screw hole image rapid positioning method based on vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810915432.3A CN109118529B (en) | 2018-08-13 | 2018-08-13 | Screw hole image rapid positioning method based on vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109118529A CN109118529A (en) | 2019-01-01 |
| CN109118529B true CN109118529B (en) | 2022-06-03 |
Family
ID=64853056
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810915432.3A Active CN109118529B (en) | 2018-08-13 | 2018-08-13 | Screw hole image rapid positioning method based on vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109118529B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458891A (en) * | 2019-06-12 | 2019-11-15 | 五邑大学 | A kind of screw hole caliberating device using three reconstruct |
| CN110906924A (en) * | 2019-12-17 | 2020-03-24 | 杭州光珀智能科技有限公司 | Positioning initialization method and device, positioning method and device and mobile device |
| CN111815718B (en) * | 2020-07-20 | 2022-03-01 | 四川长虹电器股份有限公司 | Method for switching stations of industrial screw robot based on vision |
| CN112465050B (en) * | 2020-12-04 | 2024-02-09 | 广东拓斯达科技股份有限公司 | Image template selection method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046271A (en) * | 2015-06-25 | 2015-11-11 | 哈尔滨工业大学 | MELF (Metal Electrode Leadless Face) component positioning and detecting method based on match template |
| CN105335711A (en) * | 2015-10-22 | 2016-02-17 | 华南理工大学 | Fingertip detection method in complex environment |
| CN106778518A (en) * | 2016-11-24 | 2017-05-31 | 汉王科技股份有限公司 | A kind of human face in-vivo detection method and device |
| CN106991707A (en) * | 2017-05-27 | 2017-07-28 | 浙江宇视科技有限公司 | A kind of traffic lights image intensification method and device based on imaging features round the clock |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09209013A (en) * | 1996-01-30 | 1997-08-12 | Nisshin Steel Co Ltd | Detection of clogging of iron tapping hole by picture processing and method for releasing clogging |
| CN2444564Y (en) * | 2000-10-30 | 2001-08-29 | 姚美辉 | Interlocked bone marrow internal nail screw hole locator |
| US7925072B2 (en) * | 2007-03-08 | 2011-04-12 | Kla-Tencor Technologies Corp. | Methods for identifying array areas in dies formed on a wafer and methods for setting up such methods |
| CN102156978B (en) * | 2010-12-24 | 2012-09-26 | 辽宁科锐科技有限公司 | Industrial device rapid locating method based on machine vision |
| CN106251354B (en) * | 2016-07-28 | 2018-11-06 | 河北工业大学 | Machine vision localization method for screw automatic assembling |
| CN106650717B (en) * | 2016-12-17 | 2020-07-28 | 复旦大学 | Accurate positioning method for round object with thickness interference |
| CN107984201B (en) * | 2017-11-30 | 2019-08-16 | 中国地质大学（武汉） | A kind of screw hole positioning of view-based access control model servo and lock unload screw method |
| CN108372130B (en) * | 2018-03-20 | 2019-10-18 | 华南理工大学 | A kind of target locating, sorting system and its implementation based on FPGA image procossing |
-
2018
- 2018-08-13 CN CN201810915432.3A patent/CN109118529B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046271A (en) * | 2015-06-25 | 2015-11-11 | 哈尔滨工业大学 | MELF (Metal Electrode Leadless Face) component positioning and detecting method based on match template |
| CN105335711A (en) * | 2015-10-22 | 2016-02-17 | 华南理工大学 | Fingertip detection method in complex environment |
| CN106778518A (en) * | 2016-11-24 | 2017-05-31 | 汉王科技股份有限公司 | A kind of human face in-vivo detection method and device |
| CN106991707A (en) * | 2017-05-27 | 2017-07-28 | 浙江宇视科技有限公司 | A kind of traffic lights image intensification method and device based on imaging features round the clock |
Non-Patent Citations (1)
| Title |
|---|
| Target Image Matching Algorithm based on Pyramid Model and Higher Moments;Yu Xiang 等;《Journal of Computational Science》;20170619;第21卷;189-194 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109118529A (en) | 2019-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109118529B (en) | Screw hole image rapid positioning method based on vision | |
| CN111775146B (en) | Visual alignment method under industrial mechanical arm multi-station operation | |
| CN110084854B (en) | System and method for runtime determination of camera calibration errors | |
| WO2012053521A1 (en) | Optical information processing device, optical information processing method, optical information processing system, and optical information processing program | |
| CN109859272B (en) | Automatic focusing binocular camera calibration method and device | |
| CN103292695B (en) | A kind of single eye stereo vision measuring method | |
| CN109377551B (en) | Three-dimensional face reconstruction method and device and storage medium thereof | |
| US7120286B2 (en) | Method and apparatus for three dimensional edge tracing with Z height adjustment | |
| Krotkov et al. | Stereo ranging with verging cameras | |
| CN105844692B (en) | Three-dimensional reconstruction apparatus, method, system and unmanned plane based on binocular stereo vision | |
| CN112161619A (en) | Pose detection method, three-dimensional scanning path planning method and detection system | |
| Cvišić et al. | Recalibrating the KITTI dataset camera setup for improved odometry accuracy | |
| Belhaoua et al. | Error evaluation in a stereovision-based 3D reconstruction system | |
| US20210407135A1 (en) | Calibration method for multi-degree-of-freedom movable vision system | |
| CN108805940B (en) | Method for tracking and positioning zoom camera in zooming process | |
| JP7353757B2 (en) | Methods for measuring artifacts | |
| CN114494462A (en) | Binocular camera ranging method based on Yolov5 and improved tracking algorithm | |
| US20130342659A1 (en) | Three-dimensional position/attitude recognition apparatus, three-dimensional position/attitude recognition method, and three-dimensional position/attitude recognition program | |
| CN112001945B (en) | Multi-robot monitoring method suitable for production line operation | |
| CN116393982B (en) | Screw locking method and device based on machine vision | |
| CN112643324A (en) | Automatic screw driving equipment and automatic screw driving method adopting same | |
| CN116147477A (en) | Joint calibration method, hole site detection method, electronic device and storage medium | |
| CN113587829A (en) | Edge thickness measuring method and device, edge thickness measuring equipment and medium | |
| Ping et al. | Verification of turning insert specifications through three-dimensional vision system | |
| Hemayed et al. | The CardEye: A trinocular active vision system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |