CN111210413B - Pose detection method in movement process of wire feeding mechanism - Google Patents
Pose detection method in movement process of wire feeding mechanism Download PDFInfo
- Publication number
- CN111210413B CN111210413B CN202010002448.2A CN202010002448A CN111210413B CN 111210413 B CN111210413 B CN 111210413B CN 202010002448 A CN202010002448 A CN 202010002448A CN 111210413 B CN111210413 B CN 111210413B
- Authority
- CN
- China
- Prior art keywords
- wire feeding
- circle
- image
- pose
- feeding mechanism
- 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
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000008569 process Effects 0.000 title claims abstract description 25
- 230000007246 mechanism Effects 0.000 title claims abstract description 21
- 238000001514 detection method Methods 0.000 title claims abstract description 14
- 230000033001 locomotion Effects 0.000 title claims abstract description 10
- 238000004891 communication Methods 0.000 claims abstract description 5
- 238000001914 filtration Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000002146 bilateral effect Effects 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000013519 translation Methods 0.000 claims description 2
- 239000002131 composite material Substances 0.000 abstract description 15
- 238000004519 manufacturing process Methods 0.000 abstract description 10
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000009941 weaving Methods 0.000 description 10
- 229920000049 Carbon (fiber) Polymers 0.000 description 4
- 239000004917 carbon fiber Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000002245 particle Substances 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000011157 advanced composite material Substances 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 235000015842 Hesperis Nutrition 0.000 description 1
- 235000012633 Iberis amara Nutrition 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000032798 delamination Effects 0.000 description 1
- 239000003733 fiber-reinforced composite Substances 0.000 description 1
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- 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
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30124—Fabrics; Textile; Paper
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to a pose detection method in the movement process of a wire feeding mechanism in the manufacturing process of a composite material, belonging to the crossing field of composite materials, mechanical manufacturing and computer technology. The method comprises the following steps: the industrial camera is placed on two sides of the wire feeding platform, gray images of white circles placed on the compacting plates are collected and enhanced by adopting a local self-adaptive image enhancement method, the mass center of the circles is roughly divided by utilizing a maximum communication area method, the mass center is roughly identified as a base point, the edge points of the circles are identified, the circle center is extracted by utilizing a least square method, the position coordinates of the identification points and the standard points are compared, if the offset of the two sides is the same, the wire feeding platform is translated, and if the offset of the two sides is different, the wire feeding platform is rotated or rotated and translated. The pose detection method in the moving process of the wire feeding mechanism has high automation degree, can judge the position before wire feeding, and avoids the situation that the wire feeding position is wrong or the wire cannot be fed.
Description
Technical Field
The invention relates to a pose detection method in the movement process of a wire feeding mechanism, belonging to the technical field of intersection of composite materials, mechanical manufacturing and computer technology.
Background
The advanced composite material represented by the continuous fiber reinforced composite material has the advantages of far higher specific stiffness and specific strength than those of steel materials, good corrosion resistance and fatigue resistance, strong designability and the like, and is widely applied to the industrial fields of carrier rockets, satellites, wind power generation, rail transit and the like. For a long time, the two-dimensional structure composite material is one of the most widely applied structures in the composite material structure due to simple manufacturing, mature forming process and equipment.
The three-dimensional structure composite material is introduced with the reinforcement body in the thickness direction, solves the problems of low layering resistance, easy delamination and the like of the two-dimensional composite material, and is the main direction of the current advanced composite material research, wherein a new process and a new device for the three-dimensional structure composite material become research hot spots and difficulties. The existing three-dimensional structure composite material has the defects of complicated preparation process, long manufacturing period and more manual intervention, so that the forming performance of the composite material is unstable; in addition, the automation level of the equipment is low in the manufacturing process, and the detection and regulation methods of the process parameters are still immature.
In recent years, researchers have studied the weaving process and equipment of carbon fiber preforms, but the problems of excessive human intervention, low weaving efficiency and the like exist in the weaving process, and the pose of a wire feeding mechanism needs to be manually judged before wire feeding, and misjudgment often occurs, so that wire feeding cannot be performed or the wire feeding position is wrong. The pose detection method based on machine vision in the moving process of the wire feeding mechanism provided by the invention can detect the wire feeding position in the weaving process of the composite material preform, ensure that carbon fibers are orderly and accurately laid in a set path, improve the automation degree in the weaving process, shorten the manufacturing period of a composite material member, reduce the manufacturing cost and provide a basis for realizing high-precision and high-efficiency manufacturing of a large-sized and complex-structure high-performance composite material member.
Disclosure of Invention
The invention mainly aims to provide a pose detection method in the moving process of a wire feeding mechanism, in particular to a pose detection method based on digital image processing, thereby realizing automatic positioning of a wire feeding position in the manufacturing process of a large-sized and complex-structure high-performance composite material preform and ensuring that carbon fibers are orderly and accurately laid in a set path.
1. A pose detection method in the moving process of a wire feeding mechanism comprises the following specific steps:
(1) identifying circle image acquisition; placing CCD industrial cameras on two sides of a wire feeding platform, keeping the placing direction of the cameras consistent with the wire feeding direction, and collecting gray images of white circles placed on a compacting plate, wherein the sizes, the contrast and the like of the images are fixed;
(2) preprocessing the identification circle image; carrying out median filtering treatment on the gray level image to realize noise reduction and restoration of the image under the condition of image edge fidelity; the contrast ratio of the circular area and the background area is improved by adopting a local self-adaptive image enhancement method; performing binarization processing on the image;
(3) identifying a circular centroid for rough extraction; dividing an identification circle area by using a maximum communication area method, and extracting the mass center of a circle;
(4) identifying a circle center of mass and extracting precisely; extracting a line gray scale waveform of a circular area by taking the rough extraction centroid as a reference point, extracting edge points of a circle by the line gray scale waveform, fitting the extracted edge points by using a least square method, and extracting the position of the centroid of the circle;
(5) judging the wire feeding pose; judging the relative pose between the wire feeding mechanism and the array, so that the wire feeding mechanism can be orderly laid in the array, and calibrating the position coordinates of the mass center of the circle as a reference point; repeating the steps (1), (2), (3) and (4) before starting wire feeding each time, comparing the identified circular centroid position coordinates with the datum point position coordinates, if the offsets of centroids identified by cameras on two sides in the X direction are equal, performing translational movement on the wire feeding platform, and if the offsets of centroids identified by cameras on two sides in the X direction are different, performing rotation or combined movement of rotation and translation on the wire feeding platform; further, a two-dimensional coordinate system is established by taking the mass center as an origin, intersection point coordinates of straight lines forming +/-45 degrees and +/-135 degrees with the X axis and round edges are respectively extracted, coordinates P1', P2', P3' and P4 of the straight lines and the round edges under the world coordinate system are established, internal references of the camera are calibrated, the relative pose between the camera and the array can be obtained through conversion relation of coordinates of four points under the pixel coordinate system and the coordinates under the world coordinate system and geometric relation among the four points, and the relative pose between the camera and the array can be obtained through comparison with the pose relation of initial positions.
2. The image acquisition utilizes a CCD camera, an annular light source and a light source controller.
3. The image acquisition of the identification circle is monocular, binocular or multi-mesh.
4. The CCD industrial camera is a linear array camera or an area array camera.
5. The least square method is least square circle fitting or least square ellipse fitting.
6. The filtering method is median filtering, mean filtering, gaussian filtering or bilateral filtering.
The beneficial effects of the invention are as follows:
1. the method has high degree of automation, reduces human intervention in the weaving process, improves the weaving efficiency, reduces the labor cost, and has higher detection precision compared with the traditional manual detection.
2. The method detects the relative pose between the wire feeding mechanism and the array in the weaving process of the composite material preform, avoids the situation that the wire feeding position is incorrect or the wire cannot be fed due to inaccurate wire feeding position, and ensures that the carbon fibers are orderly and accurately laid in a set path.
3. The method has higher robustness under different illumination conditions, and identifies the same circular centroid at the same position under different illumination conditions, wherein the maximum deviation of centroid coordinates is 0.8 pixel.
Drawings
FIG. 1 is a schematic diagram of a pose detection method mechanism in the motion process of a wire feeding mechanism.
Reference numerals
1-compacting the plate; 2-identifying a circle; 3-a wire feeding mechanism; 4-industrial camera.
Fig. 2 an industrial camera captures artwork.
Fig. 3 is a partially adaptive image enhanced image.
Fig. 4 is an image edge extraction effect diagram.
Fig. 5 is a schematic diagram of a circle center of mass recognition effect.
Detailed Description
The present invention will be described in detail with reference to the accompanying drawings.
Preferred embodiment 1 of the present invention comprises the following specific steps:
A. placing CCD industrial cameras on two sides of a wire feeding platform as shown in figure 1, keeping the placing direction of the cameras consistent with the wire feeding direction, collecting gray images of white circles placed on a compacting plate as shown in figure 2, and fixing the image sizes 1280×960, contrast-3 and the like;
B. carrying out median filtering treatment on the gray level image to realize noise reduction and restoration of the image under the condition of image edge fidelity;
the contrast ratio of the circular area and the background area is improved by adopting a local self-adaptive image enhancement method, as shown in figure 3; performing binarization processing on the image; the area of a search frame opening of the local self-adaptive image enhancement method is 20, and the gain coefficient is 100; the circular area is white, the background area is black, the pixel point with the gray value smaller than 90 on the image is set as 0, the pixel point with the gray value larger than or equal to 90 on the image is set as 255, and the whole image shows obvious black-white effect;
C. in the weaving field image acquisition process, field interference factors are more, in the image recognition process, the generation of pseudo recognition areas and interference points inevitably occurs, but the area of the pseudo recognition areas and the interference points is smaller than that of a recognition circle, as shown in fig. 4, therefore, the recognition circle area is divided by using the maximum communication area method, the circular area and the background area are divided, and the circle particles are extracted as [608,392];
D. setting the pixel value of the non-circular area as 20, and extracting row gray waveforms with interval of 5 according to the coarse extracted circular particles as a reference; wherein the intercept pixel value i is X axis, the gray value f t (j) Is the Y axis; performing first-order difference on the B spline curve;
E. searching the maximum and minimum change value points of the first-order difference from left to right, namely the positions of the round edge points, and performing least square fitting on the obtained edge points to obtain an identification circle, wherein the mass centers of the circles identified by the two cameras are [610,392], as shown in fig. 5;
F. comparing the identified circle center of mass [610,392] with the reference point [601,392], the wire feeding platform moves horizontally due to the fact that the offset of the two cameras is 9 pixels, and the wire feeding mechanism cannot feed wires due to incorrect wire feeding positions.
Preferred embodiment 2 of the present invention comprises the following specific steps:
A. placing CCD industrial cameras on two sides of a wire feeding platform, keeping the placing direction of the cameras consistent with the wire feeding direction, collecting gray images of white circles placed on a compacting plate as shown in figure 2, and fixing the image sizes 1280×960, contrast-3 and the like;
B. carrying out median filtering treatment on the gray level image to realize noise reduction and restoration of the image under the condition of image edge fidelity; the contrast ratio of the circular area and the background area is improved by adopting a local self-adaptive image enhancement method, and binarization processing is carried out on the image; the area of a search frame opening of the local self-adaptive image enhancement method is 30, and the gain coefficient is 110; the circular area is white, the background area is black, the pixel point with the gray value smaller than 90 on the image is set as 0, the pixel point with the gray value larger than or equal to 90 on the image is set as 255, and the whole image shows obvious black-white effect;
C. in the weaving field image acquisition process, field interference factors are more, and in the image recognition process, false recognition areas and interference points inevitably occur, but the area of the false recognition areas and the interference points is smaller than that of a recognition circle, so that the recognition circle area is divided by using a maximum communication area method, the circular area and a background area are divided, and circular particles are extracted;
D. setting the pixel value of a non-circular area as 20, and extracting row gray waveforms with interval of 10 according to the coarse extracted circular particles as a reference; wherein, the pixel value of the truncated line is X axis, the gray value is Y axis; performing first-order difference on the B spline curve;
E. searching maximum and minimum change value points of the first-order difference from left to right, namely, the positions of the round edge points, performing least square fitting on the obtained edge points to obtain an identification circle and obtaining the mass center of the identification circle, establishing a two-dimensional coordinate system by taking the mass center as an origin, and respectively extracting intersection point coordinates of straight lines forming +/-45 degrees and +/-135 degrees with an X axis and the round edge, wherein the intersection point coordinates are P1, P2, P3 and P4;
F. the coordinates P1', P2', P3 'and P4' of the coordinates P1, P2, P3 and P4 under the world coordinate system are established, internal references of the camera are calibrated, the relative pose between the camera and the array can be obtained through the conversion relation between the coordinates of the four points under the pixel coordinate system and the coordinates under the world coordinate system and the geometric relation among the four points, and the change of the relative pose between the camera and the array can be obtained through comparison with the pose relation of the initial position.
The above embodiments are further illustrative of the present invention, and the scope of the subject matter should not be construed as being limited to the embodiments.
Claims (6)
1. A pose detection method in the movement process of a wire feeding mechanism is characterized in that:
the method comprises the following specific steps:
(1) image acquisition of the identification circle; placing CCD industrial cameras on two sides of a wire feeding platform, keeping the placing direction of the cameras consistent with the wire feeding direction, and collecting gray images of white circles placed on a compacting plate;
(2) image preprocessing of the identification circle; carrying out median filtering treatment on the gray level image to realize noise reduction and restoration of the image under the condition of image edge fidelity; the contrast ratio of the circular area and the background area is improved by adopting a local self-adaptive image enhancement method, and binarization processing is carried out on the image;
(3) identifying a circular centroid for rough extraction; dividing an identification circle area by using a maximum communication area method, and extracting the mass center of a circle;
(4) identifying a circle center of mass and extracting precisely; extracting a line gray scale waveform of a circular area by taking the rough extraction centroid as a reference point, extracting edge points of a circle by the line gray scale waveform, fitting the extracted edge points by using a least square method, and extracting the position of the centroid of the circle;
(5) judging the pose of the wire feeding mechanism; judging the pose of the wire feeding mechanism, enabling the wire feeding mechanism to be orderly laid in the array, and calibrating the position coordinates of the mass center of the circle as a datum point; repeating the steps (1), (2), (3) and (4) before starting wire feeding each time, comparing the position coordinates of the identified circular mass centers with the reference point coordinates, if the offset of the mass centers identified by the cameras at two sides in the X direction is equal, performing translational movement on the wire feeding platform, and if the offset of the mass centers identified by the cameras at two sides in the X direction is different, performing rotation or combined movement of rotation and translation on the wire feeding platform; further, a two-dimensional coordinate system is established by taking the mass center as an origin, intersection point coordinates of straight lines forming +/-45 degrees and +/-135 degrees with the X axis and round edges are respectively extracted, coordinates P1', P2', P3' and P4 of the straight lines and the round edges under the world coordinate system are established, internal references of the camera are calibrated, the relative pose between the camera and the array can be obtained through conversion relation of coordinates of four points under the pixel coordinate system and the coordinates under the world coordinate system and geometric relation among the four points, and the relative pose between the camera and the array can be obtained through comparison with the pose relation of initial positions.
2. The method of claim 1, wherein the image acquisition uses a CCD camera, an annular light source and a light source controller.
3. The method of claim 1, wherein the image of the identified circle is acquired as monocular, binocular or multi-ocular.
4. The method for detecting the pose of the wire feeder in the moving process of claim 1, wherein the CCD industrial camera is a line camera or an area camera.
5. The method of claim 1, wherein the least square method is least square circle fitting or least square ellipse fitting.
6. The method for detecting the pose in the moving process of the wire feeding mechanism according to claim 1, wherein the filtering method is median filtering, mean filtering, gaussian filtering or bilateral filtering.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010002448.2A CN111210413B (en) | 2020-01-02 | 2020-01-02 | Pose detection method in movement process of wire feeding mechanism |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010002448.2A CN111210413B (en) | 2020-01-02 | 2020-01-02 | Pose detection method in movement process of wire feeding mechanism |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111210413A CN111210413A (en) | 2020-05-29 |
CN111210413B true CN111210413B (en) | 2023-10-03 |
Family
ID=70789517
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010002448.2A Active CN111210413B (en) | 2020-01-02 | 2020-01-02 | Pose detection method in movement process of wire feeding mechanism |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111210413B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112539714B (en) * | 2020-06-30 | 2022-07-26 | 深圳中科飞测科技股份有限公司 | Eccentricity detection method, processing method and detection equipment |
CN112877863B (en) * | 2021-01-14 | 2022-08-23 | 北京机科国创轻量化科学研究院有限公司 | Automatic edge bar placing device and method in composite material preform weaving process |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011107083A (en) * | 2009-11-20 | 2011-06-02 | Omron Corp | Posture recognition method and 3d vision sensor using the same |
CN108416791A (en) * | 2018-03-01 | 2018-08-17 | 燕山大学 | A kind of monitoring of parallel institution moving platform pose and tracking based on binocular vision |
CN108596980A (en) * | 2018-03-29 | 2018-09-28 | 中国人民解放军63920部队 | Circular target vision positioning precision assessment method, device, storage medium and processing equipment |
-
2020
- 2020-01-02 CN CN202010002448.2A patent/CN111210413B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011107083A (en) * | 2009-11-20 | 2011-06-02 | Omron Corp | Posture recognition method and 3d vision sensor using the same |
CN108416791A (en) * | 2018-03-01 | 2018-08-17 | 燕山大学 | A kind of monitoring of parallel institution moving platform pose and tracking based on binocular vision |
CN108596980A (en) * | 2018-03-29 | 2018-09-28 | 中国人民解放军63920部队 | Circular target vision positioning precision assessment method, device, storage medium and processing equipment |
Also Published As
Publication number | Publication date |
---|---|
CN111210413A (en) | 2020-05-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107590835B (en) | Mechanical arm tool quick-change visual positioning system and positioning method in nuclear environment | |
CN111210413B (en) | Pose detection method in movement process of wire feeding mechanism | |
CN104923593B (en) | Vision-based positioning method for top layer bending plate | |
CN103264738B (en) | Automatic assembling system and method for vehicle windshield glass | |
CN106000904A (en) | Automatic sorting system for household refuse | |
CN111266315A (en) | Ore material online sorting system and method based on visual analysis | |
CN109000557A (en) | A kind of nuclear fuel rod pose automatic identifying method | |
CN108765495B (en) | Rapid calibration method and system based on binocular vision detection technology | |
CN106709529B (en) | Visual detection method for photovoltaic cell color difference classification | |
CN110108712A (en) | Multifunctional visual sense defect detecting system | |
CN109225941B (en) | Automatic detection and sorting system and method for internal thread tapping condition | |
Wang et al. | Error analysis and improved calibration algorithm for LED chip localization system based on visual feedback | |
CN111292376B (en) | Visual target tracking method of bionic retina | |
CN110954555A (en) | WDT 3D vision detection system | |
CN108171753A (en) | Stereoscopic vision localization method based on centroid feature point Yu neighborhood gray scale cross correlation | |
CN109916914A (en) | A kind of product defects detection method and device | |
CN109614868A (en) | Automobile tire decorative pattern graph line identifying system | |
CN106097323B (en) | Engine cylinder block casting positioning method based on machine vision | |
CN113970560B (en) | Defect three-dimensional detection method based on multi-sensor fusion | |
CN107622484A (en) | A kind of photovoltaic cell unfilled corner detection algorithm based on form fit | |
CN111267094A (en) | Workpiece positioning and grabbing method based on binocular vision | |
CN111539951B (en) | Visual detection method for outline size of ceramic grinding wheel head | |
CN116858139B (en) | Metal structure flatness measuring method based on binocular vision | |
CN117876308A (en) | Photovoltaic panel detection method based on image analysis | |
CN106949881B (en) | A kind of mobile robot fast vision localization method |
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 |