CN116766194A - Binocular vision-based disc workpiece positioning and grabbing system and method - Google Patents
Binocular vision-based disc workpiece positioning and grabbing system and method Download PDFInfo
- Publication number
- CN116766194A CN116766194A CN202310831249.6A CN202310831249A CN116766194A CN 116766194 A CN116766194 A CN 116766194A CN 202310831249 A CN202310831249 A CN 202310831249A CN 116766194 A CN116766194 A CN 116766194A
- Authority
- CN
- China
- Prior art keywords
- axis
- workpiece
- binocular camera
- binocular
- disc
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 239000013598 vector Substances 0.000 claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 8
- 230000033001 locomotion Effects 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims description 42
- 238000013519 translation Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000003384 imaging method Methods 0.000 claims description 7
- 238000004519 manufacturing process Methods 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 7
- 230000002146 bilateral effect Effects 0.000 claims description 6
- 230000003287 optical effect Effects 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000012821 model calculation Methods 0.000 claims description 2
- 210000000078 claw Anatomy 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
Abstract
The invention discloses a binocular vision-based disc workpiece positioning and grabbing system and a binocular vision-based disc workpiece positioning and grabbing method, wherein a control mechanical arm drives a binocular camera to move to an image acquisition point position and acquire a workpiece image; secondly, adopting a shape template matching-based method to realize image recognition and positioning of the disc workpiece; then calculating the spatial position of the contour point of the disc workpiece through a stereo matching algorithm, and fitting the contour point to obtain the centroid position of the contour point and the normal vector of the plane; finally, according to the hand-eye relation, converting the workpiece pose information under the binocular camera coordinate system to the mechanical arm base coordinate system, and according to the workpiece pose, adjusting the motion of the pneumatic hand claw pose at the tail end of the mechanical arm to grasp the disc workpiece; on the basis of lacking of workpiece models and positioning feature points, the accurate grabbing task of the mechanical arm on the workpiece is realized.
Description
Technical Field
The invention belongs to the technical field of vision detection and reconstruction, and relates to a binocular vision-based disc workpiece positioning and grabbing system and method.
Background
At present, most industrial mechanical arms realize repeated motion of fixed tracks in production and manufacture, and the operation mode depends on off-line programming or on-line teaching. Along with the digital upgrade of the production line in the production and manufacture, the mechanical arm is required to acquire the working environment information through an external sensor. In order to realize autonomous operation of the mechanical arm, three-dimensional reconstruction is needed to be carried out on a workpiece to be grabbed by utilizing a binocular camera, feature information such as the size and the pose of the workpiece is obtained, and the feature information of the workpiece is transmitted to the mechanical arm, so that the mechanical arm is guided to execute a grabbing task.
The positioning mode of the workpiece to be grasped by using the binocular camera is mainly divided into two modes: the first is a three-dimensional matching mode by adopting ICP registration model point clouds. The ICP (Iterativeclosetpoint) algorithm is called an iterative closest point algorithm, and is an algorithm for iteratively calculating a rigid body transformation matrix of a departure target point cloud and a model point cloud after the target point cloud and the model point cloud are obtained. The method comprises the steps of discretizing a three-dimensional model of a workpiece, performing fitting calculation on model point cloud data generated after discretization and workpiece point cloud data acquired by a binocular camera, and finding out a rotation matrix R and a translation matrix T between real-point cloud data and model point cloud data. The second method is to match the three-dimensional features to locate the target position. The feature description is based on the distribution state of a certain point and other points in the neighborhood range and the mathematical description of the point. The feature matching is to find the nearest combination between the workpiece features of the actual measurement target and the workpiece model features, and the rotation translation matrix between the actual measurement target and the workpiece model can be solved through the feature matching with geometric consistency. Because the sizes of the grabbed workpieces are different and part of the workpieces lack a three-dimensional model, the two positioning modes are not feasible, and a new positioning method for disc workpieces needs to be found.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention aims to provide a binocular vision-based disc workpiece positioning and grabbing system and method, which can realize the accurate grabbing task of a mechanical arm on a workpiece under the condition of lacking a grabbing workpiece model and different sizes of grabbing workpieces.
The invention is realized by the following technical scheme:
a disc workpiece positioning and grabbing method based on binocular vision comprises the following steps:
step 1), controlling a mechanical arm to drive a binocular camera to move to an image acquisition point, and placing a disc workpiece on the plane of an operation table; the distance between the binocular camera and the plane of the operation table is selected by referring to the hardware parameter calculation value of the binocular camera, and the height of the plane of the operation table from the ground is determined according to the working space of the six-degree-of-freedom mechanical arm;
step 2) carrying out internal and external parameter identification on the binocular camera by using MATLAB software and a calibration plate, and obtaining left and right internal parameters of the binocular camera and pose relation between the left and right binocular cameras according to the parameter identification result;
step 3) processing the collected image by using a bilateral filter, manufacturing a matching template by adopting a shape feature matching-based mode according to the outline features of the disc workpieces, realizing automatic identification of the disc workpieces in the collected image, and determining the positions of the workpieces in the image;
step 4) calculating pixel point coordinates of the outline of the disc workpiece on the left image and the right image respectively through a stereo matching algorithm, calculating corresponding parallax by utilizing coordinate information, and reconstructing the outline space position of the disc workpiece according to a binocular imaging principle and by combining the parallax of the pixel points;
step 5) reconstructing the space contour points of the disc workpiece in the step 4) by using a least square fitting method, and acquiring the circle center coordinates and the normal vector of the plane where the space circle contour is located according to fitted information;
step 6) calculating a rotation matrix R and a translation matrix T between the coordinate system of the pneumatic paw and the coordinate system of the binocular camera through the hand-eye model acquisition data;
step 7) converting pose information of the disc-type workpiece into a base coordinate system of the mechanical arm by utilizing the hand-eye model in the step 6);
and 8) the mechanical arm carries out inverse solution operation according to the pose information of the disc workpiece, obtains the rotation angles of all joints, and adjusts the motions of all joints to carry out the grabbing task in accurate pose.
Further, step 2) performing internal and external parameter identification on the binocular camera by using MATLAB software to obtain the parameters in the binocular camera as shown in formula (1); substituting the left and right binocular camera internal parameter results into a binocular camera parameter calibration program to calculate a position and posture matrix of the right binocular camera relative to the left binocular camera as shown in formula (2), wherein the position and posture matrix is generally represented by a 3×3 rotation matrix R and a 3×1 translation matrix T:
wherein M is 1 F in matrix x Using pixels to describe the length of the x-axis focal length, f y To describe the length of the focal length in the y-axis direction using pixels, γ is the twist factor of the image in the physical coordinate system when x, y are not perpendicular, typically 0, u 0 、v 0 A number of horizontal and vertical pixels representing a phase difference between a center pixel coordinate of the image and an origin pixel coordinate of the image;
r in R matrix 1 、r 4 、r 7 The chord values of the clamping angles of the x axis, the y axis and the z axis in the new coordinate axes after the x axis and the rotation are respectively represented, r 2 、r 5 、r 8 And the chord values of the clamping angles of the x axis, the y axis and the z axis in the new coordinate axes after the y axis and the rotation are respectively represented, and r 3 、r 6 、r 9 Respectively representing the residual string values of the clamping angles of the x axis, the y axis and the z axis in the new coordinate axes after the z axis and the rotation;
t in the translation matrix T x 、t y 、t z Representing the translation distances of the new coordinate axis relative to the translation front coordinate axis in the x-axis, the y-axis and the z-axis respectively.
Further, the bilateral filter templates in the step 3) are:
wherein, (x, y) is the position of the pixel point to be calculated, (s, t) is the central coordinate of the template window, and g (x, y) is the pixel value; f (s, t) represents the coordinate value of the image at the point (s, t), σ 1 、σ 2 Representative ofStandard deviation, K 1 、K 2 Representing coefficients at different standard deviations.
Further, in the step 3), a matching template is manufactured in a mode based on shape feature matching according to the circular outline features of the disc workpieces, and the workpieces in the image are searched by setting the diameter of the circle as a threshold parameter, so that the disc workpieces are automatically identified in the acquired image, and the positions of the workpieces in the image are determined.
Further, in the step 4), the three-dimensional coordinate calculation process of the space point by utilizing the parallax method (5) is utilized, and the outline space position of the disc workpiece is reconstructed according to the binocular imaging principle and the parallax of the pixel point;
knowing d=u l -u r Representing the parallax corresponding to the pixel point; f and (u) 0 ,v 0 ) Representing the effective focal length and principal point parameters of the binocular camera respectively; b is a baseline distance, and the value of b is the distance between the x axes of the left and right binocular camera coordinate systems in the step (2).
Further, in the step 8), the gesture of the pneumatic gripper is adjusted according to the normal vector n1 of the plane where the circular outline is located, the mechanical arm moves to the image acquisition point, the direction vector n2 between the TCP point of the pneumatic gripper and the centroid of the workpiece is calculated, and in the process of grabbing the mechanical arm, the angle transformation between the vectors n1 and n2 is converted into the rotation angle of each joint of the mechanical arm, so that the superposition of the two vectors is realized, and the aim of adjusting the grabbing gesture is achieved.
Further, the optical axis of the binocular camera is distributed in parallel.
The disc workpiece positioning and grabbing system based on binocular vision comprises a six-degree-of-freedom mechanical arm, a binocular camera, a pneumatic paw, a calibration plate and an operation table;
in the grabbing process, a disc workpiece and a calibration plate are placed on the plane of an operation table, optical axes of binocular cameras used in visual positioning are distributed in parallel, and the binocular cameras and the pneumatic claws are fixed at the tail end of a six-degree-of-freedom mechanical arm through rigid connecting pieces;
the method comprises the steps that a tool point TCP calibration process is utilized to determine a homogeneous transformation matrix T between a coordinate system of a pneumatic gripper relative to a coordinate system of a mechanical arm base, and a rotation matrix R and a translation matrix T between the coordinate system of a binocular camera and the coordinate system of the pneumatic gripper are obtained through hand-eye model calculation; calculating the distance between the binocular camera and the plane of an operation table for placing a workpiece by combining the type selection parameters of the binocular camera and the working space of the six-degree-of-freedom mechanical arm, controlling the mechanical arm to drive the binocular camera to move to a set image acquisition position to acquire images, and implementing the grabbing task by adopting the positioning and grabbing method as set forth in any one of claims 1-7.
The binocular vision-based disc workpiece positioning and grabbing method of claim 1, wherein: the diameter of the disc workpiece is 20-40mm.
Compared with the prior art, the invention has the beneficial effects that:
according to the binocular vision-based disc workpiece positioning and grabbing method, spatial contour information of a workpiece to be grabbed is collected in a mode that a binocular camera is arranged at the tail end of a mechanical arm, the mechanical arm is controlled to drive the binocular camera to move to an image collection point position and collect images of the workpiece, and an OpenCV image processing library is used for image processing. Firstly, calibrating a binocular camera by using a calibration plate to obtain internal parameters of the binocular camera and relative position relations between left and right binocular cameras; secondly, adopting a shape template matching-based method to realize image recognition and positioning of the disc workpiece; then calculating the spatial position of the contour point of the disc workpiece through a stereo matching algorithm, and fitting the contour point to obtain the centroid position of the contour point and the normal vector of the plane; and finally, converting the pose information of the workpiece in the binocular camera coordinate system into the mechanical arm base coordinate system according to the hand-eye relation, and adjusting the movement of the pneumatic gripper pose at the tail end of the mechanical arm according to the pose of the workpiece to grasp the disc workpiece.
On the basis of lacking of a workpiece model and positioning characteristic points, the contour points of a target workpiece are extracted, the centroid coordinates and the normal vector of the plane where the workpiece is positioned are obtained through fitting, the pose information of the workpiece is converted into the coordinate system of the mechanical arm through the hand-eye relation, the pose of the pneumatic gripper of the mechanical arm is adjusted to achieve the grabbing task of the workpiece, and the accurate grabbing task of the mechanical arm on the workpiece is achieved.
Drawings
FIG. 1 is a schematic diagram of a system of the present invention;
FIG. 2 is a schematic diagram of the outline space position of a disc workpiece reconstructed by combining the binocular imaging principle and the parallax of pixel points;
in the figure: the device comprises a 1-six-degree-of-freedom mechanical arm, a 2-binocular camera, a 3-pneumatic paw, a 4-calibration plate, a 5-operating platform and a 6-disc workpiece.
Detailed Description
The following description of the embodiments of the present invention will be made by referring to the drawings, in which the embodiments of the present invention are shown, it being apparent that the embodiments described are only some, 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.
Referring to fig. 1, the present embodiment is a binocular vision-based positioning and grabbing system for a disc workpiece, which includes a six-degree-of-freedom mechanical arm 1, a binocular camera 2, a pneumatic gripper 3, a calibration plate 4, an operation table 5, and a disc workpiece 6. Binocular camera model: hbv-1780-2S2.0; computer configuration: the processor I5-7300HQRAM 16GB, the image processing portion of the system uses an open source OpenCV image processing library. The OpenCV library is written in C language and c++ language, and the objective is to provide an easy-to-use computer vision interface, which helps beginners quickly build up exquisite vision applications. The OpenCV library contains up to 500 functions derived from various fields of computer vision, including industrial quality detection, medical image processing, binocular vision, and the like.
In the above-described positioning and gripping system, the disk-like workpiece 6 has a spatial circular outline and a direction vector of a plane on which the circle is located, and the disk-like workpiece 6 and the calibration plate 4 are placed on the plane of the operation table 5. The optical axes of the binocular cameras 2 used in visual positioning are distributed in parallel, the binocular cameras 2 and the pneumatic gripper 3 are fixed at the tail end of the six-degree-of-freedom mechanical arm 1 through a rigid connecting piece, a tool point TCP calibration process is utilized to determine a homogeneous transformation matrix T between a coordinate system of the pneumatic gripper 3 and a coordinate system of the mechanical arm base 1, and a rotation matrix R and a translation matrix T between the coordinate system of the binocular cameras 2 and the coordinate system of the pneumatic gripper 3 are obtained through hand-eye relation calculation. And calculating the distance between the binocular camera 2 and the plane of the operating platform 5 for placing the workpiece by combining the model selection parameters of the binocular camera 2 and the working space of the six-degree-of-freedom mechanical arm 1. The control mechanical arm 1 drives the binocular camera 2 to move to a set image collecting position to collect images.
The system for implementing the positioning grabbing task comprises the following steps:
(1) The control mechanical arm 1 drives the binocular camera 2 to move to an image acquisition point, and a disc workpiece 6 is placed on the plane of the operation table 5; the diameter of the disc-type workpiece is 20-40mm, and the maximum diameter of the workpiece grasped by the pneumatic gripper 3 is 47mm; the distance between the binocular camera 2 and the plane of the console 5 is selected by referring to the calculated values of the hardware parameters of the binocular camera, and the height of the plane of the console 5 from the ground is determined according to the working space of the six-degree-of-freedom mechanical arm 1.
(2) Calibrating binocular camera
The left and right cameras are controlled to simultaneously acquire images and correct the images by using a 'stereocamera library' command in matlab software. Opening matlab input 'stereoCameraCalibrator', entering a toolbox, clicking addimages, adding a picture path, modifying the size (according to the side length of a grid), clicking calibrete, and obtaining internal parameters, external parameters, distortion parameters and the like of the binocular camera.
Performing internal and external parameter identification on the binocular camera by using MATLAB software to obtain the internal parameters of the binocular camera as shown in formula (1); substituting the left and right binocular camera internal parameter results into the binocular camera parameter calibration program can calculate the position and posture matrix of the right binocular camera relative to the left binocular camera as shown in the formula (2), and the position and posture matrix is generally represented by a 3×3 rotation matrix R and a 3×1 translation matrix T.
Wherein M is 1 F in matrix x Using pixels to describe the length of the x-axis focal length, f y To describe the length of the focal length in the y-axis direction using pixels, γ is the twist factor of the image in the physical coordinate system when x, y are not perpendicular, typically 0, u 0 、v 0 A number of horizontal and vertical pixels representing a phase difference between a center pixel coordinate of the image and an origin pixel coordinate of the image;
r in R matrix 1 、r 4 、r 7 The chord values of the clamping angles of the x axis, the y axis and the z axis in the new coordinate axes after the x axis and the rotation are respectively represented, r 2 、r 5 、r 8 And the chord values of the clamping angles of the x axis, the y axis and the z axis in the new coordinate axes after the y axis and the rotation are respectively represented, and r 3 、r 6 、r 9 Respectively representing the residual string values of the clamping angles of the x axis, the y axis and the z axis in the new coordinate axes after the z axis and the rotation;
t in the translation matrix T x 、t y 、t z Representing the translation distances of the new coordinate axis relative to the translation front coordinate axis in the x-axis, the y-axis and the z-axis respectively.
(3) According to the outline characteristics of the disc-like workpiece 6, a matching template is manufactured by adopting a mode based on shape characteristic matching
1) Opening a binocular camera SDK to collect shaft workpiece pictures;
2) Preprocessing the collected original image, and processing the collected image by using a bilateral filtering function 'bilateralFilter' for the purposes of denoising the image and storing the edge of a workpiece;
the template of the bilateral filter is shown as equation (3):
wherein (x, y) is the pixel position to be calculated, and (s, t) isThe center coordinates of the template window, g (x, y) being the pixel value; f (s, t) represents the coordinate value of the image at the point (s, t), σ 1 、σ 2 Represents standard deviation, K 1 、K 2 Representing coefficients at different standard deviations.
3) The profile features of the original image and the template image are extracted using the "findContours" function in the opencv library.
4) The outline features of the template image are scaled and rotated using the "getRotationMatrix2D" and "warp affine" functions to generate multiple templates.
(4) The automatic identification and determination of the position of the disc-type workpiece 6 in the image are realized in the acquired image.
1) And matching the outline features of the original image by using a 'matchShapes' function in an opencv library, and calculating the shape similarity.
2) If the shape similarity is smaller than 0.1, the matching is considered to be successful, and the matching result is saved.
3) The coordinates of pixel points on the left and right images of the outline of the disc workpiece 6 are calculated through a stereo matching algorithm, corresponding parallaxes are calculated by utilizing coordinate information, and the outline space position of the disc workpiece 6 is reconstructed according to the binocular imaging principle and by combining the parallaxes of the pixel points.
And (3) identifying the position information of the circular outline of the workpiece on the left and right images respectively, as shown in fig. 2, reconstructing the outline space position of the disc workpiece according to the binocular imaging principle and combining the parallax of the pixel points, wherein the formula (5) is a space point three-dimensional coordinate calculation process by utilizing a parallax method.
Knowing d=u l -u r Representing the parallax corresponding to the pixel point; f and (u) 0 ,v 0 ) Representing the effective focal length and principal point parameters of the binocular camera respectively; b is a baseline distance, and the value of b is the distance between the x axes of the left and right binocular camera coordinate systems in the step (2).
(5) Fitting the spatial contour points of 6 of the disc-like workpiece in step (4) by using a least square method in matlab
1) Expressing the scattered point data as a matrix containing x and y coordinates;
2) Defining an error function, and calculating the distance between each data point and the fitting circle by using the Euclidean distance formula;
3) The lsqnonlin function is used in matlab to minimize the error function and find the best center and radius parameters.
4) And drawing a fitting circle by using fitting parameters, and acquiring a normal vector of a plane where the circle center coordinates and the space circle outline are located according to the fitted information.
(6) The rotation matrix R and the translation matrix T between the coordinate system of the pneumatic gripper 3 and the coordinate system of the binocular camera 2 are calculated by the hand-eye model acquisition data.
(7) And (3) converting pose information of the disc workpiece 6 into a base coordinate system of the mechanical arm 1 by using the hand-eye conversion matrix in the step (6).
(8) The mechanical arm 1 carries out inverse solution operation according to the pose information of the disc workpiece 6 to obtain the rotation angles of all joints, and adjusts the motions of all joints to carry out grabbing tasks in accurate poses.
The mechanical arm executes a grabbing task, and the gesture of the tail end pneumatic gripper is required to be adjusted according to the normal vector n1 of the plane where the circular outline is located. The mechanical arm moves to the image acquisition point, and a direction vector n2 between the TCP point of the pneumatic gripper and the centroid of the workpiece is calculated. In the grabbing process of the mechanical arm, the angle transformation between the vectors n1 and n2 is converted into the rotation angle of each joint of the mechanical arm, so that the superposition of the two vectors is realized, and the aim of adjusting the grabbing gesture is fulfilled.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended only to illustrate the invention by the editorial staff. The preferred embodiments are not exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention.
Claims (9)
1. A disc workpiece positioning and grabbing method based on binocular vision is characterized by comprising the following steps:
step 1), controlling a mechanical arm to drive a binocular camera to move to an image acquisition point, and placing a disc workpiece on the plane of an operation table; the distance between the binocular camera and the plane of the operation table is selected by referring to the hardware parameter calculation value of the binocular camera, and the height of the plane of the operation table from the ground is determined according to the working space of the six-degree-of-freedom mechanical arm;
step 2) carrying out internal and external parameter identification on the binocular camera by using MATLAB software and a calibration plate, and obtaining left and right internal parameters of the binocular camera and pose relation between the left and right binocular cameras according to the parameter identification result;
step 3) processing the collected image by using a bilateral filter, manufacturing a matching template by adopting a shape feature matching-based mode according to the outline features of the disc workpieces, realizing automatic identification of the disc workpieces in the collected image, and determining the positions of the workpieces in the image;
step 4) calculating pixel point coordinates of the outline of the disc workpiece on the left image and the right image respectively through a stereo matching algorithm, calculating corresponding parallax by utilizing coordinate information, and reconstructing the outline space position of the disc workpiece according to a binocular imaging principle and by combining the parallax of the pixel points;
step 5) reconstructing the space contour points of the disc workpiece in the step 4) by using a least square fitting method, and acquiring the circle center coordinates and the normal vector of the plane where the space circle contour is located according to fitted information;
step 6) calculating a rotation matrix R and a translation matrix T between the coordinate system of the pneumatic paw and the coordinate system of the binocular camera through the hand-eye model acquisition data;
step 7) converting pose information of the disc-type workpiece into a base coordinate system of the mechanical arm by utilizing the hand-eye model in the step 6);
and 8) the mechanical arm carries out inverse solution operation according to the pose information of the disc workpiece, obtains the rotation angles of all joints, and adjusts the motions of all joints to carry out the grabbing task in accurate pose.
2. The binocular vision-based disc workpiece positioning and grabbing method of claim 1, wherein: step 2) performing internal and external parameter identification on the binocular camera by using MATLAB software to obtain parameters in the binocular camera as shown in formula (1); substituting the left and right binocular camera internal parameter results into a binocular camera parameter calibration program to calculate a position and posture matrix of the right binocular camera relative to the left binocular camera as shown in formula (2), wherein the position and posture matrix is generally represented by a 3×3 rotation matrix R and a 3×1 translation matrix T:
wherein M is 1 F in matrix x Using pixels to describe the length of the x-axis focal length, f y To describe the length of the focal length in the y-axis direction using pixels, γ is the twist factor of the image in the physical coordinate system when x, y are not perpendicular, typically 0, u 0 、v 0 A number of horizontal and vertical pixels representing a phase difference between a center pixel coordinate of the image and an origin pixel coordinate of the image;
r in R matrix 1 、r 4 、r 7 The chord values of the clamping angles of the x axis, the y axis and the z axis in the new coordinate axes after the x axis and the rotation are respectively represented, r 2 、r 5 、r 8 Representing the y-axis and new after rotation, respectivelyThe chord values of the clamping angles of the x axis, the y axis and the z axis in the coordinate axis, r 3 、r 6 、r 9 Respectively representing the residual string values of the clamping angles of the x axis, the y axis and the z axis in the new coordinate axes after the z axis and the rotation;
t in the translation matrix T x 、t y 、t z Representing the translation distances of the new coordinate axis relative to the translation front coordinate axis in the x-axis, the y-axis and the z-axis respectively.
3. The binocular vision-based disc workpiece positioning and grabbing method of claim 1, wherein: the bilateral filter template in the step 3) is as follows:
wherein, (x, y) is the position of the pixel point to be calculated, (s, t) is the central coordinate of the template window, and g (x, y) is the pixel value; f (s, t) represents the coordinate value of the image at the point (s, t), σ 1 、σ 2 Represents standard deviation, K 1 、K 2 Representing coefficients at different standard deviations.
4. The binocular vision-based disc workpiece positioning and grabbing method of claim 1, wherein: in the step 3), a matching template is manufactured according to the circular outline characteristics of the disc workpieces in a shape characteristic matching mode, and the workpieces in the image are searched by setting the diameter of the circle as a threshold parameter, so that the disc workpieces are automatically identified in the acquired image, and the positions of the workpieces in the image are determined.
5. The binocular vision-based disc workpiece positioning and grabbing method of claim 1, wherein: in the step 4), the three-dimensional coordinate calculation process of the space point by utilizing the parallax method of (5) is utilized, and the outline space position of the disc workpiece is reconstructed according to the binocular imaging principle and the parallax of the pixel point;
knowing d=u l -u r Representing the parallax corresponding to the pixel point; f and (u) 0 ,v 0 ) Representing the effective focal length and principal point parameters of the binocular camera respectively; b is a baseline distance, and the value of b is the distance between the x axes of the left and right binocular camera coordinate systems in the step (2).
6. The binocular vision-based disc workpiece positioning and grabbing method of claim 1, wherein: in the step 8), the gesture of the pneumatic gripper is adjusted according to a plane normal vector n1 where the circular outline is located, the mechanical arm moves to an image acquisition point, a direction vector n2 between a TCP point of the pneumatic gripper and the centroid of the workpiece is calculated, and in the grabbing process of the mechanical arm, the angle transformation between the vectors n1 and n2 is converted into the rotating angle of each joint of the mechanical arm, so that the superposition of the two vectors is realized, and the aim of adjusting the grabbing gesture is fulfilled.
7. The binocular vision-based disc workpiece positioning and grabbing method of claim 1, wherein: the optical axis of the binocular camera is distributed in parallel.
8. Disc type work piece location and snatchs system based on binocular vision, its characterized in that: comprises a six-degree-of-freedom mechanical arm (1), a binocular camera (2), a pneumatic paw (3), a calibration plate (4) and an operation table (5);
in the grabbing process, a disc workpiece (6) and a calibration plate (4) are placed on the plane of an operation table (5), optical axis lines of binocular cameras (2) used in visual positioning are distributed in parallel, and the binocular cameras (2) and a pneumatic paw (3) are fixed at the tail end of a six-degree-of-freedom mechanical arm (1) through a rigid connecting piece;
the coordinate system of the pneumatic gripper (3) can be determined to be in homogeneous transformation matrix T relative to the coordinate system of the mechanical arm base 1 by utilizing the tool point TCP calibration process, and a rotation matrix R and a translation matrix T between the coordinate system of the binocular camera (2) and the coordinate system of the pneumatic gripper (3) are obtained through hand-eye model calculation; by combining the model selection parameters of the binocular camera (2) and the working space of the six-degree-of-freedom mechanical arm (1), calculating the distance between the binocular camera (2) and the plane of the operating platform (5) for placing the workpiece, controlling the mechanical arm (1) to drive the binocular camera (2) to move to a set image acquisition position to acquire images, and implementing the grabbing task by adopting the positioning and grabbing method as claimed in any one of claims 1-7.
9. The binocular vision-based positioning and gripping system for disc-type workpieces of claim 1, wherein: the diameter of the disc workpiece is 20-40mm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310831249.6A CN116766194A (en) | 2023-07-07 | 2023-07-07 | Binocular vision-based disc workpiece positioning and grabbing system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310831249.6A CN116766194A (en) | 2023-07-07 | 2023-07-07 | Binocular vision-based disc workpiece positioning and grabbing system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116766194A true CN116766194A (en) | 2023-09-19 |
Family
ID=87992910
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310831249.6A Withdrawn CN116766194A (en) | 2023-07-07 | 2023-07-07 | Binocular vision-based disc workpiece positioning and grabbing system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116766194A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117455984A (en) * | 2023-12-26 | 2024-01-26 | 深圳市信润富联数字科技有限公司 | Method and device for determining acquisition point of arm-following camera |
| CN117549338A (en) * | 2024-01-09 | 2024-02-13 | 北京李尔现代坦迪斯汽车系统有限公司 | Grabbing robot for automobile cushion production workshop |
-
2023
- 2023-07-07 CN CN202310831249.6A patent/CN116766194A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117455984A (en) * | 2023-12-26 | 2024-01-26 | 深圳市信润富联数字科技有限公司 | Method and device for determining acquisition point of arm-following camera |
| CN117455984B (en) * | 2023-12-26 | 2024-03-26 | 深圳市信润富联数字科技有限公司 | Method and device for determining acquisition point of arm-following camera |
| CN117549338A (en) * | 2024-01-09 | 2024-02-13 | 北京李尔现代坦迪斯汽车系统有限公司 | Grabbing robot for automobile cushion production workshop |
| CN117549338B (en) * | 2024-01-09 | 2024-03-29 | 北京李尔现代坦迪斯汽车系统有限公司 | Grabbing robot for automobile cushion production workshop |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113524194B (en) | Target grabbing method of robot vision grabbing system based on multi-mode feature deep learning | |
| CN109202912B (en) | Method for registering target contour point cloud based on monocular depth sensor and mechanical arm | |
| JP6004809B2 (en) | Position / orientation estimation apparatus, information processing apparatus, and information processing method | |
| CN116766194A (en) | Binocular vision-based disc workpiece positioning and grabbing system and method | |
| CN111775146A (en) | Visual alignment method under industrial mechanical arm multi-station operation | |
| CN111476841B (en) | Point cloud and image-based identification and positioning method and system | |
| CN109702738B (en) | Mechanical arm hand-eye calibration method and device based on three-dimensional object recognition | |
| CN110065068B (en) | Robot assembly operation demonstration programming method and device based on reverse engineering | |
| CN112862878B (en) | Mechanical arm blank repairing method based on 3D vision | |
| CN111801198A (en) | Hand-eye calibration method, system and computer storage medium | |
| CN113910219A (en) | Exercise arm system and control method | |
| CN112509063A (en) | Mechanical arm grabbing system and method based on edge feature matching | |
| CN113421291B (en) | Workpiece position alignment method using point cloud registration technology and three-dimensional reconstruction technology | |
| CN113172659B (en) | Flexible robot arm shape measuring method and system based on equivalent center point identification | |
| Hsu et al. | Development of a faster classification system for metal parts using machine vision under different lighting environments | |
| Jerbić et al. | Robot assisted 3D point cloud object registration | |
| Sangeetha et al. | Implementation of a stereo vision based system for visual feedback control of robotic arm for space manipulations | |
| Du et al. | Eye-to-hand robotic tracking and grabbing based on binocular vision | |
| CN113172632A (en) | Simplified robot vision servo control method based on images | |
| Han et al. | Grasping control method of manipulator based on binocular vision combining target detection and trajectory planning | |
| CN116872216B (en) | Robot vision servo operation method based on finite time control | |
| CN117340929A (en) | Flexible clamping jaw grabbing and disposing device and method based on three-dimensional point cloud data | |
| CN113793383A (en) | 3D visual identification taking and placing system and method | |
| Pachidis et al. | Vision-based path generation method for a robot-based arc welding system | |
| Ranjan et al. | Identification and control of NAO humanoid robot to grasp an object using monocular vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230919 |