CN114913229A - Visual positioning method and system for polishing local discontinuous area by robot - Google Patents
Visual positioning method and system for polishing local discontinuous area by robot Download PDFInfo
- Publication number
- CN114913229A CN114913229A CN202210454578.9A CN202210454578A CN114913229A CN 114913229 A CN114913229 A CN 114913229A CN 202210454578 A CN202210454578 A CN 202210454578A CN 114913229 A CN114913229 A CN 114913229A
- Authority
- CN
- China
- Prior art keywords
- plane
- robot
- fitting
- cubes
- point cloud
- 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
Images
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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B1/00—Processes of grinding or polishing; Use of auxiliary equipment in connection with such processes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B49/00—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation
- B24B49/12—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation involving optical means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B51/00—Arrangements for automatic control of a series of individual steps in grinding a workpiece
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- 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
- 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
- G06T7/77—Determining position or orientation of objects or cameras using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
Abstract
The invention belongs to the field of machine vision and robot application, in particular to a vision positioning method for polishing local discontinuous areas by a robot, which comprises the following steps: scanning a workpiece by a linear array camera to obtain a point cloud on the surface of the workpiece; acquiring bounding box size information of a workpiece, and dividing the bounding box into a plurality of plane cubes along the maximum value and the minimum value of the side length of the bounding box; fitting a fitting plane to each plane cube; calculating the distance from each point cloud in each plane cube to the fitting plane, wherein the average value of all the distances is roughness; counting the roughness of all the plane cubes and dividing the plane cubes into different grades; selecting all plane cubes to be polished, setting a polishing threshold value, and transmitting the polishing threshold value, point cloud mass center coordinates in the plane cubes and fitted surface normal vectors to a robot controller to enable the robot to perform polishing operation; according to the invention, the two-dimensional image data is expanded to the three-dimensional point cloud data, the data volume is increased, and the obtained roughness precision is improved.
Description
Technical Field
The invention belongs to the field of machine vision and robot application, and particularly relates to a vision positioning method and a vision positioning system for polishing local discontinuous areas by a robot.
Background
At present, the technology for precisely polishing the surface of a workpiece with a complex texture is developed into the advanced research field of automatic processing. The grinding and processing industry in China at present uses mechanical arms to replace manual work for automatic production, but some workpiece grinding and processing production lines still adopt a manual detection mode. Manual detection is not only inefficient for workpiece grinding, but also the quality is not uniform. At present, the research of the technology is also strived for the direction of achieving high speed, high precision, simple system operation, low maintenance cost, good integration and small influence from the outside.
Sunrei et al constructed a three-dimensional shape model based on the reflection of the detected light wave by using the difference in the degree of influence of the surface roughness on the phase of the light, and showed the roughness at different positions (Sunrei, Schacholor. a material surface quality detection method, system, and storage device [ P ]. Guangdong: CN113970551A, 2022-01-25.). Li Shunji et al extracted the sound pressure level root mean square and the dimensionality reduction vibration acceleration root mean square from the time domain signals of the milling noise and the three-dimensional milling vibration acceleration as characteristic values, and utilized Tamura texture characteristics to obtain the workpiece surface texture characteristic values (Li Shunji, Li Song Yuan, Liu Zhi, huiting, Shao Ming Hui, Song Guo Lu. A method for predicting the surface roughness based on the sound vibration and the texture characteristics [ P ]. Jiangsu province: CN113704922A, 2021-11-26.). The method comprises the steps of preprocessing, graying, filtering and the like of an image by Tianjiayan and the like, and extracting texture features of the image based on a gray level co-occurrence matrix to calculate roughness (Tianjiayan, DongLiang, Weiwangzhen, Gaoyun, Guoguo and Yangqiang, part surface roughness support vector machine detection method and system [ P ] based on the image, Shanxi province: CN113989233A, 2022-01-28.). The Wangmeng et designs a color distribution statistical matrix containing five matrix indexes of matrix non-zero point number, contrast, homogeneity, information entropy and energy to represent roughness (Wangmeng et. roughness identification research based on the color distribution statistical matrix and a variable prediction model [ D ]. Hunan university, 2016.). Guo uses computer micro-vision as a detection means, and adopts a light and shade recovery shape algorithm to realize three-dimensional reconstruction and roughness detection of the micro-topography of the processing surface (Guo. processing surface micro-vision image three-dimensional reconstruction and roughness detection [ D ]. SiAn university of Engineers, 2010.).
Currently, the roughness measurement method can be roughly divided into two methods according to the difference of sampling modes: contact and contactless. The contact measurement accuracy, speed, area and the like are limited by the equipment, and the sample is easy to damage. Non-contact roughness measurement methods include optical measurement, acoustic emission detection, and visual detection. Where optical detection and acoustic emission are environmentally sensitive and costly. However, the current visual detection method usually adopts a two-dimensional image method, but the feature extraction of the two-dimensional image depends on the contrast (edge data) of the measured object, certain illumination conditions are required, and the area with the roughness exceeding the threshold value can be determined by matching with a certain positioning method subsequently.
Disclosure of Invention
The invention aims to provide a visual positioning method and a visual positioning system for polishing a local discontinuous area by a robot, which overcome the defect that the conventional visual detection method is easily interfered by other scene factors such as light, color and the like and is difficult to obtain an ideal effect.
The technical scheme adopted by the invention for realizing the purpose is as follows: the vision positioning method for grinding the local discontinuous area by the robot comprises the following steps:
1) scanning a workpiece to be polished by a linear array camera to obtain a point cloud on the surface of the workpiece;
2) obtaining bounding box size information of a workpiece by using a PCA method, and dividing the bounding box into a plurality of plane cubes along the maximum value and the minimum value of the side length of the bounding box;
3) fitting a contour line for each plane cube by using least square, and fitting a plane by using dispersion;
4) calculating the distance from each point cloud collected by the linear array camera in each plane cube to the fitting plane, and obtaining the average value of all the distances as roughness R a ；
5) Counting R of all plane cubes a Numerical value, according to the grinding process requirement a Dividing into different grades;
6) selecting all plane cubes to be polished, setting polishing threshold values t according to the different levels of division, and transmitting the polishing threshold values t, point cloud mass center coordinates in the plane cubes and fitted surface normal vectors to a robot controller to enable the robot to perform polishing operation; after one-time polishing is finished, judging the relationship between the roughness Ra of the surface of the whole workpiece and a polishing threshold value t, and if Ra is less than or equal to t, finishing polishing; otherwise, repeating the steps 1) to 6).
The side length of the plane cube is determined according to the grinding process and requirements of the robot.
The step 3) is specifically as follows:
since the point cloud is composed of countless points, a plane is fitted through dispersion, that is, a plane is found, namely, the distance and the nearest distance from the plane to each point, namely:
ax+by+cz+d＝0
wherein, a, b, c and d are plane equation coefficients respectively, and x, y and z are plane equation variables respectively;
and obtaining the values of a, b and c by using a matrix form of a least square method, and substituting the values into a plane formula to obtain a fitting plane.
The step 4) is specifically as follows:
calculating the distance between each point in each plane cube and the fitting plane, namely fitting the fitting plane formula to the two-dimensional data R a In the expression (2), that is, the average value of the distance per point is taken as the roughness R a Comprises the following steps:
wherein a, b, c and d are respectively plane equation coefficients, x i ，y i ，z i Are respectively plane equation variables, and n is the number of sampling points.
The fitted surface normal vector is:
a vision positioning system for local discontinuous area polishing for a robot, comprising:
the point cloud acquisition module is used for scanning a linear array camera on a workpiece to be polished to acquire a point cloud on the surface of the workpiece;
the plane fitting module is used for acquiring bounding box size information of the workpiece by using a PCA method, and dividing the bounding box into a plurality of plane cubes along the maximum value and the minimum value of the side length of the bounding box; fitting a contour line for each plane cube by using least square, and fitting a plane by using dispersion;
the roughness construction module is used for calculating the distance from each point cloud collected by the linear array camera to the fitting plane in each plane cube and obtaining the average value of all the distances as the roughness R a (ii) a Counting R of all plane cubes a Numerical value, according to the grinding process requirement a Dividing into different grades;
and the grinding control module is used for selecting all plane cubes to be ground, setting a grinding threshold t according to different grades of division, and transmitting the grinding threshold t, point cloud mass center coordinates in the plane cubes and the fitted surface normal vector to the robot controller so that the robot can carry out grinding operation.
The invention has the following beneficial effects and advantages:
1. the linear array camera adopted by the invention has a large scanning range, is insensitive to illumination change or interference of ambient light, and improves the adaptability of the algorithm to the environment and enhances the robustness compared with the traditional RGB recognition algorithm;
2. the linear array camera can efficiently acquire sequence data in real time, so that the real-time data can be processed in real time, and compared with the traditional steps of scanning firstly and processing secondly, the welding seam data can be processed in real time more efficiently, and the process beat is reduced;
3. according to the method, the two-dimensional image data is expanded to the three-dimensional point cloud data, so that the data volume is improved, and the algorithm precision is improved;
4. the point cloud data can send the three-dimensional appearance data classified according to different roughness to the display end, and can capture the specific shape and position of the defect more quickly.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a schematic diagram of the cube partitioning of the present invention;
FIG. 3 is a schematic diagram of a partitioning cube of the present invention;
FIG. 4 is a schematic diagram of a fitted contour of the present invention;
FIG. 5 is a schematic diagram of the calculated roughness Ra of the present invention;
FIG. 6 is a schematic illustration of the surface roughness of a workpiece per unit sample length in accordance with the present invention;
FIG. 7 is a schematic diagram of the roughness of a cut surface of a workpiece per unit sampling length in accordance with the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
Roughness R as measured by roughness and smoothness of the surface a (the arithmetic mean of the absolute values of the relative heights of the surface of the object over a sample length 1) is an important measure of roughness, since the sanding plane is large and three-dimensional in space. Therefore, the present invention reduces the roughness R a The concept of (2) extends to three-dimensional planes.
As shown in fig. 1, is a flow chart of the method of the present invention, and the specific steps are as follows:
step 1) carrying out linear array camera scanning on a workpiece to be polished to obtain a point cloud on the surface of the workpiece;
and step 2) as shown in fig. 2, calculating a workpiece bounding box by using a PCA method, dividing a sampling plane cube along the maximum value and the minimum value of the side length of the bounding box, and as shown in fig. 3, dividing the bounding box into a plurality of plane cubes. The side length of the cube is determined according to the grinding process and requirements of the robot.
Step 3) dividing the cube into small squares, as shown in fig. 4, fitting an ideal profile surface principle schematic diagram for the invention, and fitting each cube with least squares to obtain an ideal profile surface, namely fitting an ideal profile corresponding to the least squares;
because the point cloud is composed of countless points, a plane is fitted through dispersion, namely a plane with the nearest distance to each point is found, and the plane formula is as follows:
ax+by+cz+d＝0#(4-1)
wherein, a, b, c and d are plane equation coefficients respectively, and x, y and z are plane equation variables respectively;
according to the least squares method, then:
S＝∑(ax i +by i +c-z i ) 2 (4-2)
if the value of S is minimized, then:
substituting formula 4-2 for formula 4-3 to obtain:
changing the equation into a matrix equation to obtain:
and (3) simultaneously multiplying two sides of the formula (4-5) by the coefficient inverse matrix to obtain the values of a, b and c, and further obtaining a fitting plane formula. Meanwhile, fitting a surface normal vector by the values of a, b and c as follows:
step 4), as shown in fig. 5, which is a schematic diagram of the roughness calculating principle of the present invention, the distance from each point in each cube to the fitting plane is calculated, and the average value of the distances is the roughness R a ：
R in two-dimensional data a The calculation formula is as follows:
wherein lr is the sampling length, and Z (x) is the ordinate of all the profiles in the sampling length;
the discrete expressions of equations (4-6) are as follows:
wherein n is the number of sampling points, and Z (i) is the distance from the sampling points to a central line fitted by the sampling points on the contour surface;
FIG. 7 is a schematic diagram showing the roughness of the cut surface of a workpiece per unit sampling length according to the present invention, wherein R is a After the concept of (2) is extended to a three-dimensional plane, the distance from each point in each cube to the fitting plane is calculated, and the fitting plane formula of formula (4-1) needs to be substituted into formula (4-6), then:
wherein a, b, c and d are respectively plane equation coefficients, x i ，y i ，z i Respectively, are plane equation variables.
The roughness of the surface of the workpiece per unit sampling length is shown in FIG. 6, where l is the sampling length, and R, which is different from the surface of the object, can be measured a Because the actual surface profile includes three geometric errors, i.e., roughness, waviness and macroscopic shape error, when measuring the surface roughness profile, the measurement should be limited to a short enough length h to reduce the influence of the surface waviness and the macroscopic shape error on the measurement result of the surface roughness profile, which is called the sampling length, in example 1.
The distance between two peaks is called the wave pitch:
the wave distance is within 1mm, and the micro roughness is called;
the wave distance is changed periodically within 1-10mm, which is called surface waviness;
the wave pitch is not periodically changed above 10mm, and is called macroscopic geometric error.
Step 5): counting R of all plane cubes a Numerical value, according to the grinding process requirement a Dividing into different grades;
in this example, the frog roughness R was adjusted according to a set grinding process a The following grades are divided, the calculated occupied proportion is visualized, and the process is convenientPersonnel can inquire and debug at the display end;
wherein 0.00mm-0.05mm, 0.05mm-0.10mm, 0.10mm-0.20mm, 0.20mm-0.40mm, 0.40mm-0.60mm, not less than 0.80 mm;
the invention uses the frog roughness R according to the set grinding process a The method comprises the following steps of dividing the roughness R into several grades, calculating the occupied proportion to be visualized, and aiming at the roughness R of different positions a And comparing to obtain a visual image after comparison.
6) Selecting all plane cubes to be polished, setting polishing threshold values t according to the different levels of the division, and transmitting the polishing threshold values t, point cloud mass center coordinates in the plane cubes and fitted surface normal vectors to a robot controller to enable the robot to perform polishing operation; after one-time polishing is finished, judging the relationship between the roughness Ra of the surface of the whole workpiece and a polishing threshold t, and if Ra is less than or equal to t, finishing polishing; otherwise, repeating the steps 1) to 6).
The invention is suitable for a vision positioning system for grinding local discontinuous areas by a robot, and comprises:
the point cloud acquisition module is used for scanning a linear array camera on a workpiece to be polished to acquire a point cloud on the surface of the workpiece;
the plane fitting module is used for acquiring bounding box size information of the workpiece by using a PCA method, and dividing the bounding box into a plurality of plane cubes along the maximum and minimum side lengths of the bounding box; fitting a contour line for each plane cube by using least square, and fitting a plane by using dispersion;
the roughness construction module is used for calculating the distance from each point cloud collected by the linear array camera to the fitting plane in each plane cube and obtaining the average value of all the distances as the roughness R a (ii) a Counting R of all plane cubes a Numerical value, according to the grinding process requirement a Dividing into different grades;
and the grinding control module is used for selecting all plane cubes to be ground, setting a grinding threshold t according to different grades of division, and transmitting the grinding threshold t, point cloud mass center coordinates in the plane cubes and the fitted surface normal vector to the robot controller so that the robot can carry out grinding operation.
Claims (6)
1. The robot is used for the vision positioning method of local discontinuous area polishing, and is characterized by comprising the following steps:
1) scanning a workpiece to be polished by a linear array camera to obtain a point cloud on the surface of the workpiece;
2) obtaining bounding box size information of the workpiece by using a PCA method, and dividing the bounding box into a plurality of plane cubes along the maximum and minimum side lengths of the bounding box;
3) fitting a contour line for each plane cube by using least square, and fitting a plane by using dispersion;
4) calculating the distance from each point cloud collected by the linear array camera to the fitting plane in each plane cube, and obtaining the average value of all the distances as roughness R a ；
5) Counting R of all plane cubes a Numerical value, according to the grinding process requirement a Dividing into different grades;
6) selecting all plane cubes to be polished, setting polishing threshold values t according to the different levels of division, and transmitting the polishing threshold values t, point cloud mass center coordinates in the plane cubes and fitted surface normal vectors to a robot controller to enable the robot to perform polishing operation; after one-time polishing is finished, judging the relationship between the roughness Ra of the surface of the whole workpiece and a polishing threshold t, and if Ra is less than or equal to t, finishing polishing; otherwise, repeating the steps 1) to 6).
2. A visual positioning method for local discontinuity area grinding by a robot as claimed in claim 1 wherein the planar cube side length is determined according to the robot grinding process and requirements.
3. A visual positioning method for local discontinuity area grinding by a robot according to claim 1, characterized by said step 3), in particular:
since the point cloud is composed of countless points, a plane is fitted through dispersion, that is, a plane with the closest distance to each point is found, that is:
ax+by+cz+d＝0
wherein, a, b, c and d are respectively plane equation coefficients, and x, y and z are respectively plane equation variables;
and obtaining the values of a, b and c by using a matrix form of a least square method, and substituting the values into a plane formula to obtain a fitting plane.
4. A visual positioning method for local discontinuity area grinding by a robot as claimed in claim 1, wherein said step 4), in particular:
calculating the distance between each point in each plane cube and the fitting plane, namely fitting the fitting plane formula to the two-dimensional data R a In the expression (2), that is, the average value of the distance per point is taken as the roughness R a Comprises the following steps:
wherein a, b, c and d are respectively plane equation coefficients, x i ，y i ，z i Are respectively plane equation variables, and n is the number of sampling points.
5. A visual positioning method for local discontinuity area grinding by a robot as claimed in claim 1 wherein said fitted surface normal vector is:
6. the robot is used for vision positioning system that local discontinuous area ground, its characterized in that includes:
the point cloud acquisition module is used for scanning a linear array camera on a workpiece needing to be polished to acquire a point cloud on the surface of the workpiece;
the plane fitting module is used for acquiring bounding box size information of the workpiece by using a PCA method, and dividing the bounding box into a plurality of plane cubes along the maximum and minimum side lengths of the bounding box; fitting a contour line for each plane cube by using least square, and fitting a plane by using dispersion;
the roughness construction module is used for calculating the distance from each point cloud collected by the linear array camera to the fitting plane in each plane cube and obtaining the average value of all the distances as the roughness R a (ii) a Counting R of all plane cubes a Numerical value, according to the grinding process requirement a Dividing into different grades;
and the grinding control module is used for selecting all plane cubes to be ground, setting a grinding threshold t according to different grades of division, and transmitting the grinding threshold t, point cloud mass center coordinates in the plane cubes and the fitted surface normal vector to the robot controller so that the robot can carry out grinding operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210454578.9A CN114913229A (en) | 2022-04-27 | 2022-04-27 | Visual positioning method and system for polishing local discontinuous area by robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210454578.9A CN114913229A (en) | 2022-04-27 | 2022-04-27 | Visual positioning method and system for polishing local discontinuous area by robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114913229A true CN114913229A (en) | 2022-08-16 |
Family
ID=82764068
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210454578.9A Pending CN114913229A (en) | 2022-04-27 | 2022-04-27 | Visual positioning method and system for polishing local discontinuous area by robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114913229A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117433491A (en) * | 2023-12-20 | 2024-01-23 | 青岛亿联建设集团股份有限公司 | Foundation pit engineering safety monitoring method based on unmanned aerial vehicle image |
-
2022
- 2022-04-27 CN CN202210454578.9A patent/CN114913229A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117433491A (en) * | 2023-12-20 | 2024-01-23 | 青岛亿联建设集团股份有限公司 | Foundation pit engineering safety monitoring method based on unmanned aerial vehicle image |
| CN117433491B (en) * | 2023-12-20 | 2024-03-26 | 青岛亿联建设集团股份有限公司 | Foundation pit engineering safety monitoring method based on unmanned aerial vehicle image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109489580B (en) | On-machine point cloud detection and compensation method for surface processing of aero-engine blade | |
| CN111007073B (en) | Method and system for online detection of part defects in additive manufacturing process | |
| CN108986048B (en) | Three-dimensional point cloud rapid composite filtering processing method based on line laser scanning | |
| CN109532021B (en) | 3D printing fused deposition defect layer-by-layer detection method based on structural light property abnormal points | |
| CN105066915B (en) | Mould camber processing error and surface roughness On-machine Test device and detection method | |
| CN111055293A (en) | High-precision constant-force grinding method for industrial robot based on curved surface self-adaption | |
| CN115388817B (en) | Method for realizing polishing quality detection of casting parts based on image processing analysis | |
| CN113865508B (en) | Automatic detection device and method for through hole rate of sound lining of honeycomb sandwich composite material | |
| CN107133565B (en) | Line laser-based laser engraving line feature extraction method | |
| CN105118059A (en) | Multi-scale coordinate axis angle feature point cloud fast registration method | |
| CN105783723A (en) | Machine vision-based precise die surface processing precision detection device and method | |
| CN112697058A (en) | Machine vision-based large-size plate assembly gap on-line measurement system and method | |
| CN116402866A (en) | Point cloud-based part digital twin geometric modeling and error assessment method and system | |
| CN114913229A (en) | Visual positioning method and system for polishing local discontinuous area by robot | |
| CN111540001B (en) | Method for detecting axial direction of air film hole of turbine blade of aero-engine | |
| Yu et al. | Cutting plane based cylinder fitting method with incomplete point cloud data for digital fringe projection | |
| CN111238405A (en) | Workpiece curvature detection system and method | |
| CN110966937B (en) | Large member three-dimensional configuration splicing method based on laser vision sensing | |
| CN111795970A (en) | Irregular contour defect detection method | |
| CN204881558U (en) | Mould curved surface machining error and roughness are at quick -witted detection device | |
| CN109426216B (en) | Rectangular plane machining depth identification method for numerical control milling machine | |
| CN115971004A (en) | Intelligent putty spraying method and system for carriage | |
| CN110021027B (en) | Edge cutting point calculation method based on binocular vision | |
| CN114488943A (en) | Random multi-region efficient polishing path planning method oriented to cooperation condition | |
| CN111985308A (en) | Stereo vision space curve matching method of differential geometry |
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 |