CN107883929B - Monocular vision positioning device and method based on multi-joint mechanical arm - Google Patents
Monocular vision positioning device and method based on multi-joint mechanical arm Download PDFInfo
- Publication number
- CN107883929B CN107883929B CN201710864061.6A CN201710864061A CN107883929B CN 107883929 B CN107883929 B CN 107883929B CN 201710864061 A CN201710864061 A CN 201710864061A CN 107883929 B CN107883929 B CN 107883929B
- Authority
- CN
- China
- Prior art keywords
- target
- monocular camera
- mechanical arm
- pose
- monocular
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/02—Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/10—Programme-controlled manipulators characterised by positioning means for manipulator elements
- B25J9/12—Programme-controlled manipulators characterised by positioning means for manipulator elements electric
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides monocular vision positioning devices and methods based on multi-joint mechanical arms, and the methods comprise the steps of collecting image information containing a target to be positioned, identifying the target in the image information, controlling the multi-joint mechanical arms to be in at least two different pose states, enabling optical axis points of a monocular camera to coincide with the target respectively, recording the pose coordinates of the monocular camera in the coincidence state respectively, calculating the space coordinates of the target to be positioned by using a space geometry principle according to the different pose coordinates of the monocular camera, and obtaining the position of the target by adopting space geometry operation under the condition that the target is aligned with an optical axis, wherein the space geometry operation does not involve complex processing algorithms and camera internal parameter calibration, is efficient and practical, does not need a special range finder, does not need a binocular camera, and has the advantages of low equipment cost and simple operation.
Description
Technical Field
The invention relates to the technical field of machine vision, in particular to monocular vision positioning devices and methods based on multi-joint mechanical arms.
Background
With the increase of the level of intelligence and the popularization of robot use, the mechanical arm movement control based on machine vision has attracted attention, namely, the target location is acquired through machine vision, and then the end of the mechanical arm is controlled to move to the target point to perform related operations such as grabbing.
In the process of visual guidance, currently, commonly adopted visual positioning methods comprise special distance measurement + monocular vision, binocular stereo vision, monocular vision and the like, wherein in the special distance measurement + monocular vision method, a Z-direction distance coordinate of a target is obtained through a special distance meter (an ultrasonic distance meter, a laser distance meter and the like), and a X, Y-direction coordinate is obtained through two-dimensional image processing.
In the monocular vision positioning, a monocular camera acquires multi-frame target images at different poses, the three-dimensional position of the target is calculated based on camera internal parameters, image characteristic point matching, a basic matrix, an essential matrix, a camera transfer matrix and target pixel coordinates, a target coordinate system is established through multi-point position information, and pose information is deduced.
The invention patent 201710209981.4 discloses servo follow-up visual devices and a dynamic tracking ranging method, wherein two cameras with a constant distance of are driven by a servo to enable a target to approach an optical axis, then an included angle between the optical axis and a base line is measured by a servo motor encoder, and the position of the target is obtained through geometric operation.
The invention patent 201210203745.9 discloses spray positioning methods based on mechanical arms and monocular vision, which includes aligning an optical axis of a monocular camera to a centroid of a target, moving along the optical axis, acquiring images under two different distance conditions, calculating characteristic sizes of the target images based on internal parameters of the camera, obtaining a distance value from the target to the camera through proportional operation by combining a moving distance difference, obtaining position and size information of the target under a coordinate system of the monocular camera according to the obtained distance, the size of the target image and the focal length of the monocular camera, and finally obtaining the position information of the target under a world coordinate system through coordinate system conversion.
The invention patent 201410016272.0 discloses a target pose measurement method based on mechanical arms and monocular vision, which comprises the steps of firstly calibrating internal parameters of a camera, calibrating hands and eyes of the mechanical arms, acquiring a basic matrix of a target image under two different shooting poses based on a antipodal geometry method, then acquiring a monocular camera rotation matrix and a displacement transformation matrix of two shooting positions by combining the basic matrix, an internal reference matrix, an essential matrix and a hand and eye calibration matrix, then acquiring three-dimensional coordinates of a target upper calibration point relative to a monocular camera based on the two monocular camera transformation matrices, a target pixel coordinate and an actual physical distance of a target upper calibration point, and finally establishing a target coordinate system according to a multi-marker space position to acquire an overall pose state of the target relative to a monocular camera coordinate system and a target coordinate system.
However, although the above-mentioned visual positioning method can achieve better effect in terms of accuracy, there are disadvantages such as high system cost, tedious calibration of camera internal parameters, and complex processing algorithm, so how to propose monocular visual positioning devices and methods with low cost and simple operation and calculation is a problem that the present invention needs to solve.
Disclosure of Invention
In view of the above disadvantages of the prior art, the present invention aims to provide monocular vision positioning devices and methods based on multi-joint mechanical arms, which are used to solve the problems of high cost, complicated camera internal reference calibration, and complex processing algorithm of the monocular vision positioning system of the robot arm in the prior art.
To achieve the above and other related objects, the present invention provides monocular vision positioning devices based on articulated robotic arms, comprising:
the system comprises a mechanical arm base, a multi-joint mechanical arm, a monocular camera and control equipment;
the multi-joint mechanical arm is arranged on the mechanical arm base, and the monocular camera is arranged on the mechanical arm and used for acquiring image information in real time; the image information comprises images of the target to be positioned in various pose states;
the control device is connected with the multi-joint mechanical arm and the monocular camera respectively, the control device comprises a memory and a processor, the memory is used for storing programs and image information, the processor is used for operating the programs, and the programs further comprise:
an identification program configured to identify a target to be positioned within the image information;
the control program is configured to control the multi-joint mechanical arm to be in different pose states, wherein the optical axis point corresponding to the monocular camera in the pose state is coincided with the target to be positioned;
and the calculation program is configured to acquire at least two different camera pose coordinates under the coincidence of the optical axis point of the monocular camera and the target according to the received image information, and calculate the space coordinate of the target to be positioned by utilizing a space geometric principle.
Another object of the present invention is to provide monocular vision positioning methods based on a multi-joint robot arm, including:
collecting image information containing a target to be positioned;
identifying a target within the image information;
controlling the multi-joint mechanical arm to be in at least two different pose states, enabling optical axis points of the monocular camera to coincide with the target respectively, and recording pose coordinates of the monocular camera in the coinciding states respectively;
and calculating the space coordinate of the target to be positioned by utilizing a space geometric principle according to different pose coordinates of the monocular camera.
As described above, the monocular vision positioning device and method based on the multi-joint mechanical arm of the present invention have the following beneficial effects:
the monocular vision positioning method provided by the invention obtains the target distance by adopting space geometric operation under the condition that the target is aligned with the optical axis, does not relate to complex processing algorithm and camera internal parameter calibration, is efficient and practical, does not need a special range finder, does not need a binocular monocular camera, and has the advantages of low system cost and simple operation.
Drawings
FIG. 1 shows a block diagram of a monocular vision positioning system of types based on multi-joint mechanical arms provided by the present invention;
FIG. 2 is a flow chart of monocular vision positioning methods based on articulated robotic arms according to the present invention;
fig. 3 is a schematic diagram showing the target position solving structures of geometric operations according to the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the drawings only show the components related to the present invention rather than the number, shape and size of the components in practical implementation, the form, quantity and proportion of each component in practical implementation can be random changes, and the layout of the components may be more complicated.
Referring to fig. 1, a structural block diagram of monocular vision positioning systems based on multi-joint robot arms provided by the present invention includes:
the system comprises a mechanical arm base, a multi-joint mechanical arm, a monocular camera and control equipment;
the multi-joint mechanical arm is arranged on the mechanical arm base, and the monocular camera is arranged on the mechanical arm and used for acquiring image information in real time; the image information comprises images of the target to be positioned in various pose states;
the control device is connected with the multi-joint mechanical arm and the monocular camera respectively, the control device comprises a memory and a processor, the memory is used for storing programs and image information, the processor is used for operating the programs, and the programs further comprise:
an identification program configured to identify a target to be positioned within the image information;
the control program is configured to control the multi-joint mechanical arm to be in different pose states, wherein the optical axis point corresponding to the monocular camera in the pose state is coincided with the target to be positioned;
and the calculation program is configured to acquire at least two different camera pose coordinates under the coincidence of the optical axis point of the monocular camera and the target according to the received image information, and calculate the space coordinate of the target to be positioned by utilizing a space geometric principle.
In particular, the mechanical arm is composed of a plurality of rotary joints, preferably six rotary joints, and can achieve the state of any posture in space theoretically. Therefore, the mechanical arm drives the monocular camera arranged on the mechanical arm to move and rotate at any pose, a larger visual space is obtained, visual shielding is avoided, a target can be tracked more freely relative to the single-joint mechanical arm, and the target is prevented from overflowing an image surface.
The base coordinate system B of the robot arm base is located at the th joint while the coordinate system remains fixed with the geodetic coordinate system the tool coordinate system is located at the monocular camera mounting position at the end of the robot arm, coinciding with the camera coordinate system, i.e. the pose coordinates of the monocular camera can be seen as the pose coordinates of the tool coordinate system T relative to the base coordinate system B]Relative to a base coordinate system [ B ]]The position and pose relationship between the two is converted by a transformation matrix
And acquiring the conversion matrix, wherein the conversion matrix is related to the structure of the mechanical arm and the angle of each joint and can be acquired by a tool coordinate system calibration method.
In addition, for convenience of control, when the tail end of the mechanical arm is controlled to move, the tool coordinate system T can be selected as a reference, and accurate control of the pose coordinates of the camera is achieved on the basis of a kinematics/dynamics model. The monocular camera can optically focus or amplify at will to acquire a clear target image and improve the tracking and ranging precision.
In the embodiment, the control system controls the multi-joint mechanical arm to be in at least two different pose states, so that an optical axis point of a monocular camera coincides with the target respectively, pose coordinates of the monocular camera in the coinciding states are recorded respectively, and the space coordinate of the target to be positioned is calculated according to the different pose coordinates of the monocular camera by using a space geometry principle.
Referring to fig. 2, the present invention provides a flow chart of monocular vision positioning methods based on multi-joint robot arms, including:
step S1, collecting image information containing the target to be positioned;
the monocular camera is mounted on the multi-joint mechanical arm, so that the target to be positioned enters the visual field range of the monocular camera.
A step S2 of identifying an object within the image information;
the image preprocessing filters noise, and the stored image information is compared with the currently acquired image information to realize image positioning of the target to be positioned, so that the target to be positioned in the image information is identified.
Step S3, controlling the multi-joint mechanical arm to be in at least two different pose states, enabling the optical axis point of the monocular camera to coincide with the target respectively, and recording the pose coordinates of the monocular camera in the coincidence state respectively;
specifically, the steps are detailed as follows:
s301, controlling the pose change of the monocular camera to enable a target to be positioned to enter the visual field range of the monocular camera;
step S302, controlling the pose of the monocular camera to enable the optical axis point of the monocular camera to coincide with the target according to the distance difference between the target to be positioned in the image and the optical axis point of the monocular camera, and acquiring the pose coordinate of the monocular camera in the state;
and S303, repeating the steps to obtain the pose coordinates of the monocular camera with the optical axis point of the monocular camera coincident with the target in at least two different pose states.
And controlling the tail end of the mechanical arm to move to the position above the target to be positioned by taking the pose coordinate of the camera as a control object in the positioning process of the target to be positioned, so that the target enters the visual field range of the monocular camera, simultaneously acquiring the image information and identifying the target of the image information.
After the target is obtained, according to the distance difference between the axis point in the camera image and the target, based on the tool coordinate system [ T ]]Controlling the end of the arm in the tool coordinate system [ T ]]Moving in the XY plane to make the image axis point of the monocular camera and the target point basically coincide, and recording the tool coordinate system [ T ] under the coincidence state]Relative to a base coordinate system [ B ]]Has a pose coordinate of
After the point P1 is obtained, the tail end of the mechanical arm is controlled to enable the tool coordinate system [ T ] to be in]Rotating the angle J1 around the X axis, moving the tip position in the XY plane of the tool coordinate system to make the image axis point coincide with the target point again, and recording the tool coordinate system [ T ] in the state]Attitude coordinates relative to the base coordinate system are
And step S4, calculating the space coordinate of the target to be positioned by using the space geometry principle according to the different pose coordinates of the monocular camera.
When the extended line of the optical axis of the monocular camera intersects with the target to be positioned, step S4 is detailed as follows:
s401, the optical axis point of the monocular camera is coincided with a target under at least two different camera pose states, and the extension line of the optical axis of the monocular camera intersects with the target to be positioned;
step S402, obtaining a linear equation of at least two optical axes according to at least two pose coordinates;
and S403, calculating the three-dimensional coordinates of the target to be positioned by using the intersection solution mode of the linear equation.
Alternatively, the two straight lines may not have an intersection point due to a measurement error of a plane coordinate, noise, and an influence of a monocular camera during the process of acquiring an image. Whereas, when the extension line of the optical axis of the monocular camera cannot intersect the object to be positioned but is very close to intersecting the object to be positioned, step S4 is detailed as follows:
s401, the optical axis point of the monocular camera is coincided with a target under at least two different camera pose states, and the extension lines of the optical axis of the monocular camera are not intersected with the target to be positioned and are approximately intersected with the target to be positioned;
step S402, obtaining a linear equation of at least two optical axes according to at least two pose coordinates;
and step S403, calculating the three-dimensional coordinates of the target to be positioned by using the midpoints of the common vertical lines of the linear equations.
Specifically, please refer to fig. 3, which is a schematic diagram of a target position solving structure based on geometric operations according to the present invention, and the details are as follows:
the extension lines of the optical axes of the monocular cameras in two overlapped states will intersect with the target p, and the equations of the two optical axes (the Z axis of the tool coordinate system) can be expressed as L1 ═ (x1, y1, Z1, α 1, β 1, γ 1) and L2 ═ x2, y2, Z2, α 2, β 2, γ 2) respectively, wherein (α 1, β 1, γ 1), (α 2, β 2, γ 2) are unit vectors of the two optical axes in the base coordinate system respectively, and the obtained attitude coordinate of the monocular camera can be passed through to obtain the attitude coordinate of the cameraAnd (4) obtaining.
Finally, the three-dimensional coordinate of the target can be obtained by a method of solving intersection points of linear equations, wherein the three-dimensional coordinate of the target is (k α 1+ x1, k β 1+ y1, k gamma 1+ z1)
Wherein:
or, when the intersection point of the extension lines of the two optical axes may not exist, the midpoint of the common perpendicular line of the two linear equations may be obtained to be approximated as the intersection point of the two linear equations, and the three-dimensional coordinate of the midpoint of the common perpendicular line is as follows:
wherein:
N1＝(β1β2+γ1γ2)α1-(β12+γ12)α2
N2＝(β1β2+γ1γ2)α2-(β22+γ22)α1
Q1＝(α1α2+γ1γ2)β1-(α12+γ12)β2
Q2＝(α1α2+γ1γ2)β2-(α22+γ22)β1
M1＝(β1β2+α1α2)γ1-(β12+α12)γ2
M2＝(β1β2+α1α2)γ2-(β22+α22)γ1
in conclusion, the monocular vision positioning method provided by the invention adopts space geometric operation to obtain the target coordinate under the condition that the target is aligned with the optical axis, does not relate to complex processing algorithm and camera internal parameter calibration, is efficient and practical, does not need a special range finder of , does not need a binocular camera, and has the advantages of low system cost and simple operation.
It will be appreciated by those skilled in the art that modifications and variations can be made to the disclosed embodiments without departing from the spirit and scope of the invention, and therefore, is equivalent to modifications and variations that would be apparent to those skilled in the art without departing from the spirit and scope of the invention as disclosed in the appended claims.
Claims (7)
1, monocular vision positioning device based on multi-joint mechanical arm, which is characterized in that the device comprises a mechanical arm base, a multi-joint mechanical arm, a monocular camera and a control device;
the multi-joint mechanical arm is arranged on the mechanical arm base, and the monocular camera is arranged on the mechanical arm and used for acquiring image information in real time; the image information comprises images of the target to be positioned in various pose states;
the control device is connected with the multi-joint mechanical arm and the monocular camera respectively, the control device comprises a memory and a processor, the memory is used for storing programs and image information, the processor is used for operating the programs, and the programs further comprise:
an identification program configured to identify a target to be positioned within the image information;
the control program is configured to control the multi-joint mechanical arm to be in different pose states, wherein the optical axis point corresponding to the monocular camera in the pose state is coincided with the target to be positioned;
and the calculation program is configured to acquire at least two different camera pose coordinates under the coincidence of the optical axis point of the monocular camera and the target according to the received image information, and calculate the space coordinate of the target to be positioned by utilizing a space geometric principle.
2, monocular vision positioning method based on multi-joint mechanical arm, characterized by comprising:
collecting image information containing a target to be positioned;
identifying a target within the image information;
controlling the multi-joint mechanical arm to be in at least two different pose states, enabling optical axis points of the monocular camera to coincide with the target respectively, and recording pose coordinates of the monocular camera in the coinciding states respectively;
and calculating the space coordinate of the target to be positioned by utilizing a space geometric principle according to different pose coordinates of the monocular camera.
3. The monocular vision positioning method based on multi-joint mechanical arm as recited in claim 2, wherein the step of collecting image information containing an object to be positioned comprises:
and mounting the monocular camera on the multi-joint mechanical arm, so that the monocular camera can acquire image information of the target to be positioned in various pose states.
4. The monocular vision positioning method based on multi-joint mechanical arm as recited in claim 2, wherein the target is any points in space.
5. The monocular vision positioning method based on the multi-joint mechanical arm as recited in claim 2, wherein the step of controlling the multi-joint mechanical arm to be located at least two different pose states so that the optical axis point of the monocular camera coincides with the target respectively comprises:
controlling the pose change of the monocular camera to enable the target to be positioned to enter the visual field range of the monocular camera;
controlling the pose of the monocular camera to enable the optical axis point of the monocular camera to coincide with the target according to the distance difference between the target to be positioned in the image and the optical axis point of the monocular camera, and acquiring the pose coordinate of the monocular camera in the state;
and repeating the steps to obtain the pose coordinates of the monocular camera with the optical axis point of the monocular camera coincident with the target under at least two different pose states.
6. The monocular vision positioning method based on the multi-joint mechanical arm as recited in claim 2, wherein the step of calculating the spatial coordinates of the target to be positioned by using the spatial geometry principle according to the different pose coordinates of the monocular camera comprises:
the monocular camera optical axis point coincides with the target under at least two different camera pose states, and the extension line of the monocular camera optical axis line intersects with the target to be positioned;
obtaining a linear equation of at least two optical axes according to at least two pose coordinates;
and calculating the three-dimensional coordinates of the target to be positioned by using the intersection solution mode of the linear equation.
7. The monocular vision positioning method based on the multi-joint mechanical arm as recited in claim 2, wherein the step of calculating the spatial coordinates of the target to be positioned by using the spatial geometry principle according to the different pose coordinates of the monocular camera comprises:
the monocular camera optical axis point coincides with the target under at least two different camera pose states, and the extension lines of the optical axis of the monocular camera do not intersect with the target to be positioned and are close to intersect with the target to be positioned;
obtaining a linear equation of at least two optical axes according to at least two pose coordinates;
and calculating the three-dimensional coordinates of the target to be positioned by utilizing the midpoints of the common vertical lines of the linear equation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710864061.6A CN107883929B (en) | 2017-09-22 | 2017-09-22 | Monocular vision positioning device and method based on multi-joint mechanical arm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710864061.6A CN107883929B (en) | 2017-09-22 | 2017-09-22 | Monocular vision positioning device and method based on multi-joint mechanical arm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107883929A CN107883929A (en) | 2018-04-06 |
| CN107883929B true CN107883929B (en) | 2020-01-31 |
Family
ID=61780659
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710864061.6A Active CN107883929B (en) | 2017-09-22 | 2017-09-22 | Monocular vision positioning device and method based on multi-joint mechanical arm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107883929B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108908344A (en) * | 2018-08-17 | 2018-11-30 | 云南电网有限责任公司昆明供电局 | A kind of crusing robot mechanical arm tail end space-location method |
| CN109115173B (en) * | 2018-08-23 | 2020-09-11 | 西安科技大学 | Monocular vision measuring method for position and attitude of heading machine body based on linear positioning model |
| CN109175832B (en) * | 2018-09-20 | 2020-11-10 | 上海理工大学 | Control method of 3D welding positioning system based on monocular measurement |
| CN109360243B (en) * | 2018-09-28 | 2022-08-19 | 安徽爱观视觉科技有限公司 | Calibration method of multi-degree-of-freedom movable vision system |
| CN109636859B (en) * | 2018-12-24 | 2022-05-10 | 武汉大音科技有限责任公司 | Single-camera-based calibration method for three-dimensional visual inspection |
| CN111300405B (en) * | 2019-12-12 | 2021-07-30 | 国网山东省电力公司电力科学研究院 | Visual identification positioning device and method for mobile platform |
| CN111673735A (en) * | 2020-04-28 | 2020-09-18 | 平安科技（深圳）有限公司 | Mechanical arm control method and device based on monocular vision positioning |
| CN111815711B (en) * | 2020-06-01 | 2023-08-18 | 佛山隆深机器人有限公司 | Single-camera multi-view calibration method based on robot |
| CN113084827B (en) * | 2021-04-01 | 2022-06-14 | 北京飞影科技有限公司 | Method and device for calibrating optical center position of camera device |
| CN113232019A (en) * | 2021-05-13 | 2021-08-10 | 中国联合网络通信集团有限公司 | Mechanical arm control method and device, electronic equipment and storage medium |
| CN113499094B (en) * | 2021-07-08 | 2023-07-25 | 中山大学 | Heart color Doppler ultrasound examination device and method guided by vision and force feedback |
| CN113487759B (en) * | 2021-07-16 | 2023-04-18 | 杭州海康汽车软件有限公司 | Parking patrol method and device, mobile patrol equipment and patrol system |
| CN114165706A (en) * | 2021-10-22 | 2022-03-11 | 北京注色影视科技有限公司 | Control method for positioning target of camera supporting device and camera supporting device |
| CN115446836B (en) * | 2022-09-17 | 2023-09-12 | 上海交通大学 | Visual servo method based on mixing of various image characteristic information |
| CN115741690B (en) * | 2022-11-14 | 2024-06-07 | 中冶赛迪技术研究中心有限公司 | Material bag grabbing method, system, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2065408A (en) * | 1979-10-22 | 1981-06-24 | Australasian Training Aids Pty | Improvements in or relating to projectile detecting means |
| CN201170773Y (en) * | 2008-03-18 | 2008-12-24 | 飞秒光电科技(西安)有限公司 | System for detecting building cranny |
| CN103292695A (en) * | 2013-05-10 | 2013-09-11 | 河北科技大学 | Monocular stereoscopic vision measuring method |
| CN103528571A (en) * | 2013-10-12 | 2014-01-22 | 上海新跃仪表厂 | Monocular stereo vision relative position/pose measuring method |
| CN103759716A (en) * | 2014-01-14 | 2014-04-30 | 清华大学 | Dynamic target position and attitude measurement method based on monocular vision at tail end of mechanical arm |
| JP2015212629A (en) * | 2014-05-01 | 2015-11-26 | 機械設計中畑株式会社 | Detection device and manipulator operation control including detection device |
| CN106441098A (en) * | 2016-09-26 | 2017-02-22 | 中国农业大学 | Recognizing and positioning method for picking fruits and vegetables |
| CN106878598A (en) * | 2017-03-13 | 2017-06-20 | 联想(北京)有限公司 | Processing method and electronic equipment |
-
2017
- 2017-09-22 CN CN201710864061.6A patent/CN107883929B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2065408A (en) * | 1979-10-22 | 1981-06-24 | Australasian Training Aids Pty | Improvements in or relating to projectile detecting means |
| CN201170773Y (en) * | 2008-03-18 | 2008-12-24 | 飞秒光电科技(西安)有限公司 | System for detecting building cranny |
| CN103292695A (en) * | 2013-05-10 | 2013-09-11 | 河北科技大学 | Monocular stereoscopic vision measuring method |
| CN103528571A (en) * | 2013-10-12 | 2014-01-22 | 上海新跃仪表厂 | Monocular stereo vision relative position/pose measuring method |
| CN103759716A (en) * | 2014-01-14 | 2014-04-30 | 清华大学 | Dynamic target position and attitude measurement method based on monocular vision at tail end of mechanical arm |
| JP2015212629A (en) * | 2014-05-01 | 2015-11-26 | 機械設計中畑株式会社 | Detection device and manipulator operation control including detection device |
| CN106441098A (en) * | 2016-09-26 | 2017-02-22 | 中国农业大学 | Recognizing and positioning method for picking fruits and vegetables |
| CN106878598A (en) * | 2017-03-13 | 2017-06-20 | 联想(北京)有限公司 | Processing method and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107883929A (en) | 2018-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107883929B (en) | Monocular vision positioning device and method based on multi-joint mechanical arm | |
| US11396100B2 (en) | Robot calibration for AR and digital twin | |
| JP6966582B2 (en) | Systems and methods for automatic hand-eye calibration of vision systems for robot motion | |
| CN109859275B (en) | Monocular vision hand-eye calibration method of rehabilitation mechanical arm based on S-R-S structure | |
| RU2664257C2 (en) | Systems and methods for tracking location of mobile target objects | |
| JP4021413B2 (en) | Measuring device | |
| JP5365379B2 (en) | Robot system and robot system calibration method | |
| JP6855492B2 (en) | Robot system, robot system control device, and robot system control method | |
| US9519736B2 (en) | Data generation device for vision sensor and detection simulation system | |
| US20190242971A1 (en) | Relative Object Localization Process for Local Positioning System | |
| CN111801198B (en) | Hand-eye calibration method, system and computer storage medium | |
| WO2022012337A1 (en) | Moving arm system and control method | |
| CN104786226A (en) | Posture and moving track positioning system and method of robot grabbing online workpiece | |
| CN111028340B (en) | Three-dimensional reconstruction method, device, equipment and system in precise assembly | |
| CN204585232U (en) | Capture robot pose and the movement locus navigation system of online workpiece | |
| TWI613054B (en) | Assembly device and assembly method of gear mechanism | |
| CN112658643A (en) | Connector assembly method | |
| CN116766194A (en) | Binocular vision-based disc workpiece positioning and grabbing system and method | |
| US20230123629A1 (en) | 3d computer-vision system with variable spatial resolution | |
| CN111699445A (en) | Robot kinematics model optimization method and system and storage device | |
| Abbott et al. | University of Illinois active vision system | |
| CN116100562B (en) | Visual guiding method and system for multi-robot cooperative feeding and discharging | |
| CN114794667B (en) | Tool calibration method, system, device, electronic equipment and readable storage medium | |
| NL2016960B1 (en) | System and method for controlling a machine, in particular a robot | |
| Dai et al. | An optimization based vision calibration method for PTZ camera's errors in model and execution |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |