CN117450922A - Casting cleaning robot 3D vision measurement method and measurement system - Google Patents
Casting cleaning robot 3D vision measurement method and measurement system Download PDFInfo
- Publication number
- CN117450922A CN117450922A CN202311397449.1A CN202311397449A CN117450922A CN 117450922 A CN117450922 A CN 117450922A CN 202311397449 A CN202311397449 A CN 202311397449A CN 117450922 A CN117450922 A CN 117450922A
- Authority
- CN
- China
- Prior art keywords
- angle
- casting
- point cloud
- cleaned
- cloud data
- 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
- 238000005266 casting Methods 0.000 title claims abstract description 171
- 238000004140 cleaning Methods 0.000 title claims abstract description 46
- 238000005259 measurement Methods 0.000 title claims abstract description 19
- 238000000691 measurement method Methods 0.000 title claims abstract description 17
- 239000012535 impurity Substances 0.000 claims abstract description 92
- 230000000007 visual effect Effects 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims description 22
- 238000000034 method Methods 0.000 claims description 20
- 238000001914 filtration Methods 0.000 claims description 13
- 238000012800 visualization Methods 0.000 claims description 12
- 238000005516 engineering process Methods 0.000 claims description 9
- 230000007246 mechanism Effects 0.000 claims description 8
- 230000003993 interaction Effects 0.000 claims description 7
- 238000009434 installation Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 6
- 238000005286 illumination Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 4
- 239000002184 metal Substances 0.000 description 4
- 238000004806 packaging method and process Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000012636 effector Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
- G01B11/25—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures by projecting a pattern, e.g. one or more lines, moiré fringes on the object
- G01B11/254—Projection of a pattern, viewing through a pattern, e.g. moiré
-
- 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
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a 3D vision measurement method and a measurement system of a casting cleaning robot, which are characterized in that point cloud data of a casting to be cleaned at a 1 st angle are obtained through a 3D binocular camera and a digital grating projector, a relative motion path of the casting is recorded when the casting is shot by the 3D binocular camera, point cloud data of a plurality of angles are obtained on the basis of the path, and point cloud registration operation is carried out to obtain complete point cloud data; dividing the cleaning tool into six areas, and acquiring contour information and position information of a part to be cleaned corresponding to each area; and carrying out curved surface reconstruction based on the profile information of the six areas to obtain a model of the casting to be cleaned by impurities, and obtaining the final profile information and position information of the part to be cleaned to finish the visual measurement of the casting to be cleaned by impurities. The detection method is not influenced by external conditions such as illumination, has high accuracy and high working efficiency of detection results, and can identify workpiece features with complex structures.
Description
Technical Field
The invention relates to the technical field of casting cleaning of machine vision auxiliary robots, in particular to a 3D vision measurement method and a measurement system of a casting cleaning robot.
Background
With the development of robots and automation technology, industrial robots are increasingly replacing manual work to complete work with special properties of severe working environment. The rapid development of industrial robot technology can replace manual cleaning of impurities on cast castings. The cleaning of impurities after casting is critical to the final quality of castings, but the existing casting impurity cleaning technology still cannot meet the requirements of actual production and processing on high efficiency and high quality, and manual treatment is still needed in many cases, so that on one hand, the working environment is bad, the physical health of workers is damaged to a certain extent, on the other hand, the impurity cleaning effect cannot be ensured, the cleaning effect of the final castings is greatly influenced by the cleaning experience of the workers, and the production efficiency and quality are greatly influenced.
An important link for cleaning casting impurities by using a robot technology instead of manpower is identification and measurement of casting impurity characteristics. In a simple case, the cleaning path of the casting can be planned by an off-line programming method, but the planned path is required to depend on a three-dimensional model of a workpiece completely, and the off-line programming is complex, time-consuming and low in efficiency. In some scenes, defects of the workpiece are detected based on the 2D image, but the detection method is easily influenced by external conditions such as illumination, the accuracy of detection results is not high, and the workpiece features with complex structures cannot be identified. Compared with a 2D image, the three-dimensional point cloud contains more comprehensive and rich characterization information, and can obtain the geometric shape and size information of the workpiece with the complex structure with high precision. The 3D vision technology has strong characteristic expression capability, but has larger application difficulty and low measurement result precision.
Disclosure of Invention
The invention provides a 3D vision measurement method and a measurement system for a casting cleaning robot, which are used for solving the problems.
The application adopts the following technical scheme:
a 3D vision measurement method of a casting cleaning robot, which comprises the following steps,
step 1: mounting a casting to be cleaned by impurities on a positioner clamp of a casting cleaning robot, so that the casting to be cleaned by impurities is fixed at a 1 st angle; the 1 st angle is the angle of the casting to be cleaned by impurities when the installation of the casting on the positioner is completed;
step 2: using Zhang Zhengyou calibration method to complete hand-eye calibration of the casting cleaning robot and the 3D binocular camera;
step 3: shooting the casting to be cleaned by impurities at the 1 st angle by adopting a digital grating projector and the 3D binocular camera to acquire point cloud data at the 1 st angle, and recording a relative motion path adopted by the 3D binocular camera when shooting relative to the casting to be cleaned by impurities;
step 4: the position and the posture of the casting to be cleaned by impurities are adjusted through a position changer of the casting cleaning robot, so that the casting to be cleaned by impurities is fixed at the 2 nd angle, the 3 rd angle, the … … th angle and the nth angle respectively; the 1 st angle, the 2 nd angle and the … … th angle are all different;
step 5: based on the relative motion path, a digital grating projector and the 3D binocular camera are adopted to shoot castings to be cleaned by impurities at the 2 nd angle, the 3 rd angle, the … … th angle and the nth angle respectively so as to obtain point cloud data of the 2 nd angle, the 3 rd angle, the … … th angle and the nth angle respectively;
step 6: performing point cloud registration operation based on the point cloud data of the 1 st angle, the point cloud data of the 2 nd angle, the 3 rd angle, the … … th angle and the point cloud data of the n th angle to obtain complete point cloud data of the casting to be cleaned by impurities;
step 7: filtering the complete point cloud data, dividing the filtered complete point cloud data into six areas to obtain six area point cloud data, and respectively identifying and measuring the parts to be cleaned of the six area point cloud data to obtain contour information and position information of the parts to be cleaned corresponding to each area;
step 8: and carrying out curved surface reconstruction based on the contour information of the part to be cleaned corresponding to each region to obtain a model of the casting to be cleaned by impurities, carrying out repeated comparison on the model of the casting to be cleaned by impurities and a standard digital-analog file of the casting to obtain final contour information and position information of the part to be cleaned, and controlling a casting robot to clean the casting to be cleaned by impurities based on the final contour information and position information of the part to be cleaned to finish visual measurement of the casting to be cleaned by impurities.
Further, the method for dividing the complete point cloud data after the filtering processing into six areas is as follows:
1) Acquiring two points with the largest distance in the whole point cloud data and connecting the two points to form a line segment;
2) Taking two equal dividing points on the line segment to trisect the line segment;
3) Obtaining a vertical plane passing through the bisection point and perpendicular to the line segment;
4) And acquiring a plane passing through the line segment, dividing the complete point cloud data into six areas by the plane and the vertical plane, and enabling the reference characteristic of the casting to be cleaned by impurities to be in any one of the six areas.
Further, in the step 3, the method for acquiring the point cloud data of the 1 st angle is as follows:
1) Controlling a digital grating projector to project a structural light pattern to the casting to be cleaned by impurities by using an OpenCV technology;
2) Utilize 3D vision camera to shoot the foundry goods of having cast structure light pattern to carry out impurity clearance to based on the profile of foundry goods of waiting to carry out impurity clearance, obtain the three-dimensional surface information of foundry goods of waiting to carry out impurity clearance, and then obtain the point cloud data of foundry goods of waiting to carry out impurity clearance.
Further, the step 5 further includes: and (3) realizing visualization of the casting shooting result, the 1 st angle, the 2 nd angle, the 3 rd angle, the … … th angle, the nth angle, the 1 st angle, the 2 nd angle, the 3 rd angle, the … … th angle, the point cloud data of the nth angle, the complete point cloud data, the regional point cloud data, the contour information and the position information of the part to be cleaned of each region, the model of the casting and the final impurity part to be cleaned by utilizing a visualization interface of the Qt graphical user interface based on a signal and a slot mechanism of Qt software.
The measuring system of the 3D vision measuring method of the casting cleaning robot is characterized by comprising a data acquisition module, a point cloud data processing module and a man-machine interaction interface module;
the data acquisition module comprises a 3D binocular camera and a digital grating projector, and is used for combining a position shifter of a casting cleaning robot, shooting castings at the 1 st angle, the 2 nd angle, the 3 rd angle, … … and the nth angle by adopting a relative motion path, and acquiring point cloud data of the castings at the 1 st angle, the 2 nd angle, the 3 rd angle, … … and the nth angle to be cleaned by impurities;
the point cloud data processing module is used for performing point cloud registration operation based on the point cloud data of the 1 st angle, the 2 nd angle, the 3 rd angle, the … … th angle and the nth angle to obtain complete point cloud data of the casting; filtering the complete point cloud data, dividing the complete point cloud data after filtering into six areas to obtain six area point cloud data, and respectively identifying and measuring the parts to be cleaned of the six area point cloud data to obtain contour information and position information of the parts to be cleaned of each area; carrying out curved surface reconstruction based on the contour information of the part to be cleaned of each region to obtain a model of the casting to be cleaned of impurities, and further carrying out repeated comparison with a standard digital-to-analog file of the casting to obtain final contour information and position information of the part to be cleaned; completing visual measurement of castings to be cleaned of impurities;
the man-machine interaction interface module is used for realizing visualization of the 1 st angle, the 2 nd angle, the 3 rd angle, the … … th angle, the 1 st angle, the 2 nd angle, the 3 rd angle, the … … th angle, the n-th angle point cloud data, the complete point cloud data, the regional point cloud data, the contour information and the position information of the part to be cleaned of each region, the model of the casting and the final impurity part to be cleaned by utilizing a visual interface of the Qt graphical user interface and based on a signal and a groove mechanism of Qt software.
The beneficial effects are that: according to the 3D vision measurement method and measurement system of the casting cleaning robot, point cloud data of a casting to be cleaned at the 1 st angle are obtained through the 3D binocular camera and the digital grating projector, a relative motion path of the casting is recorded when the 3D binocular camera shoots the casting, the point cloud data of the 2 nd angle, the 3 rd angle, the … … th angle and the n th angle are obtained on the basis of the path, and point cloud registration operation is carried out to obtain complete point cloud data of the casting to be cleaned by impurities; the complete point cloud data is divided into six areas after being subjected to filtering processing, and contour information and position information of a part to be cleaned corresponding to each area are obtained; further, curved surface reconstruction is carried out based on the profile information of the six areas, a model of the casting to be cleaned by impurities is obtained, the profile information and the position information of the final part to be cleaned are obtained, the casting robot is controlled to clean the casting to be cleaned by impurities, and visual measurement of the casting to be cleaned by impurities is completed. The detection method is not influenced by external conditions such as illumination, has high accuracy and high working efficiency of detection results, and can identify workpiece features with complex structures.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it will be obvious that the drawings in the following description are some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of a 3D vision measurement method of the present invention;
FIG. 2 is a block diagram of a casting cleaning robot 3D vision measurement method of the present invention;
FIG. 3 is a flow chart of a 3D vision measurement method according to an embodiment of the present invention;
FIG. 4 is a schematic view showing the division of a casting to be cleaned of impurities into six zones in an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment discloses a casting cleaning robot 3D vision measurement method for assisting the casting cleaning robot to rapidly and accurately measure the position and the outline of the casting to be cleaned impurities, comprising the following steps, as shown in figures 1 and 3:
step 1: mounting a casting to be cleaned of impurities on a positioner clamp of a casting cleaning robot; fixing the casting to be cleaned by impurities at a 1 st angle;
step 2: the existing Zhang Zhengyou calibration method is used for completing hand-eye calibration of the casting cleaning robot and the 3D binocular camera;
step 3: shooting the casting to be cleaned by impurities at the 1 st angle by adopting a digital grating projector and the 3D binocular camera to acquire point cloud data at the 1 st angle, and recording the relative motion path of the 3D binocular camera relative to the casting to be cleaned by impurities;
preferably, in the step 3, the method for acquiring the point cloud data of the 1 st angle is as follows:
1) Controlling a digital grating projector to project a structural light pattern to the casting to be cleaned by impurities by using an OpenCV technology;
2) Utilize 3D vision camera to shoot the foundry goods of having cast structure light pattern to carry out impurity clearance to based on the profile of foundry goods of waiting to carry out impurity clearance, obtain the three-dimensional surface information of foundry goods of waiting to carry out impurity clearance, and then obtain the point cloud data of foundry goods of waiting to carry out impurity clearance.
Specifically, the digital grating projector and the 3D vision camera are used as a photographic combination to shoot the casting, and the relative positions of the digital grating projector and the 3D vision camera are fixed.
Step 4: the position and the posture of the casting to be cleaned by impurities are adjusted through a position changer of the casting cleaning robot, so that the casting to be cleaned by impurities is fixed at the 2 nd angle, the 3 rd angle, the … … th angle and the nth angle respectively;
specifically, a 3D binocular camera is entrained by an end effector of the casting cleaning robot, a casting to be cleaned by impurities is fixed on a positioner clamp of the casting cleaning robot, and the pose of the casting fixed on the positioner clamp is adjusted through the positioner.
Step 5: based on the relative motion path, a digital grating projector and the 3D binocular camera are adopted to shoot castings to be cleaned by impurities at the 2 nd angle, the 3 rd angle, the … … th angle and the nth angle respectively so as to obtain point cloud data of the 2 nd angle, the 3 rd angle, the … … th angle and the nth angle respectively;
step 6: performing point cloud registration operation based on the point cloud data of the 1 st angle, the point cloud data of the 2 nd angle, the 3 rd angle, the … … th angle and the point cloud data of the n th angle to obtain complete point cloud data of the casting to be cleaned by impurities;
specifically, the OpenCV technology is utilized to control the digital grating projector to project a structural light pattern onto the casting to be measured, the 3D vision camera obtains three-dimensional surface information of the casting to be measured by the mapping relation between depth information of the casting surface to be measured and grating phase information, multi-angle shooting is carried out on the casting, and a multi-angle point cloud data file of the casting is obtained. In order to adapt to the working environment for cleaning large castings, a metal shell is used for packaging the 3D binocular camera and the digital grating projector; the metal shell plays a role in protection, and the service life of the binocular camera equipment is greatly prolonged.
Specifically, the 1 st angle, the 2 nd angle, the 3 rd angle, the … … th angle and the n th angle are all shooting angles set by workers in the field. The relative motion path is recorded after the 1 st angle shooting, and in other application examples, the relative motion path can be preset in advance, and the casting is shot based on the preset relative motion path.
Specifically, in this embodiment, an improved ICP method is adopted, after a casting at angle 1 is photographed, a photographing route of a 3D double-sided camera with respect to the casting is recorded, and after the casting is adjusted to other angles, the casting is photographed by using the relative motion path, so that point cloud data of photographing the casting at different angles based on the same relative motion path is obtained, and point cloud registration operation is performed on the point cloud data based on multiple angles to obtain complete point cloud data of the casting; because the space coordinate systems of the plurality of point cloud data acquired at multiple angles are not uniform, the point cloud data acquired by adopting a uniform relative motion path in the embodiment are unified into the same coordinate system, and the complete point cloud data of the casting is acquired. The method has high registration efficiency, perfectly solves the problems that the traditional ICP algorithm has higher requirement on the initial position, is easy to generate a local optimal solution and can not be successfully matched, and greatly improves the registration precision and efficiency; in combination with the casting cleaning robot in the embodiment, in the practical application process, a large number of castings are placed on the position changer of the robot, compared with the traditional industrial production, the method has certain path order, the position of the castings is adjusted through the position changer of the casting cleaning robot, and the angles and the sequences of the castings with large numbers shot by the 3D binocular camera are controlled to be fixed, so that the flow is consistent when the point cloud data are aligned each time, the method is suitable for the requirement of registering the point cloud data of the large number of castings, the complexity of registration is greatly reduced, and the point cloud processing efficiency is improved.
Step 7: filtering the complete point cloud data, dividing the complete point cloud data after filtering into six areas to obtain six area point cloud data, and respectively identifying and measuring the parts to be cleaned of the six area point cloud data by using a PCL point cloud processing library to obtain contour information and position information of the parts to be cleaned of each area; specifically, the recognition and measurement difficulty of the impurity characteristics to be cleaned of the integral casting are high, and after the integral casting is divided into six areas, the impurity characteristics contained in each area are different, so that the impurity characteristics can be conveniently treated separately. The dividing steps are as follows: firstly, analyzing two points with the largest distance in the point cloud, namely two corresponding endpoints of the casting, then, trisecting the connecting line section of the two endpoints, and dividing the connecting line of the two endpoints into six areas through the trisecting points vertical to the connecting line of the two endpoints.
Preferably, the method for dividing the filtered complete point cloud data into six areas is as follows: as shown in figure 4 of the drawings,
1) Acquiring two points with the largest distance in the whole point cloud data and connecting the two points to form a line segment;
2) Taking two bisecting points a and b on the line segment, and trisecting the line segment;
3) Obtaining vertical planes A and B which pass through the bisection point and are perpendicular to the line segment;
4) Acquiring a plane C passing through the line segment, dividing the complete point cloud data into six areas by the plane C, a vertical plane A and a vertical plane A, wherein the reference characteristic of the casting to be cleaned by impurities is located in any one of the six areas; in particular, in the foundry industry, there are mold-based reference features that are present when the mold is released as the casting proceeds.
In one embodiment of the invention, the datum feature on the casting is a dowel hole 1. Specifically, when two points with the largest distance in the whole point cloud data are acquired and connected to form a line segment and then six region division is performed, if the reference feature cannot be located in any one of the six regions, adjacent points of the two points with the largest distance in the whole point cloud data are acquired and connected to form the line segment, the initial position of the line segment is adjusted until the reference feature is located in any one of the six regions, and two equal-division points are selected on the obtained line segment.
Specifically, the point cloud data processing module performs processing such as filtering, feature recognition, curved surface reconstruction, point cloud visualization and the like on the point cloud data of the casting to be cleaned of the six divided areas based on a PCL point cloud processing algorithm.
Specifically, in order to obtain the outline and position information of the part to be cleaned of the casting with high precision, a casting regional characteristic identification method is adopted, namely, the complete point cloud data of the casting is divided into six regions, and the parts to be cleaned of the six regions are respectively identified and measured;
step 8: carrying out curved surface reconstruction based on the contour information of the part to be cleaned of each region to obtain a model of the casting to be cleaned of impurities, and further carrying out repeated comparison with a standard digital-to-analog file of the casting to obtain final contour information and position information of the part to be cleaned; and (3) completing visual measurement of the casting to be cleaned of impurities.
Specifically, the model obtained by PCL processing the point cloud is further subjected to repeated comparison with a digital-analog file STL, and the final difference is the impurity part to be cleaned;
preferably, a casting cleaning robot 3D vision measurement method of the present embodiment further includes: and utilizing a visual interface of the Qt graphical user interface, and realizing visualization of casting shooting results of a plurality of angles, point cloud data of a plurality of angles, complete point cloud data, regional point cloud data, contour information and position information of a part to be cleaned of each region, a model of the casting and a final impurity part to be cleaned based on a signal and slot mechanism of Qt software.
Specifically, in the embodiment, a visual interface designed by a Qt graphical user interface application program development framework is utilized, the PCL function of processing point cloud data is integrated, and operations such as camera calling, point cloud processing, result visualization and the like can be completed by clicking a function button in the interface through a signal and slot mechanism of Qt software;
specifically, the human-computer interaction interface module is designed to obtain a visual interface by utilizing a Qt graphical user interface application program development framework, integrates the function of PCL for processing point cloud data, and can finish operations such as camera invoking, point cloud processing, result visualization and the like by clicking a function button in the interface through a signal and slot mechanism of Qt software.
Specifically, the software used in the embodiment is compiled under a Windows10 system, programming development and design of an upper computer software interface are performed in a Visual Studio 2015 by using a C++ language and a Qt, and calibration of a 3D binocular camera, image processing and three-dimensional point cloud data processing of castings are realized by combining an OpenCV Visual open source library and a PCL point cloud library. And 3D vision and point cloud data processing are utilized to realize rapid and accurate measurement of the part to be cleaned of the casting. In the method of this embodiment, the 3D binocular camera, the digital grating projector, the upper computer and the 3D vision measurement software are all existing products in the field, and the 3D vision measurement method proposed by the present embodiment is only used.
The embodiment also discloses a measuring system of the casting cleaning robot 3D vision measuring method, which comprises a data acquisition module, a point cloud data processing module and a man-machine interaction interface module; as shown in figure 2 of the drawings,
the data acquisition module comprises a 3D binocular camera and a digital grating projector, and is used for shooting castings to be cleaned by impurities at a plurality of angles by adopting a relative motion path in combination with a positioner of the casting cleaning robot to acquire point cloud data at a plurality of angles of the castings to be cleaned by impurities;
specifically, the data acquisition module is used for adjusting the pose of the casting to be cleaned by impurities in combination with a positioner of the casting cleaning robot so as to assist the 3D binocular camera to shoot the casting to be cleaned by impurities at multiple angles and obtain point cloud data of the casting to be cleaned by impurities at multiple angles;
the point cloud data processing module is used for carrying out point cloud registration operation based on point cloud data of a plurality of angles to obtain complete point cloud data of the casting; filtering the complete point cloud data, dividing the complete point cloud data after filtering into six areas to obtain six area point cloud data, and respectively identifying and measuring the parts to be cleaned of the six area point cloud data to obtain contour information and position information of the parts to be cleaned of each area; carrying out curved surface reconstruction based on the contour information of the part to be cleaned of each region to obtain a model of the casting to be cleaned of impurities, and further carrying out repeated comparison with a standard digital-to-analog file of the casting to obtain final contour information and position information of the part to be cleaned; and (3) completing visual measurement of the casting to be cleaned of impurities.
The man-machine interaction interface module is used for realizing visualization of casting shooting results of multiple angles, point cloud data of multiple angles, complete point cloud data, regional point cloud data, contour information and position information of a part to be cleaned of each region, a model of the casting and a final impurity part to be cleaned based on a signal and slot mechanism of Qt software by utilizing a visualization interface of the Qt graphical user interface.
Preferably, the 3D binocular camera and the digital grating projector are disposed inside the packaging shell, and are used for packaging and protecting the 3D binocular camera and the digital grating projector.
Specifically, in order to adapt to the working environment for cleaning large castings, a metal shell is used for packaging a 3D binocular camera and a digital grating projector; the metal shell plays a role in protection, and the service life of the binocular camera equipment is greatly prolonged.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (5)
1. A3D vision measurement method of a casting cleaning robot is characterized by comprising the following steps,
step 1: mounting a casting to be cleaned by impurities on a positioner clamp of a casting cleaning robot, so that the casting to be cleaned by impurities is fixed at a 1 st angle; the 1 st angle is the angle of the casting to be cleaned by impurities when the installation of the casting on the positioner is completed;
step 2: using Zhang Zhengyou calibration method to complete hand-eye calibration of the casting cleaning robot and the 3D binocular camera;
step 3: shooting the casting to be cleaned by impurities at the 1 st angle by adopting a digital grating projector and the 3D binocular camera to acquire point cloud data at the 1 st angle, and recording a relative motion path adopted by the 3D binocular camera when shooting relative to the casting to be cleaned by impurities;
step 4: the position and the posture of the casting to be cleaned by impurities are adjusted through a position changer of the casting cleaning robot, so that the casting to be cleaned by impurities is fixed at the 2 nd angle, the 3 rd angle, the … … th angle and the nth angle respectively; the 1 st angle, the 2 nd angle and the … … th angle are all different;
step 5: based on the relative motion path, a digital grating projector and the 3D binocular camera are adopted to shoot castings to be cleaned by impurities at the 2 nd angle, the 3 rd angle, the … … th angle and the nth angle respectively so as to obtain point cloud data of the 2 nd angle, the 3 rd angle, the … … th angle and the nth angle respectively;
step 6: performing point cloud registration operation based on the point cloud data of the 1 st angle, the point cloud data of the 2 nd angle, the 3 rd angle, the … … th angle and the point cloud data of the n th angle to obtain complete point cloud data of the casting to be cleaned by impurities;
step 7: filtering the complete point cloud data, dividing the filtered complete point cloud data into six areas to obtain six area point cloud data, and respectively identifying and measuring the parts to be cleaned of the six area point cloud data to obtain contour information and position information of the parts to be cleaned corresponding to each area;
step 8: and carrying out curved surface reconstruction based on the contour information of the part to be cleaned corresponding to each region to obtain a model of the casting to be cleaned by impurities, carrying out repeated comparison on the model of the casting to be cleaned by impurities and a standard digital-analog file of the casting to obtain final contour information and position information of the part to be cleaned, and controlling a casting robot to clean the casting to be cleaned by impurities based on the final contour information and position information of the part to be cleaned to finish visual measurement of the casting to be cleaned by impurities.
2. The casting cleaning robot 3D vision measurement method according to claim 1, wherein the method for dividing the filtered complete point cloud data into six areas is as follows:
1) Acquiring two points with the largest distance in the whole point cloud data and connecting the two points to form a line segment;
2) Taking two equal dividing points on the line segment to trisect the line segment;
3) Obtaining a vertical plane passing through the bisection point and perpendicular to the line segment;
4) And acquiring a plane passing through the line segment, dividing the complete point cloud data into six areas by the plane and the vertical plane, and enabling the reference characteristic of the casting to be cleaned by impurities to be in any one of the six areas.
3. The 3D vision measurement method of a casting cleaning robot according to claim 1, wherein in the step 3, the method for acquiring the point cloud data of the 1 st angle is as follows:
1) Controlling a digital grating projector to project a structural light pattern to the casting to be cleaned by impurities by using an OpenCV technology;
2) Utilize 3D vision camera to shoot the foundry goods of having cast structure light pattern to carry out impurity clearance to based on the profile of foundry goods of waiting to carry out impurity clearance, obtain the three-dimensional surface information of foundry goods of waiting to carry out impurity clearance, and then obtain the point cloud data of foundry goods of waiting to carry out impurity clearance.
4. The method of claim 1, wherein the step 5 further comprises: and (3) realizing visualization of the casting shooting result, the 1 st angle, the 2 nd angle, the 3 rd angle, the … … th angle, the nth angle, the 1 st angle, the 2 nd angle, the 3 rd angle, the … … th angle, the point cloud data of the nth angle, the complete point cloud data, the regional point cloud data, the contour information and the position information of the part to be cleaned of each region, the model of the casting and the final impurity part to be cleaned by utilizing a visualization interface of the Qt graphical user interface based on a signal and a slot mechanism of Qt software.
5. The measurement system of the 3D vision measurement method of the casting cleaning robot according to any one of claims 1 to 4, comprising a data acquisition module, a point cloud data processing module and a man-machine interaction interface module;
the data acquisition module comprises a 3D binocular camera and a digital grating projector, and is used for combining a position shifter of a casting cleaning robot, shooting castings at the 1 st angle, the 2 nd angle, the 3 rd angle, … … and the nth angle by adopting a relative motion path, and acquiring point cloud data of the castings at the 1 st angle, the 2 nd angle, the 3 rd angle, … … and the nth angle to be cleaned by impurities;
the point cloud data processing module is used for performing point cloud registration operation based on the point cloud data of the 1 st angle, the 2 nd angle, the 3 rd angle, the … … th angle and the nth angle to obtain complete point cloud data of the casting; filtering the complete point cloud data, dividing the complete point cloud data after filtering into six areas to obtain six area point cloud data, and respectively identifying and measuring the parts to be cleaned of the six area point cloud data to obtain contour information and position information of the parts to be cleaned of each area; carrying out curved surface reconstruction based on the contour information of the part to be cleaned of each region to obtain a model of the casting to be cleaned of impurities, and further carrying out repeated comparison with a standard digital-to-analog file of the casting to obtain final contour information and position information of the part to be cleaned; completing visual measurement of castings to be cleaned of impurities;
the man-machine interaction interface module is used for realizing visualization of the 1 st angle, the 2 nd angle, the 3 rd angle, the … … th angle, the 1 st angle, the 2 nd angle, the 3 rd angle, the … … th angle, the n-th angle point cloud data, the complete point cloud data, the regional point cloud data, the contour information and the position information of the part to be cleaned of each region, the model of the casting and the final impurity part to be cleaned by utilizing a visual interface of the Qt graphical user interface and based on a signal and a groove mechanism of Qt software.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311397449.1A CN117450922A (en) | 2023-10-25 | 2023-10-25 | Casting cleaning robot 3D vision measurement method and measurement system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311397449.1A CN117450922A (en) | 2023-10-25 | 2023-10-25 | Casting cleaning robot 3D vision measurement method and measurement system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117450922A true CN117450922A (en) | 2024-01-26 |
Family
ID=89586751
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311397449.1A Pending CN117450922A (en) | 2023-10-25 | 2023-10-25 | Casting cleaning robot 3D vision measurement method and measurement system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117450922A (en) |
-
2023
- 2023-10-25 CN CN202311397449.1A patent/CN117450922A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112964186B (en) | Device and method for measuring clearance in automatic shaft hole assembly process | |
| CN106346315B (en) | Machine tool control system capable of obtaining workpiece origin and workpiece origin setting method | |
| JP5606786B2 (en) | Calibration method and calibration apparatus | |
| US9080855B2 (en) | Method utilizing image correlation to determine position measurements in a machine vision system | |
| CN109648202B (en) | Additive manufacturing forming precision control method for non-flat surface autonomous recognition robot | |
| US10579890B2 (en) | Automatic alignment of a 3D model to a test object | |
| Bernal et al. | Performance evaluation of optical scanner based on blue LED structured light | |
| CN111531407A (en) | Workpiece attitude rapid measurement method based on image processing | |
| JP2021193400A (en) | Method for measuring artefact | |
| CN113222955A (en) | Gear size parameter automatic measurement method based on machine vision | |
| Quinsat et al. | A novel approach for in-situ detection of machining defects | |
| CN117450922A (en) | Casting cleaning robot 3D vision measurement method and measurement system | |
| JP3340143B2 (en) | Polishing tool control device | |
| TWI575344B (en) | Tool processing and positioning method and device | |
| CN209036141U (en) | Numerically-controlled machine tool processes three-dimensional aided positioning system | |
| JP6562724B2 (en) | Blade position measuring method and blade position measuring apparatus | |
| JP6010711B1 (en) | Defect inspection method and defect inspection apparatus | |
| Bao | Research on machine vision technology of high speed robot sorting system based on deep learning | |
| Lerones et al. | Total quality control for automotive raw foundry brake disks | |
| Shivshankar et al. | 3D scanning: A new approach towards model development in advanced manufacturing system | |
| Marchewka et al. | An approach to an intelligent scanning of the machine tool workspace | |
| CN117392129B (en) | Diesel engine gluing detection method and device based on 2D machine vision | |
| Deng et al. | Calibration of a robot vision system coupled with structured light: method and experiments | |
| Srikanthan et al. | Development of reverse engineering methododolgy for the production of machine part | |
| CN207319046U (en) | A kind of laser is in machine centering and inter process measuring device |
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 |